GB Wave XII Capability Studies - Lean Ohio Studies.pdfProcess Capability Before Mean Shift Needed...
Transcript of GB Wave XII Capability Studies - Lean Ohio Studies.pdfProcess Capability Before Mean Shift Needed...
8/4/2015
1
SIMPLER. FASTER. BETTER. LESS COSTLY.
Transforming the Public Sector
Green Belt
Process Capability
SIMPLER. FASTER. BETTER. LESS COSTLY.
SIMPLER. FASTER. BETTER. LESS COSTLY.
DMAIC Flow
• Measure:– Understand Metrics– Validate
Measurement System
– Determine Process Performance
Capability
8/4/2015
2
SIMPLER. FASTER. BETTER. LESS COSTLY.
Why Care About Process Capability?
• How capable is the process?• How close are we to meeting the
desired state?• Allows comparison from baseline to
after process improvement• Demonstrate Success!
SIMPLER. FASTER. BETTER. LESS COSTLY.
Process Capability Study: Set-Up
• Process capability study assumes that you have a stable process
• Identify Specification Limits • Capability improvements can be in terms of
decreased variation or improved centering, but are always relative to the spec limits
SIMPLER. FASTER. BETTER. LESS COSTLY.
Control Limits vs. Spec Limits
• Where do Control Limits come from?– The DATA: +/- 3σ (99.73% of the
process variation is expected to fall between these limits)
• Where do Specification Limits come from?– The customer: spec limits are not
found on control charts
6
8/4/2015
3
SIMPLER. FASTER. BETTER. LESS COSTLY.
Upper Control Limits = UCLLower Control Limits = LCL
Upper Specification Limits = USLLower Specification Limits = LSL
Is The Process Below Making Defects ?
UCL
LCL
TIME
USL
LSL
Control Limits vs. Spec Limits
SIMPLER. FASTER. BETTER. LESS COSTLY.
Upper Control Limits = UCLLower Control Limits = LCL
Upper Specification Limits = USLLower Specification Limits = LSL
Is The Process Below Making Defects ?
UCL
LCL
USL
LSL
TIME
Control Limits vs. Spec Limits
SIMPLER. FASTER. BETTER. LESS COSTLY.
Process Capability Study Steps
• Four Basic Steps1. Verify that the process is stable2. Verify that the distribution of the data is
normal3. Calculate capability indices and
determine the level of quality4. Recommend process improvements
that increase process capability
8/4/2015
4
SIMPLER. FASTER. BETTER. LESS COSTLY.
Before We Get Too Far Ahead
• Refresher on process stability– How do you know if you have a stable
process?
• Refresher on data normality– How do you know if you have normal
data?
SIMPLER. FASTER. BETTER. LESS COSTLY.
Process Capability Vs. Control
• Remember…– Process capability is relative to spec limits– Process control is relative to the outputs
Spec limits are not the same as control limits
USLLSL
SIMPLER. FASTER. BETTER. LESS COSTLY.
Process Capability Vs. Control
8/4/2015
5
SIMPLER. FASTER. BETTER. LESS COSTLY.
Dissecting Process Capability
LSL USL
Defects
Process Capability
Inadequate
Training, SOP,
Visual Mgt.
Inadequate
Process
Capability
Process
Variation
Inadequate
Measurement
Capability
SIMPLER. FASTER. BETTER. LESS COSTLY.
Centering – Put The Process On Target
Spread – Reduce The Variation
LSL USL
DefectsDefects
Process Capability - The Strategy
SIMPLER. FASTER. BETTER. LESS COSTLY.
Very Low Probability of
Defects
Very Low Probability of
Defects
LSL USL
BetterProcess Capability After
Very High Probability of
Defects
Very High Probability of
Defects
LSL USL
Poor Process Capability Before
Spread Reduction
Very Low Probability of
Defects
Very Low Probability of
Defects
LSL USL
BetterProcess Capability AfterVery High
Probability of Defects
LSL USL
Poor Process Capability Before
Mean Shift Needed
The Focus of Improvement
8/4/2015
6
SIMPLER. FASTER. BETTER. LESS COSTLY.
Process Capability Ratios• There are two key measures for short-term capabilit y
– Cp and Cpk
USLC
- LSL|
6sp =
Cpk = Min (X - LSL
3s
USL - X
3s, )
Total Tolerance
Process Spread=
SIMPLER. FASTER. BETTER. LESS COSTLY.
LSL USL
x̄ = 30 Inches
s = 1
27 Inches 33 Inches
Let’s Calculate Cp!
SIMPLER. FASTER. BETTER. LESS COSTLY.
Cp Answer• Cp = ( |33 - 27| / (6 x 1))
• Cp = 6 / 6
• Cp = 1.0
USLC
- LSL|
6sp =
Cpk = Min (X - LSL
3s
USL - X
3s, )
Total Tolerance
Process Spread=
8/4/2015
7
SIMPLER. FASTER. BETTER. LESS COSTLY.
Interpretation of Cp
LSL USL
Cp
<1.0
1.0 – 1.5
>1.5
>2.0
Poor capability
Marginal capability
Good capability
6 Sigma capability
Interpretation
SIMPLER. FASTER. BETTER. LESS COSTLY.
We’ve calculated Cp• Q: So if Cp > 2 we are good to go?• A: Not necessarily!... Remember the third mantra???
USLC
- LSL|
6sp =
Cpk = Min (X - LSL
3s
USL - X
3s, )
Total Tolerance
Process Spread=
SIMPLER. FASTER. BETTER. LESS COSTLY.
Shift Happens
8/4/2015
8
SIMPLER. FASTER. BETTER. LESS COSTLY.
LSL USL
28 Inches 32 Inches
x = 33 Inches
s = .333
Let’s Calculate Cpk!
Cp = |USL – LSL|/6s
= 4/2
=2
SIMPLER. FASTER. BETTER. LESS COSTLY.
Cpk Answer• Cpk = Min CpL or CpU
CpL = ((33 – 28) / 3 x .333)
CpL = (5 / .999)
CpL = 5
CpU = ((32 – 33) / 3 x .333)
CpU = (-1 / .999)
CpU = -1 so Cpk = -1
Cpk = Min (X - LSL
3s
USL - X
3s, )
SIMPLER. FASTER. BETTER. LESS COSTLY.
T USLLSL
Cpk = 2.0 Cpk = 1.0Cpk = 1.0
Three Processes with Cp = 2.0
CPK = -1.0 CPK = 1.0CPK = 2.0
8/4/2015
9
SIMPLER. FASTER. BETTER. LESS COSTLY.
Is The Process
In Control ?
Is It Producing
Defects ?
35302520151050
39
34
29
24
Observation Number
Indi
vidu
al V
alue
I Chart for C1
X=30.60
3.0SL=37.36
-3.0SL=23.84
Short Term Capability• A Short-term Capability study covers a relatively short period of
time (Days, Weeks) generally consisting of 30 to 50 data points. The actual number depends on the subject under study.
SIMPLER. FASTER. BETTER. LESS COSTLY.
A Long-term capability study covers a relatively long period
of time (Weeks, Months) generally consisting of 100-200 data
points. Again, the actual amount depends on the subject
under study.
Is The Process
In Control ?
Is It Producing
Defects ?
100500
50
40
30
20
Observation Number
Indi
vidu
al V
alue
X=33.80
3.0SL=47.12
-3.0SL=20.49
Long Term Capability: Pp and Ppk
SIMPLER. FASTER. BETTER. LESS COSTLY.
What is the difference between the Short-term and the Long-
term Data?
What Implication does this have in doing capability studies?
Descriptive Statistics
Variable N Mean Median St Dev
short term 35 30.6 30.4 2.253
long term 110 33.8 33.5 4.438
A Further Look at Capability• Compare the estimates of the process deviations from
the short-term and long-term data
8/4/2015
10
SIMPLER. FASTER. BETTER. LESS COSTLY.
LSL
Short-Term
Capability
Long-Term
Capability
Over time, a process tends to shift by approximately 1.5σ
Short-Term
Capability
USL
The Dynamic Process
SIMPLER. FASTER. BETTER. LESS COSTLY.
5040302010
14
13
12
11
10
Index
CO
2-S
hrt
CO2 Levels for 55 Time Points
Process Performance: Total
Variation including shifts and
drifts
(Pp & Ppk)
Capability: Only
random or short term
variability
(Cp & Cpk)
Capability vs. Performance
SIMPLER. FASTER. BETTER. LESS COSTLY.
Calculating Pp and Ppk• Minitab →
• Quality Tools →
• Capability Analysis
Minitab gives you Cp, Cpk, Pp, and Ppk all in one analysis
Interpret Pp the same way you would Cp
8/4/2015
11
SIMPLER. FASTER. BETTER. LESS COSTLY.
Goal Setting
• Generic sequence of process improvement:
– Near-Term Goal: Center the process
– Mid-Term Goal: Reduce Variation
– Long-Term Goal: Eliminate Random Variation
SIMPLER. FASTER. BETTER. LESS COSTLY.
Reminder!
• Capability studies require a stable process and normal data
• Without these two factors the results will be misleading
• What do you do if you don’t have a stable process or normal data?
SIMPLER. FASTER. BETTER. LESS COSTLY.
Recap… What did we learn?
• Process Capability Vs. Process Control
• Calculating Cp and Cpk• Long-term process performance
matters– Shift Happens!
8/4/2015
12
SIMPLER. FASTER. BETTER. LESS COSTLY.
Questions?