CHAPTER I
INTRODUCTION
All types of production lines or manufacturing chains are faced with the
need to store their reserves, components, and tools in appropriate locations.
In most cases, this task is carried out in warehouses or storage units. A
Warehouse is an open platform used for material storage. It involves
continuous picking, moving and replenishing of inventories. These methods
require large manpower which might result in statistical human errors. Due
to these disadvantages, new methods were researched and adopted.
At the very beginning, warehouse management was carried using a pen and
paper-based recording system which was carried forward for many years to
come. This system proved to be laborious and demanded large amounts of
manual labor. The system also led to a significant amount of loss and
inaccuracy due to human error.
Gradually with developing technologies in the field of Electronics, Radio
Frequency Identification (RFID) came into existence. RFID uses
electromagnetic waves to automatically track tags attached to various
objects. The system comprises two main components, a radio transmitter,
and a radio receiver.
The technology of RFID was then employed in the scanning system using
RFID tags that were adopted for the identification of the warehouse
products. RFID technology was used over a wide range of identification
methods such as QR code or bar code scanning methods, to name a few.
However, the sensing and communication performances of the RFID tags
were affected when subjected to high temperatures and also establishing a
powerful communication link and retrieving accurate sensing operations
were the most oppressive challenges when dealing with RFID sensor
networks. Apart from the technical exertion, the presence of numerous
SKUs(Storage Keeping Units) decreased the accuracy and efficiency at
which commodities were selected, moved and replenished, thereby leading
to a significant reduction in ROI (Return on Investment). To overcome these
disadvantages arising in manual operation, innovative techniques have been
employed in the field of logistics, warehouse management, and supply chain
management.
The proposed system uses speech recognition that allows operators to
communicate with the warehouse environment verbally. The voice picking
technique is a proven process for increased efficiency and accuracy of
pickers in warehouses. Using this technique, the productivity of warehouses
can be increased by about 35% and errors can be reduced up to 50%.
The applications of this project cater to a wide variety of industries, which
are concentrated in the area of e-commerce, manufacturing, construction,
transportation and warehouse and inventory management.
In addition to this, the application of artificial intelligence in the proposed
system in the form of AI-driven voice-assistants that make use of the Vertibi
algorithm and Hidden Markov Model (HMM) for speech recognition and
enhancement allows us to contribute further to the benefits of the proposed
system. The proposed concept helps bridge the gaps created by the scanning
procedure prevalent today.