Basics of Quality and

Competing of Quality
 What is Quality?
 Fitness for Use
 Conformance to Specifications
 Total Customer Satisfaction
 Exceeding Customer Expectations
 Producing the Very Best Products
 Excellence in Products and Services

 Quality improvement starts with reducing

Product VARIABILITY and waste.
 Who Decides Quality?

Q
Customer

Understanding and Satisfying

Customer Needs and
Expectations is Key to TQM
 Total Quality Management

Total : Balancing and Satisfying

needs of all Stake Holders

Quality : Sustained Customer Focus

(Conformance to requirement)

Continuous Improvement
with Fact and Data based
Management: decisions in a Planned &
Systematic way
 TQM Means

v Improvement
v Improvements over
Improvement

Continuous Improvement
To achieve Excellence
 Total Quality Management
 Continuously maximizing Customer Satisfaction
 Continuously identifying and eliminating Non-
Non-Value
Adding activities
 Continuously harnessing Human, Material, and other
Resources of an Organisation in most effective way to
achieve Company Objectives
 Embedding a culture of Continuous Improvement in all
areas of operation with Customer focus
 TQM :Definitions

TQM is an integrated organization approach in

delighting customers (internal & external) by
meeting their expectations on a continuous
basis. This requires product/service providers
involvement on a continuous basis for
improvement in all product/ processes along
with proper problem solving methodology.
TQM Philosophy
 TQM Philosophy
 Focus on Customer
 Identify and meet customer needs
 Stay tuned to changing needs, e.g. fashion styles

 Continuous Improvement
 Continuous learning & problem solving, e.g. Kaizen, 6 sigma

 Quality at the Source

– Inspection vs. prevention & problem solving

 Employee Empowerment
– Empower all employees; external and internal customers
 TQM Philosophy
 Understanding Quality Tools
 Ongoing training on analysis, assessment, correction &
implementation tools

 Team Approach
 Teams formed around processes – 8 to 10 people
 Meet weekly to analyze and solve problems

 Benchmarking

 Studying practices at “best in class” companies

 Managing Supplier Quality
 Certifying suppliers vs. receiving inspection
TQM Elements
 Elements of TQM
 Top management commitment and involvement
 Customer involvement
 Design products for quality
 Design production processes for quality
 Control production processes for quality
 Developing supplier partnerships
 Customer service, distribution, and installation
 Building teams of empowered employees
 Benchmarking and continuous improvement
Quality - What’s the Big Deal?

 The Endless Battle:

Battle: Quantity vs. Quality

 Quantity goes directly to the bottom line:

– more product out ==> more $$$

 But what are the costs associated with Quality?

Direct Cost Indirect Cost

Quality - What’s the Big Deal?
 Direct Costs of Poor Quality:
– Lost Revenue:
Revenue: scrap, rework, repair

– Lost Productivity:
Productivity: materials, machines, and personnel

– Inspection Costs:
Costs: inspectors, testing machines

– External Costs:
Costs: warranty claims, price adjustments, late charges

 Indirect Costs of Poor Quality - Upset Customers:

Customers:
– It is harder to attract a new customer than to retain a current one

– Dissatisfied customers tell 8-

8-20 people about their dissatisfaction.

3-5 people.
– Satisfied customers only tell 3-
 Cost of uality
Element Decision Flow
Is Cost related to
Prevention of Non- YES PREVENTION
Conformance?
NO
Is Cost related to
Evaluating the YES APPRAISAL
Conformance ?
NO INTERNAL FAILURE
Is Non-Conformance
Is Cost related to
found prior to
Non-conformance? YES YES
Shipment ?
NO
NO
Not a Quality Cost

EXTERNAL FAILURE
 Quality Costs
 Prevention:
– avoiding defects by planning, preparation, training, preventative
maintenance and evaluation.

 Appraisal::
Appraisal
– finding defects by inspection, audit, calibration, test and measurement.

 Internal Failure:
– scrap, rework, redesign, modifications, corrective action, down time,
concessions and overtime.

 External Failure:
Failure:
– equipment failure, warranty, administrative cost in dealing with failure and
the loss of goodwill.
Quality Costs
 Prevention vs. Detection
Detection Model:
– $$$ lost to:
» making defective parts
» finding defective parts
» repairing or scrapping defective parts
– if/when detection fails, additional $$$ lost to:
» warranties
» cancelled orders
Prevention Model:
– minimal increased cost due to adding prevention measures
in the process
– utilizes SPC to reduce product variability at the source
– no waste!
 Detection Example
 Count the number of f’s in this paragraph:

 The study of SPC can be both fun and rewarding for

everyone. When you find out that the fundamental ideas
of statistics are fairly easy to learn, you will discover that
your efforts result in a great deal of satisfaction. If you
treat a production problem as a puzzle, the application of
SPC provides clues for its solution, and when the puzzle is
finally solved, the feeling of satisfaction is very fulfilling.
Puzzles can be frustrating, but their final solution is fun.
1:10:100: Rule
 Competing on Quality (D.Gravin)
-Strategic Quality Management-
Management-
 Strategic Quality Management’s
Aspect of Quality

 High Quality means pleasing customers, not just

protecting them from annoyance

 Product designers should shift their attention from

prices at the time of purchase to life cycle costs that

include expenditures on service and maintenance –

the customers total costs.

 8 Dimensions/Categories of Quality
Dimensions of Quality that can serve as a
framework for strategic analysis:

2. Features 3. Reliability

1. Performance 4. Conformance

8. Perceived Quality 5. Durability

7. Aesthetics 6. Serviceability
 1. Performance
 Performance refers to a product’s primary operating
characteristics.
– Ex: Automobile: acceleration, comfort
Television: picture clarity, color, sound
 Because this dimension of quality involves
measurable attributes, brands can usually be ranked
objectively on individual aspects of performance
 Overall ranking are difficult to develop as they
involve benefits that not every customers need.
 The superior performer depends entirely on the task
being performed.
 2. Features

 Features: characteristics that supplement the

product/service basic functioning.

Ex: Free drink on plane, automatic tuner on color TV

 Features also involve objective and measurable

attributes

 objective individual needs affects their translation

into quality difference.
 3. Reliability
 Reliability reflects the probability of the product failing or
malfunctioning within a specified time period.
 Most common measures of reliability:
– Mean Time to First Failure / Mean Time to Failure (MTTF)
– Mean Time Between Failure (MTBF)
– Failure Rate per Unit Time
 Reliability become more important to customers as downtime
and maintenance become more expensive.
Reliability Engineering Measures Lead to:

 Techniques for reducing failure rates while products were

still in the design phase
 Failure mode and Effect Analysis (FMEA): systematically
review how alternative designs could fail
 Individual component analysis: computed the failure
probability of key components and aimed to eliminate or
strengthen the weakest link
 Derating: required that parts be used below their specified
stress levels.
 Redundancy: called for parallel systems to back up an
important component or subsystem in case it failed.
 4. Conformance
 Conformance is the degree to which product’s design and
operating characteristics meet established standards.
 Drawback: Dispersion within specification limits are ignored
leading to tolerance stack up.
 Alternative: Taguchi Approach
 Two most common measures of failure in conformance:
– Defects rate in factory
– Incidences of service calls Manufacturing
– Accuracy and timeliness
– Counts of processing errors Service
– Unanticipated Delays
 5. Durability
 Two views:
– Durability can be defined as the amount of use one
gets from the product before it deteriorates. No
chance of repair. Ex. Bulb
– Durability may be defined as the amount of use
one gets from a product before it breaks down and
replacement is preferred to continued repair.
– Durability and reliability are closely linked
 6. Serviceability
 Serviceability is :
– the speed,
– courtesy,
– Technical competence (represented by frequency with which
the service calls or repair fail to correct outstanding problems) ,

– Responsiveness (time before which the service is restored –

Mean Time To Repair MTTR) and

– ease of repair.
 7. Aesthetics

 Aesthetics is all about how a product:

– looks,
– feels,
– sounds,
– tastes or smells
 It is clearly a matter of personal judgment
and a reflection of individual preference.
 8. Perceived Quality

 Reputation is a primary stuff of

perceived quality.
 Competing on Quality

A company should use the above 8

dimensional framework to explore the
opportunities it has so as to distinguish its
products from competitors.

The company need not follow all the

dimensions simultaneously. Sometimes
trade--off among dimensions has to be done.
trade
Statistical Quality Control
Seven Basic Quality Control Tools
 Cause-and-effect diagram (also called Ishikawa or fishbone diagrams):
Identifies many possible causes for an effect or problem and sorts ideas
into useful categories.

 Check sheet: A structured, prepared form for collecting and analyzing

data; a generic tool that can be adapted for a wide variety of purposes.

 Histogram: The most commonly used graph for showing frequency

distributions, or how often each different value in a set of data occurs.

 Pareto chart: A bar graph that shows which factors are more significant.

 Scatter diagram: Graphs pairs of numerical data, one variable on each

axis, to look for a relationship.

 Flow chart

 Control chart: Graph used to study how a process changes over time.
Theoretical Basis of Control Charts
Central Limit Theorem
As sample size gets large enough, sampling distribution becomes
almost normal regardless of population distribution

X
X x
X  x 
n
 The Normal Distribution

Common Cause
Special Cause
Variation
Variation

Control Limits
Examining Variation
Stable Process

Prediction

Time

Normal distribution at all times

 Examining Variation
Unstable Process

? ?

Prediction

Time

Any process that is not stable is called an

unstable or out
out--of
of--control process.
 Process Control:
Three Types of Process Outputs
(a) In statistical control and
capable of producing within
control limits. A process
with only natural causes of
variation and capable of
Frequency producing within the
specified control limits.

Lower control limit Upper control limit

(b) In statistical control, but not
capable of producing within
control limits. A process in
control (only natural causes of
variation are present) but not
capable of producing within the
specified control limits; and

(c) Out of control. A process out of control

Size having assignable causes of variation.
(Weight, length, speed, etc. )
What are the sources of variation in a process?

– Machine variation
– Raw Material variation
– Different methods used
– Measurement variation
– Operator variation
– Environmental factors
 Causes of Variation
What prevents perfection? Process variation...

Natural Causes Assignable Causes

 Inherent to process  Exogenous to process

 Random  Not random
 Cannot be controlled  Controllable
 Cannot be prevented  Preventable
 Examples  Examples
 weather – tool wear
 Power failure – “Monday” effect
 capability of machine – poor maintenance
– Worker fatigue
– Drastic changes in raw material
 Natural
and
Assignable
Variation
 Statistical Quality Control
Statistical quality control (SQC) is the term used to describe
the set of statistical tools used by quality professionals to
control quality.

SPC Acceptance
Sampling
– Statistical process control (SPC)
» Involves inspecting the output from a process
» Quality characteristics are measured and charted
» Helpful in identifying in-process variations
– Acceptance sampling: used to randomly inspect a batch of goods to
determine acceptance/rejection
» Does not help to catch in-process problems
 Statistical Process Control
It is a methodology for monitoring quality of manufacturing
and service delivery processes to help identify and
eliminate unwanted causes of variation.

Used to determine whether a process is performing as

expected.
 SPC attempt to find answers to question?

 What is the distribution of process output?

– centering, range or “spread”
 Is the process capable of meeting customer expectations :
 Is the supplier’s product meeting specs.?
 What is cause the variability?
 Can we afford to minimize the variability?
 Over time, how can we be sure the process hasn’t changed?
 When should we “tinker” with the process & when should we leave it alone?
 Who needs to understand and
commit to SPC?
 Everyone in the plant
 management Giving one person all of
 production the responsibility
 engineering and design for SPC will not work
 sales
 Implications for Managers
 How much and how often to inspect?
– Consider product cost and product volume
– Consider lot size
– Consider process stability
 Where to inspect?
– Inbound materials
– Finished products
– Prior to costly processing
 Which tools to use?
– Control charts are best used for in-process production
– Acceptance sampling is best used for inbound/outbound
Statistical Process Control Steps

Produce Good No
Start
Provide Service
Can we
Take Sample assign
causes?
Yes
Inspect Sample Stop Process

Create
Find Out Why
Control Chart
 Control Chart Construction Steps
1. Select the process to be charted;
2. Determine sampling method and plan:
– How large a sample needs to be selected? (4-5 no.) Balance the time and
cost to collect a sample with the amount of information you will gather.
– As much as possible, obtain the samples under the same technical
conditions: the same machine, operator, lot, and so on.
– Frequency of sampling will depend on whether you are able to detect
patterns in the data. Consider hourly, daily, shifts, monthly, annually,
lots, and so on. Once the process is “in control”, you might consider
reducing the frequency with which you sample.
– Generally, collect 20-25 groups of samples before calculating the
statistics and control limits.
Control Chart Construction Steps
3. Initiate data collection:
– Run the process untouched, and gather sampled data.
– Record data on an appropriate Control Chart sheet or other
graph paper. Include any unusual events that occur.
4. Calculate the appropriate statistics and control limits:
– Use the appropriate formulas.
5. Construct the control chart(s) and plot the data.

Control chart makes it very easy for you to identify visually points and
processes that are out of control without using complicated statistical tests.

This makes the control chart an ideal tool for the shop floor, where quick
and easy methods are needed.
 Process Control Charts: Practice
Look for
assignable
In control Out of control ! cause !

UCL Problem
corrected

Target

LCL

Time
Samples
Natural variation
 Control Charts
 As long as the points remain between the lower and upper
control limits, we assume that the observed variation is
controlled variation and that the process is in control
 Control Chart
 The process is out of control. Both the fourth and the twelfth
observations lie outside of the control limits, leading us to
believe that their values are the result of uncontrolled variation.
 Control Chart
 Even control charts in which all points lie between the control
limits might suggest that a process is out of control. In particular,
the existence of a pattern in eight or more consecutive points
indicates a process out of control, because an obvious pattern
violates the assumption of random variability.
 Control Chart
 The first eight observations are below the center line,
whereas the second seven observations all lie above the center
line. Because of prolonged periods where values are either
small or large, this process is out of control.
Patterns to Look for in Control Charts
 Control Chart Types

Continuous Categorical or Discrete

Numerical Data Control Numerical Data
Charts

Variables Attributes
Charts Charts

R X P C
Chart Chart Chart Chart
 Quality Characteristics

Variables Attributes
 Characteristics that you  Characteristics for which you
measure, e.g., weight, length focus on defects
 May be in whole or in  Classify products as either
fractional numbers ‘good’ or ‘bad’, or yes/ No
 Continuous random variables – e.g., radio works or not
 e.g. length, weight, diameter,  Categorical or discrete
time random variables
 % defective, number of flaws
in a shirt, number of broken
eggs in a box
 Variable Control Charts
(length, width, etc.)
 Mean (x-bar) charts
– Tracks the central tendency (the average or mean value observed) over
time

 Range (R) charts:

– Tracks the spread of the distribution over time (estimates the observed
variation or Difference between highest and lowest data point).
 Control Chart for 9 Samples
Variation due to
assignable causes

17=UCL
Variation due to
16=Mean
natural causes
15=LCL
Variation due to
1 2 3 4 5 6 7 8 9 10 11 12 assignable causes
Sample Number
Out of control
 X Chart : Control Limits

UCL x  x  A R X = Sample Average

Range for
LCL x  x  A  R sample i
Mean for
n sample i

 xi n
 Ri
x  i  i 1
R 
n n
No. of Samples
 x Computations

x1  x 2  ... x n 
x x  “n” here equals no.
k n of observations in
“k” here = no. of samples each sample

UCLx  x  z x
LCLx  x  z x

z =desired
standard normal variable or the no. of std. deviations
to use to develop the control limits
Factors for Computing Control Chart
Limits
Sample Mean Upper Lower
Size, n Factor, A2 Range, D4 Range, D3
2 1.880 3.268 0
3 1.023 2.574 0
4 0.729 2.282 0
5 0.577 2.115 0
6 0.483 2.004 0
7 0.419 1.924 0.076
8 0.373 1.864 0.136
9 0.337 1.816 0.184
10 0.308 1.777 0.223
12 0.266 1.716 0.284
 The Range Chart
 Range Chart measures the dispersion or variance of
the process while, the X- Bar chart measures the
central tendency of the process.

 If some observations exhibit very large ranges and

others very small ranges, you might conclude that
the spread is not consistent over time.
 The Range Chart
If σ is known, the control limits are:
LCL  D1
Center line  d 2
UCL  D2

If σ is not known, the control limits are:

LCL  D3 R
selecting D4 and D3 use number
of observations per sample
UCL  D4 R for n (same sample size).

d 2 , D1 , D2 , D3 and D4 are the correction

factors from the table QC correction Control
and R is the average subgroup range
 QC Correction Factors
n A2 d2 Dl D2 D3 D4
2 1.88 1.128 0 3.686 0 3.268
3 1.023 1.693 0 4.358 0 2.574
4 0.729 2.059 0 4.698 0 2.282
5 0.577 2.326 0 4.918 0 2.114
6 0.483 2.534 0 5.078 0 2.004
7 0.419 2.704 0.204 5.204 0.076 1.924
8 0.373 2.847 0.388 5.306 0.136 1.864
9 0.337 2.970 0.547 5.393 0.184 1.816
10 0.308 3.078 0.687 5.469 0.223 1.777
11 0.285 3.173 0.811 5.535 0.256 1.744
12 0.266 3.258 0.922 5.594 0.284 1.717
13 0.249 3.336 1.025 5.647 0.308 1.692
 The Range Chart
12.00
Out control limits

10.62

10.00

8.00

6.00

4.00

3.25

2.00

0.00 0
0 5 10 15 20 25 30
 Analysis of Range Chart

 Each point on the range chart represents the range within

each subgroup.

 The average subgroup range is 3.25, with the control limits

going from 0 to 10.62. According to the range chart shown,
only the 27th observation has an out-of-control value.

 The special cause should be identified if possible. However,

in discussing the problem with the operator, sometimes you
might not be able to determine a special cause.
 Using x-
x-bar & R
R--charts

 Use together
 Reveal different
problems
 A shift in the
range or mean x R
may mean the
process is out if
control, so it is
important to use
both measures!

R x
 Control Charts for Attribute Data
(% defective or no. of flaws)
 p-Charts:
– Tracks proportion of defectives/nonconforming in a sample

 np--Charts
np
– Tracks the number of nonconforming items in a sample

 c-Charts:
– Track the average number of defects/nonconformities per unit of output
p Chart (Fraction Defective Chart )
 Nominally scaled categorical data: e.g., good-bad, acceptable/not
acceptable, works/doesn’t work, on time/late

 Shows % of nonconforming items in a sample

 The distribution of the proportions can be approximated
by the normal distribution, provided that np and n(1 - p)
are both at least 5.
 If p is very close to 0 or 1, a very large subgroup size
might be required for the approximation to be legitimate.
 p Chart
Control Limits
p (1  p )
UCL p  p  z
n
z = 2 for 95.5% limits;
p (1  p ) z = 3 for 99.7% limits
LCL p  p z
n
k k
 ni  xi No. Defective
n  i 1
and p  i 1
k Items in Sample i
k  ni
i 1

p (1  p ) Size of sample i
 p 
n
where n i  size of each sample
p = proportion of nonconforming items
p = average proportion of nonconforming items
 P-Chart Example:
Production manager for a tire company has inspected the number of defective
tires in five random samples with 20 tires in each sample. The table below
shows the number of defective tires in each sample of 20 tires. For Z= 3.
Calculate the control limits.
 Solution:
Sample Number Number of Proportion
of Tires in Defective
Defective each Sample
Tires No.of Defectives 9
1 3 20 .15
p   .09
TotalInspected 100
2 2 20 .10
p(1 p) (.09)(.91)
3 1 20 .05 σp    0.064
n 20
4 2 20 .10
UCLp  p  zσ  .09 3(.064) .282
5 1 20 .05
Total 9 100 .09
LCLp  p  zσ  .09 3(.064) .102 0

Note: Lower control limit can’t be negative.

 np Chart
 The number of nonconforming items is assumed to
be given by a binomial distribution
Disadvantage:
If the sample size changes, the center line or mean as well as
the control limit changes. Thus, making inference difficult.
An np-chart should not be used when sample size varies
CLnp  np
UCLnp  np  3 np (1  p )
LCLnp  np  3 np (1  p )
where  np  np (1  p )
 c Chart
 Discrete quantitative data
 Shows number of nonconformities (defects) in a unit
– Unit may be chair, steel sheet, car etc.
– Size of unit must be constant
 Example: Count no. of defects (scratches, chips etc.) in
each chair of a sample of 100 chairs; Plot

c is the average number of counts in each subgroup. If

the LCL is less than zero, by convention it will set to
equal zero, because a negative count is impossible.
k
LCL  c  3 c  c i
c  i 1

k
UCL  c  3 c No. of units
sampled
 C-Chart Example:
The number of weekly customer complaints are monitored in a large
hotel using a c-
c-chart. Develop three sigma control limits using the data
table below. Z=3.
Week Number of  Solution:
Complaints
1 3 _
no. of complaints 22
2 2 c   2.2
3 3 no. of samples 10
4 1
UCLc  c  z c  2.2  3 2.2  6.65
5 3
6 3 LCLc  c  z c  2.2  3 2.2  2.25  0
7 2
8 1
9 3
10 1
Total 22
 Deciding Which Control Chart to Use
 Using an X and R chart:
– Observations are variables
– Collect 20-25 samples of n=4, or n=5, or more each from a stable process and compute the
mean for the X chart and range for the R chart.
– Track samples of n observations each.

 Using the P-Chart:

– We deal with fraction, proportion, or percent defectives
– Observations are attributes that can be categorized in two states
– Have several samples, each with many observations
– Assume a binomial distribution unless the number of samples is very large – then assume
a normal distribution.

 Using a C-Chart:
– Observations are attributes whose defects per unit of output can be counted
– The number counted is often a small part of the possible occurrences
– Assume a Poisson distribution
– Defects such as: number of blemishes on a desk, number of typos in a page of text, flaws
in a bolt of cloth
Control chart for individual observations
 Sometimes it's not possible to group your data into subgroups.
 This could occur when each measurement represents a single
batch in a process or when the measurements are widely
spaced in time.
 Ex. Rate of production is low, every unit is inspected because
of criticality and costly nature of item, testing process is
destructive on the item.
 With a subgroup size of 1, it's not possible to calculate
subgroup ranges. This makes many of the regular formulas
impractical to apply.
Control chart for individual observations
 The method is to create a "subgroup" consisting of each
consecutive observation and then calculate the MOVING
RANGE of the data. The subgroup variation is determined
by the variation from one observation to another, and that
variation will be used to determine the control limits for the
variation between subgroups. The limits are:

Here x is the sample average of all

R
of the observations, R is the LCL X
 x  3
d2
average range of consecutive
values in the data set, and d2 is
the control limit factor from the R
UCL X
 x  3
QC Correction factors, 1.128. d2
Range chart for individual observations

 We can also create a moving range chart of the moving

range values; that is, the range between consecutive
values. The limits are:

LCL  D3 R
LCL  D4 R

HERE sample size=n=2

 The tensile strength

63.778

61.778 61.718

59.778 Upw ard trend may indicate a

process that is not in control
57.778

55.778
55.18

53.778

51.778

49.778
48.642
47.778

45.778

43.778
0 5 10 15 20 25 30
 Analysis

 The chart shown gives the values of the individual observations (not the
moving averages) plotted alongside the upper and lower control limits.

 No values fall outside the control limits, which would lead us to

conclude that the process is in control. However, the last eight
observations were all either above or near the center line, which might
indicate a process going out of control toward the end of the process.
This is something that should be investigated further.
 Moving Range I-
I-chart
9.000

8.000 8.031

7.000

6.000
Trend in the moving range
indicates a process not in
5.000
control

4.000

3.000
2.458
2.000

1.000

0.000 0
0 5 10 15 20 25 30
 Analysis

 The chart shows additional indications of a

process that is not in control. The last seven
values all fall below the center line, and
there appears to be a generally downward
trend to the ranges from the sixth
observation on. We would conclude that
there is sufficient evidence to warrant
further investigation and analysis.
Control Limits vs. Specification Limits

Control Limits Specification Limits

 Based on performance of the
 Based on performance of the
product..
product
process.
 desired range of product
 Tell us when to take action on attribute

the process.  part of product design

 Ex. length, weight, thickness,
 defines and limits process
etc. with upper and lower
capability specification limits
 Tell us when to disposition the
product..
product
 Process Capability

 A measure of the ability of a process to meet preset design

specifications:
– Determines whether the process can do what we are
asking it to do
 Design specifications (a/k/a tolerance limits):
– Preset by design engineers to define the acceptable range
of individual product characteristics (e.g.: physical
dimensions, elapsed time, etc.)
– Based upon customer expectations & how the product
works (not statistics!)

Process may not be capable of meeting specification!

 Process Capability
Lower spec. limit
LSL Spec USL Process variation

 Capable process

 Very capable process

 Process not capable

Upper spec. limit
 Process Capability

Design (a) Natural variation exceeds

Specifications
design specifications; process
is not capable of meeting
specifications all the time.

Process
Design
Specifications

(b) Design specifications and

natural variation the same;
process is capable of meeting
Process
specifications most of the time.
 Process Capability
Design
Specifications (c) Design specifications greater
than natural variation; process
is capable of always conforming
to specifications.
Process

Design
Specifications

(d) Specifications greater than

natural variation, but process off
center; capable but some output
will not meet upper specification.
specification. Process
 Process Capability
 Product Specifications
– Preset product or service dimensions, tolerances
– e.g. bottle fill might be 16 oz. ±.2 oz. (15.8oz.-16.2oz.)
– Based on how product is to be used or what the customer expects
 Process Capability – Cp and Cpk
– Assessing capability involves evaluating process variability relative to
preset product or service specifications
– Cp assumes that the process is centered in the specification range
specification width USL  LSL
Cp  
process width 6σ

– Cpk helps to address a possible lack of centering of the process

 USL  μ μ  LSL 
C pk  min , 
 3σ 3σ 

Cp=Cpk when process is centered

Relationship between Process Variability
and Specification Width
 Three possible ranges for Cp

Fig. (a): Cp = 1,
Process variability just meets
specifications

Fig. (b) : Cp ≤ 1
Process not capable of
producing within specifications

Fig. (c) Cp ≥ 1
Process exceeds minimal
specifications

If 6σ < (USL - LSL), then at least 99.7%

of output of process will fall within
specification limits
 Computing the Cp Value at Cocoa Fizz: three bottling machines
are being evaluated for possible use at the Fizz plant. The
machines must be capable of meeting the design specification of
15.8-16.2 oz. with at least a process capability index of 1.0 (Cp≥1)
 The table below shows the information  Solution:
gathered from production runs on each
machine. Are they all acceptable? – Machine A
USL  LSL .4
Cp    1.33
6σ 6(.05)
Machine σ USL
USL--LSL 6σ
– Machine B
A .05 .4 .3
USL  LSL .4
Cp    0.33
B .1 .4 .6 6σ 6(.1)

C .2 .4 1.2
– Machine C
USL  LSL .4
Cp    0.25
6σ 6(.2)
Computing the Cpk Value at Cocoa Fizz
 Design specifications call for a target
value of 16.0 ±0.2 OZ.
(USL = 16.2 & LSL = 15.8)

 Observed process output has now

shifted and has a µ of 15.9 and a
σ of 0.1 oz.
 16.2  15.9 15.9  15.8 
Cpk  min , 
 3(.1) 3(.1) 
.1
Cpk   .33
.3

 Cpk is less than 1, revealing that the

process is not capable
 Process Capability -- Example
A manufacturer of granola bars has a weight specification
2 ounces plus or minus 0.05 ounces. If the standard deviation
of the bar-making machine is 0.02 ounces, is the process capable?

USL = 2 + 0.05 = 2.05 ounces

LSL = 2 - 0.05 = 1.95 ounces

Cp = (USL - LSL) / 6
= (2.05 - 1.95) / 6(0.02)
= 0.1 / 0.12
= 0.85

Therefore, the process is not capable!

 Process Centering -- Example
For the granola bar manufacturer, if the process is
incorrectly centered at 2.05 instead of 2.00 ounces, what
fraction of bars will be out of specification?

LSL=1.95 2.0 USL=2.05

Out of spec!

50% of production will be out of specification!

Service at a bank: The Dollars Bank competes on customer service and is
concerned about service time at their drive-by windows. They recently
installed new system software which they hope will meet service specification
limits of 5±2 minutes and have a Capability Index (Cpk) of at least 1.2. They
want to also design a control chart for bank teller use.

 They have done some sampling recently (sample size of 4 customers) and
determined that the process mean has shifted to 5.2 with a Sigma of 1.0
minutes.
USL  LSL 7 - 3
Cp   1.33
6σ  1.0 
6  
 4 
 5.2  3.0 7.0  5.2 
Cpk  min  , 
 3(1/2) 3(1/2) 
1.8
Cpk   1.2
1.5

 Control Chart limits for ±3 sigma limits

 1 
UCL  X  z σ x  5.0  3 
x   5.0  1.5  6.5 minutes
 4
 1 
LCL x  X  zσ x  5.0  3    5.0  1.5  3.5 minutes
 4
 Process Control Charts
Error Trade-
Trade-offs
 Setting control limits too tight (e.g., µ± 2σ) means that
normal variation will often be mistaken as an out-
out-of
of--
control condition (Type I error).
 Setting control limits too loose (e.g., µ ± 4σ) means that an
out--of
out of--control condition will be mistaken as normal
variation (Type II error).
error).
 Using control limits works well to balance Type I and
Type II errors in many circumstances.
 Applying SPC to Service
 Hospitals
– timeliness and quickness of care, staff responses to requests, accuracy
of lab tests, cleanliness, courtesy, accuracy of paperwork, speed of
admittance and checkouts

 Grocery Stores
– waiting time to check out, frequency of out-
out-of
of--stock items, quality of
food items, cleanliness, customer complaints, checkout register errors

 Airlines
– flight delays, lost luggage and luggage handling, waiting time at ticket
counters and check-
check-in, agent and flight attendant courtesy, accurate
flight information, passenger cabin cleanliness and maintenance
 Applying SPC to Service
 Fast--Food Restaurants
Fast
– waiting time for service, customer complaints, cleanliness, food
quality, order accuracy, employee courtesy

 Catalogue--Order Companies
Catalogue
– order accuracy, operator knowledge and courtesy, packaging,
delivery time, phone order waiting time

 Insurance Companies
– billing accuracy, timeliness of claims processing, agent availability
and response time
 Where to Use Control Charts
 Process has a tendency to go out of control
 Process is particularly harmful and costly if it goes out of
control
 Examples
– at the beginning of a process because it is a waste of time and
money to begin production process with bad supplies
– before a costly or irreversible point, after which product is difficult
to rework or correct
– before and after assembly or painting operations that might cover
defects
– before the outgoing final product or service is delivered
Reasons for using Control Charts

 Improve productivity

 Make defects visible

 Determine what process adjustments need to be made

 Determine if process is “in” or “out of control

How Will Control Charts help your Company?

 Possible Goals when using Control Charts in your

Company:
– Line reengineering
– Increased Employee motivation
– Continually improve of your process
– Increased profits
– Zero defects
 Quality is not simply a
problem to be solved ; it is a
competitive opportunity.
 Important Tools for TQM

 Quality Function Deployment

Deployment:: House of Quality
 Determines what will satisfy the customer
 Translates those customer desires into the target design
 Taguchi technique:
technique: Experimental design methods to improve
product & process design
design.. Identify key component & process
variables affecting product variation
 Important Tools for TQM
 Tools for generating ideas
 Check sheet
 Scatter diagram
 Cause and effect diagram
 Tools for identifying problems
 Histograms
 Statistical process control chart
 Tools to organize data
 Pareto charts
 Process charts (Flow diagrams)
diagrams)
 Why TQM Efforts Fail

 Lack of a genuine quality culture

 Lack of top management support and commitment

 Over
Over-- and under
under--reliance on SPC methods
 10 Steps of Implementing SPC

1. Analyze the process

2. Decrease obvious variability
3. Gauge capability study
4. Sampling plan
5. Implement CONTROL CHARTS
6. Put the operator in charge
7. Process capability study
8. Improve the process
9. Reduce sampling
10. Return to step 1