Index

Note: Page numbers followed by f or t refer to figures or tables, respectively.

A statistical tolerance factors (Appendix K),

306
accelerated life tests, 167–173 values of the t distribution (Appendix J),
acceptable quality level (AQL), 87 304–305
achieved availability, 30 areas under standard normal curve
addition rules, in probability, 88–89 (Appendix E), 288–289
advertising. See marketing and advertising Army Materiel Systems Analysis Activity
American Society for Quality (ASQ) (AMSAA) model, 158
Certified Reliability Engineer Body of Arrhenius, Savanti, 168
Knowledge (Appendix A), 276–283 Arrhenius acceleration model, 168–170, 170f,
Code of Ethics, 8–10, 284–285 202–204, 206, 209
AND and OR gates, 45, 45f as low as reasonably practicable (ALARP), 61
ANOVA procedures, in DOE, 240, ASQ Code of Ethics
242–243, 242t document (Appendix B), 284–285
appendices in reliability engineering, 8–10
areas under standard normal curve AT&T Bell Labs, 217
(Appendix E), 288–289 attributes, definition of, 111
ASQ Certified Reliability Engineer Body availability, 17, 30–31, 271
of Knowledge (Appendix A), 276–283
ASQ Code of Ethics (Appendix B),
284–285
B
binomial distribution (Appendix O), balanced designs. See design of
311–312 experiments (DOE)
chi-square distribution (Appendix I), bathtub curve, 20f, 28–29, 174f, 181
302–303 Bayesian analysis, 188–189
constants for control charts Bellcore (SR-22) standard, 260
(Appendix D), 287 benchmarking, 12
control limit formulas (Appendix C), 286 binomial distribution, 97–99, 115, 117, 132–133
critical values for the Mann-Whitney test Appendix O, 311–312
(Appendix L), 307 black-box testing, 181
critical values for Wilcoxon signed rank block diagrams and models, 183–187,
test (Appendix M), 308 184–185f
exponential distribution (Appendix P), blocking, in DOE, 231
313–314 BMW, 163
F distribution F0.01 (Appendix H), 298–301 brinnelling failure, 196
F distribution F0.1 (Appendix F), 290–293 brittle fracture failure, 196
F distribution F0.5 (Appendix G), 294–297 buckling failure, 201
median ranks (Appendix Q), 315–316 built-in testing (BIT), 273–274
Poisson distribution (Appendix N), burn-in testing. See stress screening
309–310 BX life, 18

339

H1535_Durivage.indd 339 6/14/17 12:27 PM

 340 Index

C corrosion failure, 197–198

cost of poor reliability, 31–34
cause-and-effect diagrams, 25 creep buckling failure, 201
c-charts, 114–115, 116f critical values
censored data, 16–19 Mann-Whitney test (Appendix L), 307
central limit theorem, 70 Wilcoxon signed rank test (Appendix M),
China 299B (software), 260 308
chi-square distribution, 126–127, 130–131 Croston method, 269–270
Appendix I, 302–303 Crowe, Larry, 158
chi-square tests. See goodness-of-fit tests Crump, S. Scott, 221
combinations, in probability, 94 cumulative MTBF, 158–160
combined environmental reliability testing
(CERT), 166
common cause failure (CCF), 56–57
D
complementation rule, 88 data management, 136–150
compliance testing. See qualification/ data collection methods, 140–141
demonstration tests data summary and reporting, 141–147
conditional probability, 90 failure analysis methods, 147–149
condition-based maintenance. See FRACAS and, 149–150, 150f
maintainability sources of reliability data, 138, 139t
confidence and tolerance intervals, 120–135 types of data, 139–140
binomial distribution, 132–133 warranty program data, 136–137
confidence interval for the mean of decreasing failure rate stage, 20
binomial distribution, 133–134 degradation (wear-to-failure) tests,
confidence interval for the mean of the 179–180
exponential distribution, 130–132 degradation models, 205–207, 205f
confidence interval on standard degrees of freedom, 125
deviation, 126–127 dependability, 17
confidence intervals, 123 derating, 260
consistency, 121 design FMEA (DFMEA), 56
estimate of binomial mean from design for reliability (DfR), 256–259, 257f
sample, 133 design for X (DFX), 255–256
estimate of standard deviation, 122–123 design of experiments (DOE), 228–245
estimate of the mean, 121 balanced designs, 235–236, 235t
exponential distribution, 129–130 blocking, 231
maximum likelihood estimates, 120–121 full factorial experiments, 241–242t,
normal distribution, 123–126, 127f 241–243
point estimates, 121 interaction effects, 233–235, 234f, 235t
statistical tolerance intervals, 128–135, 306 main effects, 231–232, 232f
success testing, 134–135 one-factor experiments, 238–241, 240f, 240t
constant failure rate stage, 20 planning and organization, 230–231
constants for control charts (Appendix D), 287 randomization, 231–233
consumers, 21, 22, 65, 254 resolution, 236–238
consumer’s risk. See type II errors robustness concepts, 243–245, 245t
contingency tables, 89–90 23 full-factorial data collection sheets,
continuous (variables) data, 139 229t, 232–234t
control charts, 110–119. See also constants for 24 full-factorial data collection sheets,
control charts (Appendix D) 236–237t
interpretation of, 111–112, 112–114f, 119f design prototyping, 219–222, 220–222f
types and selection of, 111, 111t discrete (attributes) data, 139
control limit formulas (Appendix C), 286 DMAIC (define, measure, analyze, improve,
corrective and preventive action (CAPA), and control), 37
23–24, 23–24f, 60, 253 Duane, James, 158

H1535_Durivage.indd 340 6/14/17 12:27 PM

 Index 341

Duane model, 158–160 F distribution

ductile rupture failure, 196 F0.01 (Appendix H), 298–301
dynamic system models, 192–194, 193f F0.1 (Appendix F), 290–293
F0.5 (Appendix G), 294–297
tables, 133–134
E fishbone diagrams. See cause-and-effect
early failure stage, 20 diagrams
end of life considerations, 65 five whys, in root cause analysis, 25
engineering change request (ECR), 41, 253 fixed-time compliance test, 176
environmental stress screening (ESS), 173 flowcharts, 26, 26f
environmental stress variables, 160–162 Ford, Henry, 36
ethical issues. See ASQ Code of Ethics forecasting, 12
exact failure times, 16 formulas for sample size, 109t
exponential distribution, 100–102, 129–130 fretting action failure, 200
Appendix P, 313–314 full factorial experiments. See design of
Eyring model, 170, 202, 208–209 experiments (DOE)
functional testing. See black-box testing
fused deposition modeling (FDM), 221
F
FACETs of leadership, 6
failure analysis methods, in data
G
management, 147–149 galling failure, 201
failure consequences, 162–163 goodness-of-fit tests, 81–83
failure models, 202–211, 205f Government–Industry Data Exchange
failure modes, 195, 195–196t Program (GIDEP), 138, 217
failure modes, effects, and criticality analysis Gray, Dave, 219
(FMECA), 36, 40–41, 54–56 Gu, J., 195
failure modes and effects analysis (FMEA),
48–56, 49f
1–5 rating scheme, 52–53t, 53t
H
1–10 rating scheme, 50–51t, 53t Handbook for Reliability Prediction for
definition of, 48–49 Mechanical Systems (NSWC-07), 217
during design, 54–56 hazard, definition of, 57
failure consequences ranking, 163 hazard analysis, 57–60, 58f
in risk analysis, 40–41, 48–56 hazard function, 16–17, 143–145
safety risks, 5 health hazards, 8
in Six Sigma, 36, 37 hierarchy of controls. See Safety Decision
steps in, 49, 52 Hierarchy (Manuele)
types of, 56 highly accelerated life testing (HALT), 152,
failure rate, 16–17 155–157, 171–174, 173f
failure reporting, analysis, and corrective highly accelerated stress audit (HASA)
action system (FRACAS), 13–14f, test, 174
149–150, 150f, 225 highly accelerated stress screening (HASS)
failure review board, 149 test, 153, 157, 174
faster–better–cheaper, 34–35 histograms, 23–24, 23–24f, 141–143
fatigue failure, 196–197 human error
fault tolerance, 258 definition of, 41–42
fault tree analysis (FTA), 44–48 mistake-proofing and, 41–42, 61–62
AND and OR gates, 45, 45f in reliability design, 248–255, 249–250f, 250t
common cause failure and, 57 system safety programs and, 61–62
diagrams of, 46–47f human reliability analysis (HRA), 251
success tree analysis, 47–48, 48f human variation, in reliability testing,
voting OR gates, 45–46, 45f 254–255

H1535_Durivage.indd 341 6/14/17 12:27 PM

 342 Index

hypotheses testing, 70–87 leadership foundations, in reliability

goodness-of-fit, 81–83 engineering, 2–14
one-tailed tests, 71–72, 71–72f ASQ Code of Ethics, 8–10, 284–285
paired-comparison tests, 77–79 benefits of, 2–3
statistical vs. practical significance, 86 function of reliability in engineering, 7–8
steps in, 72 performance monitoring, 11–13
tests for means, 73–75 product lifecycle, 6–7
tests for means of two populations, 75–77 responsibilities of reliability engineers, 5–6
tests for means of two population safety, quality, and reliability, 3–5
standard deviations, 79–80 supplier reliability assessments, 10–11
tests for proportions, 83–86 lean manufacturing, 36–37
truth tables, 71t lean thinking, 36–37
two-tailed tests, 71–72, 72f left-censored data, 16, 140
type I errors, 70–71, 77, 86–87 life-cycle cost, 31–34
type II errors, 70–71, 77, 86–87 load sharing model, 192–193
log-normal distribution, 106–107
I
identification, in risk management, 40
M
idiotproofing. See human error machinery and equipment FMEA, 56
IEC standard 61123-1997 Reliability Testing— maintainability, 17, 19, 264–274
Compliance Plans for Success Ratio, 175 apportionment and allocation, 265–266
IEC standard 61124-2006 Reliability Testing— corrective maintenance analysis, 270,
Compliance Tests for Constant Failure 273–274
Rate and Constant Failure Intensity, 175, Croston method, 269–270
177–179 definition of, 265
impact failure, 199–200 maintenance strategies, 264–271
imperative statements, 34 moving average and, 268–269
increasing failure rate stage, 20 preventive maintenance analysis,
infant mortality stage, 20 270, 272
inherent availability, 30 single exponential smoothing, 269
inner/outer array design (Taguchi), 245, 245t spare parts analysis, 266–268
Institute of Electrical and Electronics testability and, 256
Engineers (IEEE), 138 Mann-Whitney test. See critical values
interval-censored data, 16 Manuele, J., 63–64
inverse power law (IPL), 168, 170, 202–203, 204 Manufacturing Extension Partnership
Ishikawa diagrams. See cause-and-effect (NIST), 36
diagrams margin of error, 108, 126
margin tests, 173
marketing and advertising, 7–8, 12
J Markov analysis, 213–215, 213f
Jet Propulsion Laboratory (JPL), 161 McLean, Harry W., 166, 172
mean, definition of, 68
mean active maintenance time (MAMT), 30
K mean cycles between failures (MCBF), 15
Kececioglu, Dimitri, 153–154 mean downtime (MDT), 30
k-values. See statistical tolerance factors mean time between failures (MTBF), 15–19,
(Appendix K) 35, 129, 152–153, 154–155, 158–160,
172, 175–179, 258, 271
mean time between maintenance actions
L (MTBMA), 30
laminated object manufacturing (LOM), 221 mean time between unplanned maintenance
leader, definition of, 5 action (MTBUMA), 18

H1535_Durivage.indd 342 6/14/17 12:27 PM

 Index 343

mean time to failure (MTTF), 15–18, 129, 172, normal distribution, 104–106, 117,
175–176, 218, 258 123–126, 127f
mean time to repair (MTTR), 17–18, 265–267, np-charts, 115, 117f
271, 273
measure of central tendency, 68
measures of dispersion, 68
O
median ranks (Appendix Q), 315–316 obsolescence, 65
memory corruption, 202 O’Connor, P., 181, 272
Microsoft Excel, 94 one-factor experiments. See design of
MIL-HDBK-189 standard, 158 experiments (DOE)
MIL-HDBK-217 standard, 215–217, 260 operating characteristic (OC) curve,
MIL-HDBK-781 standard, 175 175–179, 175f
minimum reliability requirements, 21 operational availability, 30
mistake-proofing. See human error optimum replacement time, 272
mitigation
obsolescence/end of life considerations, 65
product improvement, 64
P
reliability acceptance goals, 63 paired-comparison tests, 77–79
in risk management, 63–65 parallel system and redundancy, 185–186, 185f
strategies to minimize risk, 63–64, 64f parameters, 70
mode, 68 parametric vs. non-parametric statistics, 70
modeling, 183–222 parts and systems development, 260–263, 261f
block diagrams and models, 183–187, p-charts, 117, 118f, 141–142
184–185f Pecht, M., 195
design prototyping, 219–222, 220–222f Peck model, 168, 170
dynamic system models, 192–194, 193f performance accounting, 12
failure models, 202–211, 205f performance indicators, 12
physics of failure (PoF) and failure performance monitoring, 11–13
mechanisms, 194–202, 195–196t development of RMS performance
reliability prediction methods, 211–219, indicators, 12–13
213f examples of, 13–14f
special case reliability models, 187–192, quality function deployment (QFD),
191f 12–13
Monte Carlo simulation, 211–212, 253, 259 use of performance indicators, 12
m out of n system model, 187–188 permutations, in probability, 94–95
multiple-stress tests, 170–173, 171f, 173f PHM Society, 202
multiplication rules, in probability, 91–94 physics of failure (PoF) and failure
multivariate charts, 139–140 mechanisms, 194–202, 195–196t
planning, 152–166
environmental and conditions of use
N factors, 160–162
NASA motto, 22 failure consequences, 162–163
National Institute of Standards and failure criteria, 164–165
Technology (NIST), 36 reliability test strategies, 152–160
National Oceanic and Atmospheric steps in test plans, 153–154
Administration (NOAA), 161 test environments, 165–166
National Technical Information Service, 138 Poisson distribution, 99–100, 115
Naval Surface Warfare Center (NSWC), Appendix N, 309–310
217, 260 poka-yoke. See human error
nonelectrical parts (NPRD) data, 138 population, 69
Non-electronic Parts Reliability Data (NPRD- population standard deviation, 69
2011), 217 power law model. See inverse power law (IPL)
non-value-added, 36 predictive maintenance, 264, 265

H1535_Durivage.indd 343 6/14/17 12:27 PM

 344 Index

preventive maintenance (PM), 18, 19, 272 public relations, use of performance
PRISM reliability prediction method, 216–217 indicators, 12
probability, definition of, 2, 68
probability and statistics, for reliability,
68–135. See also data management
Q
basic probability concepts, 87–95 qualification/demonstration tests, 153, 155,
basic statistics, 68–87 174–179, 175f, 179f
confidence and tolerance intervals, 120–135 qualitative fault tree analysis, 44
formulas for sample size, 109t quality and reliability, 3–5
probability distributions, 95–96 quality triangle, 34–35
probability functions, 97–108 quantitative fault tree analysis, 44
process capability, 119, 119f
sampling plans for testing, 108–110
statistical process control, 110–118
R
probability density functions (PDFs), 97, 98, radiation damage failure, 201
101, 120, 143, 143–145 random, definition of, 68
probability distributions, 95–96 random causes stage, 20
probability ratio sequential test (PRST) plans. randomization, in DOE, 231–233
See sequential test plans random sample, 69
process capability indices, 119, 119f rapid prototyping, 220–221, 220–221f
process design, 21–22 raw as possible (RAP) principle, 262
process FMEA (PFMEA), 56 redundancy, 185–186, 185f, 193, 193f, 258–259
producer’s risk. See type I errors reliability, definition of, 2, 15
product availability, 30–31 reliability, maintainability, and safety (RMS)
product design objectives, 11–13
FMEA/FMECA technique, 54–56 reliability acceptance goals, 63, 164
reliability analysis, 7 reliability acceptance tests, 154
reliability engineering and effectiveness, Reliability Analysis Center (RAC), 216
35–36 reliability-centered maintenance (RCM)
reliability requirements, 21–22 programs, 19
reliability tasks, 13f Reliability Data Handbook 2000, 260
product development tests, 154 reliability design techniques, 224–259
product improvement, 64 design for reliability (DfR), 256–259, 257f
product liability, 8 design for X (DFX), 255–256
product lifecycle design of experiments, 228–245, 229t,
engineering stages, 28–29 232–237t, 232f, 234f, 240–242t, 240f,
production stages of, 226 244–245t
reliability tasks, 13f human error factors, 248–255, 249–250f,
role of reliability engineer, 6–7 250t
safety risks, 6–7 reliability optimization, 246–248
three stages of, 20 stress-strength analysis, 226–228, 227f
product maintainability, 30–31 validation and verification, 224–226
product-prototype cycle, 220, 220f reliability engineering, study of, 3
product reliability formula, 32 reliability foundations, 15–38. See also
product specifications, 19 modeling; planning; testing
prognostics and health management basic reliability terminology, 15–20
(PHM), 202 corrective and preventive action, 23–24
project planning, 22–23. See also planning cost of poor reliability, 31–34
proportional hazard models, 209–211 drivers of reliability requirements and
prototypes targets, 21–23
in design modeling, 219–222, 220–222f economics of product maintainability and
as source of reliability data, 138, 139t availability, 30–31

H1535_Durivage.indd 344 6/14/17 12:27 PM

 Index 345

product lifecycle engineering stages, 28–29 scatter diagrams, 27, 27f

quality triangle, 34–35 selective laser sintering (SLS), 221, 222f
root cause analysis, 24–27 sequential test plans, 178–179, 179f
Six Sigma methodologies, 35–37 series model (constant failure rate), 191, 191f
systems engineering and integration, 38 series-parallel model, 186–187
reliability growth models, 14f series system block diagrams, 183–185, 184f
reliability growth testing, 158–160 serviceability, 19
reliability measurement formulas, 15–17 service interval, 18
reliability optimization, 246–248 signal-to-noise (S/N) ratio (Taguchi), 244
reliability performance tests, 154 significance
reliability prediction methods, 211–219, 213f definition of, 123
reliability testing and human factors, 254–255 in reliability modeling, 188
reliability verification tests, 154–155 single-stress tests, 168
repairable systems. See maintainability Six Sigma methodologies, 35–37
required function, 2 data collection and analysis, 37
right-censored data, 16, 140 lean manufacturing and thinking, 36–37
risk reliability engineering in design phase,
definition of, 43 35–36
types of 42–43 waste elimination, 36
risk analysis, 40–41, 44–62, 253 skewness, 107–108
common cause failure, 56–57 smart products, 162
failure modes, effects, and criticality software FMEA, 56
analysis, 54–56 software products
failure modes and effects analysis, 48–56, coding rules, 34
49f, 50–53t reliability curve, 33f
fault tree analysis, 44–48, 45–48f, 57 reliability engineering stages, 33–34
hazard analysis, 57–60, 58f techniques, 33
risk matrix, 59–60, 59f testing strategies, 180–182
system safety, 60–62, 61f, 253 spalling failure, 201
risk management, 40–43 special case reliability models, 187–192, 191f
risk matrix, 41, 43, 59–60, 59f specified period of time, 2
risk priority number (RPN), 49, 51t, 52, 53t, 54 standard deviation, 68–69
robustness concepts, 243–245, 245t standby redundant systems, 193, 193f
Rome Air Development Center, 138 stated conditions, 2
root cause analysis, 24–27 static system reliability models, 183–187,
cause-and-effect diagrams, 25 184–185f
five whys, 25 statistic, definition of, 69–70. See also
flowcharts, 26, 26f probability and statistics, for
scatter diagrams, 27, 27f reliability
statistical process control (SPC), 37,
110–118, 174
S statistical thinking, 37
safe operating area (SOA), 260, 261f statistical tolerance factors (Appendix K), 306
safety and reliability, 3–5, 8, 41. See also step-stress testing, 171, 171f
product lifecycle; system safety stereolithography (SLA), 221
Safety Decision Hierarchy (Manuele), stress-life distributions, 261, 261f
63–64, 64f stress rupture failure, 201
safety hazards, in system safety programs, stress screening, 173–174, 174f
60, 252–254 stress-strength analysis, 226–228
sample mean, 69 structural testing. See white-box testing
sample standard deviation, 69 success tree analysis (STA), 47–48, 48f
sample variance, 69 supplier reliability assessments, 10–11

H1535_Durivage.indd 345 6/14/17 12:27 PM

 346 Index

system FMEA, 56 use conditions, 160–162

system safety use environment, 160–162
continuous efforts, 62 useful life stage, 20
elements and functions of programs, U.S. Energy Department (DOE), 161
60, 60f U.S. Food and Drug Administration, Hazard
as low as reasonably practicable Analysis and Critical Control Point
principle, 61 (HACCP) System, 59
in risk analysis, 60–62, 61f, 253
systems engineering, 38
V
validation and verification, 22, 224–226
T value-added functions, 36
Taguchi, Genichi, 244–245, 259 values of the t distribution (Appendix J),
Takata Corporation, 163 304–305
t distribution. See values of the t distribution variables, definition of, 111
(Appendix J) voting OR gates, 45–46, 45f
teams, in Six Sigma, 37
Telcordia SR-332 standard, 217
test, analyze, and fix (TAAF), 158
W
testing, 167–182. See also hypotheses testing; warranty programs
specific tests collection and analysis of data, 137, 139t
accelerated life tests, 167–173, 171f, 173f data in risk management identification, 40
degradation (wear-to-failure) tests, failure criteria, 164–165
179–180 organizational functions of, 136–137
qualification/demonstration tests, predicted vs. actual, 13f
174–179, 175f, 179f reliability analysis, 7–8
software testing strategies, 180–182 waste elimination, 36, 37
stress screening, 173–174, 174f wear failure, 199
test environments, 165–166 wear-out stage, 20
thermal shock failure, 201 Weibull distribution, 102–103, 144–147,
3-D printing, 222, 222f 170, 170f
time, definition of, 15 white-box testing, 180–181
tolerance intervals. See confidence and Whitney, Eli, 36
tolerance intervals why questions, in root cause analysis, 25
Toyota Production System (TPS), 36–37 Wilcoxon signed rank test. See critical values
truncation, 157 WYSIWYG (what you see is what you get)
truth table method, 71t, 189–191, 190f process, 221
t-test, 73–75
T2 generalized variance chart, 139–140
Tukey’s quick compact two-sample test, 84
X
217(plus) method, 217 X and mR (moving range) control charts,
type I errors, 70–71, 77, 86–87, 176 117, 118f
type II errors, 70–71, 77, 86–87, 176 X-bar and R control charts, 114, 115f, 139
X-bar and s control charts, 114, 116f
U
u-charts, 115, 117f
Z
Ullman Sails, environmental/use factors, 162 zero quality control (ZQC). See human error
univariate charts, 139 z-test, 73

H1535_Durivage.indd 346 6/14/17 12:27 PM