This action might not be possible to undo. Are you sure you want to continue?

BooksAudiobooksComicsSheet Music### Categories

### Categories

### Categories

### Publishers

Scribd Selects Books

Hand-picked favorites from

our editors

our editors

Scribd Selects Audiobooks

Hand-picked favorites from

our editors

our editors

Scribd Selects Comics

Hand-picked favorites from

our editors

our editors

Scribd Selects Sheet Music

Hand-picked favorites from

our editors

our editors

Top Books

What's trending, bestsellers,

award-winners & more

award-winners & more

Top Audiobooks

What's trending, bestsellers,

award-winners & more

award-winners & more

Top Comics

What's trending, bestsellers,

award-winners & more

award-winners & more

Top Sheet Music

What's trending, bestsellers,

award-winners & more

award-winners & more

P. 1

six-sigma|Views: 37|Likes: 0

Published by Jayendra Kumar

See more

See less

https://www.scribd.com/doc/93770605/six-sigma

05/16/2012

text

original

TÜV SÜD South Asia

1

9/14/2007

INTRODUCTION

Participants • Names • Roles • Expectations from this training

TÜV SÜD South Asia

2

9/14/2007

What is Six Sigma

TÜV SÜD South Asia

3

9/14/2007

Six sigma is a fact-based. Six Sigma methodology provides the techniques and tools to improve the capability and reduce the defects in any process. • • TÜV SÜD South Asia 4 9/14/2007 .What is Six Sigma? • Sigma is a measurement that indicates how a process is performing Six Sigma stands for Six Standard Deviations (Sigma is the Greek letter used to represent standard deviation in statistics) from mean. data-driven philosophy of improvement that values defect prevention over defect detection.

This is generally expressed as the y= f (x) concept. failure mode & effects analysis.What is Six Sigma? • Philosophy: The philosophical perspective views all works as a processes that can be defined. measured. • Set of Tools: Six Sigma as a set of tools includes all the qualitative and quantitative techniques used by the six sigma expert to drive process improvement. improved & controlled (DMAIC). analyzed. TÜV SÜD South Asia 5 9/14/2007 . you will control the outputs. If you control the inputs. A few such tools include statistical process control (SPC). process mapping etc. Processes require inputs & produce outputs. Control charts.

DMAIC defines the steps a Six Sigma practitioner is expected to follow. While DMAIC is not only Six Sigma Methodology in use. it is certainly the most widely adopted and recognized. TÜV SÜD South Asia 6 9/14/2007 .4 defects per million opportunities. • Metrics: In simple terms. starting with identifying the problem and ending with the implementation of long-lasting solutions.What is Six Sigma? • Methodology: This view of Six Sigma recognizes the underlying and rigorous approach known as DMAIC. Six Sigma quality performance means 3.

. General Electric. Ford Motor. • • • • Six Sigma was developed by Bill Smith. Texas Instruments. QM at Motorola It’s implementation began at Motorola in 1987 It allowed Motorola to win the first Baldrige Award in 1988 Motorola recorded more than $16 Billion savings as a result of Six Sigma • Several of the major companies in the world have adopted Six Sigma since then …. Polaroid. The Six Sigma Breakthrough Strategy has become a Competitive Tool TÜV SÜD South Asia 7 9/14/2007 . Lockheed Martin. Asea Brown Boveri. Bombardier. AlliedSignal. Nokia Mobile Phones.A little bit of History …. Dupont. American Express.…. Sony.

537 66.3% 99. It means no more than 3.210 233 3.99966% Rolled Rolled Throughput Yield Throughput Yield (Long Term) (Long Term) • •Sigma is aa statistical Sigma is statistical unit unit for for measuring measuring quality quality • •It is correlated to the It is correlated to the defect rate and the defect rate and the complexity of the complexity of the process / /product process product Six Sigma is a Standard of Excellence.4 Defect Per Defect Per Million Million Opportunities Opportunities RTY RTY 69.97% 99.807 6.4% 99. TÜV SÜD South Asia 8 9/14/2007 .4 Defects per Million Opportunities.1% 93.Sigma as a Measure of Quality σ σ 2 3 4 5 6 Process Process Capability Capability DPMO DPMO 308.

Why Six Sigma TÜV SÜD South Asia 9 9/14/2007 .

99966% 10 Historical Standard Current Standard New Standard TÜV SÜD South Asia 9/14/2007 .000 incorrect surgical operations per week 2 short or long landings at major airports each day 200.38% Long Term Yield 99.32% Long Term Yield 99.000 lost articles of mail per hour Unsafe drinking water almost 15 minutes each day 5.000 wrong drug prescriptions each year No electricity for almost 7 hours each month 3 σ Capability 4 σ Capability 6 σ Capability Long Term Yield 93.The Classical View of Performance Practical Meaning of “99% Good” • • • • • • 20.

000 Average Company Purchased Material Reject Rate 1.Benchmarking Chart 1.000.000 Restaurant Bills Order Taking Airline Baggage Handling Payroll Processing 10.000 100 10 World Class 1 2 3 4 5 6 7 Domestic Airline Flight Fatality Rate – 0.000 100.43 PPM TÜV SÜD South Asia 11 9/14/2007 .

Six Sigma Results • • • • Defects are eliminated Production and development costs are reduced Cycle Times and Inventory Levels are reduced Profit Margin and Customer Satisfaction are improved TÜV SÜD South Asia 12 9/14/2007 .

1 Sigma Shift Improvement Yields • • • • 20% Margin Improvement 12% .18% Capacity Increase 12% Workforce Reduction 10% .30% Capital Reduction TÜV SÜD South Asia 13 9/14/2007 .

Six Sigma & Cost of Poor Quality (COPQ) TÜV SÜD South Asia 14 9/14/2007 .

Cost of Poor Quality (COPQ) Correlation ••Process Process Quality Quality Control Control is is pre-requisite pre-requisite for for error error free free ••COPQ is a result of poorly controlled process COPQ is a result of poorly controlled process ••Process Control can be measured in PPM/Yield Process Control can be measured in PPM/Yield ••PPM/Yield measurements are correlated to COPQ PPM/Yield measurements are correlated to COPQ Six Sigma has shown that the Highest Quality Producer is also Six Sigma has shown that the Highest Quality Producer is also the Lowest Cost Producer the Lowest Cost Producer TÜV SÜD South Asia 15 9/14/2007 .

What is the Cost Poor Quality Internal Costs Internal Costs ••Scrap Scrap ••Rework/Repair Rework/Repair ••Downtime Downtime ••Redesign Redesign ••Excess Inspection Excess Inspection ••Excess Inventory Excess Inventory External Costs External Costs ••Warranty Warranty ••Retrofits Retrofits ••Service Calls Service Calls ••Recalls Recalls ••Lost Sales Lost Sales ••Long Cycle Times Long Cycle Times TÜV SÜD South Asia 16 9/14/2007 .

Components of Cost of Poor Quality People (Indirect Labor) People (Indirect Labor) ••Rework Rework ••Inspection Inspection ••Material Handling Material Handling ••Maintenance Maintenance ••Setup Setup ••Excess Overtime Excess Overtime ••Labor Variance off standard Labor Variance off standard Inventory Inventory ••Raw Material Holding Cost Raw Material Holding Cost ••WIP Holding Cost WIP Holding Cost ••Finished Good Holding Cost Finished Good Holding Cost ••Obsolescence Obsolescence ••Inventory Shrinkage Inventory Shrinkage Maintenance Maintenance ••Maintenance Maintenance ••Repairs Repairs ••Rearrangement Rearrangement Defects Defects ••Scrap Scrap ••Rework Rework ••Defects Defects ••Warranty & Recalls Warranty & Recalls ••Returned Good Handling Returned Good Handling Premium Freight Premium Freight ••Air Freight Air Freight ••Expedited Truck Freight Expedited Truck Freight TÜV SÜD South Asia 17 9/14/2007 .

0 4.0 DPMO 308.0 5.210 Industry Average 233 3.807 6.0 6.4 World Class TÜV SÜD South Asia 18 9/14/2007 .0 3.537 Non Competitive 66.COPQ & Sigma / DPMO Relationship COPQ 30-40% of Sales 20-30% of Sales 15-20% of Sales 10-15% of Sales <10% of Sales Sigma 2.

4% 99.0 4.0 5.0 Yield 5% 93% 99.976% 99.COPQ & Sigma/Yield Relationship COPQ 30-40% of Sales 20-30% of Sales 15-20% of Sales 10-15% of Sales <10% of Sales Sigma 2.0 3.0 6.999655% World Class Industry Average Non Competitive TÜV SÜD South Asia 19 9/14/2007 .

Reducing the Variation 1. Reducing the Variation 2.Six Sigma Improvement Strategy Know what is Important to the Customer and to the Business Know what is Important to the Customer and to the Business Reduce Defect Levels by: Reduce Defect Levels by: 1. Centering around the Target 2. Centering around the Target Long Term LSL TÜV SÜD South Asia USL 20 9/14/2007 .

Connected to the Objective of the Business.The Goals of Six Sigma ••Improved Customer Satisfaction Improved Customer Satisfaction ••Defect Reduction/Elimination Defect Reduction/Elimination ••Yield Improvement Yield Improvement ••Reduced COPQ Reduced COPQ ••Improved Process Capability Improved Process Capability ••Stretch Goals – Target 6 Sigma standards Stretch Goals – Target 6 Sigma standards ••Process Understanding Process Understanding ••Constant Measurement of Key Metrics Constant Measurement of Key Metrics ••Breakthrough Improvement Breakthrough Improvement Six-Sigma Objectives Are Directly and Quantifiably Six-Sigma Objectives Are Directly and Quantifiably Connected to the Objective of the Business. TÜV SÜD South Asia 21 9/14/2007 .

A Final Note on Philosophy Six Sigma is a relentless. constant Six Sigma is a relentless. constant Journey of Improvement Journey of Improvement TÜV SÜD South Asia 22 9/14/2007 .

Phases of Six Sigma TÜV SÜD South Asia 23 9/14/2007 .

Five Phases of Six Sigma • Define • Measure • Analysis • Improve • Control TÜV SÜD South Asia 24 9/14/2007 .

Define Phase Tools • Voice of Customer (VOC) • CT Matrix • Business Matrix • Pareto Analysis • Project Charter • Team Selection (ARMI ) • Top Level Process Map (SIPOC) TÜV SÜD South Asia 25 9/14/2007 .

Define Voice of Customer (VOC) TÜV SÜD South Asia 26 9/14/2007 .

Establishing Customer Focus ••Customer – Anyone internal or external to the Customer – Anyone internal or external to the organization who comes in contract with the product organization who comes in contract with the product or output of work or output of work ••Quality – Performance to the standard expected by Quality – Performance to the standard expected by the Customer the Customer TÜV SÜD South Asia 27 9/14/2007 .

the greater the likelihood that a customer will product or service. TÜV SÜD South Asia 28 9/14/2007 . the greater the likelihood that a customer will repurchase from the same company.The Customer Problem Customers will not repurchase a company’s product if they are Customers will not repurchase a company’s product if they are not satisfied with the current company product. not satisfied with the current company product. The stronger the degree of satisfaction with a company’s current The stronger the degree of satisfaction with a company’s current product or service. repurchase from the same company.

Variation Is The Enemy in Achieving Customer Satisfaction ••Uncertainty Uncertainty ••Unknown Unknown Variation ••Disbelief Disbelief ••Risk Risk ••Defect Rate Defect Rate TÜV SÜD South Asia 29 9/14/2007 .

What Do You Measure Now? What Numbers get the most attention in your area? What Numbers get the most attention in your area? What Quality Measurements do you have? What Quality Measurements do you have? Do they have a Customer Focus? Do they have a Customer Focus? Do they have a Quality Focus? Do they have a Quality Focus? Do they have an Input Focus? Do they have an Input Focus? How do you use these Measures? How do you use these Measures? Switching to a Sigma base measurement system σ TÜV SÜD South Asia ••Measure of Variation and Quality Measure of Variation and Quality ••Measure of Process Capability Measure of Process Capability 30 9/14/2007 .

What Do You Measure Now? Driving value from the Need – Do interaction Customer Supplier Need Do Customers and Suppliers Exchange Value Customers and Suppliers Exchange Value Through the Need-Do Interaction Through the Need-Do Interaction TÜV SÜD South Asia 31 9/14/2007 .

Maximizing the Need/Do Interaction Delivery Cycle Time Price Supplier Need Customer Do Cost Quality Defects Supplier strives for performance in Cycle Time. Price and Quality Customers expectations in Delivery. Cost and Defects To Meet To Meet Customers expectations in Delivery. Price and Quality TÜV SÜD South Asia 32 9/14/2007 . Cost and Defects Supplier strives for performance in Cycle Time.

Critical To Critical To Matrix Matrix CT’s TÜV SÜD South Asia 33 9/14/2007 .

Key Questions •• What does the phrase “critical to satisfaction” mean What does the phrase “critical to satisfaction” mean in terms of a customer? CTS in terms of a customer? CTS •• What does the phrase “critical to quality” mean in What does the phrase “critical to quality” mean in terms of a product or service? CTQ terms of a product or service? CTQ •• What does the phrase “critical to delivery” What does the phrase “critical to delivery” terms of a product service? CTD terms of a product service? CTD •• What does the phrase “critical to cost” mean What does the phrase “critical to cost” mean mean in mean in in terms in terms of a product or service? CTC of a product or service? CTC •• What does the phrase “critical to process” mean in What does the phrase “critical to process” mean in terms of a product or service? CTP terms of a product or service? CTP TÜV SÜD South Asia 34 9/14/2007 .

CT Concept Need Do Quality Defect-free Delivery Cycle time -Critical to Delivery Price Cost -Critical to Cost Cost CTQ1 -Critical to Quality CTQ2 CTQ3 Processes CTP1 -Critical to Process 1 CTP2 TÜV SÜD South Asia 35 9/14/2007 .

CTQ and CTP Characteristics CTQ1 -Critical to Quality CTQ2 CTQ3 Processes CTP1 .Critical to Process CTP2 Output Y1 Input f1 (X) TÜV SÜD South Asia 36 9/14/2007 .

“Critical to” Characteristics The inherent variation of any dependent variable (Y) is The inherent variation of any dependent variable (Y) is determined by the variations inherent in each of the determined by the variations inherent in each of the independent variables f(x). independent variables f(x). Delivery or Cost Product Capability Probability of Defects Critical-to-Quality characteristic CTQ1 Defect Opportunity TÜV SÜD South Asia Y = f (X) One of the “vital few” process variable (x) that significantly affect Y Process Capability Probability of Defects Critical-to-Process characteristic CTP1 Control Opportunity 37 9/14/2007 Probability of Defects . Product or Service requirement that impacts Quality.

The Focus of Six Sigma Y = f (X) Y Y •• Dependent Dependent •• Output Output •• Effect Effect •• Symptom Monitor Symptom Monitor X11….XN •• Independent Independent •• Input Variables Input Variables •• Cause Cause •• Problem Control Problem Control TÜV SÜD South Asia 38 9/14/2007 ...XN X ….

Y f(X) TÜV SÜD South Asia 39 9/14/2007 .CTD and CTC Characteristics • Breakdown of the processes required to produce the product or service.XN) • Translation of customer needs into product or service requirements in terms of Quality. • These are the CTQ. • Identification of the process parameters f(x1. • Identification of projects by understanding the relationship between product or service requirements and the processes used.x2…….X2…….CT Matrix Components Y = f (X1. Delivery and Cost.xN) that affect the requirements.

Business Metrics Business Metrics TÜV SÜD South Asia 40 9/14/2007 .

Business Metrics •• Following Business Metrics can be used in Six Sigma Projects. Following Business Metrics can be used in Six Sigma Projects. •• Defect per Unit (DPU) Defect per Unit (DPU) •• Defects per Million Opportunities (DPMO) Defects per Million Opportunities (DPMO) •• Throughput Yield (Yield) Throughput Yield (Yield) •• Rolled Throughput Yield (RTY) Rolled Throughput Yield (RTY) •• Parts per Million (PPM) Parts per Million (PPM) TÜV SÜD South Asia 41 9/14/2007 .

Business Metrics •• An example will illustrate the use of business metrics used in An example will illustrate the use of business metrics used in previous slides. previous slides. Three types of defect can occur & number of occurrences are: occur & number of occurrences are: •• Blurred printing – 36 Blurred printing – 36 •• Wrong dimensions – 118 Wrong dimensions – 118 •• Rolled ends --11 Rolled ends 11 TÜV SÜD South Asia 42 9/14/2007 . •• Example: Example: A process produces 40000 pencils. Three types of defect can A process produces 40000 pencils.

000 = 0.004125 = 0.00.000 = DPU x 10.996 = e-DPU = e-0.000 = 4125 = 0. of units = 165 //40000 = 0.996 •• Parts per Million (PPM): Parts per Million (PPM): = DPU x 10.00.004125 •• Throughput Yield (Yield): Throughput Yield (Yield): = e-DPU = e-0.004125 x 10.00.00.004125 = 165 40000 = 0.Business Metrics •• Defect per Unit (DPU): Defect per Unit (DPU): = Total number of defects //No.000 = 4125 TÜV SÜD South Asia 43 9/14/2007 .004125 = 0.004125 x 10. of units = Total number of defects No.

000 x 2 = 80.000 + 1.000 = 2.000 + 1. so Rolled ends can occur at the top and or the bottom of the pencil.000) //(Total no. The total number of opportunities for defects is 40.5 TÜV SÜD South Asia 44 9/14/2007 . of defects x 10.000) (Total no.5 = (165 x 10.000 opportunities for dimensional defects. blurred printing occurs in only one way (the pencil slips in the fixture). of opportunities) DPMO = (Total no. so There are three independent places where dimensions are checked.40. In this product. it is necessary to find the number of ways each defect can occur on each item.000 opportunities for this defect to occur. so there are 3 x 40.20. so in the batch there are 40. Rolled ends can occur at the top and // or the bottom of the pencil. of opportunities) = (165 x 10. of defects x 10.00.000 = 2.20. number of ways each defect can occur on each item.40. so there are 40.000 + 80. In this product.000 + 80.000 = 1. There are three independent places where dimensions are checked.000 = 1. blurred printing occurs in only one way (the pencil slips in the fixture).000 DPMO = (Total no.000) (2.000) //(2.000 opportunities for this defect to occur. so in the batch there are 40.20. it is necessary to find the To Calculate the number of opportunities.000) = 687.40.40. there are 3 x 40.000) = 687. The there are 40.00.000 opportunities for this defect to occur.00.Business Metrics •• Defect per Million Opportunities (DPMO): Defect per Million Opportunities (DPMO): To Calculate the number of opportunities.20.000 x 2 = 80.000 total number of opportunities for defects is 40.00.000 opportunities for this defect to occur.000 opportunities for dimensional defects.

990. 0.994.951 & through four processes whose yields are 0.951 x 0.Business Metrics •• Rolled Throughput Yield (RTY): Rolled Throughput Yield (RTY): RTY applies to the yield from a series of processes and is found RTY applies to the yield from a series of processes and is found by multiplying the individual process yields.951 & 0.987 x 0.987 x 0.994.987.994 x 0.990 = 0. If a product goes through four processes whose yields are 0.990. If a product goes by multiplying the individual process yields. 0.924 TÜV SÜD South Asia 45 9/14/2007 .994 x 0. 0.951 x 0.987. then RTY = 0. then 0.924 RTY = 0.990 = 0. 0.

Defect per Million Opportunities (DPMO).Three A car manufacturer produces 15000 cars per month Three types of defect can occur at different stage & number of types of defect can occur at different stage & number of occurrences are: occurrences are: Initial Assembly – 50 (No.Exercise-1 •• A car manufacturer produces 15000 cars per month . of Opportunities – 4) Intermediate Assembly – 95 (No. TÜV SÜD South Asia 46 9/14/2007 . of Opportunities – 3) Final Assembly – 35 (No. of Opportunities – 2) Final Assembly – 35 (No. Throughput Yield & Parts per Opportunities (DPMO). Million (PPM). Throughput Yield & Parts per Million (PPM).. of Opportunities – 3) Calculate the Defects per Unit (DPU). of Opportunities – 2) Intermediate Assembly – 95 (No. of Opportunities – 4) Initial Assembly – 50 (No. Defect per Million Calculate the Defects per Unit (DPU).

Exercise-2 A Process A – Mixing 100# in – 90# out 90% B Process B – Making 100# in – 80# out 80% C Process C – Converting 100# in – 90# out 90% D Process D – Inspection 100# in – 95# out 95% Calculate the Rolled Throughput Yield (RTY) for the above Calculate the Rolled Throughput Yield (RTY) for the above process. process. TÜV SÜD South Asia 47 9/14/2007 .

Pareto Charts Pareto Charts TÜV SÜD South Asia 48 9/14/2007 .

performance.5 Dent 1 12. S cratch 4 50.5 100. Paretos usually allow us to focus on the improvement targets.0 TÜV SÜD South Asia 49 9/14/2007 .0 75. Paretos usually allow us to focus on the 20% of the problems that causes 80% of the poor 20% of the problems that causes 80% of the poor performance.Pareto Charts •• Pareto Diagrams are an essential tools to help prioritize Pareto Diagrams are an essential tools to help prioritize improvement targets.5 87.0 Chip 2 25.0 50.0 Bend 1 12. Pareto Chart of Damage 9 8 7 6 Count 100 80 60 40 20 0 Percent 5 4 3 2 1 0 Dam age Count Percent Cum % Interpreting the results: Focus on improvements to scratches and chips because 75% of the damage is due to these defects.

Most of the problems are due to scratches and peels. You may learn a lot about the problem if you examine that part of the process during the night shift. etc. Count Peel Scratch Other Sm udge Flaws You should drill down using third level. TÜV SÜD South Asia 50 9/14/2007 . fourth level. as far as it makes sense in solving your problem..Pareto Chart (Second Level) Pareto Chart of Flaws by Period Peel Period = Day Scratch Other Sm udge Period = Evening 20 15 10 5 Flaws Peel Scratch Other Smudge 20 15 10 5 0 Period = Night Period = Weekend 0 Interpreting the results: The night shift is producing more flaws overall.

Project Charter Project Charter TÜV SÜD South Asia 51 9/14/2007 .

Project Charter The Project should be defined through a Problem Description/ The Project should be defined through a Problem Description/ Project Objective and include: Project Objective and include: •• PPM or DPMO Baseline data PPM or DPMO Baseline data •• Cost of Poor Quality (COPQ) Cost of Poor Quality (COPQ) •• Rolled Throughput Yield (RTY) Rolled Throughput Yield (RTY) ••Inventory or Inventory or ••Other Appropriate Metric Other Appropriate Metric TÜV SÜD South Asia 52 9/14/2007 .

52 Lacs 99.06 TÜV SÜD South Asia 53 9/14/2007 .04.52 Lacs Target 47295 mtrs/shift Y and Complementary Ys 1 Improve OEE 2 Increase Availability 99. Sukhdev Narayan S.06 I 20.06.06 MileStones Define 1 Team 2 Metrics 3 Process 4 Charter Measure MSA Baseline Capability Process Map X Shortlisting Root Cause Analyze 1st level cause Improve Control Statistical SolutionMonitoring Optimum Solution Standardization Implement SolutionTrain Validate Solution Maintain D 13.06 18.01.07.45 hrs working time(Mini clean time reduced).06 C 20. M. Target Productivity calculated based on 90% Efficiency and 7./shift Project No.02. Prejith To improve the produtivity on DW Line from 28471 to 47295 mtrs.06 Process Owner : S.06.06 10..H. Arora Last Review Date: 22.06 Lacs/Annum Baseline 28471 mtrs/shift Current 30442 mtrs/shift 3.06 Metrics Business Metric(s): 1 Critical to Delivery 2 Critical to Cost 3 Z-Score Projected Savings: 3.01.SIX SIGMA PROJECT STATUS Project Status Summary Report Project Details Black Belt : Company/Plant: Process : Champion: Process Team : Problem Decsription: Arpit Upadhyay Bundy India Ltd.H.02.06 M 03. Baroda Double Wall tube manufacturing Vinod Dhar.08.06 A 20. Pathak Master Black Belt: R.06 30. Product: B 004 DW tube Status Summary Status: Status Date: Review Date: Start Date : End Date : In Progress 30.03. Jogesh Shah.01. Preliminary Plan P h a s Target Date Actual Date 21. Pathak. K.06 01.06 Lacs/Annum 3 Reduce Down time Constraints/Special Conditions 1.08.

Team Selection (ARMI) Team Selection (ARMI) TÜV SÜD South Asia 54 9/14/2007 .

The Six Sigma Team shall include following members. •• A R M II A R M •• Approver Resources Approver Resources •• Champion Champion •• Executive Executive Maser Black Belt Maser Black Belt Members Interested Party Members Interested Party Black Belt Black Belt Green Belt Green Belt Process Owner Process Owner Stake Holder Stake Holder Customer Customer Supplier Supplier TÜV SÜD South Asia 55 9/14/2007 .Team Selection (ARMI) The Six Sigma Team shall include following members.

Top Level Process Map Top Level Process Map (SIPOC) (SIPOC) TÜV SÜD South Asia 56 9/14/2007 .

– The Top Level Flow Map is the minimum level of – The Top Level Flow Map is the minimum level of process flow mapping required in order to begin a process flow mapping required in order to begin a FMEA FMEA TÜV SÜD South Asia 57 9/14/2007 . Everyone produce the output – the essentials. does these steps – no argument.Top Level Process Map Top Level Process Map – the basic steps or activities that will Top Level Process Map – the basic steps or activities that will produce the output – the essentials. without any extras. Everyone does these steps – no argument. without any extras.

Fixtures Environment Cleanliness Rework OUTPUTS Part to Print Performance to Spec Visually acceptable Leak Free Identified Clean Packaged for use Consistent standard TÜV SÜD South Asia 58 9/14/2007 .Top Level Process Map List General Input and major Customer Key Output Variables List General Input and major Customer Key Output Variables Assembly AD-SP Air Dryer Body INPUTS Assembly Labor Procedures Materials Equipment.

Top Level Process Map Remember that processes are also affected by elements that feed into Remember that processes are also affected by elements that feed into and receive from the process and receive from the process Suppliers INPUTS Assembly AD-SP Air Dryer Body OUTPUTS Customers This is known as the SIPOC Model TÜV SÜD South Asia 59 9/14/2007 .

Basic Statistics TÜV SÜD South Asia 60 9/14/2007 .

– Describing.Statistics • The Science of: – Collecting. – Interpreting data… And Making Decisions TÜV SÜD South Asia 61 9/14/2007 . – Analyzing.

Type of Data • Attribute Data (Qualitative) – – – – – – Categories like Machine 1. Pressure. # of freight claims Decimal subdivisions are meaningful Cycle Time. Machine 2. Conveyor Speed • Variable of Continuous Data (Quantitative) – – TÜV SÜD South Asia 62 9/14/2007 . No Go. No Go or Pass/Fail Good/Defective On-Time/Late Discrete (Count) Data • # of Maintenance Equipment Failures. Machine 3 Yes.

Measures of Central Tendency • What is the Middle Value of Distribution? – • Median What value represents the distribution? – Mode • What value represents the entire distribution? – Mean ( x ) • What is the best measures of central tendency? TÜV SÜD South Asia 63 9/14/2007 .

– – Does not include all values in calculation Is “robust” to extreme scores • Mode: The value or item occurring most frequently in a series of observations or statistical data.Data Distributions • Mean: Arithmetic average of a set of values – – • Reflects the influence of all values Strongly Influenced by extreme values Median: Reflects the 50% rank – the center number after a set of numbers has been sorted from low to high. TÜV SÜD South Asia 64 9/14/2007 .

Are the 2 Distributions Same? n= 1 2 3 4 5 6 7 8 9 X= X= n= What is the Difference? TÜV SÜD South Asia 65 9/14/2007 .Measure of Central Tendency .Mean • Find the value of “n” and “X” for the following 2 distribution.

Spread • Range “R” = Max – Min is an easy measure of Spread n= 1 2 3 4 5 6 7 8 9 X= X= R= R= n= TÜV SÜD South Asia 66 9/14/2007 .Measures of Variability .

Do the 2 distributions have same Variability? n= 1 2 3 4 5 6 7 8 9 X= X= R= R= How do we measure average variability from the Center? n= TÜV SÜD South Asia 67 9/14/2007 .Is Range a good Measure of Variability? • Find the value of “n”. “X” and “R” for the following 2 distribution.

Measures of Variability (Spread) • Calculate Variance & Standard Deviation for these 2 Distributions. n= 1 2 3 4 5 6 7 8 9 X= X= R= R= V= V= S= S= n= TÜV SÜD South Asia 68 9/14/2007 .

The most common and useful measure of variation is the Standard Deviation. (Highest – Lowest) The Variance(S2) is the Average Squared Deviation of each data point from the Mean. The range is more sensitive to outliers than the variance. The Standard Deviation (s) is the Square Root of the Variance.Measures of Variability • • • • • The Range is the distance between the extreme values of data set. TÜV SÜD South Asia 69 9/14/2007 .

Sample Statistics vs. Population Parameters X = Sample Mean µ = Population Mean S = Sample Standard Deviation σ = Population Standard Deviation Statistics Estimate Parameters TÜV SÜD South Asia 70 9/14/2007 .

326 71 S = ∑ n ( Xi − X ) 2 i =1 __ n −1 9/14/2007 .693 2.Statistical Calculations (Sample) Mean __ Variance Xi X= ∑ i =1 n S2 = ∑ n ( Xi − X ) 2 i =1 __ n __ n −1 Standard Deviation Standard Deviation σ = R/ d 2 N 2 3 4 6 TÜV SÜD South Asia d2 1.059 2.128 1.

Statistical Calculation (Population) Mean Variance µ≈X __ σ2 = ∑ n ( Xi − X ) 2 i =1 __ n Standard Deviation σ = TÜV SÜD South Asia ∑ n ( Xi − X ) 2 i =1 __ n 9/14/2007 72 .

Probability Density Functions (Shape) • • • • • The Shape of the distribution is shown by the probability Density Function. The Y axis is Probability Density and the X axis is Data Values Area Under the curve Represents the probability of finding a data point between 2 Values. Probability Density Function Defines the interrelation between the center and the spread. The distributions with known function are called Parametric and those with unknown functions are called Non-Parametric TÜV SÜD South Asia 73 9/14/2007 .

Distribution for a Targeted Process • If an Expert Marksman is Shooting. what place has the Highest Probability of getting a hit? TÜV SÜD South Asia 74 9/14/2007 .

Distribution for a Targeted Process TÜV SÜD South Asia 75 9/14/2007 .

Properties of Normal Distribution • Normal Distribution is Symmetric – – Has equal No. of Points on both Sides Mean Median and Mode Coincide • Normal Distribution is Infinite – The chance of finding a point outside tolerance is not absolutely Zero. – We need to define a practical Limit of the Process TÜV SÜD South Asia 76 9/14/2007 .

73 % -4 TÜV SÜD South Asia -3 -2 -1 77 0 1 Output σ 2 3 4 9/14/2007 .Properties of Normal Distribution • Normal Curve & Probability Areas 68 % 95 % 99.

To understand a data distribution. Data may be Variable or Attribute. • Normal Distribution is the most common but not the only shape. predict and improve the processes. we need to know its Center. Spread and Shape.Let’s Summarize… • • • We need data to study. TÜV SÜD South Asia 78 9/14/2007 .

Exercise-3 •• Calculate the Mean. 6. Range. 7. 6. 5. 9 2. Median. Median. 9. 7. Deviation for following data set. 9. Variance & Standard Deviation for following data set. Range. 2. 5. Variance & Standard Calculate the Mean. 2. 2. 9 TÜV SÜD South Asia 79 9/14/2007 .

Capability Analysis TÜV SÜD South Asia 80 9/14/2007 .

perceptions. Metrics provide a common language and help us share Metrics provide a common language and help us share information without subjectivity. Metrics help us set a common goal. we cannot improve it.Do we NEED Metrics and Baseline? •• •• •• •• •• •• If we cannot measure it. biases and confusions. Metrics help us move in the right direction. information without subjectivity. Metrics Help us understand where we stand Metrics Help us understand where we stand Metrics help us move in the right direction. biases and confusions. If we cannot measure it. TÜV SÜD South Asia 81 9/14/2007 . Metrics help us set a common goal. we cannot improve it. Metrics provide objectivity to peoples’ feelings and Metrics provide objectivity to peoples’ feelings and perceptions.

It is the first measure and tells us about as-is State. can we tell But. suppose. It is the first measure and tells us about as-is State. we look at the mile stones to When we start a long journey. It also helps us to set targets and scope out project. we did not know where we started. can we tell how far we have come? how far we have come? Base line sets a starting point of our journey. It also helps us to set targets and scope out project. suppose. we look at the mile stones to find out how far we have come… find out how far we have come… But.Baseline •• •• •• •• •• When we start a long journey. Base line sets a starting point of our journey. TÜV SÜD South Asia 82 9/14/2007 . we did not know where we started.

2. 1. Z Score 3.What do we need to Measure? •• •• We need to measure whatever is important to the project. We need to track the following metrics We need to track the following metrics 1. We need to measure whatever is important to the project. 2. Y Y Business Metrics Business Metrics 3. Z Score TÜV SÜD South Asia 83 9/14/2007 .

Why we need to Measure - Y

••

Y is the metric (CTQ/CTD/CTC) that we are focusing on. E.g. Y is the metric (CTQ/CTD/CTC) that we are focusing on. E.g. – PPM, No. of mistakes in a form, Dia Variation, Power – PPM, No. of mistakes in a form, Dia Variation, Power Factor, etc. Factor, etc. – Cycle Time, Lead Time, Inventory Level etc. – Cycle Time, Lead Time, Inventory Level etc. – Maintenance cost, Utility cost etc. – Maintenance cost, Utility cost etc.

TÜV SÜD South Asia

84

9/14/2007

**What we need to Measure - Business
**

•• •• •• •• Business metrics are the justification for taking up a six Business metrics are the justification for taking up a six sigma project and are required for management buy-in. sigma project and are required for management buy-in. Since Management is committing resources to the project, it Since Management is committing resources to the project, it needs to know what will be the business impact. needs to know what will be the business impact. One or more business metrics are required to maintain One or more business metrics are required to maintain management focus on the project. Or else, it will be Six Sigma management focus on the project. Or else, it will be Six Sigma for the sake of Six for the sake of Six Business metrics are best expressed in terms of money but Business metrics are best expressed in terms of money but could be any that give the big picture e.g. could be any that give the big picture e.g. •• COPQ, Customer Satisfaction Index, RTY exc. COPQ, Customer Satisfaction Index, RTY exc.

TÜV SÜD South Asia

85

9/14/2007

**What we need to Measure – Z Score
**

•• •• •• •• •• Z Score is the sigma level of the process. Z Score is the sigma level of the process. This is a common metric. This is a common metric. It is used as common scale for measuring the extent of It is used as common scale for measuring the extent of improvements. improvements. It also helps us benchmark against world class processes. It also helps us benchmark against world class processes. A world class or Six Sigma process operates at 6 Sigma A world class or Six Sigma process operates at 6 Sigma Levels or a Z Score = 6 Levels or a Z Score = 6

TÜV SÜD South Asia

86

9/14/2007

The metrics Should be relevant to the Problem Statement. consider Lean tools.While Setting The Metrics. – E.) first If your metric is a lean metric (inventory. cycle time etc. If your metric is a lean metric (inventory. Variable metric. Sometimes counter-metrics are required to ensure proper Sometimes counter-metrics are required to ensure proper output. While Improving the metric – “Cycle Time”. While Improving the metric – “Cycle Time”. output.g. If both Variable and Attribute Metrics are available. Remember… •• •• •• •• The metrics Should be relevant to the Problem Statement. prefer If both Variable and Attribute Metrics are available. prefer Variable metric. cycle time etc. Countermetric – “Defect rate” needs to be tracked so that the metric – “Defect rate” needs to be tracked so that the cycle time is not reduced at the expense of Quality cycle time is not reduced at the expense of Quality TÜV SÜD South Asia 87 9/14/2007 .g.) first consider Lean tools. Counter– E.

It expresses how__farvalue X is It expresses howfar value X is from the Center X in terms of from the Center in terms of σ σ E. a the with =70 and σ=10.g. a the value X=30 has z=(30-70)/10=value X=30 has z=(30-70)/10=4 4 In other words the point X=30 In other words the point X=30 is 4σ away From the mean on is 4σ away From the mean on –ve Side –ve Side Z= Zσ X −X __ σ •• X X TÜV SÜD South Asia 88 9/14/2007 .g. for a normal distribution E. for a normal distribution __ with X =70 and σ=10.Transform •• •• •• Z – Transform is used for a Z – Transform is used for a Normally Distributed process.The Z . Normally Distributed process.

Score •• If X was substituted by the If X was substituted by the Tolerance Limits (LSL & USL). with =70 and σ=10. This is the Sigma level or the This is the Sigma level or the Z Score Z Score E.Z=3 For USL=100.Z=3 30 Z= 4σ SL − X __ σ 3σ •• •• •• 70 100 TÜV SÜD South Asia 89 9/14/2007 . ZL=(30-70)/10=-4 ZL=(30-70)/10=-4 For USL=100.g. process. __ for normal distribution E. for normal distribution with X =70 and σ=10. LSL=30. Tolerance Limits (LSL & USL).The Z .g. Z will tell how many σs are Z will tell how many σs are there there between between Tolerance Tolerance Limits and the center of the Limits and the center of the process. LSL=30.

do we get the SAME amount of Every time we make a batch. do we get the SAME amount of Variation? Variation? Why does the process VARY from batch to batch? Why does the process VARY from batch to batch? Can we prevent Batch to Batch variation TOTALLY? Can we prevent Batch to Batch variation TOTALLY? Data from WHICH of these batches should be taken for Data from WHICH of these batches should be taken for calculating Z Score? calculating Z Score? How much data is SUFFICENT? How much data is SUFFICENT? If I Iget different Z Scores for data collected at different times If get different Z Scores for data collected at different times which of them is CORRECT? which of them is CORRECT? TÜV SÜD South Asia 90 9/14/2007 . •• •• •• •• •• •• Every time we make a batch.But Wait….

We can MINIMIZE this but not prevent it. We can MINIMIZE this but not prevent it. This means that process will have more variation in LONG This means that process will have more variation in LONG TERM when compared to SHORT TERM variation. The process varies from batch to batch due to MEAN SHIFT The process varies from batch to batch due to MEAN SHIFT over a period of time.Well •• •• •• •• •• Every time we make a batch. over a period of time. we may NOT get the same amount of Variation. A process is Six Sigma process when the short term Z Score A process is Six Sigma process when the short term Z Score is 6 is 6 TÜV SÜD South Asia 91 9/14/2007 . TERM when compared to SHORT TERM variation. we may NOT get the same Every time we make a batch. amount of Variation.

So Zlt = Zst-1.5 Approx.5 Mean Shift = 1. And Zst =Zlt+1.5σ Zlt = 6σ LSL Xlt Xst USL TÜV SÜD South Asia 92 9/14/2007 . And Zst =Zlt+1.5 observed to be 1.5 Approx. a period of time.Shot Term vs Long Term •• •• •• •• •• •• Mean of a process shifts over Mean of a process shifts over a period of time.5 Zlt =4.5 So Zlt = Zst-1.5σ Zlt = 4.5 Approx. This Shift is empirically This Shift is empirically observed to be 1. A Six Sigma Process has Zst A Six Sigma Process has Zst =6 =6 So a Six Sigma Process has So a Six Sigma Process has Zlt =4.5 Approx.

Capability vs Performance •• •• Zst represents the CAPABILITY of the process whereas Zlt Zst represents the CAPABILITY of the process whereas Zlt represents the PERFORMANCE over a period of time represents the PERFORMANCE over a period of time What is Capability? What is Capability? – Inherent ability – Inherent ability – Due to Common Causes of Variation – Due to Common Causes of Variation What is Performance? What is Performance? – Final Output – Final Output – Due to Common as well as Special Causes of variation – Due to Common as well as Special Causes of variation •• TÜV SÜD South Asia 93 9/14/2007 .

Causes of Variation •• Common Cause of Variation Common Cause of Variation – Are an intrinsic part of the process – Are an intrinsic part of the process – Give consistent Variation – Give consistent Variation – Affect each data point equally – Affect each data point equally – Are reflected in Unit to Unit Variation – Are reflected in Unit to Unit Variation •• Special Causes of Variation Special Causes of Variation – Are usually outside the process – Are usually outside the process – Appear some time and not at the other times – Appear some time and not at the other times – Affect some data points more than others – Affect some data points more than others – Are reflected in Time to time Variations – Are reflected in Time to time Variations TÜV SÜD South Asia 94 9/14/2007 .

– Excess Play in Slide due to wear over time. •• Special Causes of Variation Special Causes of Variation – Accident on Road – Accident on Road – Excess Play in Slide due to wear over time. – Illness – Illness – Variation due to Change in lot or supplier. – Variation due to Change in lot or supplier. TÜV SÜD South Asia 95 9/14/2007 . – Variation in dimensions in a lot manufactured together.Causes of Variation .Examples •• Common Cause of Variation Common Cause of Variation – Usual Traffic on Road – Usual Traffic on Road – Usual Play in the Slides of machine – Usual Play in the Slides of machine – Human Attentiveness – Human Attentiveness – Variation in dimensions in a lot manufactured together.

817 -5. Stable. A Stable Process has predictable variation.442 2.5 1 1 UCL=5. A Stable Process has predictable variation.0 _ _ X=0. the process is said to be Stable.0 Sample Mean 2 1 0 -1 -2 -3 -4 1 3 5 7 9 11 13 15 Sample 17 19 21 23 25 _ _ X=0.0 1 LCL=-4. Variation becomes unpredictable. A Stable process is also called aaprocess in “Control” A Stable process is also called process in “Control” Xbar Chart of Stable 5 4 3 Sample Mean Xbar Chart of Unstable UCL=4.700 7.5 LCL=-3.73 1 3 5 7 9 11 13 15 Sam ple 17 19 21 23 25 TÜV SÜD South Asia 96 9/14/2007 . Special causes disturb the stability of the process due to which the Special causes disturb the stability of the process due to which the Variation becomes unpredictable.Stability •• •• •• •• When the variation is only due to common causes.5 0.63 -2. the process is said to be When the variation is only due to common causes.98 5.

Control Charts are used to study stability Control Charts are used to study stability The first job of Six Sigma practitioner is to Identify and The first job of Six Sigma practitioner is to Identify and remove Special Causes of Variation. Capability has a meaning only when a process is stable. the next job is to Once the process is made predictable. when the process is stable. identify the causes of inherent variation and remove them. Improvement in the inherent variation can be made only Improvement in the inherent variation can be made only when the process is stable. remove Special Causes of Variation. first we need to stabilize the If a process is out of control. If a process is out of control. TÜV SÜD South Asia 97 9/14/2007 . process. first we need to stabilize the process. the next job is to identify the causes of inherent variation and remove them.Capability vs Stability •• •• •• •• •• •• Capability has a meaning only when a process is stable. Once the process is made predictable.

Calculating Capability •Capability Can be defined as Tolerable Variation Process Variation LSL X + 1σ USL X + 2σ USL − LSL Cp = 6σ TÜV SÜD South Asia X + 3σ T Cp = 6σ 9/14/2007 98 .

Calculating Capability • Marginal Capability LSL X + 1σ USL X + 2σ X + 3σ Cp = TÜV SÜD South Asia T 6σ 6σ Cp = 6σ 99 Cp = 1 9/14/2007 .

Calculating Capability • Six Sigma Capability LSL USL 3σ 3σ X + 3σ X + 6σ Cp = TÜV SÜD South Asia T 6σ Cp = 12σ 6σ 100 Cp = 2 9/14/2007 .

⎥ ⎢ 3σ 3σ ⎦ ⎣ TÜV SÜD South Asia 101 9/14/2007 .Calculating Capability • Calculate Cp from Upper & Lower Side ___ Cp L = ___ X − LSL 3σ CpU = USL − X 3σ ___ ___ X − LSL USL − X 0 2 4 6 8 10 12 14 16 18 20 Cp K __ ⎤ ⎡ __ X − LSL USL − X ⎥ = Min ⎢ .

⎢ 3σ 3σ ⎥ ⎣ ⎦ 102 9/14/2007 .Calculating Performance • Calculate Cp from Upper & Lower Side ___ PpL = ___ X − LSL 3σ PpU = USL − X 3σ ___ ___ X − LSL USL − X 0 2 4 6 8 10 12 14 16 18 20 USL − LSL Pp = 6σ TÜV SÜD South Asia __ ⎡ __ ⎤ X − LSL USL − X ⎥ PpK = Min ⎢ .

How is the Data collection Different? How is the Data collection Different? TÜV SÜD South Asia 103 9/14/2007 .Capability vs Performance USL − LSL Cp = 6σ __ ⎡ __ ⎤ X − LSL USL − X ⎥ Cp K = Min ⎢ . Sigma in Performance covers Long Term Variation. ⎢ 3σ 3σ ⎥ ⎣ ⎦ Pp = USL − LSL 6σ __ ⎡ __ ⎤ X − LSL USL − X ⎥ PpK = Min ⎢ . Sigma in Capability covers Short Term Variation. ⎢ 3σ 3σ ⎥ ⎣ ⎦ •• •• •• •• •• If the formula are same. what is the difference? The difference is in Sigma calculation! The difference is in Sigma calculation! Sigma in Capability covers Short Term Variation. what is the difference? If the formula are same. Sigma in Performance covers Long Term Variation.

Small Subgroups of data (Generally 3-7 sample size) are Small Subgroups of data (Generally 3-7 sample size) are taken. taken. Data points within a subgroup need to be of consecutive Data points within a subgroup need to be of consecutive output. It requires data collected over short period of time. It requires data collected over short period of time. Many subgroups are collected over a period of time. R σ= Sigma is calculated using d2 Sigma is calculated using Should be used only when process is stable Should be used only when process is stable TÜV SÜD South Asia 104 9/14/2007 .Capability Calculation •• •• •• •• •• •• •• •• Capability covers short term variation. present the inherent Variation. Many subgroups are collected over a period of time. Capability covers short term variation. The average variation within a subgroup is considered to be The average variation within a subgroup is considered to be __ present the inherent Variation. output.

Data should represent more than one day. than a month of variation. It required data collected over long period of time. Performance covers long term variation. The Root Mean Square variation is considered to to The Root Mean Square variation is considered to to represent the Overall Variation. data to represent all days and batches. if possible more than a month of variation. one may randomly sample the data to represent all days and batches. TÜV SÜD South Asia 105 9/14/2007 . period of time. It required data collected over long period of time. ⎛ __ ⎞2 represent the Overall Variation. if possible more Data should represent more than one day. ⎜ xi − X ⎟ Sigma is calculated using ⎠ Sigma is calculated using σ = ⎝ n −1 Should be used only when data is available over a long Should be used only when data is available over a long period of time. If Data points are too many. one may randomly sample the If Data points are too many.Performance Calculation •• •• •• •• •• •• •• Performance covers long term variation.

random sampling. or Stability is not known. Collect Short term data Collect Short term data using Subgroups. ⎥ 3σ 3σ ⎦ __ ⎤ − LSL USL − X ⎥ . ⎥ 3σ 3σ ⎦ __ __ •• If the process is Stable. Calculate Cpk and Calculate Cpk and Zst=3xCpk Zst=3xCpk If the process is Unstable If the process is Unstable or Stability is not known. using Subgroups.Capability.5 by Zst=Zlt+1.5 ⎤ ⎡ X − LSL USL − X ⎥ Z = Min ⎢ . Convert it into Short Term bench mark Z Short Term bench mark Z by Zst=Zlt+1. Collect Long term data by Collect Long term data by random sampling. Calculate Ppk and Calculate Ppk and Zlt=3xPpk. ⎥ ⎢ σ σ ⎦ ⎣ So ZLT=3 X Ppk •• & ZST=3 X CpK TÜV SÜD South Asia 106 9/14/2007 . Convert it into Zlt=3xPpk. Performance and Z Score ⎡ __ ⎢X = Min ⎢ ⎣ ⎡ __ X = Min ⎢ ⎢ ⎣ __ Cp K Pp K ⎤ − LSL USL − X ⎥ . If the process is Stable.

Z Score Calculation Road Map Select Y Attribute Y Normal Calculate DPU Un-Stable Process/ Not Known Stable Process Non Normal Capability Calculation Variable Y Non-Normal Calculate Zlt Calculate Zst Zst is the baseline Z score TÜV SÜD South Asia 107 9/14/2007 .

26857 & Standard deviation is 10. The 1. The mean of the data first 5 pieces for each of last 35 batches.54618. The data collected for the first 5 pieces for each of last 30 shifts. Data of Length in machining process has been collected. The Process has been behaving erratically for last 8 months. The data collected for behaving erratically for last 8 months. The data was collected for the first 5 pieces for each of last 35 batches. is 540. Data for Cycle Time of a molding process has been collected. The data was collected for the consistently for last 6 months. 2.54618. The specification is 60-65 sec. The mean of the the first 5 pieces for each of last 30 shifts. data is 64.Exercise-4 •• Calculate the Z Score for the following processes. Data of Length in machining process has been collected. Data for Cycle Time of a molding process has been collected.38606. 1. The Process has been behaving required length is 555 max.26857 & Standard deviation is 10.03827 & Standard deviation is 0. TÜV SÜD South Asia 108 9/14/2007 . The mean of the data is 540. 2. The Process has been The specification is 60-65 sec. The required length is 555 max. Calculate the Z Score for the following processes. The mean of the data is 64.38606. The Process has been behaving consistently for last 6 months.03827 & Standard deviation is 0.

Implementation of Six Sigma TÜV SÜD South Asia 109 9/14/2007 .

Phases of Breakthrough Strategy Phase I: Process Measurement Characterization Phase II: Process Analysis Phase III: Process Improvement Optimization Phase IV: Process Control TÜV SÜD South Asia 110 9/14/2007 .

FMEA. Control Plan & Capability Update Process Map.Phase of Breakthrough Strategy Phase I: Process Measurement Phase I: Process Measurement ••Identify KPIV’s and KPOV’s on Process Map/FMEA Identify KPIV’s and KPOV’s on Process Map/FMEA ••Establish Measurement System Capability Establish Measurement System Capability ••Establish Process Capability Baseline Establish Process Capability Baseline Phase II: Process Analysis Phase II: Process Analysis ••Update Process Map. FMEA. Control Plan & Capability ••Identify Critical Input Variable Identify Critical Input Variable ••Analyze Process data using Six Sigma Tools Analyze Process data using Six Sigma Tools Phase III: Process Improvement Phase III: Process Improvement ••Verify and optimize Critical Input Variables Verify and optimize Critical Input Variables ••Identify and Test Proposed Solutions Identify and Test Proposed Solutions ••Implement Solutions and Confirm Results Implement Solutions and Confirm Results Phase IV: Process Control Phase IV: Process Control ••Standardization //Mistake Proofing Standardization Mistake Proofing ••Implement Process Controls and Verify Effectiveness Implement Process Controls and Verify Effectiveness ••Monitor Process by Control Plan—HOLD the Gains Monitor Process by Control Plan—HOLD the Gains TÜV SÜD South Asia 111 9/14/2007 .

Phase I: Process Measurement Plan Project and Identify Key Process Metrics. PpK – SPC Charts – Sigma (Z) Calculations TÜV SÜD South Asia 112 9/14/2007 . Inputs and Outputs • Project Selection Justification • Business Metrics (RTY. PPM) • Process Mapping / Data Collection Process/Control Plan • Cause & Effect Matrix / FMEA Quantify Variation on Vital Few Variation Sources • 3 Level Pareto charts • Vital Few Variation Sources • Gage Studies (GR&R) Perform Short-term Capability Study • Short-term and Long-term Capability – CpK. COPQ.

Documenting Input Variables • Hypothesis Tests to Verify Critical Input Variables • List of Critical Input Variables • List of Containment Actions TÜV SÜD South Asia 113 9/14/2007 .Phase II: Process Analysis Update Project Baseline and Status • Project Status From • Metric Graph with Goal Line • Process Map / FMEA / Control Plan Identify Root Causes of Variation • Multi-Vari and Horizontal Root Cause Charts • SPC Charts • Fishbone Chart.

**Phase III: Process Improvement
**

Update Project Baseline and Status

• Project Status From • Metric Graph with Goal Line • Process Map / FMEA / Control Plan

Optimize Process

• Test and Verify Critical Input Variables • Use Statistical Tools to Optimize Process • Identify, Plan and Test Proposed Solutions • Select Solutions and Confirm Results • Implement Solutions and Improvement Plans • Document Improvement Plans and Actions

TÜV SÜD South Asia

114

9/14/2007

**Phase IV: Process Control
**

Update Project Baseline and Status

• Project Status From • Metric Graph with Goal Line • Process Map / FMEA / Control Plan

Optimize Process

• Each Standardization and Mistake Proofing • Implement Process Controls • Verify Effectiveness of Process Controls and System Improvements • Monitor Process by Control Plan • HOLD and GAINS

TÜV SÜD South Asia

115

9/14/2007

Statistical Problem Solving

Physical Problem

D

M

Statistical Problem

• • • •

Define the Problem in terms of Y and Probable Xs Measures the Extent of Problem Shortlist the Xs for analyses Collect Data Eliminate important Xs that are not

A

• • • •

Finalize Xs for Optimization Confirm the short listed Xs Find Y=f(X) or Best case for the selected Xs Identify Physical controls based on constraints Verify controls and Maintain new

Physical Solution

C

I

Statistical Solution

• •

TÜV SÜD South Asia

116

9/14/2007

THANK YOU TÜV SÜD South Asia 117 9/14/2007 .

- Read and print without ads
- Download to keep your version
- Edit, email or read offline

Are you sure?

This action might not be possible to undo. Are you sure you want to continue?

CANCEL

OK

You've been reading!

NO, THANKS

OK

scribd

/*********** DO NOT ALTER ANYTHING BELOW THIS LINE ! ************/ var s_code=s.t();if(s_code)document.write(s_code)//-->