1、6 簡介,6 SIGMA 起源及主要概念6 SIGMA 組織及人員認證基本統計應用執行主要步驟 D-M-A-I-CCase Study,QRA : 2001/8/27,The Origins of SixSigmaIt originated in the 1980s as Motorola responded to the threat of Japanese competition which had far lower defective rates. The approach spread to AlliedSignal and to General Electric, whose Ch
2、ief Executive Officer, Jack Welch, has been the most passionate advocate of SixSigma. Since introducing it worldwide in 1996, GE has made over $1 billion of cost savings.,1979 年 ，當時 Motorola一位資深業務主管 Arthur Sundry 在高階主管會議上說：Our quality levels really stink ! Six Sigma Quality Program 此名稱乃為 Motorola工程師
3、 Bill Smith所建議，為Robert Galvin所採納。,何謂 6-Sigma ?,Motorola :,衡量指標標竿研究願景Philosophy方法工具符號目標價值,s,3.4,.,s,DPMO,可用以計算與衡量任何流程,Sigma 之另一稱呼為標準差,2000年達成 6-Sigma水準4, 1996 - Jack Welch,變成我們文化的一部份 - 成為我們生活的一部份.,59,Where Does “Six Sigma” Come From?,Mikel J. Harry one of the Original Architects Previously Headed Qua
4、lity Function at ABB and Motorola Now President/CEO of Six Sigma Academy in Phoenix, Arizona Has Consulted for Texas Instruments, Allied Signal (and others) Currently Retained by GE to Teach the Implementation, Deployment and Application of Six Sigma Concepts & Tools,Learning from Those Who Have had
5、 SuccessWith 6Will Accelerate its Implementation at GE,What Does “Sigma” Mean?,Sigma is a Measure of the Consistency of a Process,It (is Also the 18th Letter in the Greek Alphabet!,Motorola公司認為數據是滿足顧客的關鍵，他 們常說：1.如無法用數據表示我們所知的,那麼我們對它 所知不多 (If we cannot express what we know in numbers, we dont know mu
6、ch about it)2.如果對它所知不多，就無法控制它 (If we dont know much about it, we cannot control it)3.如果我們不能控制它，那只有靠運氣了 (If we cannot control it, we are at the mercy of chance),Why “Six Sigma”?,Proven Successful in “Quality-Demanding” Industries e.g., Motorola, Texas Instruments (many process steps in series)Proven
7、Method to Reduce CostsHighly Quantitative Method Science and Logic Instead of Gut FeelIncludes Manufacturing & Service (close to customer) and Provides Bridge to Design for Quality ConceptsHas Support and Commitment of Top Management,It Works!,6有多小?,Sigma,PPM,0.002,0.5742,63.37,2,700,45,500,317,310,
8、面積,一般教室2倍,約6甲地,約30個天安門廣場,略大於台北市,東莞市,台灣省的面積,時間,1 秒鐘,4.8 分鐘,9 小時,半個月,約 9 個月,5 年,6-Sigma 狹隘解釋 - DPPM,6 Overview,6 is Several Orders of Magnitude Better Than 3!,Sigma: A Measure of Quality,6的品質水準,0.002 DPPM , Cp=2,中心值1.5的偏移,3.4 DPPM, Cpk=1.5,或用 DPMO (Defects Per Million Opportunities)表示,偏移1.5,在動態的真實世界中，
9、每一件事都在不停的變化著溫度溼度工具的磨耗原料的差異 .1.5乃由機率、估計、經驗而來,參考資料:Evans, D.H. (1975) : Statistical Tolerancing : The State of the Art, Part III. Shifts and Drifts.,6的四個假設,常態分配1.5偏移和已知缺點乃隨意分佈，且不同零件製程相互獨立,品質改善的流程,1. 定義產品或服務2. 鑑定顧客及其需求3. 列出滿足顧客需求所需之條件4. 定義(規劃)流程5. 防範流程錯誤並消除浪費6. 確保持續改善,廣義解釋 - 流程改善(改造)/設計,Six-Sigma 如何創造不
10、一樣局面 ?,願景 (Vision)哲學 (Philosophy) 積極目標 (Aggressive goal) 量化指標 (Metric, standard of measurement)方法 (Method) 工具用於: 顧客焦點 (Customer focus)突破性改善 (Breakthrough improvement)持續改善 (Continuous improvement)人員參與 (People Involvement),Six-Sigma 願景,Six-Sigma 的願景是將我們所做的每一件事, 透過達成Six-Sigma水準的表現, 交付世界級品質產品或服務以取悅客戶.,S
11、ix-Sigma 哲學,Six-Sigma 哲學是應用結構化、系統化觀點於我們事業各嶺域達成突破性改善,推行 6-Sigma 之必要條件重點攻擊與變格管理相聯接依核心流程(非功能) 組織 黑帶或碩士級黑帶 儘量聯接與事業相關重點, 共同與言追求即早勝利 (大且易見)支持基礎結構/追溯系統改變衡量系統以更有效推動專案行動 選擇與工作直接相關專案 高層參與- 克服障礙,品質改善的流程,1. 定義產品或服務2. 鑑定顧客及其需求3. 列出滿足顧客需求所需之條件4. 定義(規劃)流程5. 防範流程錯誤並消除浪費6. 確保持續改善,Six-Sigma 整合改善、設計與績效管理方法論,Six-Sigma
12、所使用的三個主要方法論: 流程改善(DMAIC)、流程設計與再設計(DFSS)與績效管理,DMAIC用以改善現有流程、產品、服務、設計等等DFSS用以產生新的流程、產品、服務、設計等等績效管理是一個系統用以將策略連接戰術、設定優先順序、資源整合持續達成DMAIC與DFSS目標,流程改善方法論,流程設計與再設計方法論,績效管理 方法論,產品變異的來源,設計 製程材料元件,6 品質方案的架構,5 階段問題分析解決流程 (DMAIC),提高目標,另一主題,第一階段 第二階段 第三階段 第四階段 第五階段,管 制(Control),改 善(Improve),分 析(Analyze),衡 量(Measu
13、re),定 義(Define),選擇專案成立專案小組確認 CTQs Y,定義衡量指標 ($ ?)衡量系統驗證,定義不良基準線設定目標確認 X,重點少數 xs效果測試 (Pilot Soln) Y = f(x),確認效果 持續性,So.What is Six Sigma?,“THE SIX SIGMA BREAKTHROUGH STRATEGY”,DMAIC,Key CustomerOpportunity to grow or threat of loss,Is the customer telling us when the issue is?,Six Sigma Project Identi
14、fied,Define-Scope it,Measure-How are we doing,Improve-Implement,Control-Make sure it sticks,Problem has quick fix?,Fix it!,Analyze-Root Cause,Preliminary look at how we think we are doing,Set up customer meeting,Define/Refine CTQs Whats important to them?,How are we doing on these CTQs,How can we im
15、prove?,Six Sigma Is A Growth Tool,YES,YES,NO,NO,D,M,A,I,C,Customer Improvement Continuous Growth,Six-Sigma 架構,MOA(Market OpportunityAnalysis),事業策略展開Business Strategy Deployment,推行組織 (Implementing Organization),跨功能團對合作Cross-functional Teaming,(Gaining Commitment),(Culture Change),(Information Tech),(
16、Training Systems),確認關鑑業務流程Identifying Critical Business Processes,專案選擇與審查(Project Selection & Charting),專案管理(Project Management),DFSS Flow (Design for Six-Sigma),DMAIC Flow,意識(Awareness),統計工具(Statistical Tools),管理工具(Management Tools),推廣(Promotion),6-Sigma 基礎架構,市場機會分析,全體承諾,訊息科技,文化改變,訓練體系,Structure,6
17、Projects with the GE Businesses,Champions or Leaders are those senior managers who will ensure that resources are available for training and projects, and who will be involved in project reviews.,Champion,Master Blackbelt,Blackbelt,Greenbelt,扮 演 角 色,綠帶/黑帶(GB/BB),碩士黑帶(MBB),負專案全責 - 黑帶(專職)/ 綠帶(兼職)專注於1-
18、2專案小組依專案特性挑選出,流程盟主(Process Champion),專職之職位協助多個專案小組開發導入專家資源,管理之責任專注於一個關鍵流程或次流程被BU流程改造委員會依流程 性質而選出,專案小組領導技巧專案管理技巧問題分析與解決技巧,跨功能工作經驗分析/技巧專長流程之指導/監督/教育技能,負責流程功能/目標達成/維持 關鍵項目之管制/主導定期流 程審查負責跨功能介面問題與議題 之解決,跨功能認識與了解溝通/談判技巧原因分析技能專案小組領導技巧,負責專案進度/小組工作計劃, 並將之與管理層級聯接開發衡量與管制系統 (如, 資 料蒐集計劃/流程管制表等),開發BB/帶動專案小組成功/ 提供
19、流程改善與統計技巧的 專長亦可能被指派加入流程管理 小組,專長,職責,敘述,選擇核心專案小組成員訣竅 (core team) *理想人數 : 57人*訓練展開之前先選定小組成員與黑帶, 再讓這些人一起受訓*取得各階主管支持的承諾*流程盟主最好來自事業部流程改造委員會, 以利溝通與學習*專案執行期間,專案小組成員花在專案的時間可至每週 20小時 - 每週小組會議為 4 6 小時 - 每週改善專案為 10 16 小時*改善專案包括延伸小組成員, 包括事業部財務代表與其他重要資 源,Sub-Process Owners,Process Owner,Process Team,MBB,Process C
20、hampion,Members,BB (GB),Improvement Team,MBB,Process Management Teams,Improvement/Design Projects,BU 6-Sigma Council,Process Management System & Organization,Process,Roles & Responsibilities,Measurement,Process Review,Linking & Leveraging,Process Champion,35,6 個 Sigma 管理 ( 6 Program) 理念: 品質是由企業文化改變出
21、來的 策略: 創新(Innovation)/突破 (Breakthrough)/組織運作 /衡量(measures) 例 :流程簡化 (Simplification) 重點: 企業文化塑造/大量資源投入改造/有效量化執行成果 (KPIs $ ),基本統計分析工具,常態分配(Normal Distribution)變異數與標準差(Variance & Sigma)特性要因圖(Cause and Effect Diagrams)品質機能展開 (QFD)量測系統分析(Gauge R & R)實驗計畫(DOE) 變異數分析(ANOVA)相關與回歸分析(Correlation & Regression)
22、管制圖(Control Chart)電腦應用程式(Computer software),常態分配(Normal Distribution),標準差一群觀察值與平均數之差，稱為離均差，各離均差之平方的平均數（即變異數）再予開方所得即為標準差。,Z - Scale of Measure,Z,=,A Unit of Measure Equivalent to the Number of StandardDeviations that a Value is Awayfrom the Target Value,-3.0,-0.5,3.0,Z - Values,USL,LSL,2.5,0.5,3.0,=
23、Process Mean,Z,T,Target,0,A 3 Process,Problem Solving Approach,6Helps us Identify and Reduce VARIATION due to: - Insufficient Process Capability - Unstable Parts & Materials - Inadequate Design Margin,Define,What do we want to know ? - What is our problem ? - What is our defect ?,Practical Problem P
24、roject CTQs Solid Y, Spec Definition, and Defect Definition Building a Justifiable Business Case Approved Charter (R0),What did we learn Do we have a viable project ?,特性要因圖,The % Variation Due to the Measurement MethodGAGE R & R,GAGE:The instrument used for making Measurements that we want to valida
25、te.,REPEATABILITY:Does the same operator get the same results When measuring the same part several times?,REPRODUCIBILITY:Do different operators get the same results when measuring the same part several times?,CAUTION: ACalibration Sticker does not imply that Gage R&R is acceptable!,Measure,What do
26、we want to know ?,Statistical Problem Project Y, Spec Definition, and Defect Definition Gage R&R on Y Data Process Map L1 to Show Z Values with Link to Financials Rationalization for Focused Y Descriptive Statistics for Focused Y,What did we learn Mean problem ? Variance ? Both ?,時 間,GOOD,BAD,3 Sigm
27、a,6 Sigma,Breakthrough Improvement,Six-Sigma突破,表現,如果我們充份瞭解與掌握 X, 為何我們要持續測試與檢驗 Y?,Y相依 (Dependent)輸出 (Output)結果 (Effect)不良結果 (Symptom)監測 (Monitor),X1 . . . Xn互相獨立 (Independent)輸入 (Input-Process)原因 (Cause)問題 (Problem)控制 (Control),為了獲得好的結果, 我們是否要專注於 Y 或 X 的行為 ?,f (X),Y=,專注於 X 而非 Y,Six Sigma焦點,CTQs(成本, 品
28、質, 交期, 顧客滿意度)每單位缺點數複雜度DPPMRolled Thruput YieldSix-Sigma 分數流程底限 (Baseline)流程標竿 (Benchmarking)KPOVsKPIVs偏移與漂移 (Shift & Drift),Six-Sigma衡量指標,現有衡量指標,良率RMA數量返修數量顧客抱怨數?,Leadership Must Ask the Right QuestionsWhat Gets Measured Gets Managed,Six-Sigma 衡量指標 (Metrics),Six-Sigma 衡量指標 - 定 義,CTQs:重要顧客滿意參數. 通常包括
29、品質,成本,交期等.KPOVs:關鍵流程輸出變數 (Key Process Output Variables). 流程中由 KPIVs反應矯正措施之結果KPIVs:關鍵流程輸入變數 (Key Process Input Variables). 直接與其他KPIVs相關, 影響改變流程輸出之變數,Changing Focus From Output to Process,Identifying and Fixing Root Causes Will Help us Obtain the Desired Output,f (X),Y =,Some Basic 6-Related Tools,Sca
30、tter Diagram,Over Slept,Car Would Not Start,Weather,Family Problems,Other,Pareto Diagram,Frequency ofOccurrence,Reasons for Being Late for Work,Arrival Timeat Work,Time Alarm Went Off,Analyze,What do we want to know ?,Statistical Problem Understood Link Process Map to Fishbone w/C, N, X Labeling Ens
31、ure Data is Collected for All Xs Drill Down to Vital Few Xs via ANOVA, GLM, T-test, F-test List of Vital Few Xs Quantified Financial Opportunities,What did we learn What were the causal Xs ? How did we identify them ?,PM/CE/CNX/SOP,Process Mapping,Why?,* Process visual foundation for current situati
32、on and analysis Aids in identifying bottlenecks, redundancies and waste Look for Non Value Add Look for Variables (CNX),How?,Determine beginning and end of process to be mapped Involve people knowledgeable about the process Brainstorm steps & group in major process areas Layout activities in sequenc
33、e Validate by physically walking through process,PM/CE/CNX/SOP,CE: Cause & EffectSources of Variation,Output(s)& Specs,People Material Machine,X C,C N,C,N,X,X,Measurement Method Environment,Every variable on the diagram should be labeled as either:C = ConstantN = NoiseX = Experimental variable or Fa
34、ctor,PM/CE/CNX/SOP,SOP: Standard Operating Procedures,Standard Operating Procedure are rules that we define to ensure that we have Consistent processes in everything we do. Based on good judgment Common sense Engineering knowledgeRemember ISO 9000!Make sure we have defined processes and that the rul
35、es are being obeyed by all.,數據分析,1.Sample size risk,Is the risk of say there is a difference when there really isnt one(生產者冒險率) Is the risk of not finding a difference when there really is one (消費者冒險率)/ is he magnitude or size of the difference been tested. This is sometimes called the test sensitiv
36、ity.,A Basic Sample Size Table,Applies toContinuousData Only,/,For example : The 1st adhesive has an average of 13.2 and a standard deviation of 3.27The practical significance is such that any alternativeAdhesive must have an average strength of 20 or moreto make the change worth while.Q: For =5% &
37、=10% what should be the sample size in each level of the experiment?,Ans: How big of a change is important? /=(20-13.2)/3.27= 2.07 =5% =10% So follow the table we find the sample size is 5,2.T-test : Comparing Means 3.F-test : Comparing Variances (Between 2 Groups)4.ANOVA :(Analysis Of Variance) (Be
38、tween multi-groups),Improve,Statistical Control Poka-Yoke Plan (if Applicable) Confirmed Vital Xs Are They Statistically Significant ? Sample Size Calculation For Confirmation Run DOE Plan (if Applicable) Regression Equation Linked to statistical Problem SOP Changes and/or Optimal Solution Identifie
39、d Plan to Implement SOP Changes and/or Optimal Solution,What contribution did each vital X have to the Y ? How can we control the Xs ?,What do we want to know ?,How do we determine a model,Correlation & Regression,Correlation tells if you have a relationship between two variables(Y and X, or two Xs)
40、Regression is used to identify the nature of the relationship, and be able to predict Y while better understanding Y and possibly improving the controllability of Y,Correlation,Correlations (Pearson)Correlation of pull and temp = -0.978,Regression Analysis (Minitab software)The regression equation i
41、spull = 353 - 2.30 tempPredictor Coef StDev T PConstant 353.11 13.56 26.05 0.000temp -2.29520 0.09001 -25.50 0.000S = 0.3460 R-Sq = 95.6% R-Sq(adj) = 95.4%Analysis of VarianceSource DF SS MS F PRegression 1 77.832 77.832 650.28 0.000Error 30 3.591 0.120Total 31 81.423Unusual ObservationsObs temp pul
42、l Fit StDev Fit Residual St Resid 12 150 9.3122 9.9752 0.1181 -0.6630 -2.04R 31 151 4.9778 5.8438 0.0864 -0.8660 -2.59R,DOE (Design of experiment),1.篩選主要因子2.尋找最佳因子組合3.結果再現性驗證,找尋最佳之生產條件(製程參數 ),Design of Experiments,6 Overview,SCREENING,OPTIMIZATION,CHARACTERIZATION,For Experiments Involving a Large N
43、umber of Factors Useful in Isolating the “Vital Few “ from the “Trivial Many”,For Experiments Involving a Relatively Small Number of Factors Useful When Studying Relatively Uncomplicated Effects & Interactions,For Experiments Involving Only 2 or 3 Factors Useful When Studying Highly Complicated Effe
44、cts & Relationships,DOE is More Effective Than Testing One Factor at a Time,Control,What do we want to know ?,Statistical Control Poka-Yoke Plan (if Applicable) Measurement of Final Capability Using Confirmation Run Comparison of Before and After Distributions How Do You Control or Poka-Yoke the Vital Xs ? Is the Learning Transferrable Across the Business Whats the Plan ? Who Owns the Project Documentation File ? Final Financial Results Signed Off What Spin Off Projects Are There ?,How will this change the way we work ?,
