Statistical Quality Control (SQC)
Introduction
It is one of the most important applications of statistical techniques in
industry. The term Quality means a level or standard of a product which
depends on Material, Manpower, Machines, and Management (4M’s). Quality
Control ensures the quality specifications all along them from the arrival of raw
materials through each of their processing to the final delivery of goods. This
technique is used in almost all production industries such as automobile,
textile, electrical equipment, biscuits, bath soaps, chemicals, petroleum
products etc.
Meaning
Quality Control is a powerful technique used to diagnose the lack of quality in
any of the raw materials, processes, machines etc… It is essential that the end
products should possess the qualities that the consumer expects from the
manufacturer.
Causes of Variation
There are two causes of variation which affects the quality of a product,
namely
1. Chance Causes (or) Random causes
2. Assignable Causes
1. Chance Causes
These are small variations which are natural and inherent in the manufacturing
process. The variation occurring due to these causes is beyond the human
control and cannot be prevented or eliminated under any circumstances. The
minor causes which do not affect the quality of the products to an extent are
called as Chance Causes (or) Random causes. For example Rain, floods, power
cuts, etc…
2. Assignable Causes
The second type of variation which is present in any production process is due
to non-random causes. The assignable causes may occur in at any stage of the
process, right from the arrival of the raw materials to the final delivery of the
product. Some of the important factors of assignable causes are defective raw
materials, fault in machines, unskilled manpower, worn out tools, new
operation, etc.
The main purpose of SQC is to device statistical techniques which would help
in elimination of assignable causes and bring the production process under
control.
Statistical Quality Control (SQC):
Process Control and Product Control
The main objective in any production process is to control and maintain a
satisfactory quality level of the manufactured product. This is done by ‘Process
Control’. In Process Control the proportion of defective items in the production
process is to be minimized and it is achieved through the technique of control
charts. Product Control means that controlling the quality of the product by
critical examination through sampling inspection plans. Product Control aims
at a certain quality level to be guaranteed to the customers. It attempts to
ensure that the product sold does not contain a large number of defective
items. Thus it is concerned with classification of raw materials, semi-finished
goods or finished goods into acceptable or rejectable products.
Control Charts
In an industry, there are two kinds of problems to be faced, namely
(i) To check whether the process is conforming to its standard level.
(ii) To improve the standard level and reduce the variability.
Shewhart’s control charts provide an answer to both. It is a simple technique
used for detecting patterns of variations in the data. Control charts are simple
to construct and easy to interpret. A typical control charts consists of the
following three lines.
(i) Centre Line (CL) indicates the desired standard level of the process.
(ii) Upper Control Limit (UCL) indicates the upper limit of tolerance.
(iii) Lower Control Limit (LCL) indicates the lower limit of tolerance.
If the data points fall within the control limits, then we can say that the process
is in control, instead if one or more data points fall outside the control limits,
then we can say that the process is out of control.
For example, the following lines with the data points plotted, diagram shows
all the three controlsince all the points falls within the control limits, we can
say that the process is in control.
Control Charts for Variables
These charts may be applied to any quality characteristic that can be measured
quantitatively. A quality characteristic which can be expressed in terms of a
numerical value is called as a variable. Many quality characteristics such as
dimensions like length, width, temperature, tensile strength etc… of a product
are measurable and are expressed in a specific unit of measurements. The
variables are of continuous type and are regarded to follow normal probability
law. For quality control of such data, there are two types of control charts
used. They are as follows :
(i) Charts for Mean ( )
(ii) Charts for Range (R)
Construction of and R charts
Any production process is not perfect enough to produce all the products
exactly the same. Some amount of variation is inherent in any production
process. This variation is a total of number of characteristics of the production
process such as raw materials, machine setting, operators, handling new
operations and new machines, etc. The chart is used to show the quality
averages of the samples taken from the given process. The R chart is used to
show the variability or dispersion of the samples taken from the given process.
The control limits of the and R charts shows the presence or absence of
assignable causes in the production process. Both and R charts are usually
required for decision making to accept or reject the process.
The procedure for constructing and R charts are outlined below.
Procedure for
(i) Let X1,X2, X3, etc. be the samples selected, each containing ‘n’ observations
(usually n = 4, 5 or 6)
(ii) Calculate mean for each samples 1 , 2 , 3 .... by using
total of ‘n’ values included in the
sample Xi .
(iii) Find the mean ( ) of the sample means.
total of all the sample means.
Procedure for R -Charts.
Calculate R = xmax − xmin
Let R1, R2, R3… be the ranges of the ‘n’ samples. The average range is given by
The calculation of control limits for chart in two different cases is
The calculation of control limits for R chart in two different cases are
The values of A2, D3 and D4 are given in the table.
Example 9.19
A machine drills hole in a pipe with a mean diameter of 0.532 cm and a
standard deviation of 0.002 cm. Calculate the control limits for mean of samples
5.
Solution:
Example 9.20
The following data gives the readings for 8 samples of size 6 each in the
production of a certain product. Find the control limits using mean chart.
Given for n = 6, A2 = 0.483,
Solution:
Example 9.21
The data shows the sample mean and range for 10 samples for size 5 each. Find
the control limits for mean chart and range chart.
Solution:
Example 9.22
The following data gives readings of 10 samples of size 6 each in the
production of a certain product. Draw control chart for mean and range with its
control limits.
Solution:
Example 9.23
You are given below the values of sample mean ( ) and the range ( R ) for ten
samples of size 5 each. Draw mean chart and comment on the state of control of
the process.
Given the following control chart constraint for : n = 5, A 2 = 0.58, D3 = 0 and
D4 = 2.115
Solution:
The above diagram shows all the three control lines with the data points plotted,
since four points falls out of the control limits, we can say that the process is out
of control.
