sustainability

Article
Hazard Identification and Risk Assessment During
Simultaneous Operations in Industrial Plant Maintenance Based
on Job Safety Analysis
Sung-Jin Kwon 1 , So-Won Choi 1 and Eul-Bum Lee 1,2, *

1 Graduate Institute of Ferrous and Eco Materials Technology, Pohang University of Science and
Technology (POSTECH), Pohang 37673, Republic of Korea; [email protected] (S.-J.K.);
[email protected] (S.-W.C.)
2 Department of Industrial and Management Engineering, Pohang University of Science and
Technology (POSTECH), Pohang 37673, Republic of Korea
* Correspondence: [email protected]; Tel.: +82-(54)-279-0136

Abstract: The risk of accidents during simultaneous operations (SIMOPS) in plant maintenance has
been increasing. However, research on methods to prevent such accidents has been limited. This
study aims to develop a novel framework, hazard identification and risk assessment of simultaneous
operations (HIRAS), for identifying and evaluating potential hazards during concurrent tasks. The
framework developed herein is expected to be an effective safety management tool that can help
prevent accidents during these operations. To this end, the job location and hazard information
in job safety analysis (JSA) were standardized into four attributes. The standardized information
was then synchronized spatially and temporally to develop a HIRAS model that identifies and
assesses the impact of hazards between operations. The model was tested using 40 JSA documents
corresponding to maintenance operations at Company P, a South Korean steel-making company.
The model was tested in two scenarios: one with planned operations and the other with unplanned
operations in addition to planned operations. The performance evaluation results of the first scenario
showed an F1-score of 98.33%. In this case, a recall of 97.52% means that the model identified
97.52% of the hazard-inducing factors. The second scenario was compared with the results of a
review by six subject matter experts (SMEs). The comparison of the results identified by the SMEs
Citation: Kwon, S.-J.; Choi, S.-W.; Lee, and the model showed an accuracy of 89.3%. This study demonstrates the potential of JSA, which
E.-B. Hazard Identification and Risk
incorporates the domain knowledge of workers and can be used not only for individual tasks but
Assessment During Simultaneous
also as a safety management tool for surrounding operations. Furthermore, by improving the plant
Operations in Industrial Plant
maintenance work environment, it is expected to prevent accidents, protect workers’ lives and health,
Maintenance Based on Job Safety
Analysis. Sustainability 2024, 16, 9277.
and contribute to the long-term sustainable management of companies.
https://doi.org/10.3390/su16219277
Keywords: simultaneous operations (SIMOPS); job safety analysis (JSA); hazard identification and
Academic Editor: Giada La Scalia
risk assessment of simultaneous operations (HIRAS); plant maintenance; Zettelkasten method; hazard
Received: 23 September 2024 identification; risk assessment; GPT 3.5
Revised: 21 October 2024
Accepted: 22 October 2024
Published: 25 October 2024
1. Introduction
1.1. Background of Study

Copyright: © 2024 by the authors.

Historically, interest in safety began with the occurrence of accidents [1]. In 1987,
Licensee MDPI, Basel, Switzerland.
during major refurbishment work at the Marathon Oil refinery, a simultaneous operations
This article is an open access article
(SIMOPS) accident injured 100 people. In 1988, 167 people died on the Piper Alpha
distributed under the terms and offshore platform due to a lack of communication between workers during two maintenance
conditions of the Creative Commons operations.
Attribution (CC BY) license (https:// SIMOPS refers to the coordination and management of two or more potentially haz-
creativecommons.org/licenses/by/ ardous activities taking place simultaneously in the same area [2]. For instance, SIMOPS
4.0/). management is necessary in scenarios such as constructing a new bridge while maintaining

Sustainability 2024, 16, 9277. https://doi.org/10.3390/su16219277 https://www.mdpi.com/journal/sustainability

Sustainability 2024, 16, 9277 2 of 28

traffic flow on an existing one, welding pipes in a petrochemical plant while handling
flammable materials in adjacent units, and performing maintenance on a nuclear power
plant while continuing to generate electricity.
SIMOPS are especially common in complex industries like oil and gas [3]. In offshore
drilling, a typical SIMOPS scenario could involve drilling activities happening on a platform
while maintenance crews are performing repairs on the rig and another team is conducting
crane operations to transfer equipment.
Investigations into the cause of major accidents in the oil and gas sector have revealed
that SIMOPS are a major factor in such accidents [4]. SIMOPS are situations where two or
more tasks are carried out in close temporal and spatial proximity. SIMOPS activities, if
uncoordinated, could pose risks to safety, environment, or equipment. Therefore, careful
safety management during SIMOPS is necessary.
The 1987 Marathon Oil refinery accident and the 1988 Piper Alpha offshore platform
accident highlight the need for caution during SIMOPS. These incidents led to efforts in
the oil and gas industry to prevent accidents during SIMOPS [5]. The International Marine
Contractors Association (IMCA) developed and issued guidelines for preventing SIMOPS
accidents [6]. SIMOPS risks are not limited to specific sectors, such as the oil and gas
industry. In 2020, an accident occurred during maintenance operations at the Evergreen
Packaging plant, prompting the U.S. Chemical Safety and Hazard Investigation Board
to recommend the development and implementation of an accident prevention program
during SIMOPS [7].
Japan’s Industrial Safety and Health Act provides a comprehensive framework for
protecting workers from workplace hazards. While the Act does not explicitly mention
SIMOPS, its general principles and requirements apply to such operations [8]. Japan’s
Ministry of Health, Labor and Welfare (MHLW) is the government agency responsible for
enforcing the Industrial Safety and Health Act. It has taken several measures to address the
risks associated with SIMOPS work. The concept of on-site safety and health management
system, or total management, was specifically implemented for the construction and
shipbuilding sectors.
While there is not a specific term SIMOPS widely used in Chinese regulations, the
Chinese government has implemented a comprehensive framework of safety regulations
and standards to prevent industrial accidents [9], particularly in high-risk industries such
as oil, gas, and construction. State-owned enterprises like the China National Petroleum
Corporation (CNPC) have developed detailed Health, Safety, and Environmental (HSE)
management systems [10]. As the primary regulatory body for workplace safety in China,
State Administration of Work Safety (SAWS) has issued numerous regulations and stan-
dards aimed at preventing industrial accidents [11].
Germany’s Occupational Safety and Health Act (ArbSchG) and the German Social
Accident Insurance (DGUV)’s accident prevention regulations set important guidelines for
managing workplace safety, including SIMOPS [12,13]. Both laws focus on ensuring that
employers and workers take necessary precautions to prevent accidents, particularly in
high-risk environments.
In South Korea, public concern about safety accidents due to SIMOPS has been in-
creasing. Accidents such as the 2014 Goyang Terminal accident, the 2017 Taean Power
Plant accident, and the 2019 Han Express accident indicate that safety during SIMOPS is
not guaranteed [14]. In particular, a report by the Korea Occupational Safety and Health
Agency (KOSHA) indicated that the number of SIMOPS accidents in South Korea has
been increasing over the past seven years. Therefore, efforts to prevent SIMOPS accidents
are necessary. Figure 1 shows the number of occupational fatalities and fatalities due to
SIMOPS in South Korea [14,15].
 Sustainability 2024, 16, x FOR PEER REVIEW 3 of 29
Sustainability 2024, 16, 9277 3 of 28

Figure 1. Occupational fatalities and the proportion of occupational fatalities due to SIMOPS during
Figure 1. Occupational fatalities and the proportion of occupational fatalities due to SIMOPS during
2016–2022.
2016–2022.
The South
The South Korean
Korean government
governmenthas hastaken
takenthethe
following
followingsteps to prevent
steps SIMOPS
to prevent SIMOPSac-
cidents [16]:
accidents [16]:
•• TheThe2017
2017Amendment
Amendment to to the
the Occupational
Occupational Safety
Safety and
and Health
HealthAct:Act:Article
Article68
68mandates
mandates
appointing a health and safety coordinator to prevent industrial accidentsdue
appointing a health and safety coordinator to prevent industrial accidents duetoto
work interference when two or more construction projects are carried out at thesame
work interference when two or more construction projects are carried out at the same
location.
location.
•• TheThe2019
2019Amendment
Amendment to to the
the Occupational
Occupational Safety
Safety and
and Health
Health Act:
Act:Article
Article63
63expands
expands
the obligation of the contractor with respect to safety and health
the obligation of the contractor with respect to safety and health measures from measures from 22
hazardous locations to the entire workplace.
22 hazardous locations to the entire workplace.
•• TheThe2021
2021Amendment
Amendment to to the
the Occupational
Occupational Safety
Safety and
and Health
HealthAct:Act:Article
Article64
64mandates
mandates
that the timing, content, and safety and health measures of the operations
that the timing, content, and safety and health measures of the operations be confirmed be con-
firmed for operations carried out at the same location. The Presidential
for operations carried out at the same location. The Presidential Decree prescribes Decree pre-
scribes adjusting
adjusting theand
the timing timing and operation
operation in the
in the case of acase
fireof
oraexplosion
fire or explosion
risk duerisk due
to work
to work interference.
interference.
Companies are
Companies are also
also making
making efforts
efforts toto prevent
prevent SIMOPS
SIMOPS accidents.
accidents.The Theleading
leadingSouth
South
Korean steel
Korean steel maker,
maker, Company
CompanyP,P,has hasimplemented
implemented thethe
following
followingprocesses
processesto prevent SI-
to prevent
MOPS accidents during maintenance
SIMOPS accidents during maintenance work: work:
•• System
System aspects:
aspects: The
TheCompany
Company provides
providesa SIMOPS
a SIMOPS prediction list and
prediction listjob
and safety anal-
job safety
ysis (JSA) by linking an integrated safety and health platform with the
analysis (JSA) by linking an integrated safety and health platform with the enterpriseenterprise re-
source planning (ERP) system for work planning. The SIMOPS prediction
resource planning (ERP) system for work planning. The SIMOPS prediction list is list is gen-
erated based
generated on work
based on workdates andand
dates equipment classification
equipment systems.
classification systems.
•
• Work planning aspects: Managers from the work planningdepartment,
Work planning aspects: Managers from the work planning department,safety safetyman-
man-
agers, and work managers review the SIMOPS predictions in a D-1 meetingbefore
agers, and work managers review the SIMOPS predictions in a D-1 meeting before
the work
the work begins.
begins. Based
Based onon the
the review
review results,
results,they
theyestablish
establishmeasures
measuressuch suchasaspro-
pro-
hibitingconcurrent
hibiting concurrent vertical
vertical work,
work, adjusting
adjusting work
work execution
executiontimes,
times,andandimplementing
implementing
additionalsafety
additional safety measures.
measures.
• Work permit aspects:
• Work permit aspects: The The work
work permit
permit issuer
issuer reviews
reviews whether
whetherthe thework
workisismixed
mixed
with other teams for upstream, downstream, or interlocking equipment.IfIfSIMOPS
with other teams for upstream, downstream, or interlocking equipment. SIMOPS
are confirmed,
are confirmed, the
the work
work permit
permit issuer
issuer facilitates
facilitates aa toolbox
toolbox meeting
meeting (TBM)
(TBM)during
during
which work supervisors inspect the equipment on-site, identify potential
which work supervisors inspect the equipment on-site, identify potential hazards, hazards,
and
and establish
establish countermeasures
countermeasures [17]. [17].
• Work execution aspects: Workers are invited to a TBM with the operations and equip-
ment supervisors for individual tasks as well as a TBM with the related equipment
task supervisors.
ability 2024, 16, x FOR PEER REVIEW 4 of 29

• 9277
Sustainability 2024, 16, Workexecution aspects: Workers are invited to a TBM with the operations and 4 of 28
equipment supervisors for individual tasks as well as a TBM with the related equip-
ment task supervisors.
Although these processesthese
Although are effective
processesinare preventing
effective inSIMOPS accidents,
preventing SIMOPS theyaccidents,
have they have
drawbacks. The time required
drawbacks. The for
timeindividual
required fortaskindividual
TBMs is not taskuniform,
TBMs isleading to delays
not uniform, leading to delays
when additional TBMs
when are required.
additional TBMsThe aretime required
required. Thefor additional
time required TBMs increasesTBMs
for additional with increases with
an increase in an
theincrease
numberinofthe SIMOPS,
numberthereby
of SIMOPS,potentially
therebyshortening
potentially the time available
shortening the time available for
for maintenance work. Furthermore,
maintenance prioritizingprioritizing
work. Furthermore, multiple targets
multipleduring additional
targets TBMs
during additional TBMs can
can be challenging.
be challenging.
The risks
The risks associated withassociated
SIMOPS in with SIMOPS
plant in plant
maintenance aremaintenance are expected
expected to increase in to increase
in the future.
the future. As companies As companies
constantly strive toconstantly strive and
improve quality to improve quality
productivity and
[18], productivity [18],
many
many production
production activities in industrial activities
sites areinmechanized
industrial sites
and are mechanized
automated, andto
leading automated,
an in- leading to
an in
evitable increase inevitable
maintenanceincrease
work inand
maintenance
personnelwork andMaintenance
[19–22]. personnel [19–22].
work inMaintenance
plants work in
plants is compared
is a high-risk activity a high-riskto activity
other compared
tasks. From to other
2000 tasks. From
to 2011, 2000ofto184
80 out 2011, 80 out of 184 major
major
accidents in theaccidents in the process
process industry industry
in the U.S. in thewere
and Europe U.S. related
and Europe were related
to maintenance work to maintenance
work [23]. Therefore, the increase in maintenance SIMOPS
[23]. Therefore, the increase in maintenance SIMOPS in plants corresponds to a higher in plants corresponds to a higher
probability
probability of workers beingof workers
exposedbeing exposed
to accident to accident risks.
risks.
A process for
A process for identifying andidentifying and assessing
assessing work work hazards
hazards before startingbefore
work is starting
crucialwork is crucial
for preventingfor preventing
accidents [24]. accidents
JSA can help [24].identify
JSA canand helpassess
identify
workand assess [25]
hazards workand hazards
has [25] and has
been long used in various industries such as oil, construction, automation, mining, and mining, and
been long used in various industries such as oil, construction, automation,
shipbuilding
shipbuilding [26]. In JSA, the[26].
task In JSA, theinto
is divided tasksequential
is divided into the
steps, sequential
hazardssteps,
at eachthestephazards at each
step are identified and assessed, and hazard risk mitigation
are identified and assessed, and hazard risk mitigation measures are established [27]. Fig- measures are established [27].
Figure 2 depicts the JSA process currently
ure 2 depicts the JSA process currently implemented in Korea. implemented in Korea.

Figure 2. General steps of JSA.

Figure 2. General steps of JSA.

Although JSA Although

has been effectively
JSA has been used as a hazard
effectively usedidentification
as a hazard tool, its limited
identification tool, its limited
scope of identification has been pointed out as a drawback. JSA focuses
scope of identification has been pointed out as a drawback. JSA focusessolely on the task
solely on the task
being performed, and
being identifyingand
performed, hazards in surrounding
identifying hazards intasks via JSA istasks
surrounding difficult [27,28].
via JSA is difficult [27,28].
The limitation The
in the scope of identification
limitation in the scope of canidentification
be attributed can
to two
be factors.
attributedFirst,
to the
twocom-
factors. First, the
plexity of modern industries
complexity has significantly
of modern industries increased compared
has significantly to that when
increased JSA was
compared to that when JSA
first developedwas
[29]. Therefore, even planned tasks may be surrounded by other
first developed [29]. Therefore, even planned tasks may be surrounded by other tasks,
making it difficult tomaking
tasks, identifyithazards.
difficult Second,
to identifyunplanned
hazards. tasks
Second,or modifications
unplanned tasks to tasks
or modifications to
are often encountered
tasks areduring maintenanceduring
often encountered work.maintenance
Identifying hazards in advancehazards
work. Identifying for un- in advance for
planned tasks unplanned
is impossible because
tasks the tasksbecause
is impossible are unexpected.
the tasksSurrounding
are unexpected.tasksSurrounding
are in- tasks are
evitably variable due to unplanned
inevitably variable duework [30]. Therefore,
to unplanned owing
work [30]. to the limitation
Therefore, owing to in thethe
limitation in the
scope of identification, effectively preventing
scope of identification, effectivelySIMOPS accidents
preventing SIMOPSvia JSA is challenging.
accidents via JSA is challenging.

1.2. Problem Statement and Research Objectives

Despite the strengthened government regulations and proactive SIMOPS accident
prevention measures by the companies, research on hazard identification and assessment
related to SIMOPS has received limited attention [31]. Although SIMOPS-related hazard
identification has been investigated in the oil, gas production, and construction sectors,
studies on SIMOPS-related hazard identification in plant maintenance are limited.
Sustainability 2024, 16, 9277 5 of 28

Company P, the biggest steel-maker in South-Korea, regularly conducts maintenance

work, including major annual overhauls that last more than seven days, as well as inter-
mediate and regular maintenance. Managers meticulously review dozens of tasks daily
to prevent SIMOPS accidents. In addition, supervisors and workers dedicate significant
amounts of time to joint TBMs before task execution. For instance, at S plant, one of the
29 plants of the P steel mill, more than 20 tasks, involving over 70 personnel, are carried
out every day during major overhauls. In large-scale plant maintenance work, the complex-
ity and variability of tasks can increase the cognitive load on managers and supervisors.
Moreover, the increased time required for accident prevention measures can prolong the
repair period, affecting production and ultimately impacting company profits. Therefore, a
new methodology that can efficiently prevent SIMOPS accidents and optimize the review
process is needed.
This study focuses on preventing accidents during SIMOPS in plant maintenance work.
This study aims to contribute to accident prevention in SIMOPS by effectively identifying
and assessing hazards between tasks in a complex and variable environment based on
JSA. The authors investigated the identification and assessment of hazards associated with
simultaneous tasks in plant maintenance operations. As a result of this research, we have
developed a novel framework, hazard identification and risk assessment of simultaneous
operations (HIRAS) framework. This framework not only identifies hazards but also
establishes interrelationships between JSAs, allowing for a more in-depth analysis and
evaluation of risks associated with concurrent tasks.
An understanding of the inter-task impact is necessary for identifying and assessing
hazards resulting from interactions between different tasks. To achieve this, the authors
adopted the Zettelkasten method, which generates meaningful information through the
formation of relationships between information, to analyze hazards associated with simul-
taneous operations and construct a network-structured knowledge base [32]. Through
this process, they gained the idea for developing the R-JSA synchronization model, a core
component of the HIRAS framework. Furthermore, we employed Generative Pre-trained
Transformer (GPT) 3.5 and GPT prompts to classify disaster types, enabling the integration
of diverse data into an integrated knowledge system.
The hazards addressed in this study are not unforeseen harmful risk factors, but rather
the hazards that may arise during simultaneous operations in maintenance work sites,
and most of these hazards are predictable. These hazards are predominantly documented
in JSA. Given the significance of JSA in identifying these hazards, this study places an
emphasis on leveraging JSA.

1.3. Research Process

This manuscript is organized as follows. In Section 2, we conduct a comprehensive
review of the existing literature on JSA. Section 3 explains the Zettelkasten methodology, a
concept applied for the development of HIRAS. Section 4 describes the methodology used
to construct the HIRAS. The methodological framework of this study is divided into three
components. Section 4.1 details the data structuring procedure, synchronization of variables,
and attributes of the variables. Section 4.2 explains the generation of synchronized data,
methods for identifying the target and source jobs, and methods for identifying hazards in
source jobs. Section 4.3 presents the derivation of formulas to prioritize identified hazards.
Section 5 presents two scenarios to evaluate the validity of the developed framework,
wherein various evaluation metrics are used to verify the effectiveness of the framework.
The data used in this study were collected from JSA and SIMOPS accident cases at Company
P, as recorded in the OSHRI reports. The components and attributes were compared and
analyzed to clearly define the research targets. The study is summarized in Figure 3.
 of the framework. The data used in this study were collected from JSA and SIMOPS acci-
dent cases at Company P, as recorded in the OSHRI reports. The components and attrib-
Sustainability 2024, 16, 9277 6 of 28
utes were compared and analyzed to clearly define the research targets. The study is sum-
marized in Figure 3.

Figure3.
Figure 3. Overall
Overall research
research process.
process.

2.2. Literature
Literature Review
This
This section
section categorizes previous studies
categorizes the previous studies into
intoaa total
totalof
offour
fourgroups:
groups:one
onegroup
group
focusing
focusing on on hazard
hazard identification and assessment
assessment methodologies,
methodologies,and andthree
threecategories
categoriesfor
for
prior
priorresearch
research related
related to
to JSA.
JSA.

2.1.
2.1. Methodologies
Methodologies for for Hazard Identification and
Hazard Identification and Risk
Risk Assessment
Assessmentin inthe
theConstruction
ConstructionSectorSector
Hazard identification and risk assessment (HIRA) is a collective term
Hazard identification and risk assessment (HIRA) is a collective term that encom- that encompasses
all activities
passes involvedinvolved
all activities in identifying hazards hazards
in identifying and evaluating risk at facilities.
and evaluating The public
risk at facilities. Theor
the environment
public are consistently
or the environment controlledcontrolled
are consistently within each organization’s
within risk tolerance
each organization’s risk level.
tol-
Tools for simple hazard identification or qualitative risk analysis include
erance level. Tools for simple hazard identification or qualitative risk analysis include checklists, what-if
analysis,
checklists, hazard
what-ifand operability
analysis, hazardstudies (HAZOP), studies
and operability and failure modesand
(HAZOP), andfailure
effect analysis
modes
(FMEA) [33].
and effect analysis (FMEA) [33].
Checklists
Checklists offerofferaastraightforward
straightforwardand andtime-efficient
time-efficientapproach
approachtoto hazard
hazard identification,
identifica-
making them suitable for routine safety inspections [33]. What-if
tion, making them suitable for routine safety inspections [33]. What-if analysis, analysis, on the onother
the
hand, encourages
other hand, creative
encourages thinking
creative by posing
thinking hypothetical
by posing scenarios
hypothetical suchsuch
scenarios as “What
as “Whatif...?”
However, its effectiveness
if...?” However, hinges
its effectiveness on theonanalyst’s
hinges experience
the analyst’s and and
experience knowledge,
knowledge, andandit mayit
lack a systematic framework [33]. FMEA and HAZOP are more rigorous
may lack a systematic framework [33]. FMEA and HAZOP are more rigorous methodol- methodologies that
are
ogiesemployed when a detailed
that are employed when aanalysis
detailedof systemoforsystem
analysis process orsafety
processis safety
imperative [33]. JSA
is imperative
is[33].
particularly valuable when objective data are required to assess and
JSA is particularly valuable when objective data are required to assess and mitigate mitigate risks [34].
Moreover, the International Organization for Standardization (ISO) 45001
risks [34]. Moreover, the International Organization for Standardization (ISO) 45001 pro- provides a com-
prehensive framework forframework
vides a comprehensive establishing and
for maintaining
establishing an maintaining
and occupational an health and safety
occupational
management system within an organization [35]. Table 1 presents a detailed comparison of
these methods, highlighting their key characteristics, strengths, and weaknesses.
Sustainability 2024, 16, 9277 7 of 28

Table 1. Comparing hazard identification and risk assessment methods in construction sector.

Methods Characteristics Advantages Disadvantages Application Areas

Difficulty in identifying
Inspection based on a General hazard
Simple, fast, new hazards, reliance
Checklist predefined list of identification, regular
standardized on checklist
hazards inspections
completeness
Assumption of various
Encourages creative Subjectivity of the In-depth analysis of
scenarios through
What-If Analysis thinking; can identify analyst, lack of specific tasks or
questions like “What
unexpected hazards systematic approach systems
if...?”
Analysis of failure Systematic risk
Time-consuming; Analysis of complex
FMEA modes for each analysis, identification
requires expertise systems; design stage
component of a system of potential hazards
Prevention of hazards
Review of all functions Requires specialized
at the design stage; Design stage;
HAZOP of a system at the training;
improvement of system process safety
design stage time-consuming
safety
Measurement of
Accurate risk Requires measurement specific hazards such as
Evaluation based on
JSA assessment; provides equipment and hazardous substance
objective data
basis for improvement specialized personnel exposure, noise, and
vibration
Establishment of an
Systematic risk Requires significant Overall occupational
organization-wide
management; time and effort to health and safety
ISO 45001 occupational health
continuous establish and maintain management of the
and safety
improvement the system organization
management system

2.2. Origins and Limitations of Job Safety Analysis (JSA)

Previous studies on the origins and limitations of JSA were reviewed to better under-
stand the development of JSA methodologies. The origins, processes, terms, and formats of
JSA are as follows. Taylor applied systematic management methods by breaking down tasks
performed by individual workers to enhance efficiency and studied the effects of scientific
management [36]. Heinrich et al. introduced a method to analyze tasks and effectively
match employees by considering their characteristics to prevent accidents. They proposed
the term “JSA” and emphasized the benefits of accident prevention [37]. Glenn noted
that Bennett’s 1950 proposal of a three-column worksheet, structured around “task steps”,
“hazards”, and “hazard controls”, has endured as the bedrock format for contemporary
JSA [38].
Fine and Kinney conducted a risk estimation study to prioritize hazard controls for
accident prevention; they quantified the relative severity of identified potential hazards as
risk scores [39]. The currently used combination of accident probability and severity in risk
estimation appears to have originated from this study.
Brid and Germain indicated that JSA conducted in accordance with the relevant
guidelines could be useful for major activities such as employee training, task instructions,
and accident investigations [40]. The Occupational Safety and Health Administration
recommended a job hazard analysis (JHA) to address workplace hazards and reduce
worker injury and illness [25]. Friend and Kohn emphasized the importance of JSA in
system safety for systematically identifying and controlling hazards at each task step [41].
Zheng described JSA as one of the most important on-site risk management methods for
identifying hazards at each task step and eliminating or minimizing risks [42].
However, Hollnagel et al. emphasized that pre-1970s safety management was based
on relatively simple and independent systems, whereas the complexity of current industrial
systems necessitates methods that account for interdependence and variability. He argued
Sustainability 2024, 16, 9277 8 of 28

for integrating the old and new perspectives on safety instead of replacing the old perspec-
tive [1]. Zheng et al. developed a visual cognitive model to improve hazard identification
at construction sites, analyzing eye-tracking data from experts and novices in 16 simulated
field scenes [43]. The findings of this study provide insights into potential improvements
for safety training and management. Hong and Cho proposed a location tracking system
that leverages personal ID recognition, QR code scanning, and computer vision algorithms
to enhance preemptive risk recognition and real-time safety monitoring in various work
environments [44].

2.3. JSA for Individual Tasks

Heinrich proposed the domino theory, wherein he argued that a series of events leads
to injury; however, eliminating a single component in the series of events can break the
chain and prevent accidents [45]. JSA can be considered to be a methodology that helps
eliminate unsafe actions or conditions in the domino theory. JSA-related research can be
divided into studies on (1) hazard identification, (2) hazard control, (3) risk assessment,
and (4) automation and efficiency.
Research on hazard identification focuses on clear identification and rapid detection
of potential hazards. Patrucco et al. developed the Computer Image Generation for Job
Simulation method to effectively use JSA techniques. The method helped visualize worker
activities in the workspace, and consequently, hazard identification was faster and more
intuitive than that in traditional methods [46]. Zheng et al. proposed the Energy Source-
Based Job Safety Analysis method for effective hazard identification. The method provided
categories to identify hazards at each job step, and the total recordable incident rate was
50% lower than that in similar projects using traditional JSA [42].
In research related to hazard control measures, Chi et al. applied ontology-based text
classification to National Institute for Occupational Safety and Health (NIOSH) Fatality
Assessment and Control Evaluation (FACE) reports, OSHA standards, and the Center to
Protect Workers’ Rights (CPWR) Construction Solutions data to develop the Construc-
tion Safety Domain Ontology System, which reduced the effort required for JSA. This
proved to be an excellent reference during the review of control measures [47]. Li et al.
pointed out that the risk level could continuously increase in repetitive tasks and suggested
that incorporating resilience engineering into hazard control measures could reduce risk
levels [48].
In research related to risk assessment, Li et al. developed a new risk assessment
method that incorporated the concept of cumulative risk to improve the stability and safety
of operations at gas transmission stations. They demonstrated the practical applications of
the concept of cumulative risk and showed that it improved the reliability of JSA [49]. Li
et al. examined the differences in risk caused by detailed sequence changes at each task step.
They integrated a graphical model based on Petri nets into JSA to achieve intuitive, logical,
and chronological risk assessment at each step. This method was particularly effective for
non-routine tasks [50].
In research related to the automation and efficiency of JSA, Ikuma et al. combined lean
production strategies with JSA to reduce high injury rates in the construction industry. They
showed that worker exposure to hazards could be decreased or eliminated by reducing
unnecessary motions and optimizing the work environment at each process step [51]. Wang
and Boukamp aimed to reduce the time required for JHA of complex tasks. They developed
“JHA Adviser” by organizing previous JHA knowledge through ontology modeling to
reuse useful information. JHA Adviser facilitated access to safety management knowledge
and reduced the time required for new JHAs [52]. Zhang et al. developed a construction
safety ontology to automate job safety analysis and integrated it with building information
modeling (BIM). They demonstrated its utility to safety supervisors within a limited scope.
However, owing to the limitations in updating the field conditions and schedules, user
judgment is necessary for evaluating the results [53].
Sustainability 2024, 16, 9277 9 of 28

2.4. JSA for Inter-Task Relationships

Rozenfeld et al. noted that JSA was primarily a tool for analyzing the risks of the job
being performed, and JSA could not identify factors that increased the existing risks or
factors that created new risks via interactions between multiple SIMOPS [28]. Therefore,
independent analysis of individual tasks is insufficient, and analyzing the relationships
between tasks is necessary.
Related research has attracted attention in the oil and gas production and construc-
tion sectors. The IMCA issued Guidance on Simultaneous Operations for identifying and
managing SIMOPS during exploration, construction, and production at sea [6]. Marucco
assessed the SIMOPS risk to evaluate additional risks due to SIMOPS during the commis-
sioning of a new USD 1.65 billion petrochemical complex. Through SIMOPS evaluation
workshops and action tracking management involving participants from various areas,
they achieved 65 million man-hours without a lost-time injury (LTI) [54]. Baybutt proposed
processes and checklists for using each tool and provided specific guidelines for identifying
risks due to negative interactions between tasks during SIMOPS. Additionally, while the
need for SIMOPS reviews started in the marine sector, he suggested that it is also desirable
to apply it to the land sector [5].
Sacks et al. developed the Construction Hazard Assessment with Spatial and Temporal
Exposure (CHASTE) model to protect workers on construction sites from exposure to risks
posed by workers from other unrelated teams. This model assessed risks by considering
spatial and temporal exposure and overlap, and it could help managers adjust plans for
risk mitigation or take appropriate preemptive actions [55]. Rashidi Nasab et al. noted the
lack of previous research on SIMOPS in construction projects and presented a practical
framework for monitoring and assessing overlapping construction activities using the
“source–target” matching concept based on BIM [31]. Fan et al. proposes a dynamic
quantitative risk assessment (DQRA) methodology using Bayesian networks (BNs) to
address the time-varying risks of liquefied natural gas (LNG) bunkering SIMOPS [56]. A
case study of truck-to-ship LNG bunkering demonstrates that the methodology effectively
captures the dynamic risk changes over time, providing a more accurate risk assessment
compared to traditional static approaches.

2.5. Limitations of Previous Research and Objectives of This Study

The literature review revealed that traditional job safety analyses cannot clearly iden-
tify risks in the context of inter-job relationships. The novel approaches proposed to
overcome these limitations in the offshore oil and gas industry as well as the construction
sector have some constraints. Although the SIMOPS process in the offshore oil and gas
industry is systematic and comprehensive, it requires extensive data collection and nu-
merous participants. Consequently, the time required for JSA increases with increasing
task complexity, and the method does not allow for the addition of unplanned tasks or the
introduction of changes. In contrast, automated tools can be applied without restrictions
on the scale of the target tasks in the construction sector. The databases for automation
are based on expert opinions or accident cases. Although the databases include detailed
information on the tasks, identifying the specific conditions and work environments of
maintenance tasks is difficult. In industrial sites, the work methods and hazards for the
same type of task can vary depending on conditions such as weight, size, and whether
the environment is indoors or outdoors. Moreover, database expansion is necessary when
new types of tasks are introduced. From a tool operation perspective, matching tasks
with schedule and location information and judging the risk-related information requires
separate personnel.
This study proposes a JSA-based framework to overcome these limitations. The
proposed framework standardizes the domain knowledge of task experts reflected in the
JSA into attributes and uses an automated model to consider the specificity and operational
flexibility of the tasks. This approach is expected to identify and assess the impact of
hazards between tasks during SIMOPS.
Sustainability 2024, 16, 9277 10 of 28

3. Hazard Identification in SIMOPS Based on the Zettelkasten Method

This study proposes a novel method to develop HIRAS, employing JSA to identify haz-
ards associated with concurrent tasks, drawing inspiration from the Zettelkasten method.
The Zettelkasten method, developed by Niklas Luhmann, is a note-taking and knowledge
management system that effectively organizes and connects ideas to build knowledge in
a systematic manner [32]. The primary objective of the Zettelkasten method is to create
a dynamic network of interrelated ideas [32]. Rather than simply listing information, it
facilitates a deeper understanding and utilization of knowledge by establishing connections
between ideas. In order to gather hazard information from surrounding operations in a
JSA, it was necessary to establish points of connection and a structured knowledge sys-
tem. In this study, the Zettelkasten method was applied to transform the SIMOPS-related
information present in JSAs into structured data. Through this process, individual haz-
ard information was connected and relational information between tasks was generated,
resulting in the construction of an integrated knowledge system with a network-based
structure.
Another strength of the Zettelkasten method is its similarity to the way the human
brain processes and connects information. By linking and integrating individual pieces of
information, it helps to build a knowledge system, which in turn facilitates the generation
of new knowledge [57]. In other words, by encouraging connections between various
concepts, it aids in the development of original ideas. In this study, the Zettelkasten method
was applied to the development of the HIRAS framework, and it was utilized as a source
of insight for developing the core R-JSA synchronization model within HIRAS.
The Zettelkasten method builds a knowledge system wherein individual pieces of
information are connected and integrated to generate new information [57]. The choice of
connection points is crucial because connection points determine the generated informa-
tion [57]. The SIMOPS information was generated by choosing the following connection
points: date and location corresponding to the temporal and spatial attributes, respectively,
were chosen as the connection points from individual JSAs; task and hazard attributes were
chosen as the connection points to generate inter-task effects. JSAs are interconnected in the
Sustainability 2024, 16, x FOR PEER REVIEW 11 of 29
R-JSA synchronization model via the date, location, and attribute connections. A schematic
of the R-JSA synchronization model with the Zettelkasten method is shown in Figure 4.

Figure 4. Schematic of the R-JSA synchronization model and JSA.

The connection
The connection points
points between
between the
the JSAs
JSAs were
were chosen
chosen by
by matching
matching the
the SIMOPS
SIMOPS com-
com-
ponents and inter-task effects with the JSA components. The matched JSA information
ponents and inter-task effects with the JSA components. The matched JSA information was
converted into a form recognizable by the model via systematic structuring. Task locations
was converted into a form recognizable by the model via systematic structuring. Task lo-
cations were converted into coordinates, task attributes into ranges, and hazard attributes
into direction, range, and residue. The details of this conversion are provided in Section
4.2. The converted information was used in the R-JSA synchronization model to model
real-time SIMOPS situations by connecting information corresponding to the same date
and floor, and SIMOPS-related hazards were identified. These aspects are detailed in Sec-
Sustainability 2024, 16, 9277 11 of 28

were converted into coordinates, task attributes into ranges, and hazard attributes into
direction, range, and residue. The details of this conversion are provided in Section 4.2. The
converted information was used in the R-JSA synchronization model to model real-time
SIMOPS situations by connecting information corresponding to the same date and floor, and
SIMOPS-related hazards were identified. These aspects are detailed in Section 4.3. Figure 5
Sustainability 2024, 16, x FOR PEER REVIEW
shows a schematic of the SIMOPS components used to develop the R-JSA synchronization 12 of 29

model.

Figure 5. Connecting the components between SIMOPS and the R-JSA synchronization model. (S)
Figure 5. Connecting the components between SIMOPS and the R-JSA synchronization model.
*: Structured data, (U) **: unstructured data.
(S) *: Structured data, (U) **: unstructured data.

4.4.Modeling
Modeling
Section4 4provides
Section provides a comprehensive
a comprehensive description
description of development
of the the development of a HIRAS
of a HIRAS model
model designed to identify and evaluate potential hazards arising from concurrent
designed to identify and evaluate potential hazards arising from concurrent tasks. tasks.

4.1.HIRAS
4.1. HIRAS Framework
Framework
Inthis
In thisstudy,
study,thetheZettelkasten
Zettelkasten method
method was applied
applied to to develop
develop HIRAS.
HIRAS.HIRAS
HIRASwas was
usedto
used toidentify
identifyandand assess
assess possible
possible hazards during SIMOPS using JSA. JSA.
The HIRAS
The HIRAS framework
frameworkcomprises
comprisesthree
threecomponents:
components: (i) the relation-oriented
(i) the JSA (R-
relation-oriented JSA
JSA) method,
(R-JSA) method, which
whichgenerates
generatesthethe
required data
required from
data JSAJSA
from to build a database;
to build (ii) the
a database; R-
(ii) the
JSA synchronization model, which analyzes data to identify hazards
R-JSA synchronization model, which analyzes data to identify hazards during SIMOPS; during SIMOPS; and
(iii) (iii)
and SIMOPS SIMOPSrisk risk
assessment (S-RA),
assessment whichwhich
(S-RA), evaluates and prioritizes
evaluates the identified
and prioritizes risks.
the identified
The components
risks. The components are detailed below.below.
are detailed
•• R-JSA method: This methodologyaims
R-JSA method: This methodology aimstoto
standardize
standardize JSAJSAdatadata
to build an open
to build da-
an open
tabase. Coordinates
database. Coordinates areare
assigned to task
assigned locations
to task and and
locations the attributes of tasks
the attributes and haz-
of tasks and
ards are structured to standardize the data. Errors in data entry are
hazards are structured to standardize the data. Errors in data entry are prevented via prevented via
quantifiedhazard
quantified hazard classifications,
classifications, GPT
GPT validation,
validation, andand criteria
criteriafor
forhazards
hazardsthat
thatcause
cause
accidents during SIMOPS.
accidents during SIMOPS.
• R-JSA synchronization: This model uses data obtained from R-JSA to synchronize
hazard information for tasks in a spatially and temporally coordinated manner and
analyzes inter-task effects. This analysis involves the generation of synchronized
data, exploratory analysis, and hierarchical analysis, which provides a basis for iden-
tifying and assessing hazards in SIMOPS.
• S-RA: S-RA focuses on evaluating the identified hazards and determining the priority
Sustainability 2024, 16, 9277 12 of 28

• R-JSA synchronization: This model uses data obtained from R-JSA to synchronize
hazard information for tasks in a spatially and temporally coordinated manner and
analyzes inter-task effects. This analysis involves the generation of synchronized data,
exploratory analysis, and hierarchical analysis, which provides a basis for identifying
and assessing hazards in SIMOPS.
• S-RA: S-RA focuses on evaluating the identified hazards and determining the priority
Sustainability 2024, 16, x FOR PEER REVIEW 13 of 29
of actions using the information on the risk level of the source job and the SIMOPS
factor derived from expert group discussions.
The HIRAS framework integrates these components to systematically identify and
The HIRAS framework integrates these components to systematically identify and
evaluate
evaluate hazards
hazards that
that may
may occur during SIMOPS,
occur during SIMOPS, thereby
therebycontributing
contributingtotoimproving
improving
workplace safety. Figure 6 shows a conceptual map of the HIRAS framework.
workplace safety. Figure 6 shows a conceptual map of the HIRAS framework.

Figure 6. The system architecture of HIRAS.

Figure 6. The system architecture of HIRAS.

4.2.Data
4.2. DataStructuring
Structuring Through
Through a Relation-Oriented
Relation-Oriented JSAJSAMethod
Method
TheR-JSA
The R-JSAmethod
method standardizes
standardizes JSAJSA information
informationinto intoattribute
attributevalues,
values,and
andthus plays
thus plays
a crucial role in ensuring that the HIRAS framework is open and flexible.
a crucial role in ensuring that the HIRAS framework is open and flexible. Moreover, the Moreover, the
R-JSAmethod
R-JSA methodhelps
helps prevent
prevent the
the omission
omissionor oroverinclusion
overinclusionofofreview
reviewtargets byby
targets thethe
author.
author.
To achieve this, the improved components in the JSA methodology
To achieve this, the improved components in the JSA methodology are the location, are the location, jobjob
steps, and hazard.
steps, and hazard.
Thelocation
The locationinformation
informationwas wasclassified
classifiedinto
intofloors
floorsand
andwas
wascoordinated
coordinatedon onaacoordinate
coordi-
nate plane of the respective floor. For example, the location “2F B Facility”
plane of the respective floor. For example, the location “2F B Facility” was converted and was converted
and entered
entered as “2F-X70-Y67”
as “2F-X70-Y67” in the
in the standardized
standardized form.AA range
form. range attribute
attributewas
wasincluded
included to to
quantitativelyexpress
quantitatively express the
the scope
scope of
of each
each task.
task. For
Forexample,
example,aarange
rangeattribute
attributevalue
valueof of
fivefive
for a task step indicates the task area occupies five squares horizontally
for a task step indicates the task area occupies five squares horizontally and vertically and vertically
fromthe
from thelocation
locationin inthe
the coordinate
coordinate system.
system. Hazard
Hazardattributes
attributeswere
wereadded
addedtotosystematize
systematize
the impact on surrounding tasks, including disaster type classification, confirmation of
the impact on surrounding tasks, including disaster type classification, confirmation of
impact on surrounding tasks, and hazard attributes. Hazard attributes were divided into
impact on surrounding tasks, and hazard attributes. Hazard attributes were divided into
three categories: range, direction, and residue. Figure 7 shows a JSA form reflecting these
three categories: range, direction, and residue. Figure 7 shows a JSA form reflecting these
improvements, with the reflected parts separately marked. In Figure 7, the blue boxes de-
improvements, with the reflected parts separately marked. In Figure 7, the blue boxes
note the field engineerʹs input, while the yellow sections highlight areas where GPT assis-
tance is involved during the initial review by the first person.
Sustainability 2024, 16, 9277 13 of 28

denote
the field engineer’s input, while the yellow sections highlight areas where
Sustainability 2024, 16, x FOR PEER REVIEW 14 ofGPT
29
assistance is involved during the initial review by the first person.

Figure7.7.Example
Figure Exampleof ofaarelation-oriented
relation-orientedJSA form. 11 TR: Task range; 22S:S:selection;
JSAform. selection;33IOSO:
IOSO:impact
impactonon
surrounding operations; HR: hazard range; D: direction; R: residue; S: severity; P:P:probability;
surrounding operations; 4 4 HR: hazard range; 55 D: direction; 6
6 R: residue; 77S: severity; 8 8
probability;
9 RR: risk rating; 10 HV-: the downward direction of the horizontal and vertical; 11 H: horizontal.
9 RR: risk rating; 10 HV-: the downward direction of the horizontal and vertical; 11 H: horizontal.

Theimpact
The impact ofof hazards
hazards on on surrounding
surrounding tasks
tasks was
was evaluated
evaluated as as follows:
follows:
•• Classification of disaster types: Disaster types were classified tostructure
Classification of disaster types: Disaster types were classified to structurethethehazards
hazards
corresponding to individual tasks. As classification criteria may vary
corresponding to individual tasks. As classification criteria may vary across industries, across indus-
the 22 criteria detailed by KOHSA were used herein [58]. The classificationwas
tries, the 22 criteria detailed by KOHSA were used herein [58]. The classification was
conducted in
conducted in three
three steps.
steps. First,
First, the
the worker
worker classified
classified the
the types,
types,andandGPT
GPTwas wasused
usedtoto
assistclassification.
assist classification.The Therole,
role,classification
classificationcriteria,
criteria, and
and output
output format
format were
were specifi-
specifically
cally presented
presented in theinGPTthe prompt.
GPT prompt. The GPT
The GPT prompts
prompts were were combined
combined withwith
JSAJSA haz-
hazards
ards using text concatenation functions in Google Sheets, and the
using text concatenation functions in Google Sheets, and the GPT API was used for GPT API was used
for classification.
classification. Discrepancies
Discrepancies between
between thethetwo
tworesults
resultswere
were reviewed.
reviewed. TheTheaccuracy
accuracy
and reliability of the classification were improved by reviewing
and reliability of the classification were improved by reviewing and supplementing and supplementing
theresults
the resultsprovided
providedby byAI.
AI.Figure
Figure8 shows
8 shows a part
a part of of
thethe prompt
prompt used
used for for disaster-
disaster-type
type classification.
classification.
Sustainability 2024, 16,
Sustainability 2024, 16, 9277
x FOR PEER REVIEW 15
14 of 29
of 28

Sustainability 2024, 16, x FOR PEER REVIEW 15 of 29

Figure 8.
Figure 8. GPT
GPT prompt
prompt for
for disaster
disaster type
type classification.
classification.
Figure 8. GPT prompt for disaster type classification.
•• Confirmation of impact on surrounding tasks: Disaster Disaster types
types that
that could
could cause
cause acci-
acci-
• Confirmation
dents of impact
during SIMOPS on surrounding
were
were selected. Clear
selected. tasks: Disaster types
classifications thatapplied
were could cause acci-
eliminate
to eliminate
dents during
variations
variations amongSIMOPS wereand
authors
authors selected.
and ensure
ensure Clear classifications
consistent
consistent were
results.
results. Theapplied to eliminate
classification
classification criteria
criteria
variations
were based
were among
based on
on the authors and ensure
the results from a study consistent results. The classification
study conducted by the Korea Occupational criteria
Safety
were based on the results from a study conducted by the Korea Occupational Safety
and Health Research Institute, wherein 4641 accidents that occurred from 2016 to
and Health Research Institute, wherein 4641 accidents that occurred from 2016 to
2020 were analyzed according
according to to objective
objective criteria.
criteria. Among these accidents, 426 were
2020 were analyzed according to objective criteria. Among these accidents, 426 were
classified as SIMOPS accidents, and seven types of SIMOPS SIMOPS accident
accident causes
causes were
were
classified as SIMOPS accidents, and seven types of SIMOPS accident causes were
identified [14]. IfIfthe
theresults
resultsofofthe
thedisaster
disastertypetypeclassification
classification corresponded
corresponded to to
oneone
of
identified [14]. If the results of the disaster type classification corresponded to one of
of
thethe seven
seven SIMOPSaccident
SIMOPS accidentcauses,
causes,thethehazard
hazardattributes
attributes were
were reviewed. As other
the seven SIMOPS accident causes, the hazard attributes were reviewed. As other
types of accident causes do not affect surrounding tasks, the hazard attributes were
types ofaccident
accident causes do notnot affect
affectsurrounding
surroundingtasks, hazard
the hazard attributes
attributes were
not reviewed in those cases. Figure 9 shows the criteria and process for
not reviewed in those cases. Figure 9 shows the criteria and process for determining
determining
the
theimpact
impactononsurrounding
on surrounding tasks.
surrounding tasks.
tasks.

Figure 9. Criteria and process for selecting items with potential for SIMOPS accidents among disas-
Figure
Figure 9. Criteria
9. Criteriaand
ter types. andprocess
processforfor
selecting items
selecting withwith
items potential for SIMOPS
potential accidents
for SIMOPS among among
accidents disaster disas-
types.
ter types.
• Direction of the hazard: Four directions were considered: horizontal, horizontal and
•Direction of the hazard: Four directions were considered: horizontal, horizontal and
• upper,
Directionhorizontal and lower,
of the hazard: and horizontal
Four directions wereand and both upper
considered: and lower.
horizontal, The same
horizontal
upper, horizontal and lower, and horizontal both upper and lower. The sameand
hazard
upper, can occur in different directions depending on the work environment. For
hazardhorizontal
can occur and lower, and
in different horizontal
directions and both
depending on theupper
workand lower. TheFor
environment. same
example,
hazard in the
caninoccur case of
in of a fire,
different the direction
directions can vary depending on the exposure and
example, the case a fire, the directiondepending on the work
can vary depending on theenvironment.
exposure andFor
composition
example, of the space as well as the source of fire, such as gas or oil. Therefore,
composition of the space as well as the source of fire, such as gas or oil.exposure
in the case of a fire, the direction can vary depending on the Therefore,and
environmental
composition
environmental offactors
the space
factors
were
wereasconsidered
considered
based
well as thebased
source onthe
the
on of
worker’s
fire, such as
worker’s
domain knowledge.
gas orknowledge.
domain oil. Therefore,
• • Range of work
environmental and
Range of workfactors hazard: The
were The
and hazard: maximum
considered
maximum range
based that
on that
range could
the worker’sbe affected was
domainwas
could be affected considered
knowledge.
consid-
• following
Range the reviewed
ered following
of work and direction.
the reviewed
hazard: direction.
The maximum range that could be affected was consid-
• • Presence
Presence
ered ofofresidual
following residual hazard
hazard attributes:
the reviewed attributes: Therisk
direction. The riskofofa ahazard
hazardmay
may not
not bebe eliminated
eliminated
after task completion. For example, a worker might be exposed to asphyxiation or or
• after taskofcompletion.
Presence residual hazardFor example, a worker
attributes: The riskmight
of abehazard
exposed to asphyxiation
may not be eliminated
after task completion. For example, a worker might be exposed to asphyxiation or
 Sustainability 2024, 16, x FOR PEER REVIEW 16 of 29
Sustainability 2024, 16, 9277 15 of 28

poisoning risks from gases accumulated during a previous task. Therefore, the resid-
poisoning risksof
ual attributes from gasesinaccumulated
hazards during
the target task were aconsidered
previous task.
[59]. Therefore, the residual
attributes of hazards in the target task were considered [59].
The worker’s domain knowledge about the impact on surrounding tasks can be
standardized by reviewing
The worker’s the attributes
domain knowledge of work
about and hazards.
the impact Moreover,
on surrounding thecan
tasks disaster type
be standard-
classification
ized by reviewingandthe
confirmation
attributes ofofwork
impact
andonhazards.
the surrounding
Moreover,tasks preventtype
the disaster omissions and
classification
overinclusion
and confirmationofofentries
impactby onthe
theauthor, while tasks
surrounding the remaining processesand
prevent omissions ensure an open of
overinclusion
framework.
entries by the author, while the remaining processes ensure an open framework.

4.3.R-JSA
4.3. R-JSASynchronization
Synchronization Model
Model for Identifying
IdentifyingHazards
HazardsininSimultaneous
SimultaneousOperations
Operations
TheR-JSA
The R-JSAsynchronization
synchronization model
model synchronizes
synchronizesinformation
informationextracted
extractedfrom JSAs
from of of
JSAs
plannedtasks
planned tasksinto
intoaacoordinate
coordinate system
system byby matching
matchingthethetemporal
temporaland
andspatial
spatialconditions
conditions
duringactual
during actualSIMOPS
SIMOPSandand analyzes
analyzes the
the inter-task
inter-taskimpacts.
impacts.This
Thisprocess
processis is
automatically
automatically
performedby
performed bythe
theJSA
JSAsynchronization
synchronization algorithm
algorithm according
accordingtotothe
thefollowing
followingthree steps:
three steps:

4.3.1.Data
4.3.1. DataGeneration
Generation
The data generationalgorithm,
The data generation algorithm,schematically
schematicallyshown
shownininFigure
Figure10,
10,isisapplied
appliedasasfollows:
fol-
lows:
⃝1 Extract date, location, and attribute information from R-JSA. Use date information to
① classify
Extract tasks
date, location,
on the sameand date
attribute
and information from R-JSA.
location information Use datetasks
to classify information to
on the same
classify
floor. tasks on the same date and location information to classify tasks on the same
⃝2
floor.
For each floor, create a task zone (TZ) using the X and Y coordinates of the job and the
② taskFor range,
each floor,
and create
create aa task zone
hazard (TZ)(HZ)
zone using the Xthe
using and Y coordinates
hazard attributes. of the job and
⃝3
the task range, and create a hazard zone (HZ)
Combine the HZs to create a single hazard layer (HL). using the hazard attributes.
③ Combine the HZs to create a single hazard layer (HL).

Figure 10. Schematic of data generation for R-JSA synchronization.

Figure 10. Schematic of data generation for R-JSA synchronization.

Thegenerated
The generateddata
datahave
have the
the following
following components:
components:
•
• TZ: date, location coordinates, and task range.
TZ: date, location coordinates, and task range.TZ
TZindicates
indicatesthe
thelocation and
location andrange of of
range
all tasks in the coordinate system.
all tasks in the coordinate system.
• • HZ:
HZ:date,
date, location
location coordinates,
coordinates,hazard
hazarddirection, hazard
direction, range,
hazard and and
range, residue. HZ in-HZ
residue.
dicates the range of identified hazards based on location coordinates.
indicates the range of identified hazards based on location coordinates. The hazardThe hazard
maybe
may beextended
extendedupwards
upwards and
and downwards
downwardsdepending
dependingononthe thedirection. If there
direction. areare
If there
residual attributes, the HZ is not reset in the system, even if the task date changes.
residual attributes, the HZ is not reset in the system, even if the task date changes.
Resetting occurs after affecting other task TZs following the date change.
Resetting occurs after affecting other task TZs following the date change.
• HL: combines all HZs on a workplace floor to create a single layer. Hazards transmit-
• HL: combines all HZs on a workplace floor to create a single layer. Hazards transmitted
ted from other floors are also included on the basis of the hazard direction. This plays
from other floors are also included on the basis of the hazard direction. This plays a
a crucial role in comprehensively identifying hazards from multiple surrounding
crucial role in comprehensively identifying hazards from multiple surrounding tasks.
tasks. Equation (1) represents the HL [60].
Equation (1) represents the HL [60].
Hazard Layer = 𝐻𝑍 (1)
n
[
Hazard Layer = HZi (1)
i =1

where the hazard layer is the set of all HZs on a particular floor, HZ denotes the hazard
coordinates, and i is the iterative variable representing each HZ.
 Sustainability 2024, 16, x FOR PEER REVIEW 17 of 29

Sustainability 2024, 16, 9277 16 of 28

where the hazard layer is the set of all HZs on a particular floor, HZ denotes the hazard
coordinates, and i is the iterative variable representing each HZ.

4.3.2.
4.3.2.Exploratory
ExploratoryAnalysis:
Analysis:Target–Source
Target–SourceJob JobIdentification
Identification
Target
Targetjobsjobsaffected
affectedbybysurrounding
surroundingtasks and and
tasks source jobs impacting
source surrounding
jobs impacting tasks
surrounding
are identified based on the generated data. The jobs were classified
tasks are identified based on the generated data. The jobs were classified as target and as target and source
jobs as follows:
source if the hazard-affected
jobs as follows: area (HAA)
if the hazard-affected areais(HAA)
in the TZ,
is initthe
is aTZ,
target
it isjob; if it isjob;
a target in the
if it
HZ, it is a source job. For example, in Figure 11, Job_02 is classified as a target
is in the HZ, it is a source job. For example, in Figure 11, Job_02 is classified as a target job job because
its TZ overlaps
because its TZ with the HL,
overlaps withcreating
the HL,ancreating
HAA. The overlapping
an HAA. area lies within
The overlapping the HZ
area lies of
within
Job_01, and hence, Job_01 is a source job.
the HZ of Job_01, and hence, Job_01 is a source job.

Figure 11. Schematic of exploratory analysis for target–source job identification.

Figure 11. Schematic of exploratory analysis for target–source job identification.

•• HAA:HAA
HAA: HAArepresents
representsthe
thearea
areawherein 𝑇𝑍i isisaffected
whereinTZ affectedbybythe
theHZ
HZofofsurrounding
surrounding
tasks as identified from the overlapping area between 𝑇𝑍 and HL. In this
tasks as identified from the overlapping area between TZi and HL. In this case, case,the
the
𝐻𝑍 of the target 𝑇𝑎𝑠𝑘 must be excluded from the HL. Equation (2) represents
HZi of the target Taski must be excluded from the HL. Equation (2) represents the the
HAA[60].
HAA [60].

Hazard Affected Area = HL − 𝐻𝑍 ∩ 𝑇𝑍 (2)

Hazard Affected Area = (HL − HZi ) ∩ TZi (2)
where the hazard-affected area corresponds to the area wherein the target job is affected
where
by thethe hazard-affected
hazards area corresponds
due to the source job, HL denotesto thethearea wherein
hazard theHZ
layer, target job is
denotes affected
the hazard
by
coordinates, TZ denotes the task coordinates, and i is the task being reviewed. hazard
the hazards due to the source job, HL denotes the hazard layer, HZ denotes the
coordinates, TZ denotes the task coordinates, and i is the task being reviewed.
• The HAA for all scheduled jobs is calculated. The HAA serves as the basis for classi-
• The HAA
fying for all
the jobs scheduled
into jobs is calculated.
four categories: (i) If the HAA The HAA serves
coordinate as thethe
is within basis
TZ,for theclas-
task
sifying
is classified as a target job; this indicates that the task is affected by the hazards the
the jobs into four categories: (i) If the HAA coordinate is within the TZ, due
task is classified tasks.
to surrounding as a target
(ii) If job;
the HAAthis indicates
is withinthat the task
the HZ, is affected
the task by the
is classified ashazards
a source
due
job;to surrounding
this indicates thattasks.
the(ii)taskIf the HAA
poses is within
hazard risksthe
to HZ, the task istasks.
surrounding classified
(iii) Ifasthe
a
source job; this indicates that the task poses hazard risks to surrounding
HAA coordinate lies in both TZ and HZ, the task is classified as both a target and a tasks. (iii) If
the HAAjob.
source coordinate
(iv) If thelies
HAA in both TZ andlies
coordinate HZ,inthe task isTZ
neither classified
nor HZ,as both
the taska is
target and
excluded
afrom
source job. (iv) If the
SIMOPS hazard review. HAA coordinate lies in neither TZ nor HZ, the task is excluded
from SIMOPS hazard review.
4.3.3. Hierarchical Analysis: Target-Hazard Identification
4.3.3. Hierarchical Analysis: Target-Hazard Identification
The analysis is conducted for each target job and source job pairing. The overlapping
The analysis is conducted for each target job and source job pairing. The overlapping
area between the TZ of the target job and the HZ of the source job is calculated. The num-
area between the TZ of the target job and the HZ of the source job is calculated. The number
ber of HZs may vary depending on the number of hazards due to the source job. This
of HZs may vary depending on the number of hazards due to the source job. This identifies
identifies the source hazards and the HAA affecting the target job. Figure 12 shows a sche-
the source hazards and the HAA affecting the target job. Figure 12 shows a schematic of
matic of this process.
this process.
Sustainability 2024,
Sustainability 16,16,
2024, 9277
x FOR PEER REVIEW 17 29
18 of of 28

Figure12.
Figure 12.Schematic
Schematicof
of hierarchical
hierarchical analysis
analysis for
for identifying
identifyingsource
sourcejob
jobhazards.
hazards.

4.4.
4.4.SIMOPS
SIMOPSRiskRisk Assessment
Assessment
Risk
Riskassessment
assessmentcomprises
comprisesaacombination
combinationofofthetheprobability
probabilityandandseverity
severityofofananaccident
acci-
expressed as a matrix.
dent expressed It allows
as a matrix. for a quantitative
It allows comparison
for a quantitative of riskofpriorities
comparison [49]. Table
risk priorities [49]. 2
Table the
shows 2 shows the risk assessment
risk assessment matrix
matrix used toused to calculate
calculate the riskthe risk[61].
score score [61].

Table2.2.Risk
Table Riskassessment
assessmentmatrix.
matrix.

Severity
Severity (S) (S)
Risk
Risk Score
Score
Minor Minor Marginal
Marginal Critical
Critical Fatality
Fatality
Very likely 10
Very likely 10 13 13 1515 16
16
Probability Probable
Probable 6 6 9 9 1212 14
14
Probability (P)
(P) Possible
Possible 3 3 5 5 88 11
11
Unlikely
Unlikely 1 1 2 2 44 77

InInthis
thisstudy,
study,the
theprevious
previousriskrisk assessmentprocedure
assessment procedure was
was modified
modified toto calculate
calculate the
the risk
risk of
level level of hazards
hazards in SIMOPS.
in SIMOPS. The Themostmost common
common method
method usedused in risk
in risk evaluation
evaluation is the
is the risk
risk priority
priority number number
(RPN),(RPN),
whichwhich
is widelyis widely
adopted adopted
due todue to its simplicity
its simplicity and conven-
and convenience [62].
ience [62]. However, while RPN is suitable for calculating the risk
However, while RPN is suitable for calculating the risk level of individual tasks,level of individual tasks,
it has
it has limitations
limitations in evaluating
in evaluating the degree
the degree of risk
of risk in simultaneous
in simultaneous operations,asasaddressed
operations, addressed in
this study. To assess how the risk in one operation affects surrounding tasksduring
in this study. To assess how the risk in one operation affects surrounding tasks during
simultaneous operations,
simultaneous operations, this
this study
study developed
developedaanew newequation
equationcalled
calledthetheSIMOPS
SIMOPS Risk
Risk
Score by incorporating factors such as work area, hazard area, and the
Score by incorporating factors such as work area, hazard area, and the number of workers number of workers
intothe
into thetraditional
traditionalRPN.
RPN.
The base risk score was extracted from the JSA of the source job, and three additional
The base risk score was extracted from the JSA of the source job, and three additional
variables derived from the R-JSA synchronization model were used. These variables,
variables derived from the R-JSA synchronization model were used. These variables, which
which indicate the SIMOPS hazard level, were derived in consultation with safety experts.
indicate the SIMOPS hazard level, were derived in consultation with safety experts. The
The risk level increases with the size of the hazard area within the work area and the
risk level increases with the size of the hazard area within the work area and the number
number of workers in the hazard area. Therefore, TZ, HAA, and the number of workers
of workers in the hazard area. Therefore, TZ, HAA, and the number of workers (N) were
(N) were selected. These were integrated into the existing risk assessment formula and
selected. These were integrated into the existing risk assessment formula and were used as
were used as variables for the SIMOPS risk assessment. The SIMPOS risk score was calcu-
variables for the SIMOPS risk assessment. The SIMPOS risk score was calculated as shown
lated as shown in Equation (3).
in Equation (3).
SIMOPSRisk
SIMOPS Score== P𝑃 ××S𝑆 ××H AA ×× 𝑁
RiskScore N, , (3)(3)
S s
TZ
where SIMOPS Risk Score represents the risk level of hazards in SIMOPS, 𝑃 is the prob-
where SIMOPS Risk Score represents the risk level of hazards in SIMOPS, PS is the probabil-
ability of the source hazard, 𝑆 is the severity of the source hazard, HAA is the hazard-
ity of the source hazard, Ss is the severity of the source hazard, HAA is the hazard-affected
affected area, TZ is the task zone, and N is the number of workers in the TZ.
area, TZ is the task zone, and N is the number of workers in the TZ.
Once the risk level of the identified hazards in SIMOPS has been calculated by the
Once the risk level of the identified hazards in SIMOPS has been calculated by the
model, priorities are established accordingly.
model, priorities are established accordingly.
Sustainability 2024, 16, 9277 18 of 28

5. Test and Validation

5.1. Test Setup
The performance of the proposed HIRAS in identifying and assessing the hazards due
to inter-task interactions in a SIMOPS environment was evaluated as follows:
• Data collection and preprocessing: 40 JSAs used in actual maintenance work were
collected. Sensitive information on individuals and companies was selectively used.
The location coordinates and attributes necessary for the R-JSA synchronization model
were then added and standardized via the R-JSA method.
• Experimental design: A three-story plant with a floor area of 90,000 m2 was assumed.
To simulate SIMOPS, the tasks were scheduled over two consecutive days to reflect the
residual attributes as hazards. Two scenarios were chosen to evaluate the identification
capability and utility of the model in actual work environments. The first was a
scenario with planned work alone, and the second was a scenario where unplanned
work was added to the planned work.
• Details of the model used: Disaster types were classified using the GPT-3.5 model via
the OpenAI API in Google Sheets using function calls. GPT-3.5, developed by OpenAI,
is widely used for natural language processing and generation tasks. The model
was pre-trained on a large text dataset and can understand the context and perform
classification tasks. The R-JSA synchronization model developed was implemented in
Python version 3.11. Scripts were written and executed using Visual Studio version
1.86; the modules openpyxl, os, shutil, matplotlib.pyplot, and numpy were used.
• Evaluation criteria: The rate of identification of hazards leading to SIMOPS accidents
was adopted as the criterion. This criterion was used as an indicator to measure the
effective identification of hazards in complex work environments. The identification
results were validated via a confusion matrix. The validation was based on the
simulation results of the model. As the actual accidents are potential, the simulation
accuracy of the model does not imply the accuracy of accident prediction.

5.2. Performance Metrics for Model Test

A confusion matrix was used to verify the model’s performance by comparing actual
values with predicted values [63]. Table 3 shows the confusion matrix used in this study.

Table 3. Confusion matrix for the JSA synchronization model.

Predictive Value
Positive Negative
Positive True Positive (TP) False Negative (FN)
Actual Value
Negative False Positive (FP) True Negative (TN)

The cells in the confusion matrix are defined as follows:

• True positive (TP): Cases that are actually positive and correctly predicted as positive.
• False negative (FN): Cases that are actually positive and incorrectly predicted as
negative.
• False positive (FP): Cases that are actually negative and incorrectly predicted as
positive.
• True negative (TN): Cases that are actually negative and correctly predicted as negative.
The confusion matrix allows for the calculation of accuracy, precision, recall, and
F1-score as follows [63,64].
• Accuracy is the ratio of correct predictions to total predictions, as defined in Equation (4).

TP + TN
Accuracy = × 100% (4)
TP + TN + FP + FN
Sustainability 2024, 16, 9277 19 of 28

• Precision is the ratio of correctly predicted positive instances to all instances predicted
as positive, as defined in Equation (5).

TP
Precision = × 100% (5)
( TP + FP)
• Recall is the ratio of correctly predicted positive instances to all actual positive in-
stances, as defined in Equation (6).

TP
Recall = × 100% (6)
( TP + FN )
• The F1-score is the harmonic mean of precision and recall, as defined in Equation (7).
The F1-score provides a comprehensive measure of the model’s performance.

( Precision × Recall )
F1 − Score = 2 × (7)
( Precision + Recall )
The predictive value is the result calculated by the R-JSA synchronization model,
whereas the actual value is derived using the rule-based system validation methodology
proposed by Knauf. The methodology proposed by Knauf compares the system-generated
results with the final results reviewed by experts in the relevant field. It evaluates the relia-
bility of the methodology by assessing how closely the results of the proposed methodology
align with expert judgment [65]. The SME team consisted of six field managers with over
ten years of safety management experience at P steel mill. Table 4 details the qualifications
of the SMEs.

Table 4. Qualifications of the SMEs that participated in the test.

Expert Code Year of Experiences Discipline

Capital Investment,
A 12
Maintenance Management
B 13 Maintenance Management
Capital Investment,
C 11
Maintenance Management
D 17 Capital Investment
E 10 Maintenance Management
F 23 Maintenance Management

5.3. Implementation and Results

5.3.1. Scenario 1: Identification and Assessment of Hazards among Multiple Planned Tasks
The first scenario in this study focuses on the identification and evaluation of hazards
that may arise from the execution of several planned tasks. The first scenario was conducted
in two stages according to experimental conditions. First, the equipment managers re-
analyzed 37 JSAs relationally. During the analysis, only items in the JSA that affected the
surrounding tasks were selected and evaluated. The manager initially classified the hazard
types according to KOSHA standards, followed by a secondary classification using a GPT-
based prompt in Google Sheets, which indicates the matching status. The manager reviewed
and re-evaluated any discrepancies. Items that could potentially cause SIMOPS accidents
were automatically selected using Excel functions, and the manager made the final decision
considering the task and site conditions. This iterative verification alternating between the
manager and the system minimized the possibility of omission and overinclusion. The
hazard range, direction, and residue attributes of the selected hazards were evaluated.
Next, R-JSAs were synchronized temporally and spatially, and the inter-task impacts
were analyzed. The process was automated by collecting the evaluated R-JSA files into
one folder and executing the R-JSA synchronization model developed in this study. The
Sustainability 2024, 16, 9277 20 of 28

R-JSAs were classified by task date for temporal synchronization and by floor coordinates
for spatial synchronization. Table 5 lists the tasks by date and floor.

Table 5. Work data and floor-wise job list for Scenario 1.

Classification Day1 Day2

1st Floor Job_01, 02, 03, 22, 24, 25, 28 Job_04, 05, 23, 27, 29
2nd Floor Job_07, 08, 13, 14, 35, 36, 37 Job_09, 10, 11, 12, 15, 16
3rd Floor Job_18, 30, 34, 38, 39, 40 Job_ 20, 21, 26, 31, 32, 33

Next, the tasks were placed in a coordinate system based on the coordinates of each
task, and the TZ and HZ coordinate data were generated based on the task and hazard
attributes. The HZ data were processed as follows: if there was a vertical attribute in the
HZ, coordinates were assigned to the related floor HL; if there was a residual attribute, the
HZ coordinates were assigned to the coordinate system for the second day. For example,
although Job_14 was performed on the second floor, the hazard in Step 2 had a downward
vertical attribute; therefore, the same HZ coordinates were assigned to the first-floor plane.
Once the actual work situation was modeled, it was analyzed to identify the target jobs
and source jobs as well as the hazards due to source jobs affecting target jobs. Finally, a
SIMOPS risk score was calculated for the identified results, and priorities were assigned.
The target job–source job list generated from the first scenario included 119 cases: 72
on the first day and 47 on the second day. The list was sorted based on the SIMOPS risk
score, and the priority of each item was indicated. To coordinate between jobs, information
on the safety managers of Target and source jobs and information on the hazards were
provided. For example, the hazard in Step 2 of Job_14 was found to affect JSA_24. Table 6
shows a part of the identified target job–source job list.

Table 6. Target job–source job list and priority identified in Scenario 1.

Target Job Source Job

Job Steps SIMOPS Priority
JSA Safety JSA Safety Risk Score
of
Number Supervisor Number Supervisor
Hazard
JSA_14 Joseph JSA_24 Isaac 5 160 1
JSA_14 Joseph JSA_24 Isaac 10 160 2
JSA_34 Tyler JSA_37 Zachary 3 160 3
JSA_34 Tyler JSA_37 Zachary 6 160 4
JSA_25 Dylan JSA_37 Zachary 3 120 5
JSA_25 Dylan JSA_37 Zachary 6 120 6
JSA_07 Michael JSA_03 Oliver 6 120 7
JSA_07 Michael JSA_03 Oliver 8 120 8
JSA_08 Jackson JSA_03 Oliver 6 120 9
JSA_08 Jackson JSA_03 Oliver 8 120 10
JSA_13 Samuel JSA_02 Benjamin 4 120 11
JSA_13 Samuel JSA_02 Benjamin 6 120 12
JSA_13 Samuel JSA_38 Nicholas 3 120 13
JSA_13 Samuel JSA_38 Nicholas 4 120 14
JSA_13 Samuel JSA_38 Nicholas 5 120 15
JSA_13 Samuel JSA_38 Nicholas 8 120 16
JSA_13 Samuel JSA_38 Nicholas 9 120 17
JSA_36 Christian JSA_22 Christopher 3 110 18
JSA_36 Christian JSA_22 Christopher 4 110 19
JSA_24 Isaac JSA_14 Joseph 2 88 20

The results of the analysis were visualized to obtain an intuitive understanding. The
color codes and meanings of the components are detailed below. Figure 13 shows a
visualization of the results of the analysis for the first and second days of Scenario 1.
 Table 7. Validation results of the JSA synchronization model for Scenario 1.

Value Performance
Accuracy Precision Recall F1-Score
TP FN FP TN
Sustainability 2024, 16, 9277 (%) (%) (%) (%) 21 of 28
118 3 1 4659 99.92 99.16 97.52 98.33

tainability 2024, 16, x FOR PEER REVIEW 23 of 29

(a)

(b)
Figure 13. Results
Figureof13.
theResults
analysis
of for
the Scenario 1: (a)
analysis for first day;
Scenario (b) first
1: (a) secondday;day.
(b) second day.

• 2:The
5.3.2. Scenario Identification and Assessment
green rectangle represents TZ,of Hazards duringarea
the maximum Unplanned Work
of the task.
•
The second scenario considered in this study simulated unplanned work: aof
The yellow rectangle represents HZ, the maximum hazard area the task.
situation
• additional
wherein three The orange rectangle
tasks represents
were added to theHAA,
day 2the
taskarea
listwhere TZcompletion
after the is affected byof the HZ of
surrounding tasks.
the previous experiment was assumed. The model conducted an analysis including the
•
three additional Blue textanalyzed
R-JSAs indicatesby the
thesource of TZ and
equipment HZ. The SMEs were able to con-
manager.
• Red text indicates the source of the vertical
firm the analysis information for 37 planned tasks from Scenario attribute HZ. SMEs examined
1. The
• Purple text indicates the source of the residual
the hazards due to surrounding tasks through the JSAs of the additional attribute HZ.tasks
For example,
and the there is no
location maps of the tasks. The average number of hazards individually identified of
residual attribute hazard area on the first day due to the absence by previous
the work
SMEs was 11, which is 38.7% of the results identified by the model. When individual iden-
tification results were combined, it increased to 25, corresponding to an identification rate
of 89.3%. A significant difference was confirmed between the individual and combined
results. As the combined results converged at a higher level, the experiment was con-
cluded. Table 8 shows the results of identification obtained using the model compared to
Sustainability 2024, 16, 9277 22 of 28

information. On the second day, the residual hazard attribute for Step 5 from the
JSA_14 on the first day appears as HZ.
A confusion matrix based on the final results produced by the SMEs was used to
validate the model. In Scenario 1, a total of 4781 inter-task interactions were reviewed.
The model correctly identified 118 SIMOPS hazards (TP), three missing cases (FN), and
incorrectly identified one case (FP). The performance metrics of the model are shown in
Table 7.

Table 7. Validation results of the JSA synchronization model for Scenario 1.

Value Performance
Accuracy Precision Recall F1-Score
TP FN FP TN
(%) (%) (%) (%)
118 3 1 4659 99.92 99.16 97.52 98.33

5.3.2. Scenario 2: Identification and Assessment of Hazards during Unplanned Work

The second scenario considered in this study simulated unplanned work: a situation
wherein three additional tasks were added to the day 2 task list after the completion of the
previous experiment was assumed. The model conducted an analysis including the three
additional R-JSAs analyzed by the equipment manager. The SMEs were able to confirm
the analysis information for 37 planned tasks from Scenario 1. The SMEs examined the
hazards due to surrounding tasks through the JSAs of the additional tasks and the location
maps of the tasks. The average number of hazards individually identified by the SMEs was
11, which is 38.7% of the results identified by the model. When individual identification
results were combined, it increased to 25, corresponding to an identification rate of 89.3%.
A significant difference was confirmed between the individual and combined results. As
the combined results converged at a higher level, the experiment was concluded. Table 8
shows the results of identification obtained using the model compared to those of the SMEs
in Scenario 2.

Table 8. Identification results obtained using the model compared to SME results in Scenario 2.

Model SMEs
Target Job Source Job
JSA JSA Job Steps of
A B C D E F
Number Number Hazard
JSA_17 JSA_21 3 □ □ □ □ ✓ □
JSA_17 JSA_21 6 □ □ □ □ □ □
JSA_19 JSA_17 4 □ ✓ □ □ □ □
JSA_19 JSA_17 7 □ ✓ □ □ □ □
JSA_21 JSA_17 4 □ ✓ □ □ □ ✓
JSA_21 JSA_17 7 □ ✓ □ □ □ ✓
JSA_17 JSA_26 5 □ □ □ □ ✓ ✓
JSA_17 JSA_26 6 □ □ □ □ ✓ □
JSA_06 JSA_10 2 ✓ ✓ ✓ ✓ ✓ ✓
JSA_23 JSA_17 2 ✓ □ □ ✓ □ ✓
JSA_23 JSA_17 3 ✓ □ □ □ □ ✓
JSA_23 JSA_17 6 ✓ □ □ ✓ □ □
JSA_23 JSA_17 9 ✓ □ □ □ □ □
JSA_26 JSA_17 4 □ □ □ □ □ □
JSA_26 JSA_17 7 □ □ □ □ □ □
JSA_17 JSA_21 4 □ ✓ □ □ □ ✓
JSA_23 JSA_17 4 ✓ □ ✓ □ ✓ ✓
JSA_23 JSA_17 7 ✓ □ ✓ □ □ ✓
JSA_06 JSA_02 3 ✓ □ □ □ □ □
JSA_19 JSA_21 3 ✓ ✓ ✓ ✓ ✓ ✓
JSA_19 JSA_21 6 ✓ ✓ ✓ ✓ □ ✓
JSA_17 JSA_19 2 ✓ ✓ □ □ □ □
JSA_17 JSA_19 5 ✓ ✓ □ □ ✓ ✓
JSA_17 JSA_16 5 ✓ ✓ ✓ ✓ ✓ ✓
JSA_16 JSA_17 4 □ □ ✓ □ □ ✓
JSA_16 JSA_17 7 □ □ ✓ □ □ ✓
JSA_19 JSA_26 5 □ □ □ ✓ ✓ □
JSA_19 JSA_26 6 □ □ □ ✓ ✓ □
Sustainability 2024, 16, 9277 23 of 28

5.4. Discussion
The key performance metric of the JSA synchronization model in Scenario 1 was its
ability to accurately identify hazards during SIMOPS with a high recall rate of 97.52%.
The recall rate indicates that the model effectively identifies hazards and can contribute
to preventing risks during SIMOPS. The excellent performance metrics of the model can
be attributed to the improvements to the existing JSA data via the R-JSA methodology.
The improved input data played a crucial role in improving the model output results.
Nonetheless, there were three missed cases (FN) and one incorrectly identified case (TP).
The reasons can be attributed to omissions and errors. Although SMEs can identify missing
information in JSAs during the final review, the model cannot generate new information
from the R-JSA, leading to omissions. The TP was attributed to incorrect data entry
by the responsible worker for the direction attribute in the R-JSA. The quality of input
data significantly impacts the results, highlighting the need for continuous efforts to
improve data completeness and accuracy. The results of Scenario 1 affirmed Moravec’s
paradox [66]—computers easily perform complex calculations while humans excel in
intuitive understanding. Thus, better outcomes can be obtained by complementing the
strengths of both the model and humans.
Scenario 2 demonstrated that the SIMOPS process with multiple experts is useful
in identifying hazards in SIMOPS via the differences between individual and integrated
identification results by SMEs. However, the results highlighted the limitation of the
SIMOPS process in responding immediately to variable situations such as unplanned tasks,
thereby confirming the utility of the model.
During interviews, SMEs reported that they could pay sufficient attention to identify
and correct missing or incorrect information in the detailed target–source list and visual-
izations obtained from the model in Scenario 1. In contrast, despite sufficient information
on the existing and additional tasks, the identification rate was low in Scenario 2. The
SMEs reported that they repeatedly rechecked the information on surrounding tasks while
reviewing additional tasks with drawings and JSAs, making inference difficult due to the
diversity of hazard attribute variables. The results of Scenario 2 highlight the limitations
of human memory and inference ability. These results are supported by research findings
which indicate that working memory and inference share cognitive capacity. Working mem-
ory refers to a cognitive system that maintains a certain amount of information temporarily,
while inference refers to the act of drawing conclusions from given information. As the
number of variables increases, the increasing complexity of interrelationships leads to poor
inference [67].
The following insights were obtained from both scenarios. The results obtained
in this study indicate that HIRAS can help reduce the load on working memory from
a cognitive capacity perspective and help support inference on inter-task relationships.
Therefore, safety managers can focus on productive work, such as identifying missed
hazards, coordinating tasks, and developing countermeasures based on the provided
information. Moreover, HIRAS can be used for the rational allocation of resources, such
as effort, time, and cost, to manage hazards. Job managers and workers can identify the
target job they are performing, check the source job information, and use the information
for mutual coordination. A limitation of HIRAS is that some items may be omitted due to
the quality of JSAs. However, as JSAs are evaluated annually and updated as needed, the
likelihood of missing items is expected to gradually decrease.
The relevance and contribution of this study can be summarized as follows. First, by
demonstrating that hazards in SIMOPS can be identified using JSAs, this study shows that
the limitations of JSAs pointed out in previous studies can be addressed. Thus, JSAs can be
used not only as a tool for analyzing individual task risks but also as an effective tool for
identifying hazards in SIMOPS environments. Second, previous research on identifying
hazards in SIMOPS has focused on general tasks because they are based on information
derived from expert judgment. In contrast, this study uses hazard information identified
by the managers responsible for each task, including the specificity of individual tasks and
Sustainability 2024, 16, 9277 24 of 28

work environment factors. Moreover, because hazard information is updated regularly or

as needed, it reflects the actual information in changing work environments. Third, this
study considers the impact of residual hazards on subsequent tasks. To the best of our
knowledge, the impact of residual hazards has not been considered in previous studies.
Thus, HIRAS helps us to conduct a more comprehensive analysis of safety management
during SIMOPS.
Although HIRAS was developed as a proof of concept (PoC), comprehensive valida-
tion confirmed two points: (i) it can derive new information on inter-task impacts during
SIMOPS from JSAs; (ii) it can reduce the cognitive burden on safety managers in complex
and variable work environments. This study is distinct from previous studies because it
focuses on identifying and assessing hazards in SIMOPS based on JSA and targets plant
maintenance work.

6. Conclusions
6.1. Summary and Contributions
This study proposed a new safety management tool, “HIRAS,” to identify and assess
hazards between SIMOPS during plant maintenance work. The traditional JSA methodol-
ogy is useful for the safety management of individual tasks; however, managing the safety
of surrounding tasks via JSA is challenging. Industrial sites continue to evolve, becoming
more complex and variable. Hence, research on methods for ensuring worker safety and
minimizing potential hazards is essential when it comes to responding to the changes in
industrial environments. The framework developed in this study can identify and assess
the impacts of hazards resulting from interactions between tasks by synchronizing existing
JSA information temporally and spatially. The R-JSA method was developed herein to sys-
tematically standardize unstructured data, such as task locations and hazard information.
The results of the R-JSA method were used to develop the R-JSA synchronization model for
task synchronization and hazard impact analysis. The S-RA formula was used to prioritize
the results generated by the model based on the risk levels. The HIRAS framework was
validated through two scenarios, demonstrating its utility for SIMOPS safety management.
The contributions of this study are summarized in the following three points. First,
it proposes a new approach that extends the use of JSA beyond individual task safety
management to include the safety management of surrounding tasks. This suggests that
by leveraging the domain knowledge of task managers and synchronizing JSAs, hazards
in surrounding tasks can be identified and assessed. Second, it enables safety managers
to direct their focus toward preventive tasks. The visualization of target and source jobs
and detailed lists helps reduce the cognitive burden of identifying hazards in complex and
variable environments. Finally, by using easily accessible and regularly updated JSAs, it
offers small workplaces with limited safety management personnel an effective way to
enhance safety during SIMOPS. Major accidents can be prevented by improving safety in
plant maintenance work environments wherein multiple tasks are performed simultane-
ously. Ultimately, the results of this study are expected to contribute to sustainable business
management and the protection of worker lives and health in hazardous environments.

6.2. Limitations and Future Work

This study has two main limitations. First, it does not account for changes in TZ and
HZ over time. The maximum range during task execution is considered for both the TZ
and HZ. Adding a feature to specify time for selected parts of the maximum range could
increase realism regarding zone changes during tasks. Standard times, such as mornings
and afternoons, are recommended. Highly detailed units may not accommodate changes
in task progress due to the work environment. Second, the quality of input data, the
JSAs, has a decisive impact on the results. This limitation can be gradually addressed if
employers and employees actively participate in systematically managing the data through
digitization.
Sustainability 2024, 16, 9277 25 of 28

The HIRAS developed in this study represents a significant step forward, but further
research is required to address its limitations and realize its full potential. Future research
should focus on integrating HIRAS with existing enterprise systems, such as ERP and
safety management systems, to facilitate its practical application in industrial settings.
Although this study focused on industrial plant maintenance, the results are applicable
to other fields using JSA. We expect that future research based on this study on preventing
SIMOPS accidents will contribute to improving safety levels in industrial sites and corporate
sustainability management.

Author Contributions: The contributions of the authors for this article are as follows: Conceptualiza-
tion, S.-J.K., S.-W.C. and E.-B.L.; methodology, S.-J.K., S.-W.C. and E.-B.L.; software, S.-J.K.; validation,
S.-J.K., S.-W.C. and E.-B.L.; formal analysis, S.-J.K. and S.-W.C.; investigation, S.-J.K. and S.-W.C.;
resources, S.-J.K., S.-W.C. and E.-B.L.; data curation, S.-J.K.; writing, original draft preparation, S.-J.K.
and S.-W.C.; writing, review and editing, S.-J.K., S.-W.C. and E.-B.L.; visualization, S.-J.K. and S.-W.C.;
supervision, E.-B.L.; project administration, E.-B.L. All authors have read and approved the final
version of the manuscript.
Funding: This research received no external funding.
Institutional Review Board Statement: Not applicable.
Informed Consent Statement: Informed consent was obtained from all subjects involved in the
study.
Data Availability Statement: The original contributions presented in the study are included in the
article, further inquiries can be directed to the corresponding author.
Acknowledgments: The authors of this study would like to thank POSCO for their informational
support and technical cooperation. The views expressed in this paper are solely those of the authors
and do not represent those of any official organization.
Conflicts of Interest: The authors declare no conflicts of interest.

Abbreviations
The following abbreviations and parameters are used in this paper:
ERP Enterprise Resource Planning.
FMEA Failure Modes and Effect Analysis.
GPT Generative Pre-trained Transformer.
HAA Hazard-Affected Area.
HAZOP Hazard and Operability Studies.
HIRAS Hazard Identification and Risk Assessment of Simultaneous operations.
HL Hazard Layer.
HZ Hazard Zone.
IMCA The International Marine Contractors Association.
ISO International Organization for Standardization.
JSA Job Safety Analysis.
KOSHA Korea Occupational Safety and Health Agency.
PoC Proof of Concept.
R-JSA Relation-oriented JSA method.
RPN Risk Priority Number.
SIMOPS SIMultaneous OPerations.
S-RA SIMOPS Risk Assessment.
TBM ToolBox Meeting.
TZ Task Zone.

References
1. Hollnagel, E.; Wears, R.L.; Braithwaite, J. From Safety-I to Safety-II: A White Paper; University of Southern Denmark: Odense,
Denmark; University of Florida: Gainesville, FL, USA; Macquarie University: Sydney, Australia, 2015. [CrossRef]
2. The International Association of Oil & Gas Producers (IOGP). Simultaneous Operations. Available online: https://www.iogp.
org/wp-content/uploads/2018/11/11SimultaneousOps_IOGP577version1.2.pdf (accessed on 14 October 2024).
Sustainability 2024, 16, 9277 26 of 28

3. Ipieca-IOGP. Incident Management System for the Oil and Gas Industry-Good Practice Guidelines for Incident Management
and Emergency Response Personnel. Available online: https://www.ospri.online/site/assets/files/1135/ipieca-iogp_incident_
management_system.pdf (accessed on 14 October 2024).
4. Fan, H.; Enshaei, H.; Jayasinghe, S.G. Safety philosophy and risk analysis methodology for LNG bunkering simultaneous
operations (SIMOPs): A literature review. Saf. Sci. 2021, 136, 105150. [CrossRef]
5. Baybutt, P. Simultaneous operation (SIMOP) review: An important hazard analysis tool. Process Saf. Prog. 2017, 36, 62–66.
[CrossRef]
6. Association, I.M.C. Guidance on Simultaneous Operations (SIMOPS); IMCA: London, UK, 2010.
7. CSB. Evergreen Packaging Mill—Fire During Hot Work; U. S. Chemical Safety and Hazard Investigation Board: Washington, DC,
USA, 2021.
8. Japanese Law Translation Database System. Industrial Safety and Health Act. Available online: https://www.japaneselawtranslation.
go.jp/en/laws/view/3440 (accessed on 15 October 2024).
9. EnvilianceASIA. China, Labor Safety and Health Policy Report. Available online: https://enviliance.com/regions/east-asia/cn/
cn-osh/ch-labor-safety (accessed on 15 October 2024).
10. HXC Certification Center Co. Ltd. CNPC Health, Safety and Environmental Management System Certification. Available online:
https://www.hxccc.org/index.php?m=home&c=View&a=index&aid=476&lang=en (accessed on 15 October 2024).
11. Zhou, Z. Understanding the administrative regulation on occupational health and trend in China. J. Occup. Health 2018,
60, 126–131. [CrossRef]
12. DGUV. The Legal Basis of Occupational Safety and Health Activity in Germany. Available online: https://www.dguv.de/en/
prevention/rules_regulations/index.jsp (accessed on 15 October 2024).
13. Federal Ministry of Labour and Social Affairs. Occupational Safety and Health. Available online: https://www.bmas.de/EN/
Labour/Occupational-Safety-and-Health/occupational-safety-and-health-art.html (accessed on 15 October 2024).
14. The Occupational Safety and Health Research Institute (OSHRI). A Study on the Types of Accidents Caused by Simultaneous
Operations and Preventive Measures. Available online: https://oshri.kosha.or.kr/oshri/publication/researchReportSearch.do?
mode=view&articleNo=427931&attachNo= (accessed on 22 August 2024).
15. Korea Occupational Safety and Health Agency, Industrial Accident Statistics News Release. Available online: https://www.
kosha.or.kr/kosha/data/industrialDisasterStatistics.do (accessed on 16 October 2024).
16. Ministry of Government Legislation, South Korea. Occupational Safety and Health Act. Law No. 19611. Available on-
line: https://www.law.go.kr/%EB%B2%95%EB%A0%B9/%EC%82%B0%EC%97%85%EC%95%88%EC%A0%84%EB%B3%B4
%EA%B1%B4%EB%B2%95 (accessed on 22 August 2024).
17. Ministry of Employment and Labor, South Korea. Pre-Job Safety Meeting (Tool Box Meeting) Guide; Ministry of Employment and
Labor, South Korea: Sejong-si, Republic of Korea, 2023; Available online: https://www.moel.go.kr/local/seoul/news/notice/
noticeView.do?bbs_seq=20230200582 (accessed on 22 August 2024).
18. Vishnu, C.R.; Regikumar, V. Reliability based maintenance strategy selection in process plants: A case study. Procedia Technol.
2016, 25, 1080–1087. [CrossRef]
19. Garg, A.; Deshmukh, S.G. Maintenance management: Literature review and directions. J. Qual. Maint. Eng. 2006, 12, 205–238.
[CrossRef]
20. Pintelon, L.; Muchiri, P.N. Safety and maintenance. In Handbook of Maintenance Management and Engineering; Springer: London,
UK, 2009; pp. 613–648. [CrossRef]
21. Pophaley, M.; Vyas, R.K. Plant maintenance management practices in automobile industries: A retrospective and literature review.
J. Ind. Eng. Manag. 2010, 3, 512–541. [CrossRef]
22. Okoh, P.; Haugen, S. The influence of maintenance on some selected major accidents. Chem. Eng. Trans. 2013, 31, 493–498.
[CrossRef]
23. Okoh, P.; Haugen, S. A study of maintenance-related major accident cases in the 21st century. Process Saf. Environ. Prot. 2014,
92, 346–356. [CrossRef]
24. Occupational Safety and Health Administration (OSHA), US Department of Labor. Health Program Management Guidelines;
Occupational Safety and Health Administration (OSHA), US Department of Labor: Washington, DC, USA, 2015. Available online:
https://www.osha.gov/sites/default/files/SHPM_guidelines.pdf (accessed on 22 August 2024).
25. Occupational Safety and Health Administration (OSHA), US Department of Labor. Job Hazard Analysis; Occupational Safety and
Health Administration (OSHA), US Department of Labor: Washington, DC, USA, 2002. Available online: https://www.osha.
gov/sites/default/files/publications/osha3071.pdf (accessed on 22 August 2024).
26. Albrechtsen, E.; Solberg, I.; Svensli, E. The application and benefits of job safety analysis. Saf. Sci. 2019, 113, 425–437. [CrossRef]
27. Ghasemi, F.; Doosti-Irani, A.; Aghaei, H. Applications, shortcomings, and new advances of Job Safety Analysis (JSA): Findings
from a systematic review. Saf. Health Work 2023, 14, 153–162. [CrossRef]
28. Rozenfeld, O.; Sacks, R.; Rosenfeld, Y.; Baum, H. Construction job safety analysis. Saf. Sci. 2010, 48, 491–498. [CrossRef]
29. Chapanis, A.; Garner, W.R.; Morgan, C.T. Applied Experimental Psychology: Human Factors in Engineering Design; American
Psychological Association (APA): Washington, DC, USA, 1949. [CrossRef]
30. Weidner, T.J. Planned maintenance vs Unplanned maintenance and facility costs. IOP Conf. Ser. Earth Environ. Sci. 2023,
1176, 012037. [CrossRef]
Sustainability 2024, 16, 9277 27 of 28

31. Rashidi Nasab, A.; Malekitabar, H.; Elzarka, H.; Nekouvaght Tak, A.; Ghorab, K. Managing Safety Risks from Overlapping
Construction Activities: A BIM Approach. Buildings 2023, 13, 2647. [CrossRef]
32. Sascha. Introduction to the Zettelkasten Method. Zettelkasten (Blog), 27 October 2020. Available online: https://zettelkasten.de/
introduction/ (accessed on 16 October 2024).
33. Purohit, D.P.; Siddiqui, N.; Nandan, A.; Yadav, B.P. Hazard identification and risk assessment in construction industry. Int. J. Appl.
Eng. Res. 2018, 13, 7639–7667.
34. hh2. Hazard Identification and Evaluation in Construction Industry. Available online: https://www.hh2.com/construction-
management/hazard-identification-and-evaluation-in-construction-industry (accessed on 16 October 2024).
35. International Organization for Standardization (ISO). ISO 45001—All You Need to Know. Available online: https://www.iso.org/
news/ref2271.html (accessed on 16 October 2024).
36. Taylor, F.W. The Early Sociology of Management and Organizations. Volume I: Scientific Management; Routledge: New York, NY,
USA, 2003.
37. Heinrich, H.; Petersen, D.; Roos, N. In Dustrial Accident Prevention: A Safety Management Approach, 5th ed.; McGraw-Hill: New
York, NY, USA, 1980.
38. Glenn, D.D. Job safety analysis: Its role today. Prof. Saf. 2011, 56, 48–57.
39. Fine, W.T.; Kinney, W. Mathematical Evaluations for Controlling Hazards; Naval Ordnance Laboratory White Oak: Washington, DC,
USA, 1971; Available online: https://apps.dtic.mil/sti/citations/AD0722011 (accessed on 22 August 2024).
40. Bird, F.E.; Germain, G.L.; Clark, M.D. Practical Loss Control Leadership; International Loss Control Institute: Loganville, GA, USA,
1990; Available online: https://archive.org/details/practicallosscon0000bird (accessed on 22 August 2024).
41. Friend, M.A.; Kohn, J.P. Fundamentals of Occupational Safety and Health; Rowman & Littlefield: Lanham, MD, USA, 2023.
42. Zheng, W.; Shuai, J.; Shan, K. The energy source based job safety analysis and application in the project. Saf. Sci. 2017, 93, 9–15.
[CrossRef]
43. Zheng, X.; Wang, Y.; Chen, Y.; Zeng, Q.; Jin, L. Influence of Safety Experience and Environmental Conditions on Site Hazard
Identification Performance. Buildings 2023, 13, 251. [CrossRef]
44. Hong, Y.; Cho, J. Enhancing Individual Worker Risk Awareness: A Location-Based Safety Check System for Real-Time Hazard
Warnings in Work-Zones. Buildings 2024, 14, 90. [CrossRef]
45. Heinrich, H.W. Industrial Accident Prevention. A Scientific Approach, 2nd ed.; McGraw-Hill: New York, NY, USA, 1941.
46. Patrucco, M.; Bersano, D.; Cigna, C.; Fissore, F. Computer image generation for job simulation: An effective approach to
occupational Risk Analysis. Saf. Sci. 2010, 48, 508–516. [CrossRef]
47. Chi, N.-W.; Lin, K.-Y.; Hsieh, S.-H. Using ontology-based text classification to assist Job Hazard Analysis. Adv. Eng. Inform. 2014,
28, 381–394. [CrossRef]
48. Li, W.; Sun, Y.; Cao, Q.; He, M.; Cui, Y. A proactive process risk assessment approach based on job hazard analysis and resilient
engineering. J. Loss Prev. Process Ind. 2019, 59, 54–62. [CrossRef]
49. Li, W.; Zhang, L.; Liang, W. Job hazard dynamic assessment for non-routine tasks in gas transmission station. J. Loss Prev. Process
Ind. 2016, 44, 459–464. [CrossRef]
50. Li, W.; Cao, Q.; He, M.; Sun, Y. Industrial non-routine operation process risk assessment using job safety analysis (JSA) and a
revised Petri net. Process Saf. Environ. Prot. 2018, 117, 533–538. [CrossRef]
51. Ikuma, L.H.; Nahmens, I.; James, J. Use of safety and lean integrated kaizen to improve performance in modular homebuilding. J.
Constr. Eng. Manag. 2011, 137, 551–560. [CrossRef]
52. Wang, H.-H.; Boukamp, F. Ontology-based representation and reasoning framework for supporting job hazard analysis. J. Comput.
Civ. Eng. 2011, 25, 442–456. [CrossRef]
53. Zhang, S.; Boukamp, F.; Teizer, J. Ontology-based semantic modeling of construction safety knowledge: Towards automated
safety planning for job hazard analysis (JHA). Autom. Constr. 2015, 52, 29–41. [CrossRef]
54. Marucco, D. Simultaneous operations risk assessment. Chem. Eng. Trans. 2016, 53, 115–120. [CrossRef]
55. Sacks, R.; Rozenfeld, O.; Rosenfeld, Y. Spatial and temporal exposure to safety hazards in construction. J. Constr. Eng. Manag.
2009, 135, 726–736. [CrossRef]
56. Fan, H.; Enshaei, H.; Jayasinghe, S.G. Dynamic quantitative risk assessment of LNG bunkering SIMOPs based on Bayesian
network. J. Ocean Eng. Sci. 2023, 8, 508–526. [CrossRef]
57. Malashenko, G.T.; Kosov, M.E.; Frumina, S.V.; Grishina, O.A.; Alandarov, R.A.; Ponkratov, V.V.; Bloshenko, T.A.; Sanginova, L.D.;
Dzusova, S.S.; Hasan, M.F. A Digital Model of Full-Cycle Training Based on the Zettelkasten and Interval Repetition System.
Emerg. Sci. J. 2023, 7, 1–15. [CrossRef]
58. Korea Occupational Safety and Health Agency. KOSHA Guide: Guidelines for the Recording and Classification of Industrial Accidents.
Available online: http://www.knsdoit.co.kr/bri/board.php?bo_table=reference&wr_id=106 (accessed on 22 August 2024).
59. Okoh, P.; Haugen, S. Maintenance-related major accidents: Classification of causes and case study. J. Loss Prev. Process Ind. 2013,
26, 1060–1070. [CrossRef]
60. Gill, J.C.; Malamud, B.D. Hazard interactions and interaction networks (cascades) within multi-hazard methodologies. Earth Syst.
Dyn. 2016, 7, 659–679. [CrossRef]
61. Ni, H.; Chen, A.; Chen, N. Some extensions on risk matrix approach. Saf. Sci. 2010, 48, 1269–1278. [CrossRef]
Sustainability 2024, 16, 9277 28 of 28

62. Tsai, S.-B.; Yu, J.; Ma, L.; Luo, F.; Zhou, J.; Chen, Q.; Xu, L. A study on solving the production process problems of the photovoltaic
cell industry. Renew. Sustain. Energy Rev. 2018, 82, 3546–3553. [CrossRef]
63. Deng, X.; Liu, Q.; Deng, Y.; Mahadevan, S. An improved method to construct basic probability assignment based on the confusion
matrix for classification problem. Inf. Sci. 2016, 340, 250–261. [CrossRef]
64. Choi, S.-W.; Lee, E.-B. Contractor’s Risk Analysis of Engineering Procurement and Construction (EPC) Contracts Using Ontological
Semantic Model and Bi-Long Short-Term Memory (LSTM) Technology. Sustainability 2022, 14, 6938. [CrossRef]
65. Knauf, R.; Gonzalez, A.J.; Jantke, K.P. Validating rule-based systems: A complete methodology. In Proceedings of the IEEE
SMC’99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No. 99CH37028),
Tokyo, Japan, 12–15 October 1999; pp. 744–749.
66. Hassabis, D. Artificial intelligence: Chess match of the century. Nature 2017, 544, 413–414. [CrossRef]
67. Halford, G.S.; Cowan, N.; Andrews, G. Separating cognitive capacity from knowledge: A new hypothesis. Trends Cogn. Sci. 2007,
11, 236–242. [CrossRef]

Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual
author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to
people or property resulting from any ideas, methods, instructions or products referred to in the content.