1 © 2010 nkumbwa™. all rights reserved. six sigma strategy & management sir eng r. l....
TRANSCRIPT
1© 2010 Nkumbwa™. All Rights Reserved.
Six Sigma Strategy & ManagementSix Sigma Strategy & Management
Sir Eng R. L. Nkumbwa™Sir Eng R. L. Nkumbwa™www.nkumbwa.weebly.comwww.nkumbwa.weebly.com
2© 2010 Nkumbwa™. All Rights Reserved.
OutlineOutline
What is Six Sigma?What is Six Sigma? Phases of Six SigmaPhases of Six Sigma
DefineDefine MeasureMeasure Evaluate / AnalyzeEvaluate / Analyze ImproveImprove ControlControl
Design for Six SigmaDesign for Six Sigma Green Belts & Black BeltsGreen Belts & Black Belts
3© 2010 Nkumbwa™. All Rights Reserved.
A Vision and Philosophical commitment to our consumers to offer the highest quality, lowest cost products
A Metric that demonstrates quality levels at 99.9997% performance for products and processs
A Benchmark of our product and process capability for comparison to ‘best in class’
A practical application of statistical Tools and Methods to help us measure, analyze, improve, and control our process
What is Six Sigma?What is Six Sigma?
4© 2010 Nkumbwa™. All Rights Reserved.
What Six Sigma What Six Sigma is Notis Not
Just about statisticsJust about statistics A quality programA quality program Only for technical peopleOnly for technical people Used when the solution is knownUsed when the solution is known Used for “firefighting”Used for “firefighting”
5© 2010 Nkumbwa™. All Rights Reserved.
1.1. Reduces dependency on “Tribal Knowledge”Reduces dependency on “Tribal Knowledge”- Decisions based on facts and data rather than opinion- Decisions based on facts and data rather than opinion
2.2. Attacks the high-hanging fruit (the hard stuff)Attacks the high-hanging fruit (the hard stuff)- Eliminates chronic problems (common cause variation)- Eliminates chronic problems (common cause variation)- Improves customer satisfaction- Improves customer satisfaction
3.3. Provides a disciplined approach to problem solvingProvides a disciplined approach to problem solving- Changes the company culture- Changes the company culture
4.4. Creates a competitive advantage (or disadvantage)Creates a competitive advantage (or disadvantage)
5.5. Improves profits!Improves profits!
Why Companies Need Six SigmaWhy Companies Need Six Sigma
6© 2010 Nkumbwa™. All Rights Reserved.
99.9% is already VERY GOOD
But what could happen at a quality level of 99.9% (i.e., 1000 ppm),
in our everyday lives (about 4.6)?
• More than 30003000 newborns accidentally falling
from the hands of nurses or doctors each year
• 40004000 wrong medical prescriptions each year
• 400400 letters per hour which never arrive at their destination
• Two long or short landings at American airports each dayday
How good is good enough?How good is good enough?
7© 2010 Nkumbwa™. All Rights Reserved.
How can we get these results?How can we get these results?
1313 wrong drug prescriptions per year wrong drug prescriptions per year 1010 newborn babies dropped by doctors/nurses per year newborn babies dropped by doctors/nurses per year Two short or long landings Two short or long landings per yearper year in all the airports in the U.S. in all the airports in the U.S. OneOne lost article of mail per hour lost article of mail per hour
8© 2010 Nkumbwa™. All Rights Reserved.
Six Sigma as a MetricSix Sigma as a Metric
Sigma = = Deviation ( Square root of variance )
-7 -6 -5 -4 -3 -2 -1 0 1 2 3 4 5 6 7
Axis graduated in Sigma
68.27 %
95.45 %
99.73 %
99.9937 %
99.999943 %
99.9999998 %
result: 317300 ppm outside (deviation)
45500 ppm
2700 ppm
63 ppm
0.57 ppm
0.002 ppm
between + / - 1between + / - 2between + / - 3between + / - 4between + / - 5
between + / - 6
9© 2010 Nkumbwa™. All Rights Reserved.
Effect of 1.5 Sigma Process ShiftEffect of 1.5 Sigma Process Shift
10© 2010 Nkumbwa™. All Rights Reserved.
3 Sigma Vs. 6 Sigma3 Sigma Vs. 6 Sigma
The 3 sigma Company The 6 sigma Company
Spends 15~25% of sales dollars on cost of failure
Spends 5% of sales dollars on cost of failure
Relies on inspection to find defects Relies on capable process that don’t produce defects
Does not have a disciplined approach to gather and analyze data
Use Measure, Analyze, Improve, Control and Measure, Analyze, Design
Benchmarks themselves against their competition
Benchmarks themselves against the best in the world
Believes 99% is good enough Believes 99% is unacceptable
Define CTQs internally Defines CTQs externally
11© 2010 Nkumbwa™. All Rights Reserved.
Sigma and PPMSigma and PPM
2
3
4
5
6
308,537
66,811
6,210
233
3.4
PPM
Process Capability
Defects per Million Opportunities
Focusing on requires thorough process understanding and breakthrough thinkingFocusing on requires thorough process understanding and breakthrough thinking
0
10
20
30
40
50
60
70
80
1 2 3 4 5 6
Process Sigma
% C
ha
ng
e
0
100000
200000
300000
400000
500000
600000
700000
800000
PP
M
From 1 to 2
From 3 to 4
From 4 to 5
From 5 to 6
% ChangePPM
12© 2010 Nkumbwa™. All Rights Reserved.
Motorola ROI 1987-1994
• Reduced in-process defect levels by a factor of 200.
• Reduced manufacturing costs by $1.4 billion.
• Increased employee production on a dollar basis by 126%.
• Increased stockholders share value fourfold.
AlliedSignal ROI 1992-1996
• $1.4 Billion cost reduction.
• 14% growth per quarter.
• 520% price/share growth.
• Reduced new product introduction time by 16%.
• 24% bill/cycle reduction.
Six Sigma ROISix Sigma ROI
13© 2010 Nkumbwa™. All Rights Reserved.
General Electric ROI 1995-1998
• Company wide savings of over $1 Billion.
• Estimated annual savings to be $6.6 Billion by the year 2000.
Six Sigma ROISix Sigma ROI
14© 2010 Nkumbwa™. All Rights Reserved.
Six Sigma as a PhilosophySix Sigma as a Philosophy
Internal &ExternalFailure Costs
Prevention &Appraisal
Costs
Old Belief4C
ost
s
Internal &ExternalFailure Costs
Prevention &Appraisal
Costs
New BeliefCo
sts
4
5
6
Quality
Quality
Old Belief
High Quality = High Cost
New Belief
High Quality = Low Cost
is a measure of how much variation exists in a process
15© 2010 Nkumbwa™. All Rights Reserved.
““The fact is, there is more reality with this The fact is, there is more reality with this [Six Sigma] than anything that has come [Six Sigma] than anything that has come
down in a long time in business. The more down in a long time in business. The more you get involved with it, the more you’re you get involved with it, the more you’re
convinced.”convinced.”
Larry BossidyLarry Bossidy
CEO, HoneywellCEO, Honeywell
16© 2010 Nkumbwa™. All Rights Reserved.
OutlookOutlook Short termShort term Long termLong term
AnalysisAnalysis Point estimatePoint estimate VariabilityVariability
ToleranceTolerance Worst case designWorst case design RMSRMS
ProcessProcess TweakingTweaking SPCSPC
ProblemProblem FixingFixing PreventingPreventing
BehaviorBehavior ReactiveReactive ProactiveProactive
ReasoningReasoning ExperienceExperience StatisticsStatistics
AimAim OrganizationOrganization CustomerCustomer
DirectionDirection Seat of PantsSeat of Pants BenchmarkingBenchmarking
ImprovementImprovement AutomationAutomation OptimizationOptimization
IssueIssue ClassicalClassical Six Sigma Six Sigma
Six Sigma as a Strategic ToolSix Sigma as a Strategic Tool
17© 2010 Nkumbwa™. All Rights Reserved.
Six Sigma ToolsSix Sigma Tools
Process MappingProcess Mapping Tolerance AnalysisTolerance Analysis
Structure TreeStructure Tree Components SearchComponents Search
Pareto AnalysisPareto Analysis Hypothesis TestingHypothesis Testing
Gauge R & RGauge R & R RegressionRegression
Rational SubgroupingRational Subgrouping DOEDOE
BaseliningBaselining SPCSPC
18© 2010 Nkumbwa™. All Rights Reserved.
Project defined in Business Terms
Cross Functional Team Involvement
DMAIC Problem Strategy used
Qualitative and Statistical tools used
Sustained Business Results Achieved
What Does Six Sigma Look Like?What Does Six Sigma Look Like?
19© 2010 Nkumbwa™. All Rights Reserved.
Six Sigma PrinciplesSix Sigma Principles
Customer FocusCustomer Focus LeadershipLeadership Innovative and ProactiveInnovative and Proactive Boundary-lessBoundary-less World Class QualityWorld Class Quality Fact DrivenFact Driven Process ManagementProcess Management
20© 2010 Nkumbwa™. All Rights Reserved.
Breakthrough Strategy
Characterization Phase 2:Measure
Phase 3: Analyze
Optimization
Phase 4:Improve
Phase 5: Control
Projects are worked through these 5 main phases of the Six Sigma methodology.
Phase 1:Define
Problem Solving MethodologyProblem Solving Methodology
21© 2010 Nkumbwa™. All Rights Reserved.
Project CharterProject Charter
Business CaseBusiness Case Problem StatementProblem Statement Goal StatementGoal Statement Team MembersTeam Members Team Role & ResponsibilityTeam Role & Responsibility Action plan VS. budgetAction plan VS. budget
22© 2010 Nkumbwa™. All Rights Reserved.
Define PhaseDefine Phase
Define ProcessDefine Process Define Customer requirementDefine Customer requirement Prioritize Customer requirementPrioritize Customer requirement
23© 2010 Nkumbwa™. All Rights Reserved.
Define PhaseDefine Phase
SIPOC ModelSIPOC Model Kano AnalysisKano Analysis Customer SurveyCustomer Survey CTQ DiagramCTQ Diagram Customer Requirement AnalysisCustomer Requirement Analysis QFD QFD Literature ReviewLiterature Review Standard / Regulation ReviewStandard / Regulation Review
24© 2010 Nkumbwa™. All Rights Reserved.
Define PhaseDefine Phase
Project ReviewProject Review Project CharterProject Charter Business CaseBusiness Case Problem StatementProblem Statement Goal StatementGoal Statement Scope of processScope of process Prioritized customer requirementPrioritized customer requirement
25© 2010 Nkumbwa™. All Rights Reserved.
ReduceComplaints
(int./ext.)
ReduceCost
ReduceDefects
Problem Definitions need to be based onquantitative facts supported by analytical data.
Problem Definitions need to be based onquantitative facts supported by analytical data.
What are the Goals?
What do you want to improve? What is your ‘Y’?
Problem Definition
26© 2010 Nkumbwa™. All Rights Reserved.
To understand where you want to be, you need to know how to get there.v
To understand where you want to be, you need to know how to get there.v
Map the ProcessMap the Process
Measure the ProcessMeasure the Process
Identify the variables - ‘x’Identify the variables - ‘x’
Understand the Problem -’Y’ = function of variables -’x’
Y=f(x)
Understand the Problem -’Y’ = function of variables -’x’
Y=f(x)
27© 2010 Nkumbwa™. All Rights Reserved.
MeasureMeasureCharacterize Process
Understand ProcessEvaluateEvaluate
Improve and Verify ProcessImproveImprove
Maintain New ProcessControlControl
28© 2010 Nkumbwa™. All Rights Reserved.
DefineProblem
DefineProblem
UnderstandProcess
UnderstandProcess
CollectData
CollectData
ProcessPerformance
ProcessPerformance
Process Capability- Cp/Cpk- Run Charts
Understand Problem(Control or Capability)
Data Types- Defectives- Defects- Continuous
Measurement Systems Evaluation (MSE)
Define Process- Process Mapping
Historical Performance
Brainstorm Potential Defect Causes
Defect Statement
Project Goals
Measure Phase
29© 2010 Nkumbwa™. All Rights Reserved.
Measure PhaseMeasure Phase
Identify measurement and variationIdentify measurement and variation Determine data typeDetermine data type Develop data collection planDevelop data collection plan Perform measurement system analysisPerform measurement system analysis Perform data collectionPerform data collection Perform capability analysisPerform capability analysis
30© 2010 Nkumbwa™. All Rights Reserved.
Measure PhaseMeasure Phase
Effectiveness of existing processEffectiveness of existing process Efficiency of existing processEfficiency of existing process Calculate Sigma LevelCalculate Sigma Level Calculate Cost of poor qualityCalculate Cost of poor quality
31© 2010 Nkumbwa™. All Rights Reserved.
Measure PhaseMeasure Phase
SIPOC-RMSIPOC-RM CTQ-RCTQ-R Check SheetCheck Sheet MSAMSA Basic StatisticsBasic Statistics
GraphGraphRole Throughput YieldRole Throughput YieldProcess CapabilityProcess CapabilityDPMODPMOCOPQ CalculationCOPQ Calculation
32© 2010 Nkumbwa™. All Rights Reserved.
Measure PhaseMeasure Phase
Project ReviewProject Review Customer satisfactionCustomer satisfaction Effectiveness of processEffectiveness of process Efficiency of processEfficiency of process Base line sigma (Yield, DPMO, CPk)Base line sigma (Yield, DPMO, CPk) Cost of poor qualityCost of poor quality
33© 2010 Nkumbwa™. All Rights Reserved.
Baselining: Quantifying the goodness (or badness!) of the current process, before ANY improvements are made, using sample data. The key to baselining is collecting representative sample data
Sampling Plan- Size of Subgroups- Number of Subgroups- Take as many “X” as possible into consideration
Measure PhaseMeasure Phase
34© 2010 Nkumbwa™. All Rights Reserved.
Time
How do we know our process?
Process Map
Historical Data
Fishbone
35© 2010 Nkumbwa™. All Rights Reserved.
RATIONAL SUBROUPING Allows samples to be taken that include only white noise, within the samples. Black noise
occurs between the samples.
RATIONAL SUBROUPING Allows samples to be taken that include only white noise, within the samples. Black noise
occurs between the samples.
RATIONAL SUBGROUPSMinimize variation within subgroups
Maximize variation between subgroups
RATIONAL SUBGROUPSMinimize variation within subgroups
Maximize variation between subgroups
TIME
PR
OC
ES
S
RE
SP
ON
SE
WHITE NOISE (Common Cause Variation)
BLACK NOISE (Signal)
36© 2010 Nkumbwa™. All Rights Reserved.
Visualizing the Causes
st + shift = total
Time 1
Time 2
Time 3
Time 4
Within Group
•Called short term (st)
•Our potential – the best we can be
•The s reported by all 6 sigma companies
•The trivial many
37© 2010 Nkumbwa™. All Rights Reserved.
Visualizing the Causes
Between Groups
st + shift = total
Time 1
Time 2
Time 3
Time 4•Called shift (truly a measurement in sigmas of how far the mean has shifted)
•Indicates our process control
•The vital few
38© 2010 Nkumbwa™. All Rights Reserved.
Assignable CauseAssignable Cause
Outside influencesOutside influences Black noiseBlack noise Potentially controllablePotentially controllable How the process is actually performing over timeHow the process is actually performing over time
Fishbone
39© 2010 Nkumbwa™. All Rights Reserved.
Common Cause VariationCommon Cause Variation
Variation present in every processVariation present in every process Not controllableNot controllable The best the process can be within the present The best the process can be within the present
technologytechnology
40© 2010 Nkumbwa™. All Rights Reserved.
2Total = 2
Part-Part + 2R&R
Recommendation:
Resolution 10% of tolerance to measureGauge R&R 20% of tolerance to measure
• Repeatability (Equipment variation)Variation observed with one measurement device when used several times by one operator while measuring the identical characteristic on the same part.
• Reproducibility (Appraised variation)Variation Obtained from different operators using the same device when measuring the identical characteristic on the same part.
•Stability or DriftTotal variation in the measurement obtained with a measurement obtained on the same master or reference value when measuring the same characteristic, over an extending time period.
Gauge R&R
Part-PartR&R
41© 2010 Nkumbwa™. All Rights Reserved.
MeasureMeasureCharacterize Process
Understand ProcessEvaluateEvaluate
Improve and Verify ProcessImproveImprove
Maintain New ProcessControlControl
42© 2010 Nkumbwa™. All Rights Reserved.
Evaluate / Analysis PhaseEvaluate / Analysis Phase
Data AnalysisData Analysis Process AnalysisProcess Analysis Formulate HypothesisFormulate Hypothesis Test HypothesisTest Hypothesis
43© 2010 Nkumbwa™. All Rights Reserved.
Evaluate / Analysis PhaseEvaluate / Analysis Phase
Run chartRun chart HistogramHistogram Pareto chartPareto chart Scatter DiagramScatter Diagram Relation DiagramRelation Diagram CE DiagramCE Diagram Process AnalysisProcess Analysis Hypothesis TestingHypothesis Testing
Chi-squareChi-square T-Test T-Test ANOVA CorrelationANOVA CorrelationRegressionRegression
44© 2010 Nkumbwa™. All Rights Reserved.
Evaluate / Analysis PhaseEvaluate / Analysis Phase
Project ReviewProject Review
Validated root cause statementValidated root cause statement
45© 2010 Nkumbwa™. All Rights Reserved.
In many cases, the data sample can be transformed so that it is approximately normal. For example, square roots, logarithms, and reciprocals often take a positively skewed distribution and convert it to something close to a bell-shaped curve
46© 2010 Nkumbwa™. All Rights Reserved.
What do we Need?What do we Need?
LSL USL LSL USL
LSL USL
Off-Target, Low VariationHigh Potential DefectsGood Cp but Bad Cpk
On TargetHigh VariationHigh Potential DefectsNo so good Cp and Cpk
On-Target, Low VariationLow Potential DefectsGood Cp and Cpk
Variation reduction and process centering create processes with less potential for defects. The concept of defect reduction applies to ALL processes (not just manufacturing)
Variation reduction and process centering create processes with less potential for defects. The concept of defect reduction applies to ALL processes (not just manufacturing)
47© 2010 Nkumbwa™. All Rights Reserved.
Eliminate “Trivial Many”Eliminate “Trivial Many”
Qualitative Evaluation Technical Expertise Graphical Methods Screening Design of Experiments
Qualitative Evaluation Technical Expertise Graphical Methods Screening Design of Experiments
Identify “Vital Few”Identify “Vital Few”
Pareto Analysis Hypothesis Testing Regression Design of Experiments
Pareto Analysis Hypothesis Testing Regression Design of ExperimentsQuantify
Opportunity
Quantify Opportunity
% Reduction in Variation Cost/ Benefit
% Reduction in Variation Cost/ Benefit
Our Goal:Identify the Key Factors (x’s)
48© 2010 Nkumbwa™. All Rights Reserved.
Graph>Box plot
75%
50%
25%
Graph>Box plot
Without X values
DBP
Box plots help to see the data distribution
Day
DBP
10
9
10
4
99
94
109
104
99
94
Operator
DBP
10
9
10
4
99
94
Shift
DBP
10
9
10
4
99
94
49© 2010 Nkumbwa™. All Rights Reserved.
Statistical AnalysisStatistical Analysis
0.0250.0200.0150.0100.0050.000
7
6
5
4
3
2
1
0
New Machine
Fre
que
ncy
0.0250.0200.0150.0100.0050.000
30
20
10
0
Machine 6 mthsF
req
uenc
y
Is the factor really important?
Do we understand the impact for the factor?
Has our improvement made an impact
What is the true impact?
Hypothesis Testing
Regression Analysis
5545352515 5
60
50
40
30
20
10
0
X
Y
R-Sq = 86.0 %
Y = 2.19469 + 0.918549X
95% PI
Regression
Regression Plot
Compare
Sample
Means
& Variance
s
Identify
Relationsh
ips
Establis
h
Limits
Apply statistics to validate actions & improvements
50© 2010 Nkumbwa™. All Rights Reserved.
A- Poor Control, Poor Process
B- Must control the Process better, Technology is fine
C- Process control is good, bad Process or technology
D- World Class
A B
C D
TECHNOLOGY1 2 3 4 5 6
goodpoor
2.5
2.0
1.5
1.0
0.5CO
NTR
OL
shift
St
poor
good
51© 2010 Nkumbwa™. All Rights Reserved.
MeasureMeasureCharacterize Process
Understand ProcessEvaluateEvaluate
Improve and Verify ProcessImproveImprove
Maintain New ProcessControlControl
52© 2010 Nkumbwa™. All Rights Reserved.
Improvement PhaseImprovement Phase
Generate Improvement alternativesGenerate Improvement alternatives Validate ImprovementValidate Improvement Create “should be” process mapCreate “should be” process map Update FMEAUpdate FMEA Perform Cost/Benefit analysisPerform Cost/Benefit analysis
53© 2010 Nkumbwa™. All Rights Reserved.
Improvement PhaseImprovement Phase
Brain StormingBrain Storming CreativityCreativity Criteria WeightingCriteria Weighting Change Management toolsChange Management tools DOEDOE Cost/Benefit AnalysisCost/Benefit Analysis
54© 2010 Nkumbwa™. All Rights Reserved.
Improvement PhaseImprovement Phase
Project ReviewProject Review Validated pilot studyValidated pilot study Result of cost benefit analysisResult of cost benefit analysis Plan of control phasePlan of control phase
55© 2010 Nkumbwa™. All Rights Reserved.
Design of Experiments (DOE)Design of Experiments (DOE)
To estimate the effects of independent Variables on Responses.To estimate the effects of independent Variables on Responses.
TerminologyTerminology Factor Factor –– An independent variable An independent variable Level Level –– A value for the factor. A value for the factor. Response - OutcomeResponse - Outcome
X YPROCESS
56© 2010 Nkumbwa™. All Rights Reserved.
Why use DoE ?Why use DoE ?
Shift the average of a process.Shift the average of a process.
Reduce the variation.Reduce the variation.
Shift average and reduce variationShift average and reduce variation
x1 x2
57© 2010 Nkumbwa™. All Rights Reserved.
DoE TechniquesDoE Techniques
Full Factorial.Full Factorial.
2244 = 16 trials = 16 trials 2 is number of levels2 is number of levels 4 is number of factors4 is number of factors
• All combinations are tested.All combinations are tested.
• Fractional factorial can reduce number of trials from 16 Fractional factorial can reduce number of trials from 16
to 8.to 8.
58© 2010 Nkumbwa™. All Rights Reserved.
DoE TechniquesDoE Techniques
Fractional FactorialFractional Factorial
Taguchi techniquesTaguchi techniques
Response Surface MethodologiesResponse Surface Methodologies
Half fractionHalf fraction
59© 2010 Nkumbwa™. All Rights Reserved.
1. Define Objective.
2. Select the Response (Y)
3. Select the factors (Xs)
4. Choose the factor levels
5. Select the Experimental Design
6. Run Experiment and Collect the Data
7. Analyze the data
8. Conclusions
9. Perform a confirmation run.
Steps in Planning an ExperimentSteps in Planning an Experiment
60© 2010 Nkumbwa™. All Rights Reserved.
“….No amount of experimentation can prove me right; a single experiment can prove me wrong”.
“….Science can only ascertain what is, but not what should be, and outside of its domain value judgments
of all kinds remain necessary.”
- Albert Einstein
61© 2010 Nkumbwa™. All Rights Reserved.
MeasureMeasureCharacterize Process
Understand ProcessEvaluateEvaluate
Improve and Verify ProcessImproveImprove
Maintain New ProcessControlControl
62© 2010 Nkumbwa™. All Rights Reserved.
Control PhaseControl Phase
Develop control strategyDevelop control strategy Develop control planDevelop control plan Update procedure and training planUpdate procedure and training plan Monitor resultMonitor result Corrective action as neededCorrective action as needed
63© 2010 Nkumbwa™. All Rights Reserved.
Control PhaseControl Phase
Control chartControl chart
64© 2010 Nkumbwa™. All Rights Reserved.
Control PhaseControl Phase
Project ReviewProject Review ProcedureProcedure Work instructionWork instruction Full implementationFull implementation Control chart of resultControl chart of result
65© 2010 Nkumbwa™. All Rights Reserved.
Control PhaseControl Phase
Control Phase Activities:
- Confirmation of Improvement- Confirmation you solved the practical problem- Benefit validation- Buy into the Control plan- Quality plan implementation- Procedural changes- System changes- Statistical process control implementation- “Mistake-proofing” the process- Closure documentation- Audit process- Scoping next project
66© 2010 Nkumbwa™. All Rights Reserved.
Control PhaseControl Phase
How to create a Control Plan:
1. Select Causal Variable(s). Proven vital few X(s)2. Define Control Plan - 5Ws for optimal ranges of X(s)3. Validate Control Plan - Observe Y4. Implement/Document Control Plan5. Audit Control Plan6. Monitor Performance Metrics
67© 2010 Nkumbwa™. All Rights Reserved.
Control PhaseControl Phase
Control Plan Tools:
1. Basic Six Sigma control methods. - 7M Tools: Affinity diagram, tree diagram, process decision program charts, matrix diagrams, interrelationship diagrams, prioritization matrices, activity network diagram.
2. Statistical Process Control (SPC) - Used with various types of distributions - Control Charts
•Attribute based (np, p, c, u). Variable based (X-R, X)•Additional Variable based tools
-PRE-Control-Common Cause Chart (Exponentially Balanced Moving Average (EWMA))
68© 2010 Nkumbwa™. All Rights Reserved.
Control PhaseControl Phase
Control Plan Tools:
1. Basic Six Sigma control methods. - 7M Tools: Affinity diagram, tree diagram, process decision program charts, matrix diagrams, interrelationship diagrams, prioritization matrices, activity network diagram.
2. Statistical Process Control (SPC) - Used with various types of distributions - Control Charts
•Attribute based (np, p, c, u). Variable based (X-R, X)•Additional Variable based tools
-PRE-Control-Common Cause Chart (Exponentially Balanced Moving Average (EWMA))
69© 2010 Nkumbwa™. All Rights Reserved.
How do we select the correct Control Chart:
Type Data
Ind. Meas. or subgroups
Normally dist. data
Interest in sudden mean changes
Graph defects of defectives
Oport. Area constant from sample to sample
X, Rm
p, np
X - RMA, EWMA or CUSUM and Rm
u
C, u
Size of the subgroup constant
p
If mean is big, X and R are effective too
Ir neither n nor p are small: X - R, X - Rm are effective
More efective to detect gradual changes in long term
Use X - R chart with modified rules
VariablesAttributes
Measurement of subgroupsIndividuals
Yes
No No
Yes
Yes
No
Yes
No
Defects Defectives
Control PhaseControl Phase
70© 2010 Nkumbwa™. All Rights Reserved.
71© 2010 Nkumbwa™. All Rights Reserved.
1. PRE-Control•Algorithm for control based on tolerances•Assumes production process with measurable/adjustable quality characteristic that varies.•Not equivalent to SPC. Process known to be capable of meeting tolerance and assures that it does so.•SPC used always before PRE-Control is applied.•Process qualified by taking consecutive samples of individual measurements, until 5 in a row fall in central zone, before 2 fall in cautionary. Action taken if 2 samples are in Cau. zone.•Color coded
YELLOW ZONE
GREEN ZONE
YELLOW ZONE
RED ZONE
RED ZONE
1/4 TOL. 1/2 TOL. 1/4 TOL.
Low
Tol
eran
ce
Lim
t
Tol
eran
ce
Lim
t
Hig
h
Ref
eren
ce L
ine
PR
E-C
ontr
ol
DIM
EN
SIO
N
NO
MIN
AL
Ref
eren
ce L
ine
PR
E-C
ontr
ol
Additional Variable-Based ToolsAdditional Variable-Based Tools
72© 2010 Nkumbwa™. All Rights Reserved.
2. Common Causes Chart (EWMA).•Mean of automated manufacturing processes drifts because of inherent process factor. SPC consideres process static.•Drift produced by common causes.•Implement a “Common Cause Chart”.•No control limits. Action limits are placed on chart.
•Computed based on costs•Violating action limit does not result in search for special cause. Action taken to bring process closer to target value.
•Process mean tracked by EWMA •Benefits:
•Used when process has inherent drift•Provide forecast of where next process measurement will be.•Used to develop procedures for dynamic process control
•Equation: EWMA = y^t + (yt - y^t) between 0 and 1
Additional Variable-Based ToolsAdditional Variable-Based Tools
73© 2010 Nkumbwa™. All Rights Reserved.
• Improvement fully implemented and process re-baselined.• Quality Plan and control procedures institutionalized.• Owners of the process: Fully trained and running the process.• Any required documentation done.• History binder completed. Closure cover sheet signed.• Score card developed on characteristics improved and reporting method defined.
Project ClosureProject Closure
74© 2010 Nkumbwa™. All Rights Reserved.
Customer-driven design of processes with 6 capability.
Predicting design quality up front.
Top down requirements flowdown (CTQ flowdown) matched by capability flowup.
Cross-functional integrated design involvement.
Drives quality measurement and predictability improvement in early design phases.
Utilizes process capabilities to make final design decisions.
Monitors process variances to verify 6 customer requirements are met.
What is Design for Six Sigma (DFSS)?What is Design for Six Sigma (DFSS)?
75© 2010 Nkumbwa™. All Rights Reserved.
DFSS Methodology & ToolsDFSS Methodology & Tools
Define Measure Analyze Design Verify
Under-standcustomerneeds andspecifyCTQs
Developdesignconceptsand high-level design
Developdetaileddesign andcontrol/testplan
Testdesign andimplementfull-scaleprocesses
Initiate, scope,and plan theproject
DESIGN FOR SIX SIGMA
DELIVERABLES
TeamCharter
CTQs High-levelDesign
DetailedDesign
Pilot
TOOLS
Mgmt Leadership Customer ResearchFMEA/Errorproofing
Project QFD Process SimulationManagement Benchmarking Design Scorecards
76© 2010 Nkumbwa™. All Rights Reserved.
Design for Six SigmaDesign for Six Sigma
Pre-DEFINE PhasePre-DEFINE Phase
Introduction to Six SigmaIntroduction to Six Sigma DFSS / New Product Introduction (NPI) ProcessDFSS / New Product Introduction (NPI) Process
Strategic visionStrategic vision Logical chain of product conceptsLogical chain of product concepts Product evolution roadmapProduct evolution roadmap
77© 2010 Nkumbwa™. All Rights Reserved.
DEFINE PhaseDEFINE Phase
Establish Design Project Financial Analysis Project Management and Risk Assessment
Design for Six SigmaDesign for Six Sigma
78© 2010 Nkumbwa™. All Rights Reserved.
MEASURE PhaseMEASURE Phase
Establish CTQ’s and CTI’s Design problem documentation Design expectations Probability, Statistics, and Prediction MSA (Variables, Attribute and Data quality) Process Capability (Variables and Attribute) Risk Assessment Failure prediction Design Scorecard
Design for Six SigmaDesign for Six Sigma
79© 2010 Nkumbwa™. All Rights Reserved.
ANALYZE/HIGH-LEVEL DESIGN PhaseANALYZE/HIGH-LEVEL DESIGN Phase
Develop Design Alternatives Description of design options (alternatives) Analysis of design alternatives for technological barriers and
contradictions Develop High Level Design (VA/VE) Multi-Variable Analysis Confidence Intervals & Sampling Hypothesis Testing Evaluate High Level Design Failure analysis and prediction
Design for Six SigmaDesign for Six Sigma
80© 2010 Nkumbwa™. All Rights Reserved.
DETAIL DESIGN PhaseDETAIL DESIGN Phase
Risk Assessment Failure analysis Taguchi Methods Tolerancing DOE with RSM
Design for Six SigmaDesign for Six Sigma
81© 2010 Nkumbwa™. All Rights Reserved.
DETAIL DESIGN Phase (cont’d)DETAIL DESIGN Phase (cont’d)
Reliability and Availability Non-Parametric Statistics Simulation with Monte Carlo Methods Design for Manufacturability/Assembly DVT/Testability Design Scorecard
Design for Six SigmaDesign for Six Sigma
82© 2010 Nkumbwa™. All Rights Reserved.
DETAIL DESIGN Phase DETAIL DESIGN Phase
Concurrent Engineering Software Engineering Tools
(CMM, CASE)
ENHANCED DESIGN FOR:Commercial/Competitive SuccessManufacturabilityServiceabilityReliabilityAvailabilityInformation ManagementControl
Design for Six SigmaDesign for Six Sigma
83© 2010 Nkumbwa™. All Rights Reserved.
VERIFY PhaseVERIFY Phase
Design for Control Design for Mistake Proofing Statistical Process Control (SPC) MVT Transition to Process Owners Logical sequence of new scenarios Strategic knowledge base and patent portfolio Targeted competitive intelligence New product evolutionary stages Project Closure
Design for Six SigmaDesign for Six Sigma
84© 2010 Nkumbwa™. All Rights Reserved.
VERIFY Phase -- continued VERIFY Phase -- continued
– Pilot Testing– Full-Size Scale Up and Commercialization– Design Information and Data Management– Lean Manufacturing
Design for Six SigmaDesign for Six Sigma
85© 2010 Nkumbwa™. All Rights Reserved.
Con-sumer Cue
Technical Requirement
Preliminary Drawing/Database
Identity CTQs
Identify Critical Process
Obtain Data on Similar Process
Calculate Z values
Rev 0 Drawings
Stop Adjust process & design
1st piece inspection
Prepilot Data
Pilot data
Obtain dataRecheck ‘Z’ levels
Stop Fix process & design
Z<3
Z>= Design Intent M.A.I.C
M.A.DSix Sigma Design Process
86© 2010 Nkumbwa™. All Rights Reserved.
PRODUCT MANAGEMENT
OVERALL GOAL OF
SOFTWARE
KNOWLEDGE OF COMPETITORS
SUPERVISION
PRODUCT DESIGN
PRODUCT MANAGEMENT
PRODUCT DESIGN
PRODUCT MANAGEMENT
INNOVATION
OUTPUT
DIRECTORY ORGANIZATION
INTUITIVE ANSWERS
SUPPORT
METHODS TO MAKE EASIER FOR USERS
CHARACTERISTICS:
• Organizing ideas into meaningful categories
• Data Reduction. Large numbers of qual. Inputs into major dimensions or categories.
AFFINITY DIAGRAM
87© 2010 Nkumbwa™. All Rights Reserved.
MATRIX DIAGRAM
Pat
ient
sch
edul
ed
Att
enda
nt a
ssig
ned
Att
enda
nt a
rriv
es
Obt
ains
equ
ipm
ent
Tra
nspo
rts
patie
nt
Pro
vide
The
rapy
Not
ifies
of
retu
rn
Att
enda
nt a
ssig
ned
Att
enda
nt a
rriv
es
Pat
ient
ret
urne
d
Arrive at scheduled time 5 5 5 5 1 5 0 0 0 0 0Arrive with proper equipment 4 2 0 0 5 0 0 0 0 0 0Dressed properly 4 0 0 0 0 0 0 0 0 0 0Delivered via correct mode 2 3 0 0 1 0 0 0 0 0 0Take back to room promptly 4 0 0 0 0 0 0 5 5 5 5
IMPORTANCE SCORE 39 25 25 27 25 0 20 20 20 20RANK 1 3 3 2 3 7 6 6 6 6
5 = high importance, 3 = average importance, 1 = low importance
HOWS
WHATS
RELATIONSHIP MATRIX
CUSTOMER IMPORTANCE MATRIX
88© 2010 Nkumbwa™. All Rights Reserved.
Add f
eatu
res
Make e
xis
ting p
roduct
faste
r
Make e
xis
ting p
roduct
easie
r to
use
Leave a
s-is a
nd low
er
price
Devote
resourc
es t
o n
ew
pro
ducts
Incre
ase t
echnic
al support
budget
Out
arr
ow
s
In a
rrow
s
Tota
l arr
ow
s
Str
ength
Add features 5 0 5 45Make existing product faster 2 1 3 27Make existing product easier to use 1 2 3 21Leave as-is and lower price 0 3 3 21Devote resources to new products 1 1 2 18Increase technical support budget 0 2 2 18
(9) = Strong Influence
(3) = Some Influence
(1) = Weak/possible influence
Means row leads to column item
Means column leads to row item
COMBINATION ID/MATRIX DIAGRAM
CHARACTERISTICS:
•Uncover patterns in cause and effect relationships.
•Most detailed level in tree diagram. Impact on one another evaluated.
89© 2010 Nkumbwa™. All Rights Reserved.
Green Belts & Black BeltsGreen Belts & Black Belts
GE has very successfully instituted this programGE has very successfully instituted this program 4,000 trained Black Belts by YE 19974,000 trained Black Belts by YE 1997 10,000 trained Black Belts by YE 200010,000 trained Black Belts by YE 2000 ““You haven’t much future at GE unless they are selected to You haven’t much future at GE unless they are selected to
become Black Belts” - Jack Welchbecome Black Belts” - Jack Welch Kodak has instituted this programKodak has instituted this program
CEO and COO driven processCEO and COO driven process Training includes both written and oral examsTraining includes both written and oral exams Minimum requirements: a college education, basic statistics, Minimum requirements: a college education, basic statistics,
presentation skills, computer skillspresentation skills, computer skills Other companies include:Other companies include:
Allied SignalAllied Signal -Texas Instruments-Texas Instruments IBMIBM - ABB- ABB NavistarNavistar - Citibank- Citibank
90© 2010 Nkumbwa™. All Rights Reserved.
TaskTaskTime on Time on Consulting/Consulting/
TrainingTrainingMentoringMentoring
Related Related ProjectsProjects
Green BeltGreen Belt Utilize Utilize Statistical/Quality Statistical/Quality techniquetechnique
2%~5%2%~5%Find one new Find one new green beltgreen belt
2 / year2 / year
Black BeltBlack Belt
Lead use of Lead use of technique and technique and communicate new communicate new onesones
5%~10%5%~10% Two green beltsTwo green belts 4 / year4 / year
Master Master Black BeltBlack Belt
Consulting/Consulting/Mentoring/Mentoring/TrainingTraining
80~100%80~100% Five Black BeltsFive Black Belts 10 / year10 / year
Green Belts & Black BeltsGreen Belts & Black Belts
91© 2010 Nkumbwa™. All Rights Reserved.
““It is reasonable to guess that the next It is reasonable to guess that the next CEO of this company, decades down the CEO of this company, decades down the road, is probably a Six Sigma BB or MBB road, is probably a Six Sigma BB or MBB
somewhere in GE right now…”somewhere in GE right now…”
Jack WelchJack Welch
Ex-CEO, GEEx-CEO, GE