Statistical Engineering: An Algorithm for Reducing Variation in Manufacturing Processes, Volume 1

Front Cover
ASQ Quality Press, Jan 1, 2005 - Business & Economics - 328 pages
0 Reviews
Reducing the variation in process outputs is a key part of process improvement. For mass produced components and assemblies, reducing variation can simultaneously reduce overall cost, improve function and increase customer satisfaction with the product. the authors have structured this book around an algorithm for reducing process variation that they call Statistical Engineering. the algorithm is designed to solve chronic problems on existing high to medium volume manufacturing and assembly processes. the fundamental basis for the algorithm is the belief that we will discover cost effective changes to the process that will reduce variation if we increase our knowledge of how and why a process behaves as it does. a key way to increase process knowledge is to learn empirically, that is, to learn by observation and experimentation. The authors discuss in detail a framework for planning and analyzing empirical investigations, known by its acronym QPDAC (Question, Plan, Data, Analysis, Conclusion). They classify all effective ways to reduce variation into seven approaches. a unique aspect of the algorithm forces early consideration of the feasibility of each of the approaches. PRAISE FOR Statistical EngineeringThis is the most comprehensive treatment of variation reduction methods and insights Ieve ever seen. - Gary M. Hazard TellabsThroughout the text emphasis has been placed on teamwork, fixing the obvious before jumping to advanced studies, and cost of implementation. all this makes the manuscript attractive for real-life application of complex techniques. - Guru Chadha Comcast IP Services.
 

What people are saying - Write a review

We haven't found any reviews in the usual places.

Contents

Introduction
1
11 TRUCK PULL
2
12 ENGINE BLOCK LEAKS
4
13 CAMSHAFT LOBE RUNOUT
5
14 SAND CORE STRENGTH
7
16 PAINT FILM BUILD
8
17 REFRIGERATOR FROST BUILDUP
9
Setting the Stage
11
93 IMPLEMENTING THE METHOD OF ELIMINATION
124
Investigations to Compare Two Families of Variation
131
102 COMPARING TWO TIMEBASED FAMILIES
135
103 COMPARING UPSTREAM AND DOWNSTREAM FAMILIES
138
104 COMPARING ASSEMBLY AND COMPONENT FAMILIES
141
105 COMMENTS
144
Investigations to Compare Three or More Families of Variation
149
112 COMPARING FAMILIES DEFINED BY PROCESSING STEPS
163

Describing Processes
13
22 CAUSES OF VARIATION
15
23 DISPLAYING AND QUANTIFYING PROCESS VARIATION
18
24 MODELS FOR VARIATION AND THE EFFECTS OF CAUSES
23
Seven Approaches to Variation Reduction
29
31 FIXING THE OBVIOUS BASED ON KNOWLEDGE OF A DOMINANT CAUSE
30
32 DESENSITIZING THE PROCESS TO VARIATION IN A DOMINANT CAUSE
32
33 FEEDFORWARD CONTROL BASED ON A DOMINANT CAUSE
33
34 FEEDBACK CONTROL
34
35 MAKING THE PROCESS ROBUST
36
36 100 INSPECTION
38
37 MOVING THE PROCESS CENTER
39
An Algorithm for Reducing Variation
41
42 HOW TO USE THE ALGORITHM EFFECTIVELY
45
Obtaining Process Knowledge Empirically
51
51 QUESTION PLAN DATA ANALYSIS AND CONCLUSION QPDAC FRAMEWORK
52
52 EXAMPLES
58
Getting Started
67
Defining a Focused Problem
69
62 THE PROBLEM BASELINE
73
63 PLANNING AND CONDUCTING THE BASELINE INVESTIGATION
76
64 EXAMPLES
81
65 COMPLETING THE DEFINE FOCUSED PROBLEM STAGE
86
Checking the Measurement System
89
71 THE MEASUREMENT SYSTEM AND ITS ATTRIBUTES
90
72 ESTIMATING MEASUREMENT VARIATION
92
73 ESTIMATING MEASUREMENT BIAS
98
74 IMPROVING A MEASUREMENT SYSTEM
101
75 COMPLETING THE CHECK THE MEASUREMENT SYSTEM STAGE
102
Choosing a Working Variation Reduction Approach
105
81 CAN WE FIND A DOMINANT CAUSE OF VARIATION?
106
82 CAN WE MEET THE GOAL BY SHIFTING THE PROCESS CENTER WITHOUT REDUCING VARIATION?
108
83 CAN WE REDUCE VARIATION BY CHANGING ONE OR MORE FIXED INPUTS WITHOUT KNOWLEDGE OF A DOMINANT CAUSE?
110
84 DOES THE PROCESS OUTPUT EXHIBIT A STRONG PATTERN OVER TIME?
112
85 SUMMARY
113
Finding a Dominant Cause of Variation
115
Finding a Dominant Cause Using the Method of Elimination
117
91 FAMILIES OF CAUSES OF VARIATION
118
92 FINDING A DOMINANT CAUSE USING THE METHOD OF ELIMINATION
121
113 COMPARING COMPONENT FAMILIES
167
Investigations Based on Single Causes
179
122 INVESTIGATING THE RELATIONSHIP BETWEEN INPUTS AND A CONTINUOUS OUTPUT
183
Verifying a Dominant Cause
193
131 VERIFYING A SINGLE SUSPECT DOMINANT CAUSE
194
132 ISSUES WITH SINGLE SUSPECT VERIFICATION EXPERIMENTS
197
133 VERIFYING A DOMINANT CAUSE FROM A SHORT LIST OF SUSPECTS
200
134 FURTHER ISSUES AND COMMENTS
205
Assessing Feasibility and Implementing a Variation Reduction Approach
211
Revisiting the Choice of Variation Reduction Approach
213
IMPLEMENTING AN AVAILABLE SOLUTION
214
142 COMPENSATING FOR VARIATION IN THE DOMINANT CAUSE
217
143 REFORMULATING THE PROBLEM IN TERMS OF A DOMINANT CAUSE
219
144 CONTINUING THE SEARCH FOR A MORE SPECIFIC DOMINANT CAUSE
223
145 DEALING WITH DOMINANT CAUSES THAT INVOLVE TWO INPUTS
225
Moving the Process Center
227
151 EXAMPLES OF MOVING THE PROCESS CENTER
228
152 ASSESSING AND PLANNING A PROCESS CENTER ADJUSTMENT
238
Desensitizing a Process to Variation in a Dominant Cause
241
161 EXAMPLES OF DESENSITIZATION
242
162 ASSESSING AND PLANNING PROCESS DESENSITIZATION
255
Feedforward Control Based on a Dominant Cause
259
171 EXAMPLES OF FEEDFORWARD CONTROL
260
172 ASSESSING AND PLANNING FEEDFORWARD CONTROL
266
Feedback Control
269
181 EXAMPLES OF FEEDBACK CONTROL
270
182 ASSESSING AND PLANNING FEEDBACK CONTROL
280
Making a Process Robust
285
191 EXAMPLES OF PROCESS ROBUSTNESS
286
192 ASSESSING AND PLANNING PROCESS ROBUSTNESS
297
100 Inspection
301
201 EXAMPLES OF 100 INSPECTION
302
202 ASSESSING AND PLANNING 100 INSPECTION
304
Validating a Solution and Holding the Gains
307
212 HOLDING THE GAINS OVER THE LONG TERM
310
213 COMPLETING THE IMPLEMENT AND VALIDATE STAGE
312
References
313
Index
319
Copyright

Common terms and phrases

Bibliographic information