9/26/2018

07PE6105 TOTAL QUALITY MANAGEMENT

Module 2 Seven Basic Quality Control Tools

 Process Flow Charts

• Basic Tools and techniques – Quality Control Tools  Checksheets
• Management Tools  Run Charts
• Statistical process Control – Control Charts Process
 Scatter Diagrams
capability –
• Six Sigma Quality – DMAIC methodology
 Cause--and
Cause and--Effect Diagrams
 Histograms and Bar Charts
 Pareto Charts

TQM 5-15

Flow Chart Process Flow Chart

Check Sheets
Run Chart

1
 9/26/2018

Scatter diagram Cause and effect diagram

Pareto Charts

Management Tools Why Why

(Advanced QC Tools)

• Why, Why? • For finding the root cause of a problem by

• Forced Field analysis focusing on the process rather than people
• Nominal Group Technique
• Affinity diagram • Describe the problem in specific terms and ask
• Interrelationship digraph why why
• Tree diagram • Ask why three or more times to get the root
• Process decision program chart cause.
• Activity network diagram

TQM TQM

2
 9/26/2018

Forced field analysis

• To identify the forces and factors that may influence the problem or goal.
• Helps organization to better understand promoting or driving and
restraining or inhibiting forces so that the positives can be reinforced and
the negatives reduced or eliminated
• The procedure is to define the objective , determine criteria for evaluating
the effectiveness of the improvement action , brainstorm the forces that
promote and inhibit achieving the goal, prioritize the forces from greatest
to least and take action to strengthen the promoting forces weaken the
inhibiting forces

TQM

Nominal Group Technique Nominal Group technique

• This technique provides for issue /idea input

from everyone on the team and for effective
decisions.

TQM

Affinity Diagram Affinity Diagram

• The diagram allows the teams to creatively generate
a large number of issues/ideas and then logically
group them for problem understanding and possible
breakthrough solution.
• The procedure is to state the issue in a full sentence ,
brainstorm using short sentences on self adhesive
notes, post them for the team to see, sort ideas into
logical groups and create concise descriptive
headings for each group.

TQM

3
 9/26/2018

Interrelationships Digraph
Interrelationships digraph
• The interrelationship digraph clarifies the
interrelationships of many factors of a
complex situation.
• It allows the team to classify the cause and
effect relationships among all the factors so
that the key drivers and outcomes can be used
to solve the problem.

TQM

Tree Diagram
Tree Diagram
• This tool is used to reduce any broad objective into increasing
levels of detail in order to achieve the objective.
• First choose an action oriented objective statement from the
interrelationship diagram , brainstorming, team mission
statement and so forth.
• Second using brainstorming choose the major headings
• Third generate the next level by analyzing the major headings.

TQM

Process Decision program Process Decision program chart(PDPC)

chart(PDPC)
• Programs to achieve particular objectives
which do not always go according to plan and
unexpected developments may have serious
consequences.
• PDPC avoids surprises and identifies possible
countermeasures

TQM

4
 9/26/2018

Activity Network Diagram

Activity network diagram
• It allows the team to schedule a project
efficiently
• The diagram shows completion times,
simultaneous tasks, starting and ending times
of activities and critical path.

TQM

5
 9/26/2018

Statistical Quality Control Methods

Origin of Statistical Quality Control (SQC)
Statistical quality
• SQC refers to use of statistical methods to improve or control methods
enhance quality for customer satisfaction
• After World War II, W. E. Deming, the quality expert
and consultant, was invited to Japan by the
Japanese government to give a series of lectures on Acceptance Statistical process
improving product reliability. sampling control
• This was probably the single most important event
that started the Japanese toward a global quality
revolution.
• These lectures were based on statistical quality Attributes Variables Attributes Variables
control, and they became a cornerstone of the
Japanese commitment to quality management.

Supplement 5-3 2

SQC Methodologies Attributes and Variables

• Statistical Process Control – • The quality of a product can be evaluated using
Control of the transformation process operating on raw either an attribute of the product or a variable
measure.
materials and customers
• An attribute is a product characteristic (qualitative)
• Acceptance Sampling – such as color, surface texture, or perhaps smell or
Control of inputs and outputs of the transformation taste. Attributes can be evaluated quickly with a
process by sampling inspection discrete response such as good or bad, acceptable
• Design of Experiments – or not, or yes or no.
• A variable measure is a product characteristic
Process of optimization in the design of products and (quantitative) that is measured on a continuous
processes scale such as length, weight, temperature, or time.

Sources of variation
Variations in Attributes and Variables
Material Methods Environment
•Assemblies •Procedures •Noise level
•Components •Policies •Humidity
• Variations are inherent in any process and is not always •Suppliers
•Consumables
•Accounting •Temperature
•Lighting
under control
• In any process NO two objects are ever made exactly
alike or no two customers are getting exactly the same Variation
type of service.
• Magnitude of variations can be large or small and this
magnitude decides the level of quality of any product or People Machine Measurement
service. •Training
•Experience
•Technology
•Variability
•Counting
•Instruments
•Skill •Tooling •Gauging
• Data analysis helps to identify the variations •Attitude •Fixtures •Tests

1
 9/26/2018

Variations in nature and industry follows the

NORMAL FREQUENCY DISTRIBUTION
Variations
• Most things have a variable component to them
• The causes responsible for the variation are to be
rectified

• Two Types of Variations

• Variations which are inherent due to random causes or
chance causes without any reason
• Variations which are assignable due to assignable
causes

Variations
• Variations in any process can be described in general in
terms of two parameters
Central tendency – Accuracy
Dispersion – Precision
• There can be situations of Accuracy and precision both
there or both absent or one is there and other is absent.
• Controlling variations means controlling not only central
tendency but also dispersion

PROCESS CAPABILITY AND

SPECIFICATIONS
• Process capability measures are indicative of
the limits of the natural variations which can
occur in a process

• Specifications, on the other hand, are the

permissible variation in the individual values
as decided by design engineers or customers

2
 9/26/2018

Process Capability Process Capability

• Process capability is a measure of process • Process capability has got three important
performance to find out the central tendency components
and range of natural variations.  The Design Specifications
 The Centering of natural variations
• Any process which is natural will be having  The Spread of a Variation
random variations distributed in the form of a • Process control refers to controlling the
Normal Distribution with mean and standard process within the specifications including
deviation determination of reasons for deviations and
taking corrective actions

Measures of Central Tendency and Dispersion

Process Capability
Standard Deviation/
Mean Spread Process Capability Ratio
n
2 Upper specification - Lower specification
x i x  x
i
Cp = 6s
x i 1 
n n1 Process Capability Index
x- – Lower specification
Cpk = Minimum of
3s
,
Upper specification – x-
3s

Example of Process Capability Study from a Production

Process Capability Study Machine Shop

• Gather Process Data after eliminating any

assignable causes, process should be natural
• Plot Data 25 + 5 mm (Diameter)

• Find the variations and calculate the process

capability
Upper specification = 30 mm
• Take suitable actions based on the outcome Lower specification = 20 mm

Data Analysis of 1000 pieces revealed

Average diameter = 26.2 mm s = 1.35 mm

3
 9/26/2018

Process Capability Process Capability

Machine Shop Machine Shop
Upper specification = 30 mm Upper specification = 30 mm
Lower specification = 20 mm Lower specification = 20 mm
Average diameter = 26.2 mm s = 1.35 mm Average diameter = 26.2 mm s = 1.35 mm

Cpk = Minimum of x- – Lower specification

3s
,
Process
Upper specification – -x
Capability
Index 3s
Example 5.5 Example 5.5

Process Capability Process Capability

Machine Shop Machine Shop
Upper specification = 30 mm Upper specification = 30 mm
Lower specification = 20 mm Lower specification = 20 mm
Average diameter = 26.2 mm s = 1.35 mm Average diameter = 26.2 mm s = 1.35 mm

Cpk = Minimum of 26.2 – 20.0 30.0 – 26.2 Cpk = Minimum of 1.53, 0.94
3(1.35)
, 3(1.35)
Process Process
Capability Capability
Index Index
Example 5.5 Example 5.5

Process Capability Process Capability

Machine Shop Machine Shop
Upper specification = 30 mm Upper specification = 30 mm
Lower specification = 20 mm Lower specification = 20 mm
Average diameter = 26.2 mm s = 1.35 mm Average diameter = 26.2 mm s = 1.35 mm
Upper specification - 30 - 20
Cpk = 0.94 Cp = Lower specification Cpk = 0.94 Cp = 6(1.35)
6s
Process Process Process Process
Capability Capability Capability Capability
Index Ratio Index Ratio
Example 5.5 Example 5.5

4
 9/26/2018

Process Capability Process Capability

Machine Shop Machine Shop
Upper specification = 30 mm Upper specification = 30 mm
Lower specification = 20 mm Lower specification = 20 mm
Average diameter = 26.2 mm s = 1.35 mm Average diameter = 26.1 mm s = 1.20 mm

Cpk = 0.94 Cp = 1.23 Cpk = 1.08 Cp = 1.39

Process Process Process Process

Capability Capability Capability Capability
Index Ratio Index Ratio
Example 5.5 Example 5.5

Process Capability Process Capability

Nominal Nominal
value value
Process distribution Process distribution
Lower Upper Lower Upper
specification specification specification specification

20 25 30 mm 20 25 30 mm
(a) Process is capable (b) Process is not capable
Figure 5.12 Figure 5.12

5
 9/26/2018

Conclusions from Cp and Cpk

• Cp do not change as the process center changes.
• Cp = Cpk when the process is centered, process needs close
monitoring
• Cpk is always equal to or less than Cp.
• Cpk > 1.00, process conform to specifications, scope for
reducing cost.
• Cpk < 1.00, process not conform to specifications,
Process/Machine adjustment required.
• Cp < 1.00, process is not capable, Process needs
improvement.
• Cpk = 0.00, Mean is equal to one of specification limits.
• Cpk < 0.00, Mean is outside the specifications.

6
 9/26/2018

Control Charts
• Control charts are used to ensure the dynamic
performance of a process
• It helps to take decision on when to leave a
process alone and when to take action in a
process.
• Control charts are of two types
Control Chart for attributes
Control Chart for variables
1 2

Control Chart for Variables

Plotting of Control Chart for Mean & Range
Mean – Range Chart
• Take samples of a fixed size from process and calculate Mean
• Mean chart is used to keep a watch on the and Range of samples
central tendency by fixing control limits • Calculate Mean of the Sample means and Mean of the Range
• Find out Upper Control Limit and Lower Control Limit for
Samples are taken from the process and their mean and range
means are calculated • UCL/LCLX =
Mean of Sample means + A2 *(Mean of Ranges) =
• Range chart is used to keep a watch on the • UCLR = D4 *(Mean of Ranges)
dispersion by fixing control limits • LCLR = D3 *(Mean of Ranges)
• Plot Mean, Range, LCL and UCL and Verify whether any points
Samples are taken from the process and their lying outside the control limits which indicates the process
ranges are calculated. control

3 4

Example of Mean and Range Chart

5 6

1
 9/26/2018

Control Chart Examples Control Charts

for Variables
UCL
Variations

Nominal

LCL
West Allis Industries
Sample number

Figure 5.7 (a)

7 8

Control Charts Control Charts

for Variables for Variables
Special Metal Screw Special Metal Screw
Sample Sample Sample Sample
_ _
Number 1 2 3 4 R x Number 1 2 3 4 R x
1 0.5014 0.5022 0.5009 0.5027 1 0.5014 0.5022 0.5009 0.5027 0.0018 0.5018
2 0.5021 0.5041 0.5024 0.5020 2 0.5021 0.5041 0.5024 0.5020
3 0.5018 0.5026 0.5035 0.5023 3 0.5018 0.5026 0.5035 0.5023
4 0.5008 0.5034 0.5024 0.5015 4 0.5008 0.5027
0.5034 – 0.5009
0.5024 0.5015 = 0.0018
5 0.5041 0.5056 0.5034 0.5039 5 0.5041 0.5056 0.5034 0.5039

Example 5.1 9
Example 5.1 10

Control Charts Control Charts

for Variables for Variables
Special Metal Screw Special Metal Screw
Sample Sample Sample Sample
_ _
Number 1 2 3 4 R x Number 1 2 3 4 R x
1 0.5014 0.5022 0.5009 0.5027 0.0018 0.5018 1 0.5014 0.5022 0.5009 0.5027 0.0018 0.5018
2 0.5021 0.5041 0.5024 0.5020 2 0.5021 0.5041 0.5024 0.5020
3 0.5018 0.5026 0.5035 0.5023 3 0.5018 0.5026 0.5035 0.5023
4 0.5008 0.5027
0.5034 – 0.5009
0.5024 0.5015 = 0.0018 4 0.5008 0.5027
0.5034 – 0.5009
0.5024 0.5015 = 0.0018
5 0.5041 0.5056 0.5034 0.5039 5 0.5041 (0.5014
0.5056 0.5034+ 0.5022
0.5039 +
0.5009 + 0.5027)/4 = 0.5018

Example 5.1 11
Example 5.1 12

2
 9/26/2018

Control Charts Control Charts

for Variables for Variables
Special Metal Screw Control Charts – Special Metal Screw
Sample Sample
_ R-Charts R = 0.0021
Number 1 2 3 4 R x
1 0.5014 0.5022 0.5009 0.5027 0.0018 0.5018
2 0.5021 0.5041 0.5024 0.5020 0.0021 0.5027 UCLR = D4R
3 0.5018 0.5026 0.5035 0.5023 0.0017 0.5026 LCLR = D3R
4 0.5008 0.5034 0.5024 0.5015 0.0026 0.5020
5 0.5041 0.5056 0.5034 0.5047 0.0022 0.5045
R= 0.0021
=
x= 0.5027

Example 5.1 Example 5.1

13 14

Control Charts Control Charts

Table 5.1 Control Chart Factors for Variables for Variables
Factor for UCL Factor for Factor
Size of and LCL for LCL for UCL for Control Charts—Special Metal Screw
Sample x-Charts R- Charts R-Charts
(n ) ( A2) (D3) (D4) R-Charts R = 0.0021 D4 = 2.282
2 1.880 0 3.267 D3 = 0
3 1.023 0 2.575 UCLR = D4R
4 0.729 0 2.282
5 0.577 0 2.115 LCLR = D3R
6 0.483 0 2.004
7 0.419 0.076 1.924
8 0.373 0.136 1.864
9 0.337 0.184 1.816
10 0.308 0.223 1.777
Example 5.1 15
Example 5.1 16

Control Charts Control Charts

for Variables for Variables
Control Charts—Special Metal Screw Control Charts—Special Metal Screw
R-Charts R = 0.0021 D4 = 2.282 R-Charts R = 0.0021 D4 = 2.282
D3 = 0 D3 = 0
UCLR = D4R UCLR = D4R
LCLR = D3R LCLR = D3R

UCLR = 2.282 (0.0021) = 0.00479 cm. UCLR = 2.282 (0.0021) = 0.00479 cm.
LCLR = 0 (0.0021) = 0 cm.
Example 5.1 17
Example 5.1 18

3
 9/26/2018

Control Charts Range Chart -

for Variables Special Metal Screw
Control Charts—Special Metal Screw
R-Charts R = 0.0021 D4 = 2.282
D3 = 0
UCLR = D4R
LCLR = D3R

UCLR = 2.282 (0.0021) = 0.00479 cm.

LCLR = 0 (0.0021) = 0 cm.
Example 5.1 Figure 5.8
19 20

Control Charts Control Charts

for Variables for Variables
Table 5.1 Control Chart Factors
Factor for UCL Factor for Factor
Control Charts—Special Metal Screw Control
Size of Charts—Special
and LCL for Metal Screw
LCL for UCL for
Sample x-Charts R- Charts R-Charts
X-Charts R = 0.0021 X-Charts
(n ) ( A2) R = 0.0021 (D3) (D4)
x= = 0.5027 2
=
1.880x = 0.5027 0 3.267

UCLx = x= + A2R =
3 1.023 0 2.575
UCL
4 x= x + A R 0.729
2 0 2.282
LCLx = x= - A2R 5
LCL
6 x
=
=x-A R 0.577
2
0.483
0
0
2.115
2.004
7 0.419 0.076 1.924
8 0.373 0.136 1.864
9 0.337 0.184 1.816
10 0.308 0.223 1.777
Example 5.1 21
Example 5.1 22

Control Charts Control Charts

for Variables for Variables
Control Charts—Special Metal Screw Control Charts—Special Metal Screw
x-Charts R = 0.0021 A2 = 0.729 x-Charts R = 0.0021 A2 = 0.729
x= = 0.5027 x= = 0.5027

UCLx = x= + A2R UCLx = x= + A2R

LCLx = x= - A2R LCLx = x= - A2R
UCLx = 0.5027 + 0.729 (0.0021) = 0.5042 cm.

Example 5.1 23
Example 5.1 24

4
 9/26/2018

Control Charts x-Chart—

for Variables Special Metal Screw
Control Charts—Special Metal Screw
x-Charts R = 0.0021 A2 = 0.729
x= = 0.5027

UCLx = x= + A2R
LCLx = x= - A2R
UCLx = 0.5027 + 0.729 (0.0021) = 0.5042 cm.
LCLx = 0.5027 – 0.729 (0.0021) = 0.5012 cm.
Example 5.1 Figure 5.9
25 26

Control Chart for Attributes

x-Chart—
P chart and C Chart
Special Metal Screw
• Control charts for attributes consist of P chart
– Fraction Defectives
For P chart samples are drawn from the
process and the fraction defectives are found
out
 Sample the process • C chart – Number of Defects
 Find the assignable cause For C chart sample refers to a single unit and
 Eliminate the problem in the unit the no of defects are found out
 Repeat the cycle
Figure 5.9 27 28

Plotting of P Chart Plotting of nP Chart

• For Plotting P chart the value of Average fraction • The nP chart is useful when it's easy to count
defectives, Upper Control Limit and Lower Control
Limit are calculated
the number of defective items and the sample
• Average Fraction Defective size is always the same.
Ṗ = Total defectives/Number of samples • Examples might include: the number of
UCL/LCL = Ṗ + z√ Ṗ (1- Ṗ )/n (z=3) defective circuit boards, meals in a restaurant,
= Ṗ + z σp teller interactions in a bank, invoices, or bills.
• Plot Chart with Ṗ , LCL and UCL.
• Points outside control limit indicate out of control of
the process
29 30

5
 9/26/2018

Control Charts Control Charts

for Attributes for Attributes
XYZ Gears

UCLp = p + zp
XYZ Gears
HOMETOWN BANK
LCLp = p – zp

p = p(1 – p)/n
Example 5.3
31 32

Control Charts Control Charts

Sample
Number
Defective
Gears for Attributes Sample
Number
Defective
Gears for Attributes
1 15 1 15
2 12 Hometown Bank 2 12 Hometown Bank
3 19 3 19
4 2 n = 2500 4 2 n = 2500
5 19 5 19
UCLp = p + zp
6 4
Total defectives
UCLp = p + zp
6 4
147
7 24 7 24
8 7 p = Total observations 8 7 p=
LCLp = p - zp
9 10 LCLp = p - zp
9 10 12(2500)
10 17 10 17
11 15 11 15
12 3 12 3
p = p(1 - p)/n p = p(1 - p)/n
Total 147 Total 147
Example 5.3 Example 5.3
33 34

Control Charts Control Charts

Sample
Number
Defective
Gears for Attributes Sample
Number
Defective
Gears for Attributes
Proportion
Defective
1 15 1 15 0.006
2 12 Hometown Bank 2 12 Hometown
0.0048 Bank
3 19 3 19 0.0076
4 2 n = 2500 4 2 0.0008 n = 2500
5 19 5 19 0.0076
UCLp = p + zp
6 4 UCLp = p + zp
6 4 0.0016
7 24 7 24 0.0096
8 7 p = 0.0049 8 7 0.0028 p = 0.0049
LCLp = p - zp
9 10 LCLp = p - zp
9 10 0.004
10 17 10 17 0.0068
11 15 11 15 0.006
12 3 12 3 0.0012
p = p(1 - p)/n p = p(1 - p)/n
Total 147 Total 147
Example 5.3 Example 5.3
35 36

6
 9/26/2018

Control Charts Control Charts

for Attributes for Attributes
XYZ Gears XYZ Gears
n = 2500 p = 0.0049 n = 2500 p = 0.0049

UCLp = p + zp UCLp = p + zp

LCLp = p – zp LCLp = p – zp

p = p(1 – p)/n p = 0.0049(1 – 0.0049)/2500

Example 5.3 Example 5.3
37 38

Control Charts Control Charts

for Attributes for Attributes
XYZ Gears XYZ Gears
n = 2500 p = 0.0049 n = 2500 p = 0.0049

UCLp = p + zp UCLp = 0.0049 + 3(0.0014)

LCLp = p – zp LCLp = 0.0049 – 3(0.0014)

p = 0.0014 p = 0.0014
Example 5.3 Example 5.3
39 40

Control Charts p-Chart

Defective Gears
for Attributes
ZYZ Gears
n = 2500 p = 0.0049

UCLp = 0.0091
LCLp = 0.0007

p = 0.0014
Example 5.3 Figure 5.10
41 42

7
 9/26/2018

p-Chart Plotting of C Chart

Defective Gears
• For Plotting C chart the value of Average
defects per unit, Upper Control Limit and
Lower Control Limit are calculated
• Average Fraction Defects
Cbar = Total defects/Number of units
 Sample the process • UCL/LCL = Cbar + z√ Cbar (z=3)
 Find the assignable cause Plot chart with C, LCL and UCL. Points outside
 Eliminate the problem control limit indicate out of control of the
 Repeat the cycle process
Figure 5.10
43 44

Example of a C Chart Control Charts

for Attributes

Woodland
Paper
Company

45 46

Woodland Control Charts Woodland Control Charts

Paper Paper
Company for Attributes Company for Attributes

c = 20 z=2 c = 20 z=2

UCLc = c + z c UCLc = 20 + 2 20

LCLc = c – z c LCLc = 20 – 2 20
Example 5.4 Example 5.4
47 48

8
 9/26/2018

Woodland Control Charts Woodland Control Charts

Paper Paper
Company for Attributes Company for Attributes

c = 20 z=2

UCLc = 28.94

LCLc = 11.06
Example 5.4 Example 5.4
49 50

Using Control Charts for Control Chart Patterns

Process Improvement • Even though a control chart may indicate
 Sample the process that a process is in control, it is possible
 When changes are indicated, find the the sample variations within the control
assignable cause limits are not random.
• If the sample values display a consistent
 Eliminate problems, incorporate
pattern, even within the control limits, it
improvements suggests that this pattern has a
 Repeat the procedure nonrandom cause that might warrant
investigation.
51 52

Control Chart Patterns

• A pattern in a control chart is characterized
by a sequence of sample observations
that display the same characteristics--also
called a run.
• One type of pattern is a sequence of
observations either above or below the
center line.
• Several tests are available to determine if
a pattern is nonrandom or random
53 54

9
 9/26/2018

Control Chart Patterns

• One type of pattern test divides the
control chart into three "zones" on each
side of the center line, where each zone is
one standard deviation wide.
• These are often referred to as 1-sigma, 2-
sigma, and 3-sigma limits.
• The pattern of sample observations in
these zones is then used to determine if
any nonrandom patterns exist.

55 56

Guidelines associated with the zones for identifying

patterns in a control chart Sample Size Determination
1. Eight consecutive points on one side of the center line • In general, larger sample sizes are needed
2. Eight consecutive points up or down across zones for attribute charts because more
3. Fourteen points alternating up or down
observations are required to develop a
4. Two out of three consecutive points in zone A but still
inside the control limits usable quality measure.
5. Four out of five consecutive points in zone B or beyond • Variable control charts require smaller
the 1-sigma limits sample sizes because each sample
• If any of these guidelines apply to the sample
observations in a control chart, it would imply that a
observation provides usable information--
nonrandom pattern exists and the cause should be for example, weight, length, or volume.
investigated.

57 58

10
 9/26/2018

Preface Evolution of Quality Systems

Six Sigma
Total Productive
Maintenance

• Equipment reliability
• Six sigma is recognized as one of the most Lean
Manufacturing
improvement
•Focus on Overall
legitimate way to improve processes, products Total Quality
Management
• Layout
Optimisation
equipment
effectiveness

services and the bottom-line in order to Statistical • Quality in all

•JIT
•Inventory
Process Control processes
substantially improve the financial Quality as •Statistical
•Quality at
reduction

source
performance. Inspection techniques for
quality control •Total
Employee
involvement
Time
1920-1940’s 1940-1960’s 1960-1980’s 1980-1990’s

Quality Systems evolved further..!! WHY SIX SIGMA

Six Sigma Survival - Growth of business

Total Productive •Variability reduction Growth of business - Customer Satisfaction

Maintenance •Customer centric
breakthrough
• Equipment improvements
Lean
reliability
Manufacturing
improvement •Metrics and results Customer Satisfaction
focused
Total Quality • Layout •Focus on
•Sigma Scale
Management Optimisation Overall
equipment
• QUALITY
•JIT •Process redesign for
effectiveness capability building
Statistical • Quality in all
Process Control processes
•Inventory
reduction •Usage of basic and • PRICE
•Quality at advanced statistical
•Statistical tools for root cause
Quality as
Inspection techniques for
source
identification • DELIVERY
quality control •Total
Employee
involvement

1940-1960’s 1960-1980’s 1980-1990’s 1990-1997 2000-beyond Time

What Is Six Sigma?

WHAT IS SIX SIGMA ?
Six Sigma is a disciplined, data-driven approach and
methodology for eliminating defects in any process --
from manufacturing to transactional and from product to • A Philosophy • make fewer mistakes in all that
service. we do.

• A business process using tools to achieve customer satisfaction • A Metric • A measuring system for
and shareholder value process performance
• A level of performance that reflects significantly reduced
defects in our products and processes • A Methodology • To improve process
• A set of statistical “tools” to help us measure, analyze, performance by improving
improve, and control our processes quality and reducing cost
• A commitment to our customers to achieve an exceptional
level of performance
5 6

1
 9/26/2018

Process Variations – the culprit for

What Six Sigma is
quality issues
Goal Metric • In any manufacturing process NO two objects are
ever made exactly alike or no two customers are
getting exactly the same type of service.
Benchmark Philosophy
• Variations are inherent in any manufacturing process
• Magnitude of variations can be large or small
Value Vision

Method
Symbol
Tool 7 8

The Concept of Variation

Every repeatable process exhibits variation 10

Measuring Variation

We measure variation using standard deviation (s ) 11

2
 9/26/2018

3  Process
Performance and defects

LSL USL
Defects Defects

Reducing Variability Is The Essence of Six Sigma 13

What is 6 Sigma?
3σ QUALITY MEANS !!!! – 0.27%
Which one of them would you count on? defective
• 200,000 wrong drug prescriptions every year
Cricketer A
• 15000 babies accidentally dropped by nurses and
Doctors each year
• 5000 incorrect surgical operations each week
Min=45 runs Max = 55 runs
• 20000 lost pieces of mail each hour
Cricketer B
• 27 parts in an assembled aircraft consisting of
10000 parts will be defective.
• No Electricity or Water for one full day in New Delhi
each year
Min = 0 runs Max = 100 runs
16
Average = 50 runs

6  Process
LSL CL USL This is 6
LCL UCL
Process

3σ 3σ

6σ 6σ

If all readings are falling between these control lines, and

specification lines are 6σ away means this process is 6σ.

3
 9/26/2018

Performance in Context
99.73% Good (3 Sigma) 99.99966% Good (6 Sigma)

• 20,000 lost articles of mail per • Seven articles lost per hour
hour

• Unsafe drinking water for • One unsafe minute every

almost 15 minutes each day seven months

• 5,000 incorrect surgical • 1.7 incorrect operations per

operations per week week

• 340 Passengers with • 6 Passengers with Misplaced

Misplaced Luggage every day luggage each month

• 200,000 wrong drug • 68 wrong prescriptions per

prescriptions each year year
19 20

SIGMA LEVEL
Methodologies
• Two distinctly different methodologies
• The Term Sigma (σ) is used to designate the distribution or spread about
the mean (average) of any process or procedure.
• DMAIC • DMADV
– Define • The Sigma Capability (Z-Value) is a metric that indicates how well that
–Define process is performing. The higher is Sigma Capability (Z) the better is the
– Measure –Measure process.
– Analyze –Analyze
– Improve –Design • A process at Three Sigma level is expected to produce 99.73%
– Control observations within the specification limits and 0.27% (2700 PPM)
–Verify
When a process needs to be observations as non-conformance, when there is no shift of process mean
improved When a process needs to from the target value.
be invented
(aka. DFSS-Designed For
Six Sigma)
21 22

A Six Sigma Process

Process Capability –
Technical Meaning
Process Capability Ratio
Upper specification - Lower specification
Cp = 6s

Process Capability Index

-x – Lower specification
Cpk = Minimum of
3s
,
Upper specification – x-
3s
23

4
 9/26/2018

Technical Definition of Six Sigma

History of Six Sigma Quality
75%
LSL
±1.5 s USL • In this era of liberalization and globalization one or
12.5% 12.5% two sigma performance in manufacturing is down
right non competitive.
Cp=2 Cpk=1.5 Cp=2 Cpk=1.5
3.4 DPMO
Cp=Cpk = 2
3.4 DPMO • Zero defects are philosophical benchmark or
standards of excellence in quality proposed by Philip
- 6s -5s -4s -3 s -2s -1s 0 +1s +2s +3s +4s +5s +6s Crosby.
6s to LSL 6s to USL • In 1987 Motorola adopted and pioneered the six
sigma concept as a modification to the zero defects
programme.

25 26

Six Sigma at Various Engineering/Management

THE GOALS OF SIX SIGMA Levels
• Engineers/Managers at the management level can use
Six Sigma for improving market share, increasing
• To enhance Customer Satisfaction profitability and organization’s long term viability.

• To improve Product Quality • Engineers/Managers at operations level can use Six

Sigma to improve yield and reduce the labour and
• To reduce Waste material cost.
• To reduce Cost and improve Yield
• At the process level engineers can use Six Sigma to
• To improve the Financial Performance reduce defects and variation and improve process
capability leading to better customer satisfaction.
27

6 Methodology - DMAIC
SIX SIGMA DMAIC
• Define
The Define phase summarizes the business problem to be solved and
quantifies the impact on the customer, establishing the critical-to-quality
characteristics of the process.
• Measure
Define Measure Analyze Improve Control Measure establishes a data collection plan, gathers the data necessary to
study the process and establishes the validity of the data.
• Analyze
Analyze looks for the root cause of defects by comparing current
performance against the desired goal. Variables responsible for process
variation are isolated using statistical methods and other analytic tools.
• Improve
What is How do we Improve determines the best way to improve the process and might
important? What is wrong? guarantee include experimentation or simulation to arrive at an improvement plan.
performance?
• Control
How are we What needs to be
Control creates accountability for the improved process with a control
doing? done? plan and, often, statistical process control (SPC) charts to ensure the
variation does not return.
30

5
 9/26/2018

DMAIC – Methods and Tools DMAIC Process

DEFINE Problem statement, SIPOC Map, Product chart, Flow Establish Controls on the critical Xs so the
Chart, VoC, Gemba Kaizen, QFD improvements will be maintained

MEASURE Sampling, Check sheet, Control charts, Histogram,

Distributions
Identify ways Metrics (Ys) linked to
ANALYSE Stratification, Pareto, Process Capability, Cause and to improve CTQs
effect analysis, Hypothesis testing the process X1 Define the Problem
Y1
and validate X2
PROCESS Y2 Project Objective
X3
IMPROVE Brain storming, Value engineering, JIT Methods, DoE, the solution X4
Y3 Project Goal
SMED, 5S, Poka – yoke, FMEA
Measure and Analyze
data and process
CONTROL Process Quality information systems, PDCA Cycle, performance to determine
Process capability, Control charts the critical variables and
root cause of the problem
31 32

“Define” Flow
Road Map: Define
VOC, Effort/Impact
Examine Analysis
Candidate
Define Measure Analyze Improve Control Projects SIX SI GMA
Project Ch arter
Resource Requirements G eneral Information Revi ew Schedul e E ffort / Impact Analysis
P ro j ec t No: Locati on: Acti vi ty Date
Proj ec t Name: Bus in ess Start GB P rojects BB Project s
Proje c t Leader: Segm ent: D 10
G B/BB: Bus in ess M
M as ter BB: Obje c tive: A 9
H/O Champio n: Customer I
Team M em bers : Name Function % Time Initials C TQ (s ): C
8
Current C lo s e 7
Proc ess
Capabi l it y : S ig ma, C pk , DPMO, Cyc le -ti me, et c. 6

Im p act
Date:
5 Impa ct
4
Pr oject Defin ition 3
Project Pr oblem Statement:
2

Team Customer Process Develop and 1

0
0 2 4 6 8 10 12
Effo rt

Chartering Focus Mapping Approve Project

Project O bje ctive Statement:

Charter
Project Scope/Lim itations:

 Types Of Customers
Define Customer Project G oals and Targets:

 The Business Case  Process Definition CTQs Project Plan:

See page 2 of th e proj ec t charter. Proje c t Pla n and Gantt Chart
Expected Benefits: Time frame:

 Understanding Hard Dol l ar Savi ngs :

Soft Dol l ar Savi ngs :
Strategi c :

 Problem And Goal  Benefits Of Process O ther Benefit s :

Customer Needs Hands O n Champion:

Sta kehold er App rova l
M aster Black Belt:

Statements Mapping
Name: Name:
Si gnature: Si gnature :
Functional Manager: Black / Gr een Belt:
Name: Name:
Si gnature: Si gnature :

 Methods Of Collecting Other:

Name:
Other:
Name:

Project Scope The SIPOC Model

Si gnature: Si gnature :

  Date:

Customer Input Respon

Respo
Response
((Y)
Y)
(Y)
se
nse
W ha t is the mo st
a pp ro pr iate e nd po int W ho ar e the cu sto mer s fo r

 Milestones  Levels Of Process W ho ar e t he su pp lier s fo r ou r p ro du ct

Wha t mu st my
sup plie rs pr ovid e to
f or th e p ro ce ss? Wh at o ur pr od uc t o r s er vice ?
D ete rmin e th e sta rt an d e nd p oint s o f th e pr oce ss p ro du ct or se rvice d oe s W ha t a re th eir

 Voice Of The Customer Operational

Op
Operational
erational
o r s er vice ? H ow cap ab le ar e th ey in
mee tin g o ur p roc es s r equ ire men ts?
my pr oce ss to me et
my ne ed s?
a sso ciat ed with th e pr oble m an d the majo r ste ps t he pr oc ess de liver to r eq uir eme nts fo r
in th e p ro ce ss. t he cu sto me r? p er fo rman ce

Definit
Definition
Definitio n
ion Suppliers Input Process Output Customers
Roles Process Boundaries Complete
(H igh Le vel)

 Analysis  CTQ(s)
1 1
2
3
Sta rt Poin t: 1

2
1
2
1

 Translate Customer  Mapping Guidelines Th

Vo ice of
Voice
Voice
e Custo
TThe
he Cu
Cust
of
mer
stomer
omer
Product
Product
Product
arrives
arrives on
arrives --time
oonn-time
Target
Target
Target SIPOC and 2

3
1
2
3
1
1
2
O pe ra tion o r Ac tivity 3

4
2
1
2
1

Needs Into Specific Specification

Sp
Specification
ecification
Process Map 4
2
3
1
2
3
3
4
5
6
7
5

6
2
1
2
1
2
LLimit(s)
im it(s)
Limit(s)
Requirement Add additional row s where needed 8
9
10
11
En d Po int :

 Prioritizing CPMs (Kano Error

Error Rat
Rate
Ratee
© Thomas A. Little C onsulting 2002

Analysis) 33 34

MEASURE PHASE
Road Map: Measure Measures
I P O
Develop m easures
based on CTQ’s
and SIPOC m ap
Define Measure Analyze Improve Control Input
Measures
Process
Measures
Output
Measures

Funneling Process Capability

O1 O2 O3 O4
LSL USL
I1
I2 FMEA Cp = 0.4
Data I3
s = 2.7 Calculate current process
Measurement Collection Variation Six Sigma
I4

capability and sigm a

Determ ine the critical

few m easures

 What Is A Measure  Types Of Data  Understand  Why Sigma Measures

Variation
 Process Context For  What Is Data  Counting
Measurement  Common Opportunities
Data Display
 5-Step Process Data Collection Plan Gage R&R
Cause/Special Cause Data Collection Plan
UCL

 Types Of Measures For Collecting Data  Calculating

Col# 1 2 3 4 5 6
1000
Inspector A B
And Appropriate What questions do you want to answer?
Sample # 1st Trial 2nd Trial Diff 1st Trial 2nd Trial Diff X

 Developing A Data Action Process Sigma – Data Operational Definition and Procedures
What Measure type/ How Related Sampling How/
1
2
2.0
2.0
1.0
3.0
1.0
1.0
1.5
2.5
1.5
2.5
0.0
0.0
0

 Preparing For Discrete Data

Data type measured conditions notes where 3
4
1.5
3.0
1.0
3.0
0.5
0.0
2.0
2.0
1.5
2.5
0.5
0.5
-1000 LCL

Analyze Collection Plan 5

Totals
2.0
10.5
1.5
9.5
0.5
3.0
1.5
9.5
0.5
8.5
1.0
2.0
10 20 30
 Graphical Displays Averages 2.1 1.9 0.6 1.9 1.7 0.4

Sampling Of Data  Long- And Short- How will you ensure

consistency and stability?
What is your plan for
starting data collection?
How will the data be displayed?
Sum
XA
4.0
2.0 RA
Sum
XB
3.6
1.8 RB
D B F A C E Other

Forms Term Data

Histograms Develop a data Validate your Display the data in graphic
Consistency Pareto  Why 1.5 Shift collection plan m easurement system
form to show current
Planning variation and other patterns
Run Charts
35 36

6
 9/26/2018

ANALYZE : ROADMAP

Define Measure Analyze Improve Control

Approach to Measure
Deliverables

Identify Possible Narrow to Root Quantify the

Causes Causes Opportunity
Collect Validate
baseline your
Segmentation & Hypothesis Determine
data on Develop a measurement Analyze Determine
defects Sampling system patterns process Stratification testing financial
and Strategy using in data capability Cause & Effect Scatter Diagram opportunity
possible Gage R&R Diagram
causes
Graphical Tools
Sub-process
mapping
Process map
analysis
Control charts
37 38

ANALYZE PHASE

VA NVA
APPROACH TO ANALYZE Process Analysis Perform a detailed
process analysis to
identify problems

Cause & Effect

Develop a Hypothesis Display your theories

Organize about root causes using
focused Process Testing and Design of a cause & effect diagram
potential
problem Analysis Regression Experiments
causes Hypothesis-Testing
statement Analysis
Regression Analysis
Chi-Square t-test Design of Experiments
c² ANOVA

Y
Regression
X1 Verify Root causes
through statistical tools
Use hypothesis testing
Use DOE and response
to identify differences
surface
optimization
39 40

IMPROVE
A 4
B 1 Generating Solutions
Cost-Benefit Analysis
APPROACH TO IMPROVE C
D
3
2

Generate solutions including Implementation

Perform cost-benefit Benchmarking and select
analysis for the best approach based on
Planning
preferred solution screening criteria 1 2 3 4 5 6 7 8 9 10
A
B
C
D
G
E F
G
H I J

Generate,
Generate, Selecting the Solution Develop a full plan
evaluate,
evaluate, Assess risks
Assess Develop
Develop for implementation and
and
andselect
select Piloting
change management
and
andpilot
pilot implementation
implementation
solutions
solutionstoto Full scale
solutions
solutions plans
plans Assessing Risks Original
Test
identified
identified
root
rootcauses
causes Recommend a solution
involving key
stakeholders.
Pilot the solution on
a small scale and
evaluate the results
Use FMEA to identify
risks associated with the
solution and take
preventive actions
41 42

7
 9/26/2018

CONTROL PHASE

Closure
QC Process Chart
APPROACH TO CONTROL
Dat e of I ssue: I ssued by: Appr oved by:
Revision Dat e Reason Signat ur e
Pr oduct Nam e
Pr ocess Nam e
Pr ocess Code #

Cont r ol/ Check Point s Response t o Abnor m alit y

Wor k
Flowchar t Char ac- Cont r ol I m m ediat e Per m anent Not es
I nst r uct ions Code # M et hod Who Who
t er ist ics Lim it s Fix Fix

Develop and deploy a plan

for how to respond to 1

process changes 2

Key Learnings
12

Results
Process Change
Qualification, Validation,
Management and Revalidation
Learnings
•
Document results and
Before After
•

} Improvement
• summarize key learnings. Identify
Recommendations
next
potential future projects
A1 A2 A3 A4 A2 A1 A3 A4
Before After Good

} Improvement
} Remaining Gap
Step 4 c hanges Target
implemented

Standardize and Establish Hand Off,

Quality Control & Ongoing
Document Evaluating Summarize Key
Process Change Project Hand off the improved process to the
Effective Results Learnings and Documentation &
Management Monitoring
process owner for on-going process
Methods Draft Future Plans management and rewarding and
Standardization celebrating the improvement team.
Training
Training
Manual
Curriculum
Evaluating Results
LSL USL
Fill to here Monitoring s = 2.7
Cp = 0.4

UCL
Document new process, using
training manuals and other tools
to ensure standardization
LCL s = 3.7
Cp = 1.4

Monitor the process using control

charts to ensure process stays in control Recalculate process capability,
and conforms to specification process sigma, and financial
results based on improvements.
43 44

PROJECT CLOSURE People Power and Training

– Improvement must be continuous, but individual initiatives
and project teams come to an end. • From the CEO to the shop-floor worker,
– Learn when it’s time to say goodbye.
everybody should be involved in the Six Sigma
– Effective project closure weaves together the themes of:
• Project purpose.
training process.
• Improvement methods.
• Team skills and structures.
– Develop managerial systems to capture learnings and
• The deployment involves training team
enable the organization to address system issues. members to become champions, black belts
– Documentation and recognition are two critical aspects of and green belts.
project team closure.
– Celebrate!

45 46

Certification
Six Sigma Infrastructure and Resources Based on skills and actual
accomplishment in projects.
Coach

• PLAYERS: Team Leader Significant Tangible

Results
Champions, Master Black Belts, Black Belts, Green Belts, Team Member Tangible Results
Yellow Belts. Roles and Responsibilities. Successful project
Multiple projects
Achievement facilitation
completion
Project leadership
Experience Project participation Change
• TRAINING Learning/ Management
Facilitation
Skill Problem solving
Training Materials, Tools and Software, Training Personnel
In-depth Advanced
Knowledge Basic

• Financial Empowerment, Facilities. Green Belt Black Belt Master Black Belt

47

8
 9/26/2018

People Power for Six Sigma

Mentor, trainer, and coach of Black Belts and others
Six Sigma
Master
Black
in the organization.
Implementation
Belt

Leader of teams implementing the six sigma • Top Down Commitment

methodology on projects.
Black Belts
• Launching the initiative
Champions

• Measurement Systems to Track Progress

Delivers successful focused projects using
the six sigma methodology and tools.
• Tough Goal Setting
Green Belts
• Training and Education

Participates on and supports the project

• Communication
Team Members teams, typically in the context of his or
Quality Fundamentals
her existing responsibilities. • Customer Priorities
• Implementation
Deployment Responsible for supporting the Deployment • Sustaining the effort and return
Strategy within Line of Business/Customer
Champions 49 50
Segment or Golden Thread

Continuous Improvement, Enough..!?

SIGMA DEFECT RATE COST OF POOR QUALITY COMPETITIVE
Level LEVEL
(PPM) ( % OF SALES )

6 3.4 <1%
WORLD
CLASS
5 233 1 % - 5%

4 6,210 5 % - 10 %

3 66,807 10 % - 15 %
INDUSTRY
AVERAGE
2 308,537 15 % - 25 %

1 690,000 > 25 % NON-

COMPETITIVE