Statistical Quality Control

LENNY M. AMAR
 Statistical Quality Control (SQC)

• the set of statistical tools used by quality professionals

Brief History
 SQR was pioneered by Walter A. Shewhart
at Bell Laboratories in the early 1920s.
 Shewhart developed the control chart in
2914 and the concept of a state of
statistical control.
Walter A. Shewhart
 W. Edwards Deming invited Shewhart to speak at
the Graduate School of the U.S. Department of
Agriculture and served as the editor of
Shewhart’s book Statistical Method from the
Viewpoint of Quality Control (1939) which was
the result of that lecture.
W. Edwards Deming
SQC Categories
1.Descriptive Analysis
2. Statistical Process Control (SPC)
3. Acceptance Sampling
 1. Descriptive Analysis
The Mean – measure of central tendency.

The Range – difference between largest/smallest

observations in a set of data.

Standard Deviation measures the amount of data dispersion

around mean.
 The Mean

 To compute the mean we simply sum all the observations and

divide by the total no. of observations.

where
 The Range

 Range, which is the difference between the largest and

smallest observations.
 Standard Deviation
 Standard deviation is a measure of dispersion of a curve.

 It measures the extent to which these values are scattered

around the central mean.
2. Statistical Process Control
 Extend the sue of descriptive statistics to monitor the
quality of the product and process.

 Statistical process control help to determine the amount

of variation.

 To make sure the process is in a state of control.

Variation In Quality
 No two items are exactly alike.
 Some sort of variations in the two items is bound to be there.
In fact it is an integral part of any manufacturing process.
 This difference in characteristics known as variation.
 This variation may be due to substandard quality of raw
material, carelessness on the part of operator, fault in
machinery system etc..
3. Acceptance Sampling
 A form of inspection applied to lots or batches of
items before or after a process to judge
conformance to predetermined standards
E xample :

I f you ’re p rod u cin g c erea l b oxes, you c a n u se a c c eptance sa m plin g to

d etermine w h ether or n ot a l l of you r c erea l b oxes h a v e b een m a d e to th e
sa m e sp ec ific ations
Sources of Variations
1) Variation due to “CHANGE CAUSES”
2) Variation due to “ASSIGNABLE CAUSES”
 1) Variation due to “CHANGE CAUSES”

 Variation occurred due to chance.

 This variation is NOT due to defect in machine, Raw material or any

other factors.

 Behave in “random manner”.

 Negligible but Inevitable

 The process is said to be under the state of statistical control.

 2) Variation due to “ASSIGNABLE CAUSES”

Difference in quality of raw material.

Difference in machines.

Difference in operators.

Difference of time.
Distribution of Data

1) Central Tendency
2) Determine quality characteristics
3) Degree of asymmetry in distribution
 Distribution of the Data

Here are some of the ways to represent and visualize the distribution of
data:

 Check Sheets
 Histogram
 Pareto Chart
 Control Chart
 Cause and Effect Analysis Diagram
 Stratification
 Scatter Diagram
Check Sheets
It is used to collect data systematically and in real time to prepare it for
further analysis. The defining characteristic of a check sheet is that data are
recorded by making marks (checks) on it.
Histogram

It is a representation of tabulated frequencies, shown as adjacent

rectangles, erected over discrete intervals (bins), with an area equal to the
frequency of the observations in the interval. Also used to understand the
variation pattern in a measured characteristic.
Pareto Chart
• frequently used in both the measure and analyze steps of DMAIC
• a simple and formal technique which helps to identify the top portion of the
causes which are to be addressed to resolve the majority of the problems
• a decision making technique which statistically separates a limited number of
input factors as having the greatest impact on an outcome, either desirable or
undesirable
Control Chart

A control chart has upper control limit (UCL) and lower control limit (LCL)
which separate common from assignable causes of variation. The UCL is the
maximum acceptable variation from the mean for a process which is in a
state of control while the LCL is the minimum acceptable variation from the
mean for a process which is in a state of control.
Cause and Effect Analysis Diagram
• also known as Ishikawa diagram, Herringbone diagram, or Fishbone
diagram
• Cause and effect analysis diagram technique combines brain-storming
with a type of mind map
Stratification
• The technique separates the data so that the pattern can be seen
Stratification can be used in the cases
(i) before collecting the data
(ii) when data come from several sources or conditions such as shifts, days of week,
suppliers, materials, products, departments, equipment, or population groups, and
(iii) when data analysis can need separating different sources or conditions.
Scatter Diagram
• a type of mathematical diagram using Cartesian coordinates to display
values for two variables for a set of data
• The data is displayed as a collection of points, each having the value of one
variable determining the position on the horizontal axis (x axis) and the value
of the other variable determining the position on the vertical axis (y axis)
Statistical Process Control
1. Variation
2. Cause variation
3. Optimizing continuous objective
 SPC History
• SPC is effectively used in western industries since 1980, it was started
during the twenties in America.
• Walter A Shewhart developed the control chart as well as the concept
that a process could be in statistical control in 1924 at Bell Telephone
Laboratories, USA.
• Likewise, the SPC concepts are included in the management philosophy
by Dr. W.E. Deming just before World War II.
• However, SPC became famous after Japanese industries implement the
concepts and compete with western industries.
 Statistical Quality Control (SQC)

• the set of statistical tools used by quality professionals

• the use of statistical techniques to control a process or
production method

SPC tools and procedures can help you monitor process

behavior, discover issues in internal systems, and find
solutions for production issues. Statistical process control is
often used interchangeably with statistical quality control
(SQC). SPC helps move towards prevention-based quality
control instead of detection-based quality controls.
SCP Benefits
• Reduce scrap and rework
• Increase productivity
• Improve overall quality
• Match process capability to product requirement
• Continuously monitor processes to maintain control
• Provide data to support decision making
• Streamline the process
• Increase in product reliability
• Opportunity for company-wide improvements
 SCP Objectives

SPC focuses on optimizing continuous improvement by using

statistical tools to analyze data, make inferences about
process behavior, and then make appropriate decisions.

The basic assumption of SPC is that all processes are generally

subject to variation. To that end, Variation measures how data
are spread around the central tendency. Moreover, variation
may be classified as one of two types, random or chance
cause variation and assignable cause variation.
 SCP Objectives
Common Cause: A cause of variation in the process is due
to chance but not assignable to any factor. It is the variation
that is inherent in the process. Likewise, a process under the
influence of a common cause will always be stable and
predictable.

Assignable Cause: It is also known as “special cause.” The

variation in a process that is not due to chance, therefore, can
be identified and eliminated. In this case, a process under
influence of a special cause will not be stable and predictable.
How to perform SCP?
1. Identify the processes:

• Firstly, identify the key process that impacts the output of the
product or the process that is very critical to the customer. For
example, plate thickness impacts the product’s performance
in a manufacturing company, then consider the plate
manufacturing process.

2. Determine measurable attributes of the process:

• Secondly, identify the attributes that need to be measured

during production. For example, consider the plate thickness
as a measurable attribute.
3. Determine the measurement method and also perform Gage R&R:

• Thirdly, create a measurement method work instructions or

procedure, including the measuring instrument. For example,
consider a thickness gauge to measure the thickness and
create an appropriate measuring procedure. Perform Gage
Repeatability and Reproducibility (Gage R & R) to define the
amount of variation in the measurement data due to the
measurement system.
4. Develop a subgroup strategy and sampling plan:

• Fourthly, determine the subgroup size based on the

product’s criticality and determine the sampling size and
frequency. For example, collect 20 sets of plate
thicknesses in a time sequence with a subgroup size of 4.

5. Collect the data and plot the SPC chart:

• Then, collect the data per sample size and select an

appropriate SPC chart based on data type (Continuous
or Discrete) and subgroup size. For Example, for plate
thicknesses with a subgroup size of 4, select Xbar -R chart
6. Describe the natural variation of attributes:

• Next, calculate the control limits. From the above

example, calculate the upper control limit (UCL) and
lower control limit (LCL) for both Xbar Ranges.

7. Monitor process variation:

• Finally, interpret the control chart and check whether any

point is out of control and the pattern. Example: check
the Xbar R chart if the process is not in control, then
identify the assignable cause(s) and address the issue.
This is an ongoing process, so monitor the process
variation.