Read Microsoft PowerPoint - Six Sigma text version

Six Sigma

What is Six Sigma? What is Six Sigma?

Six Sigma has 3 meaning :: Six Sigma has 3 meaning

1. Statistical Measurement · Process has 6 sigma capability. · Our products are 6 sigma-quality products. 2. Problem Solving Methodology · We reduced defects by using 60 methodology. · We have Six Sigma projects. 3. Improvement Program · We implement Six Sigma this year.

1

Six Sigma as a statistical measurement

Six Sigma as a statistical measurement · Most processes have variation due : to

· Man · Machine · Material · Method · Measurement · Environment

2

Six Sigma as a problem solving methodology

DEFINE CONTROL MEASURE

DMAIC Process

IMPROVE

ANALYZE

Six Sigma is a methodology to improve processes by using : 1. Systematic thinking 2. Problem Solving tools 3. Rigorous Statistical approach

Six Sigma as a problem solving methodology

Six Sigma is a methodology that provide business with tools to improve the capability of their business process.

Kai Yang & Basem EI-Haik Design for Six Sigma (McGraw Hill, 2003)

Six Sigma methodology uses a specific problem-solving approach and Six Sigma tools to improve processes and products. This methodology is data-driven, with a goal of reducing unacceptable products or events

Warren Brussee Statistics for Six Sigma Made Easy (McGraw Hill, 2004)

3

Six Sigma as a problem solving methodology

Breakthrough Strategy

Key Questions

Define Phase Measure Phase Analyze Phase Improve Phase Control Phase

What is the problems? How big is the problem? What is the root causes? How to improve the process? How to maintain the process?

Six Sigma as a problem solving methodology

4

Six Sigma as a problem solving methodology

1. Statistically : Proven Relationships between Inputs and Outputs 2. Systematically : Control KPIV and Monitoring KPOV

Six Sigma as a problem solving methodology

Project Alignment Establish solid Baseline Determine y=f (x) Optimize y=f (x) Sustain new y=f (x) D M A I C

Six Sigma Breakthrough !

5

Six Sigma as a problem solving methodology

7 QC tools

Six Sigma Tools

Which bag would a world class golfer prefer?

Statistics Multi-vari Analysis FMEA, MSA, Control Plan Design of Experiment 6 Sigma Measurement Brainstorming tools Lean Tools Etc.

Six Sigma as a problem solving methodology

Special characteristics of Six Sigma Methodology :

· Use full set of statistical / problem solving tools · Use tools in systematic fashion · Can solve various problems · 6 Sigma good in solving the following problems : · Chronic problems · Problems with many Xs · Defect reduction · Cost reduction · Variance reduction and robust solution · Breakthrough improvement

6

Six Sigma Project

... TFN

Define

Six Sigma Team Project Champion : · Black Belt : · · · · IE

1

Define

Six Sigma Process · · · · · Define Phase **** Measure Phase Analysis Phase Improve Phase Control Phase

6 ( .. ­ .. 47)

Define

Project

Project Customer Satisfaction

OTP : 95% 82%

(PPC)

2

Define

Project

M/C Break Down OTP Start up Loss Defect R/M Delay R/M Delay

Test R/M Technical Skill

·Brain Storming and Relation Diagram

Minor Stop

R/M Labor Skill

Set up time delay

Define

Project

Y = f (x1,x2..........,xn)

OTP = f (Break Down () , Start up Loss , , Minor Stop , , Set up Delay , , R/M delay , R/M Delay , Defect , , ,) Break Down = f ( , R/M , , Labor Skill , Tech Skill) Defect = f (Labor Skill , Tech Skill , R/M) Set up Delay = f (Technical Skill) Minor Stop = f ( M/C , ) R/M Delay = f ( test R/M , ) Start up Loss = f (Minor Stop , Break Down)

3

Define

Project Matrix Data Analysis

6 / Six Sigma tools OTP

Process Inputs

Total

1 2 3 4 5 6 7 8 9 10 11 12

minor stop Set up delay R/M delay R/M delay Defect

9 8 5 8 10 10 8 10 8 5 2 2

5 6 3 5 4 5 10 5 5 10 10 10

5 10 5 9 10 10 10 10 8 10 5 5

5 8 5 6 9 10 8 10 8 10 5 5

3 10 3 3 5 3 10 8 3 10 10 10

10 5 5 3 10 10 10 10 10 6 10 6

10 8 10 1 10 10 1 1 10 1 1 1

7.95 7.8 6.45 4.4 9.05 9.15 6.25 6.25 8.35 5.45 4.25 3.85

4 5 6 10 2 1 7 7 3 9 11 12

6-Sigma Project #1

(Needle Breakage) SKP

Black Belt Candidate

Name : Company : XXX

4

Define

: Project Team Members

Project Champion

Plant Manager

Team Members (Green Belt)

Production Supervisor Production Chargehand Engineering Supervisor QA Supervisor Industrial Enigineer

Define

: Problem Statement

(Needle Breakage)

/ (QA) SKP 0.10%

5

Define

:

..- .. 47

2547

SUM 30000.00 25000.00 20000.00 15000.00 10000.00 5000.00 0.00 ACC % 120.00 100.00 80.00 60.00 40.00 20.00 0.00

42.73%

Define

() :

..- .. 47

2000000.0 Weight (Kg) 1500000.0 1000000.0 500000.0 0.0

31.93%

Percentage (%)

/ /

Type of Defect

(/Kg)

120.00 100.00 80.00 60.00 40.00 20.00 0.00

SK

GL

LO

SIN

SKP 1 3 23.21 /

INT

ER

TE

RR

TERRY

SKP

RI B

P

E

CK

Y

RIB

30 23.21 18.86 20 13.89 10.79 10.26 10 0

Percentage (%)

Weight (Kg)

6

Define

()

() : SKP ..- .. 47 %Loss 1,725.85 Kg 1,705,181.50 Kg

0.10%

Define

: Project Scope SKP : Project Objectives (Metrics)

() 80% Baseline 0.10% Goal 0.02%

: Critical To Quality PPC : Cost Of Poor Quality · PPC · PPC ( %OTP) · (0.60 /Kg) · ()

7

Define

: Benefits

· Hard Saving : · 561.6 Kg/ 146,016 / *** : %Loss = 0.10 ­ 0.02 = 0.08% = 702,000 Kg / = 561.6 Kg / - - scrap = 130 / Kg Benefit Loss = 702,000 * 130 * 0.08% = 73,008 Opportunity Loss = Benefit Loss

·Total Hard Saving 146,016 /

· Soft Saving : · PPC · · ·

Define

: Time Line

· · · · · Define Phase Measure Phase Analysis Phase Improve Phase Control Phase : 19 .. 47 : 17 .. 47 : 21 .. 47 : 19 .. 47 : 15 .. 47

· End Project

: 30 .. 47

8

Define

Process Mapping

· High Level Process Mapping (SIPOC)

Suppliers Inputs Process Outputs Customers

PPC QA

(Knitting Process)

PPC

Define

Process Mapping

· High Level Process Mapping (SIPOC) ()

Suppliers Inputs Process Outputs Customers

PPC QA QA

9

Define

Process Mapping

· Detailed Process Mapping

4 / No Yes Data Collection QA No Yes

QA

Dyeing & Finishing

Define

Process Mapping

· Detailed Process Mapping

Input

- - - -

Type

C C/S C

Process

1.

- - stop motion - - - scanner / needle detector

VA/NVA ()

VA 20

Output

- -

2.

- - - - - - - - C S S C/S C S S C/S - - - NVA NVA NVA - - - - VA -

10

Define

Process Mapping

· Detailed Process Mapping (continue)

- - - - - - - - - - - - C S S C/S C S S C/S C S S C/S - - - - - 1 - NVA NVA NVA NVA NVA VA - - - - - - - 4 / - stop motion - - NVA NVA NVA VA - - - -

Define

Process Mapping

· Detailed Process Mapping (continue)

- - - - C S S C/S - - stop motion - - - - - - - - - - - - - C S S C S S S S S - - 4 Point - - - - NVA NVA NVA NVA NVA VA - - - - - - - - QA NVA NVA NVA NVA NVA NVA VA NVA - - - - - - - - QA

11

Cause & Effect Diagram

(Brain Storming)

Measure

Data Collection

Function Y = f (X1 , X2 , X3 , X........... , Xn)

= f ( , , , , , , , , , , , %RH , , (slub) , (snarl) , , , , / needle detector , needle detector , / needle detector

4 M

Man (6) = , , , , , / needle detector Method (6) = , , , , , needle detector Machine (5) = , , , , /needle detector Material (2) = (slub) , (snarl)

12

Measure

Data Collection

Measure

Baseline Data ( Sigma Level)

SKP ..- .. 47

Descriptive Statistics

Variable: %Loss

Anderson-Darling Normality Test A-Squared: P-Value: Mean StDev Variance Skewness Kurtosis N Minimum 1st Quartile Median 3rd Quartile Maximum 0.566 0.122 0.101446 0.035308 1.25E-03 0.532003 -9.4E-01 18 0.061696 0.067421 0.095707 0.129951 0.171020

0.07

0.09

0.11

0.13

0.15

0.17

95% Confidence Interval for Mu

95% Confidence Interval for Mu 0.083888

0.07 0.08 0.09 0.10 0.11 0.12 0.13

0.119004 0.052932

95% Confidence Interval for Sigma 0.026495 95% Confidence Interval for Median

95% Confidence Interval for Median

0.068423

0.124290

P-Value >= 0.05 Normal Distribution

13

Measure

Baseline Data ( Sigma Level)

Normality Test

Normal Probability Plot

.999 .99 .95

Probability

.80 .50 .20 .05 .01 .001 0.06 0.11 0.16

Anderson-Darling Normality Test A-Squared: 0.566 P-Value: 0.122

%Loss

Average: 0.101446 StDev: 0.0353079 N: 18

P-Value >= 0.05 Normal Distribution

Measure

Baseline Data ( Sigma Level)

(Process Capability)

Process Capability Analysis for %Loss

USL

Within Overall

Process Data 0.200000 USL * Target * LSL 0.101446 Mean 18 Sample N StDev (Within) 0.0270023 StDev (Overall) 0.0358307

Potential (Within) Capability * Cp 1.22 CPU * CPL Cpk Cpm Overall Capability Pp PPU PPL Ppk * 0.92 * 0.92 1.22 * 0.00 0.05 0.10 0.15 0.20 Exp. "Overall" Performance * PPM < LSL 2974.77 PPM > USL PPM Total 2974.77

Observed Performance * PPM < LSL 0.00 PPM > USL PPM Total 0.00

Exp. "Within" Performance * PPM < LSL 131.20 PPM > USL PPM Total 131.20

Process Capability = 0.92 Sigma Level = 3*0.92 = 2.76

14

Analyze

Analysis Information

1 ­ 20 47 (171 )

Pareto Chart for Frequency

100 150 80

Percent

1 2 3 4 () (Knot) (Slub) (Snarl)

Count

100

60 40

50 20 0 0

1 3 2 e rs Oth

Defect

Count Percent Cum %

119 69.6 69.6

26 15.2 84.8

22 12.9 97.7

4 2.3 100.0

SKP 171 740.56 Kg 4.33 Kg/

Analyze

Analysis Information

1 ­ 20 47 (171 )

2

, 108.18, 15% , 99.5, 13% , 487.72, 66% , 45.16, 6%

66%

80%

· · · · · ·

13% /

15

Analyze

Analysis Information

?

(Yarn Carrier) (Incomplete Loop) (Knitting Element)

Analyze

Analysis Information

(Knitting Element)

Descriptive Statistics

Variable: Cleaning

Anderson-Darling Normality Test A-Squared: P-Value: Mean StDev Variance Skewness Kurtosis N Minimum 1st Quartile Median 3rd Quartile Maximum 2.68122

2.7 2.8 2.9 3.0

88.3%

Pareto Chart for Cleaning

100

2.77778 0.63965 0.409150 0.233039 -6.5E-01 171 2.00000 2.00000 3.00000 3.00000 4.00000 2.87434 17.481 0.000

150 80

Count

2

3

4

100

60 40

50 20 0 0

3 2 4

95% Confidence Interval for Mu

95% Confidence Interval for Mu 95% Confidence Interval for Sigma 0.57828 95% Confidence Interval for Median 0.71570 95% Confidence Interval for Median 3.00000 3.00000

Defect

Count Percent Cum %

93 54.4 54.4

58 33.9 88.3

20 11.7 100.0

Percent

16

Analyze

Analysis Information

SKP 43 78

Pareto Chart for Fan

100 150 80

Pareto Chart for Auto Clean

100 150 80

Percent

Count

100

Count

60 40

100

60 40

50 20 0 0

s Ye No

50 20 0 0

s Ye No

Defect

Count Percent Cum %

Defect

Count Percent Cum %

152 88.9 88.9

19 11.1 100.0

161 94.2 94.2

10 5.8 100.0

4 m/c 9.30%

5 m/c 11.63%

Analyze

Analysis Information

SKP 43 78

Pareto Chart for Door

100 150 80 100 150 80

Pareto Chart for Guide

100

Count

Count

60 40

100

60 40

50 20 0 0

s Ye No in Ru

50 20 0 0

s Ye No

Defect

Count Percent Cum %

Defect

Count Percent Cum %

94 55.0 55.0

63 36.8 91.8

14 8.2 100.0

96 56.1 56.1

75 43.9 100.0

4 m/c 9.30%

18 m/c 41.86%

Percent

Percent

Percent

17

Analyze

Analysis Information

10 SKP 43 78

Pareto Chart for Clatcher

100 150 80 150 80

Pareto Chart for Yarn

100

Percent

Count

100

Count

60 40

100

60 40

50 20 0 0

s Ye No

50 20 0 0

s Ye ers Oth

Defect

Count Percent Cum %

Defect

Count Percent Cum %

86 50.3 50.3

85 49.7 100.0

170 99.4 99.4

1 0.6 100.0

19 m/c 44.19%

Ne 10S 1

Analyze

Analysis Information

SKP 171

Pareto Chart for Start Up Chk

100 150 80 150 80

Pareto Chart for Fabric Chk

100

Percent

Count

100

Count

60 40

100

60 40

50 20 0 0

s Ye No

50 20 0 0

s Ye No

Defect

Count Percent Cum %

Defect

Count Percent Cum %

108 63.2 63.2

63 36.8 100.0

90 52.6 52.6

81 47.4 100.0

36.80%

47.40%

Percent

Percent

18

Analyze

Analysis Information

· (%RH) 65% ·

· / ·

/

· /

Analyze

Analysis Information

()

·

· Tightness Factor "K" K ""

· · · 4 /

19

Improve

Improvement

Machine Approach

· · · Daily Check

Improve

Improvement

Man Approach

· Visual Control · OJT Visual Control 3 · 4 / ()

20

Improve

Improvement

· DOE 24 Factorial Cylinder 27 .. 47 1 .. 47

Improve

Improvement

Main Effects Plot (data means) for score

-1

1

-1

1

-1

1

-1

1

8.7

Fractional Factorial Fit: score versus point, clean, check

score

7.9

Estimated Effects and Coefficients for score (coded units) Term Constant point clean check point*clean Effect 1.0937 3.0938 2.1562 -0.7812 Coef SE Coef T 7.1094 0.1035 68.66 0.000 0.5469 0.1035 5.28 0.000 1.5469 0.1035 14.94 0.000 1.0781 0.1035 10.41 0.000 -0.3906 0.1035 -3.77 0.003 P

7.1

6.3

5.5 point pressure clean check

Analysis of Variance for score (coded units) Source DF Main Effects 3 2-Way Interactions 1 Residual Error 11 Lack of Fit 3 Pure Error 8 Total 15 Seq SS 61.6680 2.4414 1.8867 0.2930 1.5938 65.9961 Adj SS Adj MS 61.6680 20.5560 119.85 0.000 2.4414 2.4414 14.23 0.003 1.8867 0.1715 0.2930 0.0977 0.49 0.699 1.5938 0.1992 F P

1 -1

Interaction Plot (data means) for score

-1 1 -1 1 -1 1

point

9 7 5

pressure

1 -1

9 7 5

clean

1 -1

9 7 5

check

21

Improve

New D 1.0000 Hi Cur Lo point 1.0 [-1.0000] -1.0 clean 1.0 [-1.0] -1.0 check 1.0 [1.0] -1.0

Improvement

New D 1.0000 Hi Cur Lo point 1.0 [-1.0000] -1.0 clean 1.0 [1.0] -1.0 check 1.0 [-1.0] -1.0

score Maximum y = 5.7031 d = 1.0000

score Maximum y = 7.4219 d = 1.0000

New D 1.0000

Hi Cur Lo

point 1.0 [1.0000] -1.0

clean 1.0 [-1.0] -1.0

check 1.0 [-0.9215] -1.0

New D 1.0000

Hi Cur Lo

point 1.0 [1.0000] -1.0

clean 1.0 [1.0] -1.0

check 1.0 [-1.0] -1.0

score Maximum y = 5.5065 d = 1.0000

score Maximum y = 7.7344 d = 1.0000

Improve

Machinery Cleaning Procedure 1 . 2.

22

Improve

Machinery Cleaning Procedure 3.

4.

Improve

Machinery Cleaning Procedure 5 . 6.

23

Improve

Machinery Cleaning Procedure

7. 1

8.

Improve

Machinery Cleaning Procedure

9. 1

10. "1"

24

Improve

Fabric Inspection Procedure

Improve

Improvement

SKP 48-1 6

// 22/11/2004 23/11/2004 24/11/2004 25/11/2004 26/11/2004 27/11/2004 28/11/2004 29/11/2004 30/11/2004 01/12/2004 02/12/2004 03/12/2004 06/12/2004 07/12/2004 11,880.3 13,879.2 12,699.9 12,417.7 13,709.4 13,652.7 13,109.2 12,247.8 13,671.8 12,931.9 13,941.5 14,126.1 12,076.8 13,899.6 % 15.80 40.95 12.30 23.78 12.30 8.85 6.80 9.10 14.39 6.55 6.05 13.00 2.55 7.97 0.13 0.30 0.10 0.19 0.09 0.06 0.05 0.07 0.11 0.05 0.04 0.09 0.02 0.06

// 08/12/2004 09/12/2004 10/12/2004 11/12/2004 12/12/2004 13/12/2004 14/12/2004 15/12/2004 16/12/2004 17/12/2004 18/12/2004 19/12/2004 20/12/2004 21/12/2004 12,528.5 14,593.3 14,128.7 15,950.3 14,161.0 13,203.3 13,109.4 12,857.3 11,693.5 12,151.9 11,723.1 11,714.4 10,885.6 10,993.6 % 32.42 13.47 7.78 36.87 9.07 17.90 0.00 11.51 0.00 7.04 41.82 9.45 7.58 8.04 0.26 0.09 0.06 0.23 0.06 0.14 0.00 0.09 0.00 0.06 0.36 0.08 0.07 0.07

// 22/12/2004 23/12/2004 24/12/2004 25/12/2004 26/12/2004 27/12/2004 28/12/2004 04/01/2005 05/01/2005 06/01/2005 07/01/2005 08/01/2005 09/01/2005

12,445.7 11,765.4 11,925.8 11,279.4 10,695.6 11,614.6 1,885.2 7,492.8 11,804.3 12,193.1 12,310.8 13,503.6 12,664.8

% 2.70 11.95 0.00 13.15 26.10 0.00 0.00 0.00 4.05 0.00 7.30 14.80 11.85 0.02 0.10 0.00 0.12 0.24 0.00 0.00 0.00 0.03 0.00 0.06 0.11 0.09 0.09

505,518.9 475.24

25

Improve

Improvement

SKP 48-1 6

Week 48 49 50 51 52 1 91,348.4 66,919.1 97,338.2 86,452.9 79,991.1 83,469.2 % 120.78 49.09 110.13 87.72 69.52 38.00 0.13 0.07 0.11 0.10 0.09 0.05 0.09

505,518.9 475.24

Improve

Improvement

SKP 48-1

Descriptive Statistics

Variable: %Loss

Anderson-Darling Normality Test A-Squared: P-Value: Mean StDev Variance Skewness Kurtosis N Minimum 1st Quartile Median 3rd Quartile Maximum 0.061677

0.06 0.07 0.08 0.09 0.10 0.11 0.12 0.13

0.139 0.942 9.17E-02 2.86E-02 8.17E-04 -2.5E-01 -4.7E-01 6 0.050000 0.065000 0.095000 0.115000 0.130000 0.121657 0.070089 0.122857

0.05

0.07

0.09

0.11

0.13

95% Confidence Interval for Mu

95% Confidence Interval for Mu 95% Confidence Interval for Sigma 0.017838 95% Confidence Interval for Median 0.057143 95% Confidence Interval for Median

P-Value >= 0.05 Normal Distribution

26

Improve

Improvement

Normality Test

Normal Probability Plot

.999 .99 .95

Probability

.80 .50 .20 .05 .01 .001 0.05 0.06 0.07 0.08 0.09 0.10 0.11 0.12 0.13

%Loss

Average: 0.0916667 StDev: 0.0285774 N: 6 Anderson-Darling Normality Test A-Squared: 0.139 P-Value: 0.942

P-Value >= 0.05 Normal Distribution

Improve

Improvement

(Process Capability)

Process Capability Analysis for %Loss

USL

* * 0.091667 6

Process Data USL Target LSL Mean Sample N 0.200000

Within Overall

StDev (Within) 0.0283688 StDev (Overall) 0.0300330

Potential (Within) Capability Cp CPU CPL Cpk Cpm Overall Capability Pp PPU PPL Ppk * 1.20 * 1.20 * 1.27 * 1.27 *

0.00

0.05

Observed Performance

0.10

Exp. "Within" Performance * 0.00 0.00 PPM < LSL PPM > USL PPM Total

0.15

0.20

Exp. "Overall" Performance

PPM < LSL PPM > USL PPM Total

* 67.06 67.06

PPM < LSL PPM > USL PPM Total

* 154.79 154.79

Process Capability = 1.20 Sigma Level = 3*1.20 = 3.60

27

Improve

Improvement

Parameter Mean StDev N Sigma

Before

After

0.101446 0.091667 0.035308 0.028577 18 2.76 6 3.60

Improve

Actual Benefit

: Benefits from Improvement

Hard Saving :

· Expected Benefit : 146,018 / · Actual Benefit : 8,762.32 /

*** : %Loss - - scrap Benefit Loss Opportunity Loss = = = = = = = 0.10 ­ 0.09 = 0.01% 337,012.6 Kg / 33.7 Kg / 130 / Kg 337,012.6 * 130 * 0.01% 4,381.16 Benefit Loss

·Total Hard Saving 8,762.32 /

28

Control

Control

Conclusion

Key Tools Used

1.Brain Storming 2.Pareto Diagram 3.Process Mapping 4.Cause & Effect Diagram 5.Statistical Technique (Descriptive Statistic, Process Capability Analysis) 6.Design of Experiment (DOE) 7.Control Plan

29

Control

Conclusion

Improvement Action 1. Daily Check 2. SKP Visual Control 3. OJT

4. SKP

KPI

Control

Conclusion

Achievement 1. 0.10% 0.09% 2. Sigma Level 2.76 3.60 3. (saving) 8,762.32 / Lesson Learned 1. project scope 2. 3. project BB & GB

30

Information

Microsoft PowerPoint - Six Sigma

36 pages

Find more like this

Report File (DMCA)

Our content is added by our users. We aim to remove reported files within 1 working day. Please use this link to notify us:

Report this file as copyright or inappropriate

673156