Control Charts

advertisement
Lean Six Sigma DMAIC Workshop
Green Belt Part 6
4/8/2015
Green Belt Training
1
Control
Control
4/8/2015
Green Belt Training
2
Control Process Flow
Develop
Control
strategy
Develop
control
plan
Update
SOP’s and
training
plans
4/8/2015
Green Belt Training
3
Key Concepts
 Prevention vs detection
 Visual Factory
 Control Plan
 Reaction Plan
4/8/2015
Green Belt Training
4
Control Phase
 Control is a means of sustaining
improvements by eliminating the
opportunity for defects to occur, or
monitoring the process using a feedback
system
 Sustaining the gains is key!
 We move from detection of defects to
prevention of defects
4/8/2015
Green Belt Training
5
Error Proofing
The avoidance of an error before it occurs
 Error-proofed processes are designed to
require extensive operator training while
allowing the operation to be performed
the correct way EVERY time.
 Automation
 Fixtures
 Jigs
4/8/2015
Green Belt Training
6
Visual Factory
 Visual Displays
 Communicate important information,
but do not what people or machines do
 Visual Controls
 Communicate information and/or build
controls into the process so that
activities are performed according to
standards
4/8/2015
Green Belt Training
7
Control Charts
Control Charts
4/8/2015
Green Belt Training
8
Variation
 Variation means that a process does not produce
exactly the same result every time the product
or service is delivered
 Variation exists in all processes
 Measuring and understanding variation in our
business processes helps identify specifically
what the current level of performance is and
what needs to change in order to reduce the
variability and therefore reduce the defects
delivered to customers
4/8/2015
Green Belt Training
9
What Causes Variation?
Suppliers
Process
Inputs
Business
Processes
Critical
Customer
Requirement
Process
Outputs
Defects
Root cause analysis of
variation leads to
permanent defect
reduction
4/8/2015
Variation in the
output of
processes causes
defects
Green Belt Training
10
Control Charts - Basics
Control Charts
 Have the ability to indicate the presence
of special causes that upset our
processes
 Help us to detect, diagnose, and correct
production problems in a timely fashion
 Provide an easy to understand visual
indicator of process performance
4/8/2015
Green Belt Training
11
Control Charts - Basics
Steps to building an appropriate control chart
1. Determine the type of data
2. Collect data consistently
3. Select the appropriate control chart
4. Build the control chart
5. Analyze process performance
6. Take corrective action
4/8/2015
Green Belt Training
12
Common Cause Variation
 There are always inherent chance causes
responsible for natural variation in all
processes due to “normal” variation in
materials, environments, methods, etc.
(common cause)
 Variation within a stable pattern is
inevitable
4/8/2015
Green Belt Training
13
Special Cause Variation
 Once we have an indication of a shift outside a
stable pattern of variation, we must discover
the reason for the shift (special cause)
 We want to remove the influence of a special
cause if it is adversely affecting productprocess quality
 If the special cause influence is improving
product-process quality (e.g., 6 Sigma
projects), we want to permanently capture its
effect
4/8/2015
Green Belt Training
14
Eliminate Special Causes
Out of Control Variation
Commuting Time (mins)
Commuting Time (mins)
In Control Variation
Days
4/8/2015
Time
Green Belt Training
15
Issues on Control
Charts
 It is critical to understand that:
 Control charts do not tell us whether or not we
are meeting tolerance specifications
consistently
 They neither explicitly identify nor remove
special causes
 Control charts are statistical based devices for
addressing process stability
 We need to develop meaningful process logs to
account for and document physical
characteristics, action items, and results obtained
4/8/2015
Green Belt Training
16
Commuting Time (mins)
Charting Variation –
Control Charts
Days
4/8/2015
Green Belt Training
17
Benefits of a WellDefined Control Plan
 Improves overall quality by reducing chances
of deviation
 Reduces defects by keeping processes centered
 Aid in timely troubleshooting of the process
 Serve as a communication tool for changes in
CCR‘s
 Sustain improvements
4/8/2015
Green Belt Training
18
Control Plan Contents
 Characteristic/Parameter
 CCR
 Specification/Requirement
 Measurement Method
 Sample Size
 Frequency
 Who measures
 Where recorded
 Decision Rule/Corrective Action
4/8/2015
Green Belt Training
19
Reaction Plan
 Actions to be taken when an out of
control condition occurs
 When do we react?
 Who needs to be involved?
 What other information do we need to
have?
4/8/2015
Green Belt Training
20
Procedures and
Standards
 Procedures and standards are the details
behind the activities documented on the
business process map
 They serve as a vehicle for every employee from senior executives to hourly workers -to
gain an understanding of the improvement
 Procedures are both a training aid and a
means to ensure successful
implementation
4/8/2015
Green Belt Training
21
Procedures and Standards
 Contents
 They should be at such a level that the job can be
performed well by employees who are not fully trained
 They should be specific. Tell precisely what actions to
take and when and where to take them. Make it clear
where people‘s responsibilities lie
 They should describe how to prevent product and
service variation
 They must be able to be followed. No contradictory or
unrealistic instructions.
 Priorities must be considered. Focus on the root causes
 Formats
– Procedures
– Flowcharts
4/8/2015
– Checklists
– Metrics
Green Belt Training
22
Communication
Planning
 Research has shown that one of the most significant
variables in successful implementation is the quality of
communications supporting a change. Teams must be very
careful to develop the right communications for the right
people and deliver them at the right time
 Channels: There are numerous communication channels
such as:
 One-on-one meetings
 Electronic mail
 Posters
 Bulletin boards
 Small discussion groups or workshops
 Videos
 Teleconferencing or video teleconferencing
 Memorandums or personalized letters
 Voice mail
4/8/2015
Green Belt Training
23
Presentation Checklist
Do your research and preparation:
 Understand audience
 Include stakeholders
 Anticipate questions
Presentation Opening:
 Set the expectations
 Share the burning platform
 Establish a sense of urgency
4/8/2015
Green Belt Training
24
Presentation Checklist
Deliver Body:
 Present “As Is” and “To Be”
 Use facts and data
 Show how stages of DMAIC tools were used
Sell Your Solution:
 Be Specific
 Provide Examples to prove point
4/8/2015
 Link Benefit/results
to actions
Green Belt Training
25
Presentation Checklist
Closing:
 Make recommendations
 Include How-By
 Present resource requirements
 Ask for approval
Follow-up:
 Post presentation debrief
 Publish meeting minutes
 Thank participants
4/8/2015
Green Belt Training
26
Appendix
Appendix
4/8/2015
Green Belt Training
27
Statistical Tools Summary
Tool
What
Type of Data
When to Use
Histogram
Visual display of one
variable
showing data center,
spread,
shape and outliers
Continuous or
discrete
1. Summarize large amounts of data
2. To get a “feel for the data‟
3. To compare actual description to
customer specs
Multivari
Charts
Bar chart comparison
of subgroups
on one variable.
Continuous or
discrete
To visually compare sub-groups by
individual data points and the mean.
In MINITAB 12 only. To identify
major source of variation.
Box Plots
Visual display of the
summary of Y data
grouped
by category of X
Y=continuous
X=discrete or
categorical
Summary display to visualize
differences in data center, spread and
shape across categories.
Run
Charts
Plots observation in
time
sequence
Y=continuous
or
discrete
To view process performance over
time for trends, shifts or cycles.
Control
Charts
Plots observations in
time
sequence against a
mean and
control limits
Y=continuous
or
discrete
To monitor the process in order to
control and improve process
performance over time for trends,
shifts or cycles. To identify special
causes.
Scatter
Diagram
(Plot)
Plots a response Y
versus a
predictor X
Y=continuous
X=continuous
4/8/2015
To understand the possible
relationships between two variables.
To identify possible root causes
are related to Y. Do not use
Greenwhich
Belt Training
with special causes.
How to Apply
this Tool in my
Work
28
Statistical Tools Summary
Tool
What
Type of Data
When to Use
Behaviorally
Anchored
Scales
A response scale
on which specific
points are named
or described to
clarify the
differences
between points.
Discrete / Categorical:
Nominal(name)
Ordinal(order)
Continuous: Interval
To translate subjective or
qualitative issues into data
(discrete or continuous). To
reduce variation in the response
measured.
t-Test
Determine if there
is a difference
between two
groups.
Y=continuous
X=discrete or
categorical
1. Test if sample average =
specified value
2. Test if 2 sample means are
equal
3. Paired t: to reduce variation
when comparing two sample
averages Analysis
Analysis of
Variance
Determine if there
is a difference
among many
groups.
Y=continuous
X=discrete or
categorical
(2 or more Xs)
Determine of there is a
statistically significant difference
among the groups.
Discrete
Data: Chi
Square
Determine
Determine if there
is a difference for
observed
frequencies of 2
discrete variables.
Y=discrete or
categorical
X=discrete or
categorical
Determine if there are
relationships between two
discrete variables.
4/8/2015
Green Belt Training
How to Apply
this Tool in my
Work
29
Statistical Tools Summary
Tool
What
Type of Data
Regression
(Linear
&Multiple)
Summarizes, describes,
predicts and quantifies
relationships.
Y=continuous
X=continuous
or discrete
When to Use
1.
2.
3.
4.
Logistic
Regression
Summarizes, describes,
predicts and quantifies
relationships.
Y=discrete
X=continuous
or discrete
1.
2.
3.
4.
Design of
Experiment
s(DOE)
4/8/2015
Systematic and efficient
proactive approach to
testing relationships.
Y=continuous
or discrete
X=continuous
or discrete
How to Apply
this Tool in my
Work
Determine if there is evidence of
a relationship between Xs and
Ys.
Model data to develop a
mathematical equation to
quantify the relationship.
Identify root causes.
Make predictions using the
model.
Determine if there is evidence of
a relationship between Xs and
Ys.
Model data to develop a
mathematical equation to
quantify the relationship.
Identify root causes.
Make predictions using the
model.
To establish cause and effect
relationship between Ys and Xs. To
identify “vital few” Xs.
Green Belt Training
30
Control
Websites:
•www.isixsigma.com
•www.asq.org/sixsigma/
•www.minitab.com/
4/8/2015
Green Belt Training
31
Download