- Second edition of a successful book expands on two major topics of
increasing relevance to organizations: lean production and design for six sigma
- Enables readers to identify which six sigma methods are most suitable for
particular scenarios
Lean production, has long been regarded as critical to business success in many
industries. Over the last ten years, instruction in six sigma has been increasingly linked
with learning about the elements of lean production. Introduction to Engineering
Statistics and Lean Sigma builds on the success of its first edition (Introduction to
Engineering Statistics and Six Sigma) to reflect the growing importance of the "lean
sigma" hybrid.
As well as providing detailed definitions and case studies of all six sigma
methods, Introduction to Engineering Statistics and Lean Sigma forms one of few sources on
the relationship between operations research techniques and lean sigma. Readers will be
given the information necessary to determine which sigma methods to apply in which
situation, and to predict why and when a particular method may not be effective.
Methods covered include:
• control charts and advanced control charts,
• failure mode and effects analysis,
• Taguchi methods,
• gauge R&R, and
• genetic algorithms.
The second edition also greatly expands the discussion of Design For Six Sigma
(DFSS), which is critical for many organizations that seek to deliver desirable products
that work first time. It incorporates recently emerging formulations of DFSS from industry
leaders and offers more introductory material on the design of experiments, and on two
level and full factorial experiments, to help improve student intuition-building and
retention.
The emphasis on lean production, combined with recent methods relating to
Design for Six Sigma (DFSS), makes Introduction to Engineering Statistics and Lean Sigma a
practical, up-to-date resource for advanced students, educators, and practitioners.
Table of Contents
List of Acronyms xxi
1 Introduction 1
1.1 Purpose of this Book 1
1.2 Systems and Key Input Variables 2
1.3 Problem-solving Methods 6
1.3.1 What Is “Six Sigma”? 7
1.3.2 What Is “Lean Manfacturing”? 10
1.3.3 What Is the “Theory of Constraints”? 10
1.3.4 What Is the “Theory of Constraints Lean Six Sigma”? 10
1.4 History of “Quality” and Six Sigma 11
1.4.1 History of Management and Quality 11
1.4.2 History of Documentation and Quality 15
1.4.3 History of Statistics and Quality 15
1.4.4 The Six Sigma Movement 18
1.5 The Culture of Discipline 19
1.6 Real Success Stories 21
1.7 Overview of this Book 22
Problems 23
References 27
Part I Statistical Quality Control
2 Statistical Quality Control and Six Sigma 31
2.1 Introduction 31
2.2 Method Names as Buzzwords 32
2.3 Where Methods Fit into Projects 33
2.4 Organizational Roles and Methods 35
2.5 Specifications: Non-conforming vs Defective 36
2.6 Standard Operating Procedures (SOPs). 38
2.6.1 Proposed SOP Process 39
2.6.2 Measurement SOPs 42
Problems 42
References 46
3 Define Phase and Strategy 47
3.1 Introduction 47
3.2 Systems and Subsystems 48
3.3 Project Charters 49
3.3.1 Predicting Expected Profits 51
3.4 Strategies for Project Definition 53
3.4.1 Bottleneck Subsystems 53
3.4.2 Go-no-go Decisions 54
3.5 Methods for Define Phases 55
3.5.1 Pareto Charting 55
3.5.2 Benchmarking 58
3.6 Formal Meetings 60
3.7 Significant Figures 62
3.8 Summary 65
Problems 67
References 75
4 Measure Phase and Statistical Charting 77
4.1 Introduction 77
4.2 Evaluating Measurement Systems 78
4.2.1 Types of Gauge R&R Methods 79
4.2.2 Gauge R&R: Comparison with Standards 80
4.2.3 Gauge R&R (Crossed) with Xbar & R Analysis 83
4.3 Measuring Quality Using SPC Charting 87
4.3.1 Concepts: Common Causes and Assignable Causes 88
4.4 Commonality: Rational Subgroups, Control Limits, and Startup 89
4.5 Attribute Data: p-Charting 91
4.6 Attribute Data: Demerit Charting and u-Charting 96
4.7 Continuous Data: Xbar & R Charting 100
4.7.1 Alternative Continuous Data Charting Methods 106
4.8 Summary and Conclusions 107
Problems 109
References 119
5 Analyze Phase 121
5.1 Introduction 121
5.2 Lean Production 121
5.2.1 Process and Value Stream Mapping 122
5.2.2 5S 125
5.2.3 Kanban 126
5.2.4 Poka-Yoke 126
5.3 The Toyota Production System 127
5.4 Process Flow and Spaghetti Diagrams 128
5.5 Cause and Effect Matrices 131
5.6 Design of Experiments and Regression (Preview) 133
5.7 Failure Mode and Effects Analysis 135
5.9 Summary 138
Problems 139
References 148
6 Improve or Design Phase 149
6.1 Introduction 149
6.2 Informal Optimization 150
6.3 Quality Function Deployment (QFD ) 151
6.4 Formal Optimization 154
6.5 Summary 156
Problems 157
References 161
7 Control or Verify Phase 163
7.1 Introduction 163
7.2 Control Planning 164
7.3 Acceptance Sampling 167
7.3.1 Single Sampling 168
7.3.2 Double Sampling 169
7.4 Documenting Results 171
7.5 Summary 172
Problems 173
Reference 177
8 Advanced SQC Methods 179
8.1 Introduction 179
8.2 EWMA Charting for Continuous Data 180
8.3 Multivariate Charting Concepts 183
8.4 Multivariate Charting (Hotelling’s T2 Charts) 186
8.5 Summary 190
Problems 190
References 191
9 SQC Case Studies 193
9.1 Introduction 193
9.2 Case Study: Printed Circuit Boards 193
9.2.1 Experience of the First Team 195
9.2.2 Second Team Actions and Results 197
9.3 Printed Circuitboard: Analyze, Improve, and Control Phases 199
9.4 Wire Harness Voids Study 202
9.4.1 Define Phase 203
9.4.2 Measure Phase 203
9.4.3 Analyze Phase 205
9.4.4 Improve Phase 206
9.4.5 Control Phase 206
9.5 Case Study Exercise 207
9.5.1 Project to Improve a Paper Air Wings System 208
9.6 Summary 212
Problems 213
References 215
10 SQC Theory 217
10.1 Introduction 217
10.2 Probability Theory 218
10.3 Continuous Random Variables 221
10.3.1 The Normal Probability Density Function 224
10.3.2 Defects Per Million Opportunities 230
10.3.3 Independent, Identically Distributed and Charting 231
10.3.4 The Central Limit Theorem 234
10.3.5 Advanced Topic: Deriving d2 and c4 237
10.4 Discrete Random Variables 238
10.4.1 The Geometric and Hypergeometric Distributions 240
10.5 Xbar Charts and Average Run Length 243
10.5.1 The Chance of a Signal 243
10.5.2 Average Run Length 245
10.6 OC Curves and Average Sample Number 247
10.6.1 Single Sampling OC Curves 248
10.6.2 Double Sampling.. 249
10.6.3 Double Sampling Average Sample Number 250
10.7 Summary 251
Problems 252
References 255
Part II Design of Experiments (DOE) and Regression
11 DOE: The Jewel of Quality Engineering 259
11.1 Introduction 259
11.2 Design of Experiments Methods Overview. 260
11.3 The Two-sample T-test Methodology and the Word “Proven” 261
11.4 T-test Examples 264
11.5 Randomization Testing and Paired T-testing 267
11.6 ANOVA for Two Sample T-tests 271
11.7 Full Factorials 275
11.8 Randomization and Evidence 277
11.9 Errors from DOE Procedures 278
11.10 Summary 280
Problems 282
Reference 287
12 DOE: Screening Using Fractional Factorials 289
12.1 Introduction 289
12.2 Standard Screening Using Fractional Factorials 290
12.3 Screening Examples 296
12.4 Method Origins and Alternatives 301
12.4.1 Origins of the Arrays 301
12.4.2 Alternatives to the Methods in this Chapter 303
12.5 Standard vs One-factor-at-a-time Experimentation 305
12.6 Summary 307
Problems 307
References 313
13 DOE: Response Surface Methods 315
13.1 Introduction 315
13.2 Design Matrices for Fitting RSM Models 316
13.3 One-shot Response Surface Methods 318
13.4 One-shot RSM Examples 321
13.5 Creating 3D Surface Plots in Excel 328
13.6 Sequential Response Surface Methods 329
13.7 Origin of RSM Designs and Decision-making 334
13.7.1 Origins of the RSM Experimental Arrays 334
13.7.2 Decision Support Information (Optional) 337
13.8 Appendix: Additional Response Surface Designs 340
13.9 Summary 345
Problems 345
References 349
14 DOE: Robust Design 351
14.1 Introduction 351
14.2 Expected Profits and Control-by-noise Interactions 352
14.3 Robust Design Based on Profit Maximization 355
14.4 Extended Taguchi Methods 362
14.5 Literature Review and Methods Comparison 366
14.6 Summary 368
Problems 368
References 370
15 Regression 373
15.1 Introduction 373
15.2 Single Variable Example 374
15.2.1 Demand Trend Analysis 375
15.2.2 The Least Squares Formula 375
15.3 Preparing “Flat Files” and Missing Data 376
15.4 Evaluating Models and DOE Theory 378
15.4.1 Variance Inflation Factors and Correlation Matrices 379
15.4.2 Normal Probability Plots and Other “Residual Plots” 381
15.4.3 Summary Statistics 386
15.5 Analysis of Variance Followed by Multiple T-tests 389
15.6 Regression Modeling Flowchart 392
15.7 Categorical and Mixture Factors (Optional ) 397
15.7.1 Regression with Categorical Factors 398
15.7.2 DOE with Categorical Inputs and Outputs 399
15.7.3 Recipe Factors or “Mixture Components” 400
15.8 Summary . .401
Problems .402
References 408
16 Advanced Regression and Alternatives 409
16.1 Introduction 409
16.2 Generic Curve Fitting 409
16.2.1 Curve Fitting Example 410
16.3 Kriging Model and Computer Experiments. 411
16.3.1 Design of Experiments for Kriging Models 412
16.3.2 Fitting Kriging Models 412
16.3.3 Kriging Single Variable Example 415
16.4 Neural Nets for Regression Type Problems 415
16.5 Logistics Regression and Discrete Choice Models 421
16.5.1 Design of Experiments for Logistic Regression 423
16.5.2 Fitting Logit Models 424
16.6 Summary 427
Problems 427
References 428
17 DOE and Regression Case Studies 431
17.1 Introduction 431
17.2 Case Study: the Rubber Machine . 431
17.2.1 The Situation 431
17.2.2 Background Information . 432
17.2.3 The Problem Statement 432
17.3 The Application of Formal Improvement Systems Technology 433
17.4 Case Study: Snap Tab Design Improvement . 437
17.5 The Selection of the Factors 440
17.6 General Procedure for Low Cost Response Surface Methods 441
17.7 The Engineering Design of Snap Fits 441
17.8 Concept Review 445
17.9 Additional Discussion of Randomization 446
17.10 Summary 448
Problems 449
References .451
18 DOE and Regression Theory 453
18.1 Introduction 453
18.2 Design of Experiments Criteria 454
18.3 Generating “Pseudo-Random” Numbers 455
18.3.1 Other Distributions 457
18.3.2 Correlated Random Variables 459
18.3.3 Monte Carlo Simulation (Review) 460
18.3.4 The Law of the Unconscious Statistician 461
18.4 Simulating T-testing 462
18.4.1 Sample Size Determination for T-testing 465
18.5 Simulating Standard Screening Methods 467
18.6 Evaluating Response Surface Methods 469
18.6.1 Taylor Series and Reasonable Assumptions 469
18.6.2 Regression and Expected Prediction Errors 471
18.6.3 The EIMSE Formula 474
18.7 Summary 480
Problems 481
References 483
Part III Optimization and Strategy
19 Optimization and Strategy 487
19.1 Introduction 487
19.2 Formal Optimization 488
19.2.1 Heuristics and Rigorous Methods 491
19.3 Stochastic Optimization. 493
19.4 Genetic Algorithms 495
19.4.1 Genetic Algorithms for Stochastic Optimization 495
19.4.2 Populations, Cross-over, and Mutation 496
19.4.3 An Elitist Genetic Algorithm with Immigration 497
19.4.4 Test Stochastic Optimization Problems 498
19.5 Variants on the Proposed Methods 498
19.6 Appendix: C Code for “Toycoolga” 500
19.7 Summary 504
Problems 504
References 506
20 Tolerance Design 507
20.1 Introduction 507
20.2 Summary 509
Problems 509
Reference 509
21 Design for Six Sigma 511
21.1 Introduction 511
21.2 Design for Six Sigma (DFSS) 511
21.3 Implementation 513
Problems 516
References 518
22 Lean Sigma Project Design 519
21.1 Introduction 519
21.2 Literature Review 520
21.3 Reverse Engineering Six Sigma 521
21.4 Uncovering and Solving Optimization Problems 523
21.5 Future Research Opportunities 527
21.5.1 New Methods from Stochastic Optimization 527
21.5.2 Meso-analyses of Project Databases 529
21.5.3 Test Beds and Optimal Strategies 530
Problems 531
References 532
Glossary . 535
Problem Solutions 543
Index 565
576 pages, Hardcover
