Introduction to Statistical Quality Control Assist. Prof. Dr. Benhür SATIR 02/12/2014
Transcript
Slide 1
Assist. Prof. Dr. Benhr SATIR 02/12/2014
Slide 2
Outline Variation Dimensions of Quality Definition of Quality
Descriptive Statistics Statistical Methods for Quality Improvement:
Acceptance Sampling Designed Experiments Statistical Process
Control & Magnificient Seven Total Quality Management Quality
Related Costs Benefits 14.12.20122
Slide 3
Variation Which has higher variation? mam ada McDonalds What do
you understand from this question? # of different meals the same
taste for a specific meal Something else? 14.12.20123
Slide 4
Variation Which one you like more? mam ada McDonalds
14.12.20124
Slide 5
Variation Which one you like more as an IE? mam ada McDonalds
14.12.20125
Slide 6
Variation Variation is an enemy for an IE We hate variation!
Ford T Model: Henry Ford said "You can have any colour as long as
it's black." If it is unavoidable, try to cope with it Only black
color for a Mercedes in 2015? 14.12.20126
Slide 7
Dimensions of Quality Garvin (1987) 1. Performance: Will the
product/service do the intended job? 2. Reliability: How often does
the product/service fail? 3. Durability: How long does the
product/service last? 4. Serviceability: How easy to repair the
product / to solve the problems in service? 14.12.20127
Slide 8
Dimensions of Quality 5. Aesthetics: What does the
product/service look/smell/sound/feel like? 6. Features: What does
the product do/ service give? 7. Perceived Quality: What is the
reputation of the company or its products/services? 8. Conformance
to Standards: Is the product/service made exactly as the
designer/standard intended? 9. What else? What do YOU think?
14.12.20128
Slide 9
Quality in Different Areas of Society 14.12.20129 AreaExamples
AirlinesOn-time, comfortable, low-cost service Food ServicesGood
product, fast delivery, good environment Postal Servicesfast
delivery, correct delivery, cost containment Consumer
ProductsProperly made, defect-free, cost effective InsurancePayoff
on time, reasonable cost AutomotiveDefect-free
CommunicationsClearer, faster, cheaper service
Slide 10
Definition of Quality No two products are identical; i.e. There
is always a certain amount of variability. Modern Defn : Quality is
inversely proportional to variability. Quality Improvement :
reduction of variability in processes and products.
14.12.201210
Slide 11
Quality Engineering Terminology Quality characteristics :
parameters that jointly describe the quality from customers view
point. Physical : length, weight, viscocity. Sensory : taste,
color, appearance. Time orientation : reliability, durability,
serviceability. Nominal (Target) Value : Desired value for a
quality characteristic. Upper Specification Limit (USL) : largest
allowable value for a quality characteristic that will not
influence the funciton or performance of theproduct. Lower
Specification Limit (LSL) : Similar to USL, it is the smallest
allowable value. 14.12.201211
Slide 12
Quality Engineering Terminology Nonconformity : Specific type
of failure. Failure : Fail to meet the specification. Defect :
Nonconformities that are serious enough to significantly affect the
safe or effective use of the product. Defective: A product is
defective if it has one or more defects. 14.12.201212
Slide 13
Quality Engineering Terminology Quality Engineering : Set of
operational, managerial and engineering applications to ensure that
the quality characteristics are at their corresponding nominal
values or required levels. Remember : There is always variability
and quality is inversely proportional to it. Only way of describing
variability : Statistics. Use of statistical methods are crucial in
quality improvements. 14.12.201213
Slide 14
Some Important Statistical Definitions Population Sample Use
parameters to summarize features Use statistics to summarize
features Inference on the population from the sample
14.12.201214
Slide 15
Some Important Statistical Definitions A Population (Universe)
is the whole collection of things under consideration. A Sample is
a portion of the population selected for analysis. A Parameter is a
summary measure computed to describe a characteristic of the
population. A Statistic is a summary measure computed to describe a
characteristic of the sample. 14.12.201215
Slide 16
Summary Measures Central Tendency
MeanMedianModeQuartileVariationRangeVariance Standard Devation
14.12.201216
Slide 17
Mean Population Mean: (parameter) For a finite population with
N measurements, the population mean is A reasonable estimate of the
population mean is the sample mean. Sample Mean: (statistic) If the
n observations in a sample are denoted by x 1, x 2, , x n, the
sample mean is 14.12.201217
Slide 18
Mean Example: Suppose that an engineer is developing a rubber
compound for use in O-rings. The O-rings are to be employed as
seals in plasma etching tools used in the semiconductor industry,
so their resistance to acids and other corrosive substances is an
important characteristic. The data from the modified rubber
compound are: 1037 1047 1066 1048 1059 1073 1070 1040. The sample
mean strength (psi) for the eight observations on strength is
14.12.201218
Slide 19
Mean Sample mean is affected by the extreme values and/or
outliers. 0 1 2 3 4 5 6 7 8 9 10 0 1 2 3 4 5 6 7 8 9 10 12 14
14.12.201219
Slide 20
Median Robust measure of central tendency Not affected by
extreme values In an ordered array, the median is the middle number
If n or N is odd, the median is the middle number If n or N is
even, the median is the average of the 2 middle numbers 0 1 2 3 4 5
6 7 8 9 100 1 2 3 4 5 6 7 8 9 10 12 14 14.12.201220
Slide 21
Median Example : Consider the O-rings example. 1037 1047 1066
1048 1059 1073 1070 1040. To find the median, 14.12.201221
Slide 22
Mode A Measure of central tendency Value that occurs most often
Not affected by extreme values There may not be a mode There may be
several modes Used for either numerical or categorical data 1 2 3 4
5 6 7 8 9 10 11 12 13 14 14.12.201222
Slide 23
Summary Measures Mean = 15.5 11 12 13 14 15 16 17 18 19 20 21
Data B Data A Mean = 15.5 11 12 13 14 15 16 17 18 19 20 21 Mean =
15.5 Data C 14.12.201223
Slide 24
Range Measure of variation Difference between the largest and
the smallest observations: Ignores how data are distributed 7 8 9
10 11 12 14.12.201224
Slide 25
Sample Variance & Standard Deviation Most important measure
of variation Shows variation about the mean 14.12.201225
Slide 26
Sample Variance & Standard Deviation If the n observations
in a sample are denoted by x 1, x 2,, x n, then the sample variance
is The sample standard deviation, s, is the positive square root of
the sample variance. 14.12.201226
Sample Variance & Standard Deviation 11 12 13 14 15 16 17
18 19 20 21 Data B Data A 11 12 13 14 15 16 17 18 19 20 21 Data C
Mean = 15.5 s = 3.338 Mean = 15.5 s =.9258 Mean = 15.5 s = 4.57
14.12.201228
Slide 29
Histogram The most commonly used graph to show frequency
distributions, i.e. how often each different value in a set of data
occurs. Used to visualize the distribution. Birthdate example
14.12.2012 29
Slide 30
Pareto Chart Organizes and displays information to show the
relative importance of various problems or causes of problems. A
special form of a vertical bar chart that puts items in order (from
the highest to the lowest) relative to some measurable effect of
interest: frequency, cost, time. Are arranged with longest bars on
the left and the shortest to the right. Helps teams to focus
efforts where they can have the greatest potential impact.
14.12.201230
Slide 31
Example Pareto Chart 14.12.201231
Slide 32
Cause & Effect Diagram Also called Ishikawa diagram,
fishbone diagram. Understand the root causes of a problem BEFORE
you put a solution into place. Identify and display many different
possible causes for a problem. See the relationships between the
many causes. Helps determine which data to collect.
14.12.201232
Slide 33
Cause & Effect Diagram 14.12.201233 Clearly define the
focused problem. Use brainstorming to identify possible causes.
Sort causes into reasonable clusters (no less than 3, not more than
6). Label the clusters (consider people, policies, procedures,
materials if you have not already identified labels). Develop and
arrange bones in each cluster. Check the logical validity of each
causal chain. Focused problem Root cause
Slide 34
Cause & Effect Diagram 14.12.201234 Bones should not
include solutions. Bones should not include lists of process steps.
Bones include the possible causes. Turnover in staff Policies
People Procedures Materials Inadequate training Burnout Lack of
supervision Minimal benefits No policy on staff screening Paperwork
overwhelming Lack of office space Back-biting environment
Restrictive budget Location Escorting clients to appointments and
having to wait
Slide 35
Statistical Methods for Quality Improvement 3 major areas:
Acceptance Sampling Statistical Process Control (SPC) Design of
Experiments 14.12.201235
Slide 36
Acceptance Sampling Inspection and testing of Raw materials
Semifinished products Finished products Based on inspection Accept
or Reject the product Type of inspection procedure is called
acceptance sampling. Can do either 100% inspection, or inspect a
sample of a few items taken from the lot. 14.12.201236
Slide 37
Statistical Process Control SPC is a statistics-based
methodology for achieving process stability and improving
capability by reducing variability. All processes have variation in
output: Some of the variation is caused by factors that can be
identified and managed (assignable causes). Ex: improperly adjusted
machines, operator errors, defective raw materials etc. Some of the
variation is inherent in the process (background noise) :
cumulative effect of many small, unavoidable causes. Also named as
chance causes of variation. A process is said to be in statistical
control, if only chance causes of variation is present and it is
out of control, if there are assignable causes of variation. SPC is
aimed at discovering variation resulting from assignable causes so
that adjustments can be made and bad output is not produced.
14.12.201237
Slide 38
Control Chart A control chart is a presentation of data in
which the control values are plotted against time. Used to study
how a process changes over time and to determine if variation is
chance or assignable cause. Immediate visualisation of problems.
Control charts have a central line, upper and lower warning limits,
and upper and lower action limits. 14.12.201238
Slide 39
Control chart - Illustration of construction
0102030405060708090100 0.8 0.9 1.0 1.1 1.2 1.3 X-chart Copper
Warning limit Action limit Central line Control value
14.12.201239
Slide 40
Design of Experiments Helpful in discovering the key variables
influencing the quality characteristics of interest. Systematically
change the controllable factors in the process and determine the
effect of them on the output product parameters. Statistically
designed experiments are useful to reduce the variability in the
quality characteristics and to determine the levels of controllable
factors that optimize process performance. 14.12.201240
Slide 41
TQM Consists of organization-wide efforts to install and make
permanent a climate in which an organization continuously improves
its ability to deliver high-quality products and services to
customers. W. Edwards Deming 14.12.201241
Slide 42
Demings 14 Points for the Transformation of Management 1.
Create constancy of purpose toward improvement of product and
service, with the aim to become competitive and to stay in
business, and to provide jobs. 2. Adopt the new philosophy. We are
in a new economic age. Western management must awaken to the
challenge, must learn their responsibilities, and take on
leadership for change. 3. Cease dependence on inspection to achieve
quality. Eliminate the need for inspection on a mass basis by
building quality into the product in the first place. 4. End the
practice of awarding business on the basis of price tag. Instead,
minimize total cost. Move toward a single supplier for any one
item, on a long-term relationship of loyalty and trust. 5. Improve
constantly and forever the system of production and service, to
improve quality and productivity, and thus constantly decrease
costs. 6. Institute training on the job. 7. Institute leadership
(see Point 12 and Ch. 8). The aim of supervision should be to help
people and machines and gadgets to do a better job. Supervision of
management is in need of overhaul, as well as supervision of
production workers. 8. Drive out fear, so that everyone may work
effectively for the company (see Ch. 3). 9. Break down barriers
between departments. People in research, design, sales, and
production must work as a team, to foresee problems of production
and in use that may be encountered with the product or service. 10.
Eliminate slogans, exhortations, and targets for the work force
asking for zero defects and new levels of productivity. Such
exhortations only create adversarial relationships, as the bulk of
the causes of low quality and low productivity belong to the system
and thus lie beyond the power of the work force. Eliminate work
standards (quotas) on the factory floor. Substitute leadership.
Eliminate management by objective. Eliminate management by numbers,
numerical goals. Substitute leadership. 11. Remove barriers that
rob the hourly worker of his right to pride of workmanship. The
responsibility of supervisors must be changed from sheer numbers to
quality. 12. Remove barriers that rob people in management and in
engineering of their right to pride of workmanship. This means,
inter alia, abolishment of the annual or merit rating and of
management by objective (see Ch. 3). 13. Institute a vigorous
program of education and self-improvement. 14. Put everybody in the
company to work to accomplish the transformation. The
transformation is everybody's job. 14.12.201242
Slide 43
Demings 7 Deadly Diseases 1. Lack of constancy of purpose to
plan product and service that will have a market and keep the
company in business, and provide jobs. 2. Emphasis on short-term
profits: short-term thinking (just the opposite from constancy of
purpose to stay in business), fed by fear of unfriendly takeover,
and by push from bankers and owners for dividends. 3. Evaluation of
performance, merit rating, or annual review. 4. Mobility of
management; job hopping. 5. Management by use only of visible
figures, with little or no consideration of figures that are
unknown or unknowable. 6. Excessive medical costs. 7. Excessive
costs of liability, swelled by lawyers that work on contingency
fees. 14.12.201243
Slide 44
Demings Circle PDSA: plandostudyact OPDCA: observation-PDSA
PDCA: plandocheckact or plandocheckadjust Iterative four-step
management method used in business for the control and continuous
improvement of processes and products. 14.12.201244
Slide 45
Quality-Related Costs Prevention costs Appraisal costs
Correction costs: Internal Failure Costs External Failure Costs
Costs of Conformance i.e. : The cost of doing things right the
first time Costs of Non-Conformance i.e. : The cost incurred as a
result of things not being done right the first time
14.12.201245