14-12-2015

Quality Management

What is Quality ?
Many times considered as a confusing concept
There is no universal definition for Quality
Quality is most often related to

Perfection
Consistency
Eliminate Waste
Speed of Delivery
Compliance with Polices and Procedures
Providing good, usable product
Doing the right thing correct the first time
Delighting the customer

14-12-2015

Quality Perspectives
The Quality perspectives are classified into four types:
a. Judgment criteria
b. Product based criteria
c. User based criteria
d. Value based criteria
Judgmental Criteria
Synonymous with Quality is excellence or superiority
A Mark of uncompromising standards and achievements
Often loosely related with the comparison of features
and characteristics of images
Example: ROLEX watches, Mercedes Benz, Taj Hotels etc..

Product based Criteria

The term quality is function specific
It reflect the differences in quality with respect to some
attribute such as number of stitches per inch/cm on shirt..
Kilometer per liter etc
Most often mistakenly assumed to be related with price.
User based Criteria
Based on assumption of quality is what customer wants
Fitness to use
Example: T shirt and formal suit
Kinetic Honda

14-12-2015

Value based Criteria

Based on Value
It is usefulness of the project/product or
satisfaction over the price
Quality product (with this perspective is) is one
that is useful as a competing product and is
sold at a lower prize.
Thus one would prefer a generic product than a branded
one, if performance is rated similar
..Quality is a relative term and is close with customer needs..

Garvin's Quality Dimensions. A generic perspective

Classification is carried out based on the sectors
a. Manufacturing and b.Services
For Manufacturing sector
a. Performance: The Operating Characters of a product
b. Features: Additional Features available for the product..
c. Reliability: The probability that the product will operate
for specified time for specified use.

14-12-2015

d. Conformance:Degree to which the physical and

performance characteristics of a
product match pre-established
standards
e. Durability:

Deterioration of the product

f. Serviceability: The speed courtesy and

competence of repair work
g. Aesthetics:

How the product feels, looks

smells etc..

h. Perceived quality: The brand value of the product.

Garvin's Quality Dimensions. A Case study

Consider an example of a Laser printer
Following are the quality parameters
a. Performance:

Pages per minutes

Print density
b. Features:
Multiple paper trays
Color display capability
c. Reliability:
Mean time between failure
d. Conformance: Pixel density
Crispness of printing
e. Durability:
Estimated life of obsolescence

14-12-2015

f. Serviceability: Number of authorized service centers

Ease to access the components
Ease to replace the components
g. Aesthetics:

Control panel
Ease of operation

h. Perceived Quality: Brand name recognition

Rating in the consumer reports

Relative importance of these dimensions can be

established by assigning weight to each dimension
For example:
Sr. No
1
2.
3.
4.
5.
6.
7.
8.

Dimension
Performance
Features
Reliability
Conformance
Durability
Serviceability
Aesthetics
Perceived Quality

Weight
0.30
0.05
0.15
0.10
0.15
0.10
0.05
0.1

14-12-2015

The printer is evaluated for each dimension separately

on a score of 0 to 10 ( this is dimension score)
10 - perfection and 0 indicates absolute absence
Sr. No
1
2.
3.
4.
5.
6.
7.
8.

Dimension
Performance
Features
Reliability
Conformance
Durability
Serviceability
Aesthetics
Perceived
Quality

Weight
0.30
0.05
0.15
0.10
0.15
0.10
0.05
0.1

Brand X
8
6
5
8
9
6
7
9

Brand Y
7
2
6
7
8
9
9
6

Multiplying the dimension score with dimension weight

yields overall quality rating for each printer
Sr. No Dimension

Weight

1
2.
3.
4.
5.
6.
7.
8.

0.30
0.05
0.15
0.10
0.15
0.10
0.05
0.1

Performance
Features
Reliability
Conformance
Durability
Serviceability
Aesthetics
Perceived
Quality
Total

Brand X
Score Wt
8
2.40
6
0.30
5
0.75
8
0.8
9
1.35
6
0.6
7
0.35
9
0.9

Brand Y
Score Wt
7
2.10
2
0.1
6
0.9
7
0.7
8
1.2
9
0.9
9
0.45
6
0.60

7.45

6.95

14-12-2015

Garvins Quality Dimension for services

There are six dimensions for the services sector namely:
:

Reliability: The ability to provide what was promised, dependably

and accurately.
Assurance:The knowledge and courtesy of the employees, and
their ability to convey trust and confidence.
Tangibles: The physical facilities and equipment, the appearance
of the personal providing services.
Empathy: The degree of caring and individual attention provided
to the customers,
Responsiveness: The willingness to help customers and provide
prompt services.
Perceived quality: The brand value of the product, how the other
see the product.

Features:
a. The present quality status can be quantified
b. Allows fair comparison between two products
c. Promotes group decision making

14-12-2015

Quality Tools

Quality Tools
Quality Tools are tools that help organizations
their processes to improve them.

understand

These methods are utilized by quality professionals to aid in

the analysis,documentation, and organization of quality systems.

Each tool helps in visualizing sources of variation.

Used primarily for problem solving.
They are designed so that workers at all levels can understand
the process and procedure of a system.

14-12-2015

The Quality Tools..

Flow charts : Understand the mess; Establish procedures.
Check sheet : Finding facts.
Histograms : Identifying problems.
Cause and Effect Diagram : Generating ideas, Identify problems.
Pareto diagrams : Understand the mess; Identify problems.
Scatter Diagram : Developing solutions.

Control charts : Understanding the mess; holding the gains.

Flow Charts
Flowcharts are a visual diagram of a process
broken down by activities.
Document processes as they flow from start
to finish and they show how each step is related.
At a high level, help users understand
complex processes without confusing details.
At a detail level, they help users analyze their
processes for optimization and improvements.

14-12-2015

Flow ChartsConstruction
Select a start and stop point (define boundaries).
List major steps/tasks and decision points (list, in order, the steps
or tasks and possible decisions).
Use standardized graphical symbols to document the process, e.g.
= start/stop

= dir. of flow

= step/task

= decision

Review the results (compare to real process and verify it is

complete and accurate).

Flow ChartsExample
Working of Pizza Villa
Open the Restaurant

Take Customer Order

Go to chef

Wait till available/

take new orders

no

Pizza
Available?

yes
Take it to the customer

10

14-12-2015

Flow ChartsExample
Wait till customer
has his food

Ask if
more is
needed

No

Go to chef
Yes

Get the bill and pay

Yes
Time to
close?

Stop

No

Close the Restaurant

Take customer order

Check List
Check sheets are forms used to summarize a tally count
of event occurrences.
Count the number of occurrences, such as defects, for an
event (e.g. inspection, audit etc).

Design the check sheet for a given application (include

relevant information for later reference).
Record the data in space provided (place an X or
other mark for each occurrence).
For primary data collection for other quality tools such
as Pareto charts and histograms.

11

14-12-2015

Check Sheet

Defect Type

Days

Check Sheet
COMPONENTS REPLACED BY LAB
TIME PERIOD: 22 Aug to 27 Aug 2005
REPAIR TECHNICIAN: Sunil
TV SET MODEL 1013

Integrated Circuits
||||
Capacitors
|||| |||| |||| |||| |||| ||
Resistors
||
Transformers
||||
CRT
|

12

14-12-2015

Histogram
A histogram is a bar graph that shows frequency data.
Histograms provide the easiest way to evaluate
the distribution of data.

How to construct a Histogram:

Collect data and sort it into categories.
Label the data into sets (independent/ dependent).
The characteristic you grouped the data would be independent variable.
The frequency of that set would be the dependent variable.

For each category,

Find the related frequency and make the horizontal marks
to show that frequency.

Examples of How Histograms Can Be Used

Histograms can be used to determine distribution of sales.
Say for instance a company wanted to measure the revenues
of other companies and wanted to compare numbers.

<<<<<< << See Excel sheet (histogram.xls)

for Example >>>>>>>>

13

14-12-2015

Cause and Effect Diagram

Also known as
Fishbone diagrams
Ishikawa diagrams

Show the relationships between a problem

and its possible causes

Constructing a Cause and Effect Diagram

First, clearly identify and define the problem or effect for which the causes
must be identified.
Place the problem or effect at the right or the head of the diagram.
Identify all the broad areas of the problem.
Write in all the detailed possible causes in each of the broad areas.
Each cause identified should be looked upon for further more specific causes.
View the diagram and evaluate the main causes.
Set goals and take action on the main causes.

14

14-12-2015

Cause and Effect Diagram an Example

Measurement
Faulty testing equipment
Incorrect specifications
Improper methods

Human

Machines
Out of adjustment

Poor supervision
Lack of concentration

Tooling problems

Inadequate training

Old / worn

Quality
Problem

Inaccurate
temperature
control

Defective from vendor

Not to specifications

Dust and
Dirt

Materialhandling problems

Environment

Materials

Poor process design

Ineffective quality
management
Deficiencies
in product design

Process

Cause and Effect Diagram an Example

15

14-12-2015

Pareto Diagram
Pareto charts are used to identify and prioritize
problems to be solved.
They are actually histograms aided by the 80/20 rule
adapted by Joseph Juran.
The 80/20 rule states that approximately 80% of the problems
are created by approximately 20% of the causes.

Constructing Pareto Diagram

First, information must be selected based on types or
classifications of defects that occur as a result of a process.
The data must be collected and classified into categories.
Then a histogram or frequency chart is constructed
showing the number of occurrences.

16

14-12-2015

Pareto Diagram Example:

100
90
80
70
60
50
40
30
20
10
0
1

The chart shows the number

of defects rectified in a casting

1.
2.
3.
4.
5.
6.
7.

Poor design
Wrong dimensions
Defective parts
Machine calibration
Operator Error
Defective material
Surface abrasion

Pareto Diagram for progressive analysis:

1400

Which assembly has maximum defects ?

1200
1000
800

Assembly 5

600
400
200
0
Assembly 5

Assembly 2

Assembly 3

Assembly 1

90
80
70
60

What are the common defects?

50
40
30

Electrical

20
10
0
Electrical

Assembly

Soldering

Finishing

17

14-12-2015

40

What electrical components

contribute most of
the defects ?

35
30
25
20
15
10

Relays

5
0
Relay

Capacitor

Transistor

Resistor

Switch

PCB

30

What is the most common

way in which the relay fails?

25
20
15

Thermal

10
5
0
Thermal

Offset

Noise

Dust

Flux

Scatter Diagram
Supplies the data to confirm a hypothesis that two
variables are related.
Provides both a visual and statistical means to test
the strength of a relationship.

Provides a good follow-up to cause and effect

diagrams.

18

14-12-2015

Constructing a Scatter Diagram

First, collect two types of data and create a summary
table of the data.
Draw a diagram labeling the horizontal and vertical axes.
It is common that the cause variable be labeled on the X axis and the
effect variable be labeled on the Y axis.

Plot the data pairs on the diagram.

Interpret the scatter diagram for direction and strength.

Scatter diagram Patterns

19

14-12-2015

Example

Control Charts
Used to determine whether a process will produce a product
or service with consistent measurable properties

Identify critical operations in the process where

inspection might be needed.
Establish the control limits and use the chart to monitor and
improve.
Update the limits.
Determine whether the critical product characteristic
is a variable or an attribute.

20

14-12-2015

Data types:
Variable or Attribute Data
Variable is measured on a continuous scale
Attribute is occurrences in n observations

Deviation from Mean

Upper and Lower Specs
Range

Statistical Quality Control

Statistics ?
Quality ?
Control ?

21

14-12-2015

WHY SQC ???????

Identify the present status
Improve the process.at least maintain/control
Suggest warning signals
Can Specification limits do this ?

Limitations
Assignable causes: Large influence on process

Chance causes: Low influence on the process

Assignable causes
Tool Wear
Material Variation
Poor Maintenance
Operator Performance

22

14-12-2015

Chance causes
Machine Vibrations
Machine Temperature
Sudden Breakdown
Non Homogeneity of Material

Works out for Assignable causes of variations

and not for Chance cause.

Steps
1. Preparation
a. Choose the variable/attribute to be measured
b. Determine the basis, size and frequency of sampling
c. Setup control chart
2. Data collection
a. Record the data
b. calculate the relevant strategies (mean, range etc..)
c. plot them on a chart
3. Determination of trial control limits
a. Draw center line
b. Compute upper and lower control limits

23

14-12-2015

Steps
4. Analysis and interpretation
a. Investigate the chart for lack of control
b. Eliminate out of control points
c. Re-compute control limits if necessary
5. Use a problem solving tool
a. Continue data collection and plotting
b. Identify out-of- control situations & take corrective action
6. Use the control chart data to determine process capability,
if desired.

We Discuss..

Different Statistical Methods for Quality Control

Variables
Attributes
Process Capability

24

14-12-2015

Variables
X bar and R Charts

Attributes
Sample
size is

Looking at
Defectives

Defects

Constant

np-charts

c-charts

Variable

p-charts

u-charts

25

14-12-2015

We plot
On Y axis: Values
Control Limits
Upper Control Limit
Lower Control Limit
Warning Limits
Upper Warning Limit
Lower Warning Limit
Mean Line.
On X axis: Sample number

We Plot the Values and Observe

The Scatter of points (values)
And the Pattern / Trend

26

14-12-2015

Patterns / Trends

Shift

Result of
Introduction of New Workers
Methods
Raw materials
Machines
Change in Inspection Method
Standard
Attentiveness
Motivation

Patterns / Trends

Cyclic

Result of
Environmental Changes
Temperature
Operator Fatigue
Fluctuation Of
Voltage
and/or
pressure
Maintenance schedules

27

14-12-2015

Patterns / Trends

Trend

Result of
Gradual Wearing of tool or the
deterioration
Setting or separation of
mixture.

A Process Is In Control If

No sample points are outside control limits

Most points are near the process average

About an equal (approx.) points are above

& below the centerline
Points appear randomly distributed

28

14-12-2015

Sense Danger If

1.

8 consecutive points on one side of the

center line
8 consecutive points up or down
across zones
14 points alternating up or down
2 out of 3 consecutive points in Zone A
but still inside the control limits
4 out of 5 consecutive points in Zone A or B

2.
3.
4.

5.

Zones For Pattern Tests

UCL

Zone A

x + 3 sigma

Zone B

x + 2 sigma

Zone C

x + 1 sigma

Zone C

x - 1 sigma

Zone B

x - 2 sigma

Zone A

x - 3 sigma

LCL

29

14-12-2015

Look At Control Charts

X bar Charts
Sample size
Sample number
Compute

Normally 3,4, 5, 6,7.

Normally 20 to 30.
n

X
i 1

For each of Sample groups

n= 3, 4, 5, 6, 7

On Y Axis plot
Center Line = X Double bar
m

X
j 1

m = 20 to 30

Upper Control Limit =

UCL X A2 R

Lower Control Limit =

LCL X A2 R

R max( X i ) min( X i )

30

14-12-2015

On X Axis plot
The Sample Number called as Sample Run
The Points are X bars

R Charts

Center line is the grand mean (R bar)

Points are R

D3 and D4 values are tabled according

to n (sample size)

UCL D4 R

LCL D3 R

31

14-12-2015

A Word on Constants
Derived by considering
Normal Distribution
99.7 % Confidence Interval
Eliminates Chance causes and
Considers Assignable Causes
Eliminates the Errors
Type I
Concluding a process is not
in control when it actually is.
Type II
Concluding a process is
in control when it is not.

Constants

n
3
4
5
6
7

A2
1.023
0.729
0.577
0.483
0.419

D3
0
0
0
0
0.076

D4
2.574
2.282
2.115
2.004
1.924

32

14-12-2015

Control Charts For Attributes

Nature of defect is different in services

Service defect is a failure to meet customer
requirements
Monitor times, customer satisfaction

Service Quality Examples

Hospitals

Grocery Stores

check-out time, stocking, cleanliness

Airlines

timeliness, responsiveness, accuracy

luggage handling, waiting times, courtesy

Fast food restaurants

waiting times, food quality, cleanliness

33

14-12-2015

p Charts

Calculate percent defectives in a sample;

An item is either good or bad

c Charts

Count number of defects in an item

p - Charts
Based on the binomial distribution

p = number defective / sample size, n

p=

total no. of defectives

total no. of sample observations
UCLp = p + 3 p(1-p)/n
LCLp = p - 3 p(1-p)/n

34

14-12-2015

Sample calculation for P charts

Proportion

Sample Defect Defective

1
6
.06
2
0
.00
3
4
.04

..

..

20

18
200

.18
1.00

UCL = p + 3 p(1-p) /n

..

= 0.10 + 3 0.10 (1-0.10)/100

= 0.190

100 items in each sample

total defectives

LCL = p - 3 p(1-p) /n

p =

total sample observations

p =

= 0.10 + 3 0.10 (1-0.10) /100

200
= 0.010

20(100)

0.2

0.14
0.12
0.1
0.08
0.06
0.04

20

18

16

14

12

..

10

0.02
0

Proportion defective

0.18
0.16

35

14-12-2015

c - Charts

Count the number of defects in an item

Based on the Poisson distribution

c = number of defects in an item
c=

total number of defects

number of samples
UCLc = c + 3 c
LCLc = c - 3 c

36