Statistical Process
Control
Module 2
Dr. Salih Duffuaa & Dr. Mohamed Ben Daya
Systems Engineering Department
King Fahd University of Petroleum & Minerals
Training Objectives
• The overall objective of this program is to build
a strong learning base in the area of Statistical
Process Control (SPC) in order to sustain the
implementation of SPC and contribute to the
growth of the man-power in Quality Assurance
Laboratories and production.
• This require knowledge in basic statistics and
SPC tools and their interpretation.
Objectives (cont’d)
• Create a culture of continuous improvement.
• Improve the skills of the man-power in data
analysis and the interpretation of SPC results.
Training Program Outcomes of
Module 1
• Summarize and present data in meaningful format.
• Analyze data.
• Assess variability in data.
•
Construct confidence interval using excel.
•
Develop regression models and understand their use in
calibration of instruments.
Training Program Outcomes of
Module 2
•
Understand the relation between variability and quality.
•
Construct control charts for plant key processes.
• Assess whether a process is in control or out of control.
• Utilize SPC tools to identify major causes of poor quality.
•
Initiate process improvement based on information from SPC analysis
• Assess process capability.
• Suggest action plans to improve plant's process capability
Training Modules
Module 1
•
•
•
•
•
•
•
•
•
Data collection and presentation
Descriptive statistics.
Probability
Probability distribution.
Regression
Estimation
Concept of variation
SPC tools
All with real data and realistic
examples.
Duration: 4 months:
March – June, 2005
Module 2
•
•
•
•
•
•
•
Improvement using SPC tools
Fundamentals of control charts
Control charts for variables
Control charts for attributes
Process capability
Process improvements.
SPC implementation and case studies
Duration: 1 months:
November, 2005
Typical Schedule
• 8:30– 9:30 :
First Presentation
• 9:30 – 9:45 :
Break
• 9:45– 10:30 :
Exercises
• 10:30 – 10:45 :
Break
• 10:45 – 11:45 :
Second Presentation
• 11:45 – 1:00 :
Lunch Break
• 1:00 – 3:00 :
Exercises and cases
Assessment
• Final Exam
• Small project
• Two homeworks.
Team Formation and Project
• Teams of 2 to apply SPC on a process
• Identify a process (latter)
• Project requirements
–
–
–
–
–
Define process
Choose appropriate measures
Develop control charts
Assess process capability
Suggest action plan to improve capability.
Week 1 Schedule
• 8:30 – 9:30 :
• 9:15 – 9:30 :
Module 2 Introduction
Process improvement
using SPC tools
Break
• 9:30 – 10:30 :
Basics of Control charts
• 10:30 – 10:45 :
Break
• 10:45 – 11:45 :
• 11:45 – 1:00 :
• 1:00 – 3:00 :
Basics of Control charts
Lunch Break
Cases and Examples
Learning Outcomes
•
Define Statistical Process Control.
• Define quality and quality improvement.
• Describe the role of variability and statistical
methods in controlling and improving quality.
• Explain the link between quality and
productivity and
• Define quality costs.
Learning Outcomes
• Distinguish between random and assignable
causes
• Use SPC tools other than control charts.
• Define a control chart.
• Explain the statistical basis for control charts.
• Explain essential factors in control chart design
• State the steps to implement SPC
Definition of SPC
• S: for statistical: means based on the science of
data collection and analysis.
•
P: for process: A process is A process is no more than
the steps and decisions involved in the way work is
accomplished. Everything we do in our lives involves processes and lots of them. Here are some
examples:
writing a work order, shooting a weapon, getting out of bed
repairing a valve , ordering a part, performing a test,
conducting an UNREP, preparing a message, loading a missile
allocating a budget , mooring a ship , conducting a drill.
• A sequence of activities (steps) that takes an input and produces
an output.
•
C: for control : stability and predictability.
Definitions and Meaning of Quality
The Eight Dimensions of Quality
1.
2.
3.
4.
5.
6.
7.
8.
Performance
Reliability
Durability
Serviceability
Aesthetics
Features
Perceived Quality
Conformance to Standards
•This is a traditional definition
•Quality of design
•Quality of conformance
This is a modern definition of quality
How do we measure variability ?
The Transmission Example
• The transmission example illustrates the utility of this definition
• An equivalent definition is that quality improvement is the
elimination of waste. This is useful in service or transactional
businesses.
Terminology
Terminology cont’d
• Specifications
– Lower specification limit
– Upper specification limit
– Target or nominal values
• Defective or nonconforming product
• Defect or nonconformity
• Not all products containing a defect are
necessarily defective
1-2. History of Quality Improvement
Statistical Methods for Quality Improvement
Statistical Methods
• Statistical process control (SPC)
– Control charts, plus other problem-solving tools
– Useful in monitoring processes, reducing variability through
elimination of assignable causes
– On-line technique
• Designed experiments (DOX)
– Discovering the key factors that influence process
performance
– Process optimization
– Off-line technique
• Acceptance Sampling
Walter A. Shewart (1891-1967)
• Trained in engineering and physics
• Long career at Bell Labs
• Developed the first control chart
about 1924
A factorial experiment with three factors
Quality Philosophies and
Management Strategies
W. Edwards Deming
• Taught engineering, physics in the
1920s, finished PhD in 1928
• Met Walter Shewhart at Western
Electric
• Long career in government
statistics, USDA, Bureau of the
Census
• During WWII, he worked with US
defense contractors, deploying
statistical methods
• Sent to Japan after WWII to work
on the census
Deming
• Deming was asked by JUSE to lecture on
statistical quality control to management
• Japanese adopted many aspects of Deming’s
management philosophy
• Deming stressed “continual never-ending
improvement”
• Deming lectured widely in North America
during the 1980s; he died 24 December 1993
Deming’s 14 Points
1. Create constancy of purpose toward improvement
2. Adopt a new philosophy, recognize that we are in a time of
change, a new economic age
3. Cease reliance on mass inspection to improve quality
4. End the practice of awarding business on the basis of price alone
5. Improve constantly and forever the system of production and
service
6. Institute training
7. Improve leadership, recognize that the aim of supervision is help
people and equipment to do a better job
8. Drive out fear
9. Break down barriers between departments
14 Points cont’d
10. Eliminate slogans and targets for the workforce such as zero
defects
11. Eliminate work standards
12. Remove barriers that rob workers of the right to pride in the
quality of their work
13. Institute a vigorous program of education and selfimprovement
14. Put everyone to work to accomplish the transformation
Note that the 14 points are about change
Deming’s Deadly Diseases
1. Lack of constancy of purpose
2. Emphasis on short-term profits
3. Performance evaluation, merit rating, annual
reviews
4. Mobility of management
5. Running a company on visible figures alone
6. Excessive medical costs for employee health care
7. Excessive costs of warrantees
Joseph M. Juran
• Born in Romania (1904),
immigrated to the US
• Worked at Western Electric,
influenced by Walter
Shewhart
• Emphasizes a more strategic
and planning oriented
approach to quality than does
Deming
• Juran Institute is still an
active organization
promoting the Juran
philosophy and quality
improvement practices
The Juran Trilogy
1. Planning
2. Control
3. Improvement
•
•
•
These three processes are interrelated
Control versus breakthrough
Project-by-project improvement
Some of the Other “Gurus”
• Kaoru Ishikawa
– Son of the founder of JUSE, promoted widespread use of
basic tools
• Armand Feigenbaum
– Author of Total Quality Control, promoted overall
organizational involvement in quality,
– Three-step approach emphasized quality leadership, quality
technology, and organizational commitment
• Lesser gods, false prophets
Quality Systems and Standards
• The ISO certification process focuses heavily on quality
assurance, without sufficient weight given to quality planning and
quality control and improvement
Quality Costs
Legal Aspects of Quality
•
Product liability exposure
•
Concept of strict liability
1. Responsibility of both manufacturer and
seller/distributor
2. Advertising must be supported by valid data
Quality and Productivity
• Example: Suppose a worker produces 100 units
and 20% are defective. Which is better option to
improve quality by 20% or productivity by 20%.
Does improving quality improves productivity?
Seven Quality Tools
Seven Quality Control Tools
• Pareto Chart
– Histogram
•
•
•
•
•
•
Process flow diagram
Check sheet
Scatter diagram
Control chart
Run Chart
Cause and Effect Diagram
Pareto Principle
• Vilfredo Pareto (1848-1923) Italian economist
– 20% of the population has 80% of the wealth
• Juran used the term “vital few, trivial many”. He
noted that 20% of the quality problems caused
80% of the dollar loss.
7 Quality Tools
Pareto chart
28
% Complaints
30
25
20
16
15
12
12
10
6
5
4
3
0
Loose
Threads
Stitching
flaws
Button
problems
Material
flaws
7 Quality Tools
Pareto Chart
70
(64)
Percent from each cause
60
50
40
30
20
(13)
10
(10)
(6)
(3)
0
Causes of poor quality
(2)
(2)
Histogram
25
Frequency
20
15
10
5
0
9
1.
9
2.
9
3.
9
4.
9
5.
9
6.
9
7.
9
8.
e
9
9
9
9
9
9
9
9. 10. 11. 12. 13. 14. 15. or
M
Category
7 Quality Tools
Histogram
40
35
30
25
20
15
10
5
0
1 2
6 13 10 16 19 17 12 16 20 17 13
5 6 2
1
Flowcharts
• Flowcharts
– Graphical description of how work is done.
– Used to describe processes that are to be improved.
7 Quality Tools
Flow Diagrams
" Draw a flowchart for whatever you do. Until
you do, you do not know what you are doing,
you just have a job.”
-- Dr. W. Edwards Deming.
Flowchart
Activity
Decision
Yes
No
7 Quality Tools
Flowchart
Flow Diagrams
Process Chart Symbols
Operations
Inspection
Transportation
Delay
Storage
Check Sheet
Defect Type
Shifts










7 Quality Tools
Cause-and-Effect Diagrams
• Show the relationships between a problem and
its possible causes.
• Developed by Kaoru Ishikawa (1953)
• Also known as …
– Fishbone diagrams
– Ishikawa diagrams
7 Quality Tools
Cause and Effect “Skeleton”
Materials
Procedures
Quality
Problem
People
Equipment
7 Quality Tools
Fishbone Diagram
Measurement
Faulty testing equipment
Incorrect specifications
Improper methods
Inaccurate
temperature
control
Dust and
Dirt
Environment
Human
Machines
Out of adjustment
Poor supervision
Lack of concentration
Tooling problems
Old / worn
Inadequate training
Quality
Problem
Defective from vendor
Not to specifications
Materialhandling problems
Materials
Poor process
design
Ineffective quality
management
Deficiencies
in product
design
Process
Cause and effect diagrams
• Advantages
– making the diagram is educational in itself
– diagram demonstrates knowledge of problem
solving team
– diagram results in active searches for causes
– diagram is a guide for data collection
Cause and effect diagrams
To construct the skeleton, remember:
• For manufacturing - the 4 M’s
man, method, machine, material
• For service applications
equipment, policies, procedures, people
Scatter Diagram
.
Run Charts
• Run Charts (time series plot)
– Examine the behavior of a variable over time.
– Basis for Control Charts
27
Control Chart
24
UCL = 23.35
Number of defects
21
c = 12.67
18
15
12
9
6
LCL = 1.99
3
2
4
6
8
10
12
Sample number
14
16
Control Charts
• A process is operating with only chance causes of variation present is said to
be in statistical control.
• A process that is operating in the presence of assignable causes is said to be
out of control.
• A control chart contains
– A center line
– An upper control limit
– A lower control limit
• A point that plots within the
control limits indicates the process
is in control
– No action is necessary
• A point that plots outside the
control limits is evidence that the
process is out of control
– Investigation and corrective action
are required to find and eliminate
assignable cause(s)
• There is a close connection
between control charts and
hypothesis testing
Photolithography Example
• Important quality
characteristic in hard bake is
resist flow width
• Process is monitored by
average flow width
– Sample of 5 wafers
– Process mean is 1.5 microns
– Process standard deviation is
0.15 microns
• Note that all plotted points
fall inside the control limits
– Process is considered to be in
statistical control
Shewhart Control Chart Model
More Basic Principles
• Charts may be used to estimate process parameters,
which are used to determine capability
• Two general types of control charts
– Variables Continuous scale of measurement
• Quality characteristic described by central tendency and a measure of
variability
– Attributes
– Conforming/nonconforming
• Counts
• Control chart design encompasses selection of
sample size, control limits, and sampling frequency
Types of Process Variability
• Stationary and uncorrelated  data vary around a fixed mean in a stable or
predictable manner
• Stationary and autocorrelated  successive observations are dependent with
tendency to move in long runs on either side of mean
• Nonstationary  process drifts without any sense of a stable or fixed mean
Reasons for Popularity
of Control Charts
1.
2.
3.
4.
5.
Control charts are a proven technique for improving
productivity.
Control charts are effective in defect prevention.
Control charts prevent unnecessary process
adjustment.
Control charts provide diagnostic information.
Control charts provide information about process
capability.
• 3-Sigma Control Limits
– Probability of type I error is 0.0027
• Probability Limits
– Type I error probability is chosen directly
– For example, 0.001 gives 3.09-sigma control limits
• Warning Limits
– Typically selected as 2-sigma limits
• Pattern is very nonrandom in appearance
• 19 of 25 points plot below the center line, while only 6 plot
above
• Following 4th point, 5 points in a row increase in
magnitude, a run up
• There is also an unusually long run down beginning with
18th point
• Phase I is a retrospective analysis of process data to
construct trial control limits
– Charts are effective at detecting large, sustained shifts in
process parameters, outliers, measurement errors, data entry
errors, etc.
– Facilitates identification and removal of assignable causes
• In phase II, the control chart is used to monitor the
process
– Process is assumed to be reasonably stable
– Emphasis is on process monitoring, not on bringing an
unruly process into control
SPC Implementation Issues
• Define process
• Chose Quality characteristic and measurement
system
• Focus on trends and shifts
• Calculate control charts limits.
• Investigate and act
• SPC training
•
Nonmanufacturing applications do not differ
substantially from industrial applications, but
sometimes require ingenuity
1.
2.
•
Most nonmanufacturing operations do not have a natural
measurement system
The observability of the process may be fairly low
Flow charts and operation process charts are
particularly useful in developing process definition
and process understanding. This is sometimes called
process mapping.
–
Used to identify value-added versus nonvalue-added
activity