LSSGB Lesson6 Control

Lean Six Sigma Green Belt
Lesson 6Control
Copyright 2014, Simplilearn, All rights reserved.

Objectives
After completing
this lesson, you will
be able to:
Describe Statistical Process Control (SPC)
Explain control charts
Discuss control plan strategies
Develop a control plan
Discuss visual factory
Describe control methods for 5S
Control
Topic 1Statistical Process Control
Introduction to Statistical Process Control

Statistical Process Control (SPC) was developed by Walter A. Shewhart in 1924. SPC aids in the visual
monitoring of a process and controls its parameters by placing statistical measures around the
process outputs or input variables.

Following are the benefits of SPC:
Separates the special and common causes of variability
Recognizes the unexpected changes in the process output quickly
Helps to identify the stable zone for variables where specification limits are unknown
Provides useful external information for the continuous improvement of the process
Helps in monitoring a process online
Common Cause Variation

The common cause variation is the variation that can be usually seen in the process.
Example: Minute variations in the raw materials
Part of the process and the

organization is aware of its presence.
Causes for this variation are

repetitive.
Features of
Common Cause
Variation
Frequency of its occurrence is high,

hence can be easily predicted.
Identifying and removing these

causes requires huge investment and
is time consuming.
This variation will be within the

tolerance or specification limits.
Special Cause Variation

The special cause variation is the variation that cannot be normally seen in the process.
Example: Machine or system crash
Not part of the process, affects the

regular process, and produces
defects.
Causes are non-repetitive.
Features of
Special Cause
Variation
Frequency of occurrence is less and

cannot be predicted.
Identifying and removing these

causes require less investment.
Variation affects the flow of the

process due to which the defects
appear.
Common Cause Variation vs. Special Cause Variation

Common cause variation and special cause variation can be differentiated as follows:
Common Cause Variation
Special Cause Variation
Frequency of occurrence is high
Frequency of occurrence is less
Predictable
Unpredictable
Part of the process
Is not part of the process
High investment for removal
Relatively less investment for removal
Repetitive
Not repetitive
Elimination is difficult
Elimination is comparatively easy
Rational Subgrouping
Rational subgrouping refers to the selection of subgroups or samples in a way that if assignable
causes are present, chance for differences between subgroups will be maximized and chance for
differences due to assignable causes within a subgroup will be minimized.

Approach I to construct rational subgroups
Sample consists of units produced at the same
timeconsecutive units.
Primary purpose is to detect process shifts
Approach II to construct rational subgroups

Sample consists of units that are representative of all
units produced since the last samplerandom
sample.
Often used to make decisions about acceptance
of product
Effective at detecting shifts to out-of-control state
and back into in-control state between samples
Data Collection for SPC

The data collection process for SPC is as follows:
Document purpose of data

collection
List the project goals
Identify measurable items

to understand process
Write operational
definitions for each
measure
Check for availability of

historic data
Document the name of the

person collecting the data
Confirm who will review

and validate the data and
how often
Find the duration for data

validation
Implement end-to-end
process and ensure it is
followed regularly
Determine if other
measures are appropriate
Finalize method of collecting,

aggregating/summarizing,
and displaying data
Data Collection for SPCTechniques

Some of the data collection techniques for SPC are as follows:
Census
Sampling
Experiment
Observational
Collects and uses the
Collects data from a
A controlled study
Attempts to
complete data from the
subset of a population
performed to
understand cause-and-
population.
and estimates the
understand the cause-
effect relationships,
population attributes.
and-effect relationships
however specific
between multiple
treatment is not given
variables, inputs and
to the groups.
outputs, etc.
10
Control Chart Anatomy

Control chart, developed by Walter Shewhart in the 1920s, plots and processes the data (input X data
and output Y data) over a period and connects by lines, in order to detect trends or unusual events.
Characteristics of control charts are as follows:
They are similar to Run Charts, with an addition of control limit lines and an average/center line.
Control charts can be used with discrete or continuous data.
Control limits are typically set at approximately three standard deviations (3s) from the center
line.
Specification limits (USL and LSL) do not appear on them.
11
Control Chart AnatomySample

A sample control chart is shown on the screen.
12
Control Charts and Analysis

Control charts are useful for tracking process statistics over time and detecting the presence of
special causes. A process is in control when:
most of the points fall within the bounds of the control limits; and
the points do not display any nonrandom patterns.
The data is depicted visually in a control chart. Hence it is easy to find the differences between common
cause and special cause.
13
Setting the Control Limits

A standard control chart uses control limits at three standard deviations of the mean (mean) from the
datas grand average (X, average of the sample averages, or ).
The probability of an out-of-control point when the process has not changed is only 0.27%.
If the control limits are set at:
2 standard deviationsincreases the chance of type I or alpha error.
4 standard deviationsincreases the chance of a type II or beta error.
Walter Shewhart had set 3 limits on control charts with the belief that when the process goes beyond
these limits, it needs correction.
14
Common Rules for Control Chart Analysis

An Out-Of-Control (OOC) condition is indicated if one of the following is true:
1 point is outside the Control Limits (either above UCL or
below LCL).
p(f) = 0.27%
8 consecutive points are above the Center Line (CL) or

consecutively below the CL.
p(f) = (0.5)8 = 0.39%
6 to 8 points are consecutively increasing or decreasing.
p(f) = (0.5)6 or (0.5)8 = 1.6% to 0.39%
2 out of 3 points are within 1 mean of either the UCL or the

LCL.
p(f) = (2!1!)(0.023)2(0.477) = 0.08% for one side
3!
15
Choosing an Appropriate Control ChartContinuous Data

There are two ways in which sampling of continuous data can be done.
Continuous Data
Individual Data Points

(Pulling one sample at fixed frequency)
ImR Chart
(Depicts the variability of individual
characteristics over time)
Subgroups
(Taking periodic group data)
X and R Chart
(If n is between 2 and 9)
X and s Chart
(When standard deviation is
calculated and n10)
16
Choosing an Appropriate Control ChartDiscrete Data

Discrete data can be sub-divided into two parts.
Discrete Data
Defectives
Defects
Constant Subgroup Size
Varying Subgroup Size
Constant Subgroup Size
np Chart
(Number of Units
Rejected)
p Chart
(Percentage of Units
Rejected)
c Chart
(Number of Defects)
Varying Subgroup Size
u Chart
(Average Number of
Defects per Opportunity)
17
X Chart Principles
X refers to average and the subgroup average data will be plotted on the X chart.
Some of the principles of X and R and X and s charts are as follows:
X and R and X and s charts are two separate charts of the same subgroup data.
X chart is a plot of the means of subgroup data and shows inter-subgroup or between-subgroup
variation.
R chart is a plot of the subgroup ranges (or if s, plot of subgroup standard deviation) and shows
intra-subgroup variation.
In X control charts, the control limits are calculated based on mean of means, range, or standard
deviation, and other factors.
X and R and X and s charts can be plotted with any type of data.
18
Defining UCL and LCL in X and R Chart

X is the grand average and R is the average of the range.
UCLX = X + A2 R
LCLX = X - A2 R
UCLR = D4 R
LCLR = D3 R
A2, D3, and D4 are values from the control chart table.
19
Defining UCL and LCL in X and s Chart

Standard deviation of each subgroup data is represented as s. The data is divided into subgroups and
standard deviation is calculated for each subgroup.
UCL = X + A3 S
LCL = X - A3 S
UCL = B4 S
LCL = B3 S
Values for A3, B3, and B4 are constant and are taken from the control chart table. X and s charts are used
to track process variation where the subgroup sample size 9.
20
X and R and Subgroup DataExample
Establish 1 process limits for the data set shown. Use the table of control chart constants for values of A 2, D3,
and D4.
Table for
control chart
constants
A2
D3
D4
1.88
3.27
1.02
2.57
0.73
2.28
0.58
2.11
0.48
2.00
X Chart
In Minitab, STAT -> CONTROL CHARTS -> VARIABLE CHART FOR SUBGROUPS -> X-R
21
X and R and Subgroup DataConstructing Chart
In X and R chart, point SG 6 is the point of change in the process from below the center line to above the
center.
No points are outside control limits in the given process; however, examine points 6 and 7 on X chart, and
points 10 and 11 on the R chart for rule #4 (If 2 out of 3 points are within 1 mean of either the UCL or the
LCL).
22
X and s and Subgroup DataExample
The data in subgroups with 10 samples in each subgroup is given here along with the X chart. Using this data,
find out if the process is in control.
Table for
control chart
constants
A3
B3
B4
2.659
3.267
1.954
2.568
1.628
2.266
1.427
2.089
1.287
0.030
1.970
1.182
0.118
1.882
1.099
0.185
1.815
1.032
0.239
1.761
10
0.975
0.284
1.716
X Chart
In Minitab, STAT -> CONTROL CHARTS -> VARIABLE CHART FOR SUBGROUPS -> X-S
23
X and sConstructing Chart
The X chart point SG 10 is the variation of the point from the mean.
Also, points 4, 10, and 23 have more variation from the center. These points can be analyzed further.
The points are within the limits, and hence the process is in control.
24
ImR Chart Principles

ImR charts are two separate charts of the same data. Some of the principles of the ImR chart are as
follows:
The I-chart is a plot of the individual data points.
The MR-chart is a plot of the moving range of the previous individuals.
ImR charts are sensitive to trends, cycles, patterns, and normality.
ImR charts are used:

o
when subgroup variation is zero or no subgroups exist; and
with data points from destructive testing or batch processing, or summary data from a time
period.
Control limits of the ImR chart are calculated using the same method as the X and R chart.
25
ImR and Individual DataExample
The QC department at Nutri Worldwide Inc. measures the strength of its milk cartons once in
every hour. Is the process in control?
Since the data is individual data, the ImR chart will be used here.
This is an example of a destructive test.
In Minitab, STAT -> CONTROL CHARTS -> VARIABLE CHART FOR INDIVIDUALS -> I-MR
26
ImR and Individual DataConstructing Chart
Moving range is the absolute value of difference between the last two data points.
In I-chart, point 16 is close to the upper limit (analysis required).
No points are out of control in the process.
27
ImR ChartIT/ITES Example

Given is the data used to study the number of calls handled per hour in call center operations. This
data was studied using ImR charts to check if the process is in control. The data, ImR chart, and
analysis are as follows:

Data:
ImR Chart:
Analysis:
In I-chart, all points are closer to the
mean value. The process is well
within control.
In MR chart, there are a few points
closer to LCL. The process variation
can be investigated further.
However, no point is outside the
control limits.
28
Control Charts for Attribute Data

Based on sample size and data type (defects or defectives), the following types of control charts can
be selected:
If the sample size is consistent and the data type is defectives
np chart should be used
If the sample size is consistent and the data type available changes from
defectives to defects
c chart should be used
If the sample size is inconsistent and the data type is defectives
p chart should be used
If the sample size is inconsistent and the data type is defects
u chart should be used
Control limits may be constant, such as X and R charts (for np and c charts), or vary depending on sample size
(for p and u charts.)
29
np Chart Principles
The np chart is used to measure the non-conforming proportions or number of defectives within a
standardized group size. Some of the principles of np chart are as follows:
The expectation is that the same proportion exists in each group.
The np chart follows binomial distribution.
Large subgroups are required (50 minimum) for this chart.
Subgroup size must be constant, hence there is no need to calculate p and then np to plot data
points on a control chart.
Control limits will be constant.
30
np ChartFormulae
Important formulae of np chart are as follows:
Proportion of p = n
np = n n
Control Limits = np 3np (1 )
where, D = Defectives
31
np Charts and Uniform Subgroup SizeExample
The sourcing department at Nutri Worldwide Inc. measures 125 purchase orders daily
and records the number of entry errors in them. The tabulated data is given here. Is
the order entry process in control?
Since the data has a constant subgroup size (orders processed) of defectives, an np
chart will be used.
Assumption is that there is only one error per order possible.
32
np Charts and Uniform Subgroup SizeConstructing Chart
In np chart, point 12 is beyond the control limit of three standard deviations. Analysis must be done to find
the reason and take corrective action if necessary.
Hence, point 12 is out of control in the process.
33
p Chart Principles
The p chart is used to measure the non-conforming proportion or defectives. Principles of np
chart and p chart are quite similar. Some of the principles of the p chart are as follows:
The expectation is that the same proportion exists in each group.
The p chart follows binomial distribution.
The subgroup size should at least be 50, and it does not have to be constant.
Control limits may vary from subgroup to subgroup based on the subgroup size.
Control Limits = 3
Note: When n changes, control limit also changes.
34
p Charts and Varying Subgroup SizeExample
The sourcing department in Nutri Worldwide Inc. measures the number of entry
errors on a daily basis. The tabulated data is presented here. Is the order entry
process in control?
Since the data has varying subgroup sizes (orders processed) of defectives, a p
chart will be used.
35
p Charts and Varying Subgroup SizeConstructing Chart
In a p chart, point 12 has gone beyond the limit of 3 sigma level. Analysis must be done to find the
reason and take corrective action if necessary.
Hence, point 12 is out of control in this process.
36
c Chart Principles
To form a c chart, measure the number of occurrences of non-conforming defects. Some of the
principles of the c chart are as follows:
It follows a Poisson distribution.
It is used when the sample size is fixed or the area of opportunity is constant.
It is also used to identify attribute data for the sample.
Each count is a subgroup of samples and the control limits will be constant.
The subgroup size should at least be 20.

Control Limits = 3
37
c ChartExample
Final inspection grades the tinted glass on the number of white specs. The
product is priced by grade. White specs are defects, not defectives, and are
measured over a constant sample area; so c chart will be used. Is the process in
control?
Since the data is for defects, c chart will be used.
38
c ChartConstructing Chart
Points 2, 3, 4, 12, 13, 16, and 17 are out of control in this process; additionally, points 7, 9, 18, and 19 break
rule #4.
In this c chart, the process is not stable and many points go beyond 3 sigma control levels. Analysis must be
done to find the reason and take corrective action.
The process is not in control.
39
u Chart Principles
The u chart is also used to measure the number of non-conforming defects. Principles of c chart and
u chart are quite similar. Some of the principles of u chart are as follows:
It follows a Poisson distribution.
It is used to identify attribute data for the sample.
It is used to measure defects when the sample size is not fixed.
Control limits of the process may vary.
The subgroup size should at least be 20.
Control limits = 3( )
Where, a = area of opportunity
40
u ChartExample
The plastics operation counts defects after a run which is undetermined in length (once
started, it continues until all material is used). Is the process in control?
Since the count of defects has a varying area of opportunity and the length of runs is not
constant, u chart will be used.
41
u ChartConstructing Chart
In this u chart, point 18 has gone beyond the 3 sigma level. Analysis must be done to find the reason
and corrective action must be taken if necessary.
Point 18 is out of control in this process.
42
Control
Topic 2Control Plan
Control Plan and its Uses

Control plan is a written summary description of the system for controlling a process. A control plan:
describes actions required to maintain the desired state of the process and minimize process and
product variation;
evolves and changes with the process and product requirements;
is also considered a knowledge-transfer document;
can be created for a process, a step in the process, or even a piece of equipment used in the
process;
provides a single point of reference for understanding process characteristics, specifications, and
Standard Operation Procedures for the process; and
enables assignment of responsibility for each activity within the process.
44
Control Plan Strategy

Following are the strategies of a control plan:
Minimize process tampering
State the reaction plan to out-of-control conditions
Signal when Kaizen activities are needed
Describe training needs for standard operating procedures
Describe maintenance schedule requirements in case of equipment control plan
A good control plan should clearly describe what actions are to be taken, when to take them, and who
should take them, thereby reducing the fire fighting syndrome.
45
Elements of Control Plan

The elements of control plan are as follows:
Project purpose and objectives;
Risk management plan;
Resource requirements documents;
Process ownership identification;
Communication plan recommendation;
Process stewardship; and
Financial analysis and results.
46
Elements of Response Plan

The elements of response plan are as follows:
Unstable
conditions
Define what
unstable means for
each Vital x by
performing FMEA.
Responsibility
and ownership
Describe responsibility
and ownership to take
required actions
whenever any
unstable condition
occurs.
Action plan
List down the action
steps to mitigate the
unstable conditions.
In the control plan, provide a contact list of technical experts who can be consulted to resolve any issues that
may occur.
47
Corrective and Preventive Actions

Some of the actions that can be taken to fix and prevent the issues are:
Fix the problem until the root cause is
Corrective
actions
Containment
identified
Fix the problem after identifying the root
cause
Correction
Make the process mistake-proof by
Preventive
action
eliminating the recurring issues
Prevention
48
Cost-Benefit Analysis
Cost-benefit analysis is used to evaluate the total anticipated cost of a project compared to the total
expected benefits, to determine whether the proposed implementation is worthwhile for a company
or project team.
Cost-Benefit Analysis
Understand Costs
Monetary Cost
Start-up fees, training,

tools, processes, etc.
Non-Monetary Cost
Time, lost production,

potential risk, etc.
Identify Benefits
Monetary Benefit
Direct profits, increased
production capabilities,
etc.
Non-Monetary
Benefit
Decreased production
time, increased reliability
and durability, etc.
To perform cost-benefit analysis, all the identified costs are subtracted from the expected benefits, to
determine whether the positive benefits outweigh the negative costs.
49
What to Control
It is important to define what needs to be controlled to define a strong control plan.
Process = f (x1, x2, x3) = Y
Key Performance Input Variable (KPIV)
The x factors are called KPIV.

A control plan controls the KPIV.
A control plan controls the inputs.
Key Performance Output Variable (KPOV)
The output Y is called KPOV.

A control plan ensures the desired state for the
KPOV.
A control plan monitors the output.
Monitoring the output alone is not an effective way to control a process and will not result in
in an efficient process. Both the input and output variables need to be monitored and controlled closely.
50
Identifying KPIVs
The KPIVs or the inputs to the process can be identified using various sources, such as:
Failure Mode and Effects Analysis (FMEA)
Cause-and-Effect Matrix or Diagram and Cause Verification Matrix
Multi-Vari Studies
Regression Analysis
Design of Experiments (DOE)
51
Control Plan Tools

Developing and executing control plans require the use of the following tools:
Control Charts
Useful for
tracking
process
statistics over
time and
detecting the
presence of
special causes
Error Proofing
MSA
A technique
that identifies
measurement
error (variation)
and sources of
that error in
order to reduce
the variation
Also known as
Poka-Yoke
Refers to
implementation
of fail-safe
mechanisms
within a
process to
prevent it from
creating defects
SOP
Also known as
Standard
Operating
Procedures
Is a written
document or
instruction that
details all the
steps and
activities of a
process or
procedure
PM
Also known as
Preventive
Maintenance
Inclusion of
Preventive
Maintenance as
part of the
documented
scheduled
process or
equipment
maintenance
52
Developing a Control Plan

After understanding the process, a multi-functional team must be formed that will be responsible for
controlling the process. Multiple tools can be used such as:
FMEA
Special characteristics (critical and significant)
Control plans or lessons learned from similar parts or processes
Technical documentation
Validation plan results
Optimization methods
Team knowledge of the process
53
Developing a Control Plan (contd.)

The questions that need to be asked to define the control plan are as follows:
What do you want to control?

How often do you need to measure the process?
Do you have an effective measurement system?
What is the cost of sampling?
How much shift can you tolerate?
Who needs to see the data?
What type of tool or chart is necessary?
Who will generate the data?
Who will control the process?
What are the system requirements for auditing and maintenance?
54
Choosing the Right Level of Control

It is important to identify the level of control that should be built into the process.
55
Transactional Control PlanExample

A sample transactional control plan is shown.
TRANSACTIONAL CONTROL PLAN

Prepared By :
Approved By :
Process Owner :
Business Unit :
Location
:
Department :
Page
:
Document No. :
Revision Date :
Supersedes
:
Nutri Worldwide Inc.

Prototype/Purchase
1 of 1
4
06-18-2014
Process
Step
Characteristic/
Parameter
CTQ/CL
Specification/
Requirement
Measurement
Method
Sample
Size
Frequency
Who
Measures
Where
Recorded
Decision
Rules/
Corrective
Action
Purchase
Order
Time of entry
CTD
Customer order
entry to PO less
than 3 days
Access
database
server Time
stamp
All
entered
Weekly
Admin.
Access
database
1. Review
reason for
length (Ex:
Weekend
error) and
determine
need to
solve
problem
Reference
Number
56
Process Step
The Process Step column highlights the name of the process and distinguishes a process from a
process step or a piece of equipment.
Process
Step
Characteristic/
Parameter
CTQ/
CL
Specification/
Requirement
Measurement
Method
Sample
Size
Frequency
Who
Measures
Where
Recorded
Decision
Rules/
Corrective
Action
Purchase
Order
Time of entry
CTD
Customer
Order entry to PO less
than 3 days
Access
database
server Time
Stamp
All
entered
Weekly
Admin.
Access
database
1. Review
reason for
length (Ex:
Weekend
error) and
determine
need to
solve
problem
Reference
Number
57
Characteristic or Parameter and CTQ

The Characteristic or Parameter column identifies the KPIV or KPOV to be measured to ensure the
process is in control. These parameters are often a part of the CTQ parameters of the process, as
identified in the Define phase.

Process
Step
Characteristic/
Parameter
CTQ/
CL
Specification/
Requirement
Measurement
Method
Sample
Size
Frequency
Who
Measures
Where
Recorded
Decision
Rules/
Corrective
Action
Purchase
Order
Time of entry
CTD
Customer
than 3 days
Access
database
server Time
Stamp
All
entered
Weekly
Admin.
Access
database
1. Review
reason for
length (Ex:
Weekend
error) and
determine
need to
solve
problem
Reference
Number
58
Specification or Requirement
The Specification or Requirement column defines the process, including the target goal of the process.
The goal for the process should be determined through team discussions, understanding the
technology and the history of the process.

Process
Step
Characteristic/
Parameter
CTQ/
CL
Specification/
Requirement
Measurement
Method
Sample
Size
Frequency
Who
Measures
Where
Recorded
Decision
Rules/
Corrective
Action
Purchase
Order
Time of entry
CTD
Customer
than 3 days
Access
database
server Time
Stamp
All
entered
Weekly
Admin.
Access
database
1. Review
reason for
length (Ex:
Weekend
error) and
determine
need to
solve
problem
Reference
Number
59
Measurement Method
The Measurement Method column defines the tool or gauge that will be used for measurement of
the metric. Consider the following factorsavailability of the equipment for the process, calibration
and MSA needs of the equipment, training needs on the tool or method, supporting Manufacturing
Performance Index (MPI), and operational blueprint requirements.
Process
Step
Characteristic/
Parameter
CTQ/
CL
Specification/
Requirement
Measurement
Method
Sample
Size
Frequency
Who
Measures
Where
Recorded
Decision
Rules/
Corrective
Action
Purchase
Order
Time of entry
CTD
Customer
than 3 days
Access
database
server Time
Stamp
All
entered
Weekly
Admin.
Access
database
1. Review
reason for
length (Ex:
Weekend
error) and
determine
need to
solve
problem
Reference
Number
60
Sample Size, Frequency, and Who Measures

Sample size refers to the number of data entries that will be used to calculate the metric. The
Frequency column defines the frequency at which the metric will be captured and analyzed. The next
column defines who will measure the metric based on the frequency defined earlier.
Process
Step
Characteristic/
Parameter
CTQ/
CL
Specification/
Requirement
Measurement
Method
Sample
Size
Frequency
Who
Measures
Where
Recorded
Decision
Rules/
Corrective
Action
Purchase
Order
Time of entry
CTD
Customer
than 3 days
Access
database
server Time
Stamp
All
entered
Weekly
Admin.
Access
database
1. Review
reason for
length (Ex:
Weekend
error) and
determine
need to
solve
problem
Reference
Number
61
Where Recorded
The Where Recorded section is used to indicate where the metric will be recorded. This can be done
through control sheets like charts, plots, logs, or check sheets.
Process
Step
Characteristic/
Parameter
CTQ/
CL
Specification/
Requirement
Measurement
Method
Sample
Size
Frequency
Who
Measures
Where
Recorded
Decision
Rules/
Corrective
Action
Purchase
Order
Time of entry
CTD
Customer
than 3 days
Access
database
server Time
Stamp
All
entered
Weekly
Admin.
Access
database
1. Review
reason for
length (Ex:
Weekend
error) and
determine
need to
solve
problem
Reference
Number
62
Decision Rules or Corrective Action

The Decision Rules or Corrective Action section identifies the actions to be taken for the out-ofcontrol specification situation(s).
Process
Step
Characteristic/
Parameter
CTQ/
CL
Specification/
Requirement
Measurement
Method
Sample
Size
Frequency
Who
Measures
Where
Recorded
Decision
Rules/
Corrective
Action
Purchase
Order
Time of entry
CTD
Customer
than 3 days
Access
database
server Time
Stamp
All
entered
Weekly
Admin.
Access
database
1. Review
reason for
length (Ex:
Weekend
error) and
determine
need to
solve
problem
Reference
Number
63
Reference Number
The Reference Number section is used to facilitate access to documented or corrected procedures
against each corrective measure identified in the previous section.
Process
Step
Characteristic/
Parameter
CTQ/
CL
Specification/
Requirement
Measurement
Method
Sample
Size
Frequency
Who
Measures
Where
Recorded
Decision
Rules/
Corrective
Action
Purchase
Order
Time of entry
CTD
Customer
than 3 days
Access
database
server Time
Stamp
All
entered
Weekly
Admin.
Access
database
1. Review
reason for
length (Ex:
Weekend
error) and
determine
need to
solve
problem
Reference
Number
64
Manufacturing Control PlanSample

A sample manufacturing control plan is shown.
Part Name/Family:
Part No.:
Plant/Area:
Prepared by:
Approved by:
Page:
Document No.:
Revision Date:
Process
Step
Characteristic/
Parameter
CTS
Specification/
Requirement
Measurement
Method
Sample
Size
Frequency
Who
Measures
Where
Recorded
Decision Rules/
Corrective
Action
Injection
Molding
(Machine
#16)
Y : Part Dimension
CTQ
3.250 + 0.005 in Cpk=2
Gage # 042
Each hour
Operator
X and R
Chart
If out-of-control condition
appears, 100% inspect all
parts since last check. If X
out-of control, adjust
injection pressure. If R out-of
control, adjust coolant
flows.
X : Cavity Pressure
CTQ
1200 + 15 psi
Cpk = 2
Pressure transducer
in cavity
(automatic,
continuous reading)
X and R Chart
If out-of-control condition
appears, check: Injection
pressure settings;
Temperature controller.
X : Coolant Flow
CTQ
5 gal / minute
Flow meter on
machine
Each hour
Check Sheet
by Machine
If flow is in yellow, adjust to

green. If flow is in red, 100%
inspect all parts since last
check, and adjust flow to
green.
Operator
65
IT/ITES Control PlanSample

A sample control plan for Code Review Process in IT/ITES is shown.
Process Step
What's
Controlled?
Input or Output? Spec. Limits/

Requirement
Plan review for

critical code
Critical code
Input
details in project
plan
Measurement
Method
Control Method Sample Size
Freq.
Who/What
Measures?
Where
Recorded?
100% Critical
Code
Project Plan
Weekly project
mgmt reviews
100%
Weekly
Project
Manager/
Automated
workflow for
project
management
Project database Escalation to the

Account
Manager and
update project
plan
Weekly project
mgmt reviews
100%
Weekly
Project Lead/
Automated
workflow for
project
management
Project database First level

escalation to
project manager
and second level
escalation to
account manager
As per project
plan
Project Lead /
Code control
database
Project
First level
database/ source escalation to
code database
project manager
and second level
escalation to
account manager
Conduct review Critical code

for Critical Code
Input
100% Critical
Code
Project Plan
Conduct review Critical code

for Critical Code
Output
100% Critical
Code
Project Plan and Project mgr signs 100%

Code review
off code review
reports
reports
Decision Rule/
Corrective Action
66
CuSum Chart
The Cumulative Sum Control or CuSum chart incorporates all the information by plotting the
cumulative sums of the deviations of the sample values from the target value.
When,
0 = the target for the process mean
x j = the average of the jth sample
The cumulative sum control chart is formed by plotting the quantity as:
i
Ci ( x j 0 )
j 1
The CuSum chart is used for detecting small shifts, monitoring process mean, defects, and variance.
67
CuSum ChartSample
A sample CuSum chart is shown here.
The data goes out of

the limit for the 30th
sub group number.
68
EWMA Chart
Exponentially Weighted Moving Average charts are used for:
Plotting the data to detect small shifts over a small period of time, and
Monitoring process mean or variance.
Exponentially in EWMA refers to more weight on the more recent observations and less weight on
the old observations.
This chart is frequently used in Stock Modeling Software Packages by the analysts who predict the
next day performance based on the previous weeks or months performance.
69
EWMA ChartDesign Parameters

The design parameters of the EWMA chart are L and .
In general, 0.05 < < 0.25
L = 3 when, has larger value
2.6 < L < 2.8 when, 0.1
EWMA is superior to the CuSum for larger shifts, particularly if > 0.1
Control Limits is computed as:
UCL = z + Lz
CL = z
LCL = z Lz
70
EWMA ChartSample
The sample EWMA control chart is shown here.
71
EWMA ChartHighlights
The EWMA chart:
Stores relatively smaller data;
Remembers only the current estimate of the variance rate and the most recent observation on
the market variable; and
Tracks well the volatility changes.
72
Control
Topic 3Lean Tools for Process Control
Visual Controls
Visual controls are used in visual factory to manage the factory by vision. Following are the types of
visual controls:
Control Board
Helps people to read the complete process at a
glance and analyze how the process is working.
Control Chart
Provides information on process performance, helps
to understand if the process is in control and
sustains the improvements made.
SOP
Set of rules and regulations that has to be
mandatorily followed in a particular process.
Control Plan
Plans that are displayed to know the performance
of the process on a timely basis.
74
Control Methods for 5S

The 5S in the Lean Six sigma control methods are:
Seiri (Sort))
Seiton (Stabilize))
Seiketsu (Standardize)
Seiso (Shine))
Shitsuke (Sustain)
75
Control Methods for 5SSeiri

Seiri helps in:
sorting necessary and unnecessary items;
keeping workplace clean;
preventing accumulation of items by assigning them tags;
simplifying tasks;
effectively using the workplace; and
careful purchase of items.
Seiri
(Sort)
76
Control Methods for 5SSeiton

Seiton helps in:
improving efficiency;
preventing loss and wastage of time;
making workflow smooth and efficient;
organizing storage for all items; and
identifying frequently and non-frequently used items.
Seiton
(Stabilize)
77
Control Methods for 5SSeiso

Seiso helps in:
keeping workplace shiny clean;
identifying malfunction in equipment;
mess prevention; and
finding the root cause of contamination.
Seiso
(Shine)
78
Control Methods for 5SSeiketsu

Seiketsu helps in:
standardizing best practices across work place;
performing tasks in a standard manner; and
ensuring personal and environmental cleanliness.

Seiketsu
(Standardize)
Tools used:
Job cycle charts, visual cues, scheduling of five minute 5S
periods, and checklists.
79
Control Methods for 5SSeiketsu (contd.)

Steps for implementing Seiketsu are:
Assigning 3S (sort, set in order and shine) job responsibilities

2
Integrating 3S duties into regular work duties

3
Checking the maintenance of 3S
80
Control Methods for 5SShitsuke

Shitsuke helps in:
maintaining discipline and commitment;
maintaining orderliness; and
defining a new status quo and standard of work place

organization.
Shitsuke
(Sustain)
Tools used for sustaining 5S are:
Signs and posters, newsletters, check sheets, pocket

manuals, team and management check-ins, performance
reviews, and department tours.
81
Quiz
Knowledge Check
QUIZ
1
For which of the following is the control chart mainly used?
a.
Determine if defective parts are being produced
b. Measure the process capability

c.
Determine causes of process variation
d.
Detect non-random variation in processes
83
QUIZ
1
For which of the following is the control chart mainly used?
a.
Determine if defective parts are being produced
b. Measure the process capability

c.
Determine causes of process variation
d.
Detect non-random variation in processes
Answer: d.
Explanation: A control chart is used to distinguish between random variation and variation
due to out-of-control condition.
Copyright 2012-2014,Simplilearn,All rights reserved
84
QUIZ
2
Which of the following are calculated in X and s charts?
a.
Average and Standard Deviation
b. Average and Range

c.
Mean and Variance
d.
Variance and Standard Deviation
85
QUIZ
2
Which of the following are calculated in X and s charts?
a.
Average and Standard Deviation
b. Average and Range

c.
Mean and Variance
d.
Variance and Standard Deviation
Answer: a.
Explanation: X is average and s is standard deviation. Hence, average and standard
deviation are calculated in X and s charts. It is used whenever the sample size of a subgroup
is more than 9.
86
QUIZ
3
Which of the following charts is used for continuous data?
a.
np
b. p
c.
d.
X and R
87
QUIZ
3
Which of the following charts is used for continuous data?
a.
np
b. p
c.
d.
X and R
Answer: d.
Explanation: I-MR, X and R, and X and s charts are used for continuous data.
88
QUIZ
4
What is a controlling process summary known as?
a.
Control chart
b. Control plan
c.
Control process
d.
Control program
89
QUIZ
4
What is a controlling process summary known as?
a.
Control chart
b. Control plan
c.
Control process
d.
Control program
Answer: b.
Explanation: A control plan is a written summary description of the system for controlling a
process.
90
QUIZ
5
Which of the following sections of a control plan identifies the KPIV or KPOV to be
measured to ensure a process is in control?
a.
Characteristic or Parameter
b. Process Step
c.
d.
Measurement Method
91
QUIZ
5
Which of the following sections of a control plan identifies the KPIV or KPOV to be
measured to ensure a process is in control?
a.
Characteristic or Parameter
b. Process Step
c.
d.
Measurement Method
Answer: a.
Explanation: The Characteristic or Parameter section of a control plan identifies the KPIV or
KPOV to be measured to ensure the process is in control.
92
QUIZ
6
Which of the following sections of a control plan defines the tool or gauge that will be
used for measurement of the metric?
a.
Process Step
b. Characteristic or Parameter
c.
Measurement Method
d.
93
QUIZ
6
Which of the following sections of a control plan defines the tool or gauge that will be
used for measurement of the metric?
a.
Process Step
b. Characteristic or Parameter
c.
Measurement Method
d.
Answer: c.
Explanation: The Measurement Method section of a control plan defines the tool or gauge
that will be used for measurement of the metric.
94
QUIZ
7
Which of the following helps people to read the complete process at a glance and
analyze how the process is working?
a.
SOP
b. Control board
c.
Control chart
d.
Control plan
95
QUIZ
7
Which of the following helps people to read the complete process at a glance and
analyze how the process is working?
a.
SOP
b. Control board
c.
Control chart
d.
Control plan
Answer: b.
Explanation: Control board helps people to read the complete process at a glance and
analyze how the process is working.
96
QUIZ
8
Which of the following helps in mess prevention?
a.
Seiton
b. Seiri
c.
Seiso
d.
Seiketsu
97
QUIZ
8
Which of the following helps in mess prevention?
a.
Seiton
b. Seiri
c.
Seiso
d.
Seiketsu
Answer: c.
Explanation: Seiso is the stage of the 5S in Lean Six Sigma that helps in mess prevention.
98
QUIZ
9
Which of the following stands for standardize?
a.
Seiton
b. Seiri
c.
Seiso
d.
Seiketsu
99
QUIZ
9
Which of the following stands for standardize?
a.
Seiton
b. Seiri
c.
Seiso
d.
Seiketsu
Answer: d.
Explanation: Seiketsu stands for standardize.
100
Summary
Here is a quick
recap of what we
have learned in this
lesson:
Statistical process control aids in visual monitoring of the process and controlling its
parameters by placing statistical measures around the process outputs or input variables.
Control charts are useful for tracking process statistics over time and detecting the
presence of special causes.
A good control plan should clearly describe what actions are to be taken, when to take
them, and who should take them, thereby reduce the fire fighting syndrome.
After understanding the process, a multi-functional team must be formed who will be
responsible for controlling the process. Multiple tools and techniques can be used.
Visual factory is a term used to describe a Lean production environment where charts
and signs are used to display information.
The 5S in Lean Six sigma stands for Seiri/Sort, Seiton/Simplify, Seiso/Sweep,

Seiketsu/Standardize, and Shitsuke/Sustain.
101
THANK YOU


LSSGB Lesson6 Control

Загружено:

Сведения о документе

Авторское право

Доступные форматы

Поделиться этим документом

Поделиться или встроить документ

Параметры публикации

Этот документ был вам полезен?

Это неприемлемый материал?

Авторское право:

Доступные форматы

LSSGB Lesson6 Control

Загружено:

Авторское право:

Доступные форматы

Lean Six Sigma Green Belt

Copyright 2014, Simplilearn, All rights reserved.

Describe Statistical Process Control (SPC)

Explain control charts

Discuss control plan strategies

Develop a control plan

Discuss visual factory

Describe control methods for 5S

Copyright 2014, Simplilearn, All rights reserved.

Copyright 2014, Simplilearn, All rights reserved.

Introduction to Statistical Process Control

process outputs or input variables.

Separates the special and common causes of variability

Recognizes the unexpected changes in the process output quickly

Helps in monitoring a process online

Copyright 2014, Simplilearn, All rights reserved.

Common Cause Variation

Part of the process and the

Causes for this variation are

Frequency of its occurrence is high,

Identifying and removing these

This variation will be within the

Special Cause Variation

Not part of the process, affects the

Causes are non-repetitive.

Frequency of occurrence is less and

Identifying and removing these

Variation affects the flow of the

Common Cause Variation vs. Special Cause Variation

Special Cause Variation

Frequency of occurrence is high

Frequency of occurrence is less

Part of the process

Is not part of the process

High investment for removal

Relatively less investment for removal

Elimination is comparatively easy

Copyright 2014, Simplilearn, All rights reserved.

differences due to assignable causes within a subgroup will be minimized.

Copyright 2014, Simplilearn, All rights reserved.

Approach II to construct rational subgroups

Data Collection for SPC

Document purpose of data

List the project goals

Identify measurable items

Check for availability of

Document the name of the

Confirm who will review

Find the duration for data

Copyright 2014, Simplilearn, All rights reserved.

Finalize method of collecting,

Data Collection for SPCTechniques

Collects and uses the

Collects data from a

complete data from the

and estimates the

understand the cause-

treatment is not given

variables, inputs and

Control Chart Anatomy

Characteristics of control charts are as follows:

Control charts can be used with discrete or continuous data.

Specification limits (USL and LSL) do not appear on them.

Copyright 2014, Simplilearn, All rights reserved.