PROCESS CAPABILITY
Muhammad Asif
The Normal Distribution
+1 S.D, 68% of population +2 S.D, 95% of population+3 S.D, 99.7% of population 95.46 %
99.73 % -3 -2 -1 +1 +2 +3
At 3-sigma away from process mean expect 99.73% of observations fall within these limits. At +2 expect 95.46%
2
Z- DISTRIBUTION TABLE
Process Capability
The ability of a process to meet product design/technical specifications Conducted only when the process is normally distributed
HOW TO MEASURE Cp
LTL
UTL
(UTL LTL ) Cp = 6
6 Cp = = 1 6
-4
Process Capability Index: Cp -- Measure of Potential Capability
allowable process variation USL LSL Cp = = actual process variation 6
LSL USL
Cp > 1
Cp = 1
Cp < 1
6
12 Cp = =2 6
LTL UTL
SIX SIGMA PROCESS
-4
What value of cp is acceptable
Cp<1.0 Cp=1.0 Cp1.3 - 1.5 Cp=2
poor process so ok good Excellent, that is 6 sigma
Process Capability Index
Example
A manufacturing process produces a certain part with a mean diameter of 2 inches and a standard deviation of 0.03 inches. The lower and upper engineering specification limits are 1.90 inches and 2.05 inches. USL LSL 2.05 1.90 = = 0.83 Cp = 6 6(0.03)
Process is not a capable process since Cp<1.0
9
Process Capability Index: Cpk -- Measure of Actual Capability
C pk X LSL USL X , = min 3 3
is the standard deviation of the process
10
WHY Cpk IS NEEDED? IS Cp NOT ENOUGH?
11
Impact of Process Location on Process Capability
LSL USL
= 2
Cp = 2.0 Cpk = 2.0
38
44
50
56
62
Cp = 2.0 Cpk = 1.5
38 44 50
53
56
62
Cp = 2.0 Cpk = 1.0
38 44 50 56 62
Cp = 2.0 Cpk = 0
38 44 50 56 62
12
WHY Cpk IS NEEDED? IS Cp NOT ENOUGH?
Cp TELLS U ONLY ABOUT THE SMARTNESS OF CURVE Cpk TELLS U ABOUT THE POSITIONING / LOCATION OF THE CURVE
13
Process Capability Index
Example
A manufacturing process produces a certain part with a mean diameter of 2 inches and a standard deviation of 0.03 inches. The lower and upper engineering specification limits are 1.90 inches and 2.05 inches.
2 1.90 2.05 2 X LSL USL X = , min , C pk = min 3 3 3(0.03) 3(0.03) = min[1.11,0.56] = 0.56
Therefore, the process is not capable (the variation is too large and the process mean is not on target)
14
Process Capability
Nominal value
Six sigma Four sigma Two sigma
Lower specification Upper specification
Mean
15
Six Sigma
Is the relentless and rigorous pursuit of the reduction of variation in all critical processes to achieve continuous and breakthrough improvements that impact the bottom line of the organization and increase customer satisfaction. It is an organizational initiative designed to create manufacturing, service and administrative processes that produce approximately 3.4 defects per million. Opportunities (DPMO).
16
WITH OUT ANY DEVIATION
-6
-5
-3
-2
-7
-4
-1
between + / - 1 between + / - 2 between + / - 3 between + / - 4 between + / - 5 between + / - 6
68.27 % 95.45 % 99.73 % 99.9937 % 99.999943 % 99.9999998 %
result: 317300 ppm outside (deviation)
7 45500 ppm 2700 ppm 63 ppm 0.57 ppm 0.002 ppm
17
Distribution shifted 1.5
18
DMAIC Model
The model that is used to improve a process in Six Sigma management is called the DMAIC model. This stands for:
Define Measure Analyze Improve Control
19
LEADERSHIP
Six Sigma must be implemented from the top-down.
20
Green Belt.
Green Belts are project leaders who receive two weeks of training on the Six Sigma roadmap and essential elements of Statistical methodologies supporting Six Sigma projects. Successful Green Belts are able to allocate 50% of their time to their four to six month Six Sigma Project.
21
CHAMPIONS
An executive level business leader who facilitates the leadership, implementation, and deployment of Six Sigma philosophies.
22
Black Belt.
Black Belts are project leaders who receive four weeks of training focusing on the Six Sigma Road map and extensive statistical methodologies Successful Black Belts normally dedicate at least 75% of their time to 4 -6 month Six Sigma Project.
23
Master Black Belt.
Master Black Belt provides technical leadership to Six Sigma program. The mentor and teacher of the of Six Sigma Black Belt and Six Sigma Green Belt.
24
6 Sigma Support Personnel
25
Process capability calculation using Minitab
Please refer to the examples discussed in class
26
Process Capability of Supp1
LSL
Process Data LSL 598 Target 600 USL 602 Sample Mean 599.548 Sample N 100 StDev(Within) 0.576429 StDev(Overall) 0.620865
Target
USL
Within Overall
Potential (Within) Capability Cp 1.16 CPL 0.90 CPU 1.42 Cpk 0.90 Overall Capability Pp PPL PPU Ppk Cpm 1.07 0.83 1.32 0.83 0.87
597.75 598.50 599.25 600.00 600.75 601.50
Observed Performance PPM < LSL 10000.00 PPM > USL 0.00 PPM Total 10000.00
Exp. Within Performance PPM < LSL 3621.06 PPM > USL 10.51 PPM Total 3631.57
Exp. Overall Performance PPM < LSL 6328.16 PPM > USL 39.19 PPM Total 6367.35
27
Process Capability of Supp2
LSL
Process Data LSL 598 Target 600 USL 602 Sample Mean 600.23 Sample N 100 StDev(Within) 1.67231 StDev(Overall) 1.87861
Target
USL
Within Overall
Potential (Within) Capability Cp 0.40 CPL 0.44 CPU 0.35 Cpk 0.35 Overall Capability Pp PPL PPU Ppk Cpm 0.35 0.40 0.31 0.31 0.35
597.0 598.5 600.0 601.5 603.0 604.5
Observed Performance PPM < LSL 110000.00 PPM > USL 180000.00 PPM Total 290000.00
Exp. Within Performance PPM < LSL 91186.50 PPM > USL 144933.01 PPM Total 236119.51
Exp. Overall Performance PPM < LSL 117604.95 PPM > USL 173049.32 PPM Total 290654.27
28
Process Capability Sixpack of Supplier 2
Xbar Chart
1 1
Capability Histogram
UCL=602.474 _ _ X=600.23
LSL USL
Sample Mean
602 600 598
1 3 5 7 9 11 13 15 17 19
Specifications LSL 598 USL 602
LCL=597.986
597.0 598.5 600.0 601.5 603.0 604.5
R Chart
8
Sample Range
UCL=8.225 _ R=3.890
Normal Prob Plot AD: 0.287, P: 0.615
0
1 3 5 7 9 11 13 15 17 19
LCL=0
595
600
605
Last 20 Subgroups
604
Values
Capability Plot
Within StDev 1.67231 Cp 0.4 Cpk 0.35
Within
600
Overall
Overall StDev 1.87861 Pp 0.35 Ppk 0.31 Cpm *
596
5 10 Sample 15 20
Specs
29
