Improve
Process
Capability
The
Quality
Improvement
Model
Define
Process
Select
Measures
Collect &
Interpret
Data
Improve Process Capability
Purpose: Determine/identify
fundamental
changes to the
process to improve
capability.
Is
Process
Stable
?
No
Investigate &
Fix Special
Causes
Yes
Improve
Process
Capability
No
Is
Process
Capable
?
Yes
Use SPC to
Maintain
Current
Process
9-1
Improve
Process
Capability
Improving Stable Processes




Common causes of variation usually cannot be
reduced by trying to explain the difference between
high and low points when a process is stable.
All of the data, not just the high and low points, are
relevant to further analysis.
Aspects of the system that are always present will
need to be changed to improve common cause
variation.
Stable systems usually require managerial attention
for improvement. Fundamental changes in the system
are often required.
Source: Brian Joiner
9-2
Improve
Process
Capability
Order Entry Process
Week # Errors
1
15
2
22
3
18
4
10
5
13
6
9
7
27
8
12
9
24
10
22
11
8
12
8
13
26
14
16
15
20
16
10
17
16
18
9
19
15
20
20
Total
320
Control Chart
35
30
Number
of Errors
UCL=28.0
25
20
Avg=16.0
15
10
5
0
LCL=4.0
5
10
15
20
Week
It has been decided that this process
requires further improvement
How do we go about it?
9-3
Improve
Process
Capability
Order Entry Errors by Type
Description
Number of Errors
Incorrect Account Number
Error in Order Amount
Inadequate Billing Information
Priority Code Not Checked
Incomplete Shipping Instructions
Other Errors
TOTAL
72
168
17
25
14
24
320
Pareto Chart
180
160
140
120
100
80
60
40
20
0
Error in
Order
Amount
Incorrect
Account
Number
Priority
Inadequate Incomplete Other Errors
Code Not
Billing
Shipping
Checked Information Instructions
Type Error
9-4
Improve
Process
Capability
Order Entry Process
Results of efforts to reduce errors in order amount.
Week # Errors
21
16
22
10
23
13
24
6
25
8
26
10
27
6
28
5
29
4
30
6
31
1
32
5
33
0
34
1
35
2
Total
93
Control Chart
35
Process Improvements Begin
30
Number
of Errors
UCL=28.0
25
20
Avg=16.0
15
10
5
LCL=4.0
0
5
10
15
20
25
30
35
Week
Limits based on first 20 weeks of data
9-5
Improve
Process
Capability
Order Entry Errors by Type
Description
Number of Errors
Incorrect Account Number
Error in Order Amount
Inadequate Billing Information
Priority Code Not Checked
Incomplete Shipping Instructions
Other Errors
TOTAL
42
8
7
17
9
10
93
Pareto Chart
45
40
35
30
25
20
15
10
5
0
Incorrect
Account
Number
Priority
Code Not
Checked
Incomplete
Shipping
Instructions
Error in
Order
Amount
Type Error
Inadequate Other Errors
Billing
Information
9-6
Improve
Process
Capability
Improving Stable Processes - Instrument
Measures Common Problems with Stable
Processes
Off Target
Lower Spec
Excess Variation
Upper Spec
Lower Spec
Upper Spec
Or, Both
9-7
Improving Stable Processes - Instrument
Measures Common Improvement Techniques

Improve
Process
Capability
Targeting Processes - Designed Experiments
Change process variables in a planned manner to determine
the effects of the variables on level and variability.
 Design of Experiments Course


Reducing Variation - Use Process Knowledge




Break out process steps (Process Map and C&E information)
Isolate sources of variability (Exploratory Data Analysis or
Designed Experiment)
Separate out common causes (stratification – Applied Statistical
Methods Course)
Exploratory Data Analysis (Applied Statistical Methods Course)
 Multi-Vary Studies in Six Sigma
 Analysis on existing process data
 Done on key variables identified in C&E or FMEA
9-8
Improve
Process
Capability
Breaking Out Process Steps
Extrude Parison
Extrude Parison
Blow Bottle
Melt Resin
Melt Resin
Melt Resin
Blow Bottle
Tail Detab
5
8
1
2
3
4
5
7
9
9
3
3
9
0
3
3
3
9
9
3
9
9
0
9
9
0
9
3
9
9
9
9
324
324
231
228
9
0
9
3
0
0
198
9
0
9
3
0
0
198
3
3
9
3
3
3
9
3
0
9
9
9
3
3
9
9
9
9
3
3
0
1
1
1
3
3
0
3
3
1
9
9
0
3
3
1
180
174
171
168
168
142
9
0
3
0
0
0
117
9
0
3
0
0
0
117
Wall
Variation
Weight
Blow Bottle
9
Clarity
Blow Bottle
9
Bottle Output
Melt Resin
Blow Bottle
Extrude Parison
Extrude Parison
1
Melt Temp
Process Step
10
Break %
Rating of
Importance to
Customer
Total
Process Input
Resin
Mold Design
Programing
Die Tip Temp
Mold Water
Temp
Water
Volume/Cooli
ng Rate
Head Design
Tooling
Pinch Design
Barrell Temp
Screw Speed
Screw Design
# of Mold
Cooling
Zones
Time from
extraction to
Detab
Use C&E matrix as a place to start data collection and analysis.
9-9
Isolating Sources of Variability
Improve
Process
Capability
“Polymer Manufacturing Process”
Conduct a study to evaluate measurement variability of b*.
Two b* measurements are done on each sample.
b*
3.0
2.5
Duplicate
Measurements
on Same Sample
2.0
1.5
1.0
0.5
First Measurement
0
Second Measurement
1
2
3
4
5
6
Sample
7
8
9
Possible Actions: Concentrate on improving the measurement
process (Previous Module)
9-10
Improve
Process
Capability
Separating Out Common Causes
“Shipping Process”
Run Chart
P
r
o
p
o
r
t
i
o
n
0.20
L
a
t
e
0.15
0.10
0.05
0.00
2
4
6
8
10
12
14
16
18
20
22
24
26
28
30
Week
International orders <10% of total orders
International orders 10-20% of total orders
International orders >20% of total orders
Possible Actions:
Improve process for shipping of
international orders.
9-11
Hypothesis: Are the Labs that Measure
Color the Same?
Improve
Process
Capability
9-12
Improve
Process
Capability
Minitab: Comparing Two or More
Samples
•Open Mintab Software
•Open Color Round Robin Data in the Mintab Datasets Folder and follow the
directions in the notes below.
Interval Plot of b* vs Lab
95% CI for the Mean
-1.0
-1.2
b*
-1.4
-1.6
-1.8
-2.0
-2.2
HART
Kuantan
Lab
TED
Note: The ASM course spends more time discussing Planning, Data Collection, Analysis and
Interpretation from experiments similar to the one above.
9-13
Comparing Two or More Labs
Improve
Process
Capability
Follow the instructions in the notes to perform the comparisons.
9-14
Comparing Two or More Labs …
Improve
Process
Capability
Individual 95% CIs For Mean Based on
Pooled StDev
Level
N
Mean
StDev
HART
24
-1.7658
0.2235
Kuantan
41
-1.3346
0.1369
TED
37
-1.0568
0.0846
---+---------+---------+---------+-----(-*--)
(-*)
(-*-)
---+---------+---------+---------+------1.75
-1.50
-1.25
-1.00
Pooled StDev = 0.1476
Tukey 95% Simultaneous Confidence Intervals
All Pairwise Comparisons among Levels of Lab
Individual confidence level = 98.09%
Lab = HART subtracted from:
Lab
Lower
Center
Upper
Kuantan
0.3408
0.4312
0.5216
TED
0.6169
0.7091
0.8012
--+---------+---------+---------+------(--*--)
(--*--)
--+---------+---------+---------+-------0.30
0.00
0.30
0.60
Lab = Kuantan subtracted from:
Lab
Lower
Center
Upper
TED
0.1981
0.2779
0.3576
--+---------+---------+---------+------(-*--)
--+---------+---------+---------+-------0.30
0.00
0.30
0.60
9-15
Hypotheses: Does Film IV, CHDM and
DEG Effect Shrink Stress?
Improve
Process
Capability
9-16
Minitab : Analyze Relationships
Between Two Continuous Variables
Improve
Process
Capability
•Open Minitab Software.
•Open Shrink Stress in the Minitab Datasets Folder.
•Follow the instructions below to create fitted line plots
of the data.
9-17
Improve
Process
Capability
Analyze Relationships Between Two
Continuous Variables
Fitted Line Plot
Fitted Line Plot
Avg Shrink Stress: = 15.10 - 0.5321 Film DEG
Avg Shrink Stress: = - 9.12 + 26.81 Film IV
11.5
S
R-Sq
R-Sq(adj)
10.5
10.0
9.5
9.0
8.5
S
R-Sq
R-Sq(adj)
11.0
Avg Shrink Stress:
Avg Shrink Stress:
11.0
11.5
1.04108
8.9%
2.3%
0.805410
45.5%
41.6%
10.5
10.0
9.5
9.0
8.5
8.0
8.0
7.5
7.5
0.66
0.67
0.68
Film IV
0.69
9
0.70
10
11
12
13
14
Film DEG
Fitted Line Plot
Avg Shrink Stress: = 12.58 - 0.1600 Film CHDM
11.5
S
R-Sq
R-Sq(adj)
Avg Shrink Stress:
11.0
1.01422
13.5%
7.3%
10.5
What conclusions do you make from the
analysis?
10.0
9.5
9.0
8.5
8.0
7.5
19
20
21
22
23
24
Film CHDM
25
26
27
9-18
Improve
Process
Capability
Designed Experiments
Outputs Variables
Process
Products or Services
103.4
92.6
2345
Input Variables
Making planned and deliberate changes to the
process input variables to determine the effect on
the output variables.
Properly designed experiments can yield useful cause-effect information.
9-19
Designed Experiments - Example
IV
CHDM DEG
0.75
20
9
0.71
23.6 11.2
0.743 23.6
12
0.731 25.9 10.8
0.741 24.2 13.4
0.743 24.2 13.6
0.732 23.8 10.8
0.742 19.5 10.3
0.756 24.3 13.5
0.71
23.7 11.1
0.729 23.6 12.1
0.708 18.9 11.4
0.733 19.4 10.4
0.723 23.4 13.5
0.727 19.4
9.4
0.702 19.6 11.5
Improve
Process
Capability
Objective: Choose a formulation for a new
EMBRACE product.
These 16 conditions were done on a
manufacturing line in Kingsport.
Material was taken to customers and run.
Customer fitness for use measures will
aid in determining new EMBRACE
fromulation.
9-20
Improve
Process
Capability
Designed Experiments - Example
Profiler
Contour Profiler
Horiz Vert Factor
Film IV
Film DEG
Film CHDM
Temp
Response
Pred Formula
Pred Formula
Pred Formula
Pred Formula
Current X
0.657
9.3
24.2
95
10s TD Shrinkage
10 s MD Shrinkage
Avg Shrink Stress
Glycol Sum
Contour
-5.140107
-10.33525
6.4315566
28.8
Current Y
81.756686
-9.995825
8.0112861
33.5
Lo Limit
70
.
.
.
Hi Limit
.
.
7.1
35
24.2
7.2
7.4
6.4
7.6
6.6
7.8
6.8
7
Pred Formula Avg Shrink Stress
75
8.2
19.5
Film CHDM
8
70
9.3
65
Film DEG
60
13.4
9-21
Review
•Improving Stable Processes takes intervention
Improve
Process
Capability
•All of the data is important, not just the "Special" Causes
•Exploratory Data Analysis (EDA) on historical data
•Use the C&E Matrix and the FMEA to determine
where to start
•Look for trends
•Look for differences among qualitative variables
(instruments, etc.)
•Information will be used in control plan
•Variance Component Breakdowns (Test and Process)
•Designed Experiments on Key Inputs
•Key Inputs determined by C&E, FMEA and EDA
•Information will be used in control plan
9-22
Improve
Process
Capability
Exercise
1.) Your Catapult Team should complete page 12 of the
“Catapult Process” handout.
Limit yourselves to 30 minutes for this exercise.
9-23