Muutke küpsiste eelistusi

Prognostics and Health Management of Electronics: Fundamentals, Machine Learning, and the Internet of Things [Kõva köide]

Edited by (University of Maryland, USA), Edited by (University of Maryland, USA)
  • Formaat: Hardback, 800 pages, kõrgus x laius x paksus: 246x173x51 mm, kaal: 1542 g
  • Sari: IEEE Press
  • Ilmumisaeg: 07-Sep-2018
  • Kirjastus: Wiley-IEEE Press
  • ISBN-10: 1119515335
  • ISBN-13: 9781119515333
Teised raamatud teemal:
Prognostics and Health Management of Electronics: Fundamentals, Machine Learning, and the Internet of ThingsSuurem pilt
  • Formaat: Hardback, 800 pages, kõrgus x laius x paksus: 246x173x51 mm, kaal: 1542 g
  • Sari: IEEE Press
  • Ilmumisaeg: 07-Sep-2018
  • Kirjastus: Wiley-IEEE Press
  • ISBN-10: 1119515335
  • ISBN-13: 9781119515333
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9781119515333.html
Märksõnad:

An indispensable guide for engineers and data scientists in design, testing, operation, manufacturing, and maintenance

A road map to the current challenges and available opportunities for the research and development of Prognostics and Health Management (PHM), this important work covers all areas of electronics and explains how to:

  • assess methods for damage estimation of components and systems due to field loading conditions
  • assess the cost and benefits of prognostic implementations 
  • develop novel methods for in situ monitoring of products and systems in actual life-cycle conditions
  • enable condition-based (predictive) maintenance
  • increase system availability through an extension of maintenance cycles and/or timely repair actions;
  • obtain knowledge of load history for future design, qualification, and root cause analysis
  • reduce the occurrence of no fault found (NFF) 
  • subtract life-cycle costs of equipment from reduction in inspection costs, downtime, and inventory 

Prognostics and Health Management of Electronics also explains how to understand statistical techniques and machine learning methods used for diagnostics and prognostics. Using this valuable resource, electrical engineers, data scientists, and design engineers will be able to fully grasp the synergy between IoT, machine learning, and risk assessment. 

List of Contributors xxiii
Preface xxvii
About the Contributors xxxv
Acknowledgment xlvii
List of Abbreviations xlix
1 Introduction to PHM 1(38)
Michael G. Pecht
Myeongsu Kang
1.1 Reliability and Prognostics
1(2)
1.2 PHM for Electronics
3(3)
1.3 PHM Approaches
6(18)
1.3.1 PoF-Based Approach
6(8)
1.3.1.1 Failure Modes, Mechanisms, and Effects Analysis (FMMEA)
7(1)
1.3.1.2 Life-Cycle Load Monitoring
8(2)
1.3.1.3 Data Reduction and Load Feature Extraction
10(2)
1.3.1.4 Data Assessment and Remaining Life Calculation
12(1)
1.3.1.5 Uncertainty Implementation and Assessment
13(1)
1.3.2 Canaries
14(2)
1.3.3 Data-Driven Approach
16(7)
1.3.3.1 Monitoring and Reasoning of Failure Precursors
16(4)
1.3.3.2 Data Analytics and Machine Learning
20(3)
1.3.4 Fusion Approach
23(1)
1.4 Implementation of PHM in a System of Systems
24(2)
1.5 PHM in the Internet of Things (IoT) Era
26(4)
1.5.1 IoT-Enabled PHM Applications: Manufacturing
27(1)
1.5.2 IoT-Enabled PHM Applications: Energy Generation
27(1)
1.5.3 IoT-Enabled PHM Applications: Transportation and Logistics
28(1)
1.5.4 IoT-Enabled PHM Applications: Automobiles
28(1)
1.5.5 IoT-Enabled PHM Applications: Medical Consumer Products
29(1)
1.5.6 IoT-Enabled PHM Applications: Warranty Services
29(1)
1.5.7 IoT-Enabled PHM Applications: Robotics
30(1)
1.6 Summary
30(1)
References
30(9)
2 Sensor Systems for PHM 39(22)
Hyunseok Oh
Michael H. Azarian
Shunfeng Cheng
Michael G. Pecht
2.1 Sensor and Sensing Principles
39(7)
2.1.1 Thermal Sensors
40(1)
2.1.2 Electrical Sensors
41(1)
2.1.3 Mechanical Sensors
42(1)
2.1.4 Chemical Sensors
42(2)
2.1.5 Humidity Sensors
44(1)
2.1.6 Biosensors
44(1)
2.1.7 Optical Sensors
45(1)
2.1.8 Magnetic Sensors
45(1)
2.2 Sensor Systems for PHM
46(8)
2.2.1 Parameters to be Monitored
47(1)
2.2.2 Sensor System Performance
48(1)
2.2.3 Physical Attributes of Sensor Systems
48(1)
2.2.4 Functional Attributes of Sensor Systems
49(4)
2.2.4.1 Onboard Power and Power Management
49(1)
2.2.4.2 Onboard Memory and Memory Management
50(1)
2.2.4.3 Programmable Sampling Mode and Sampling Rate
51(1)
2.2.4.4 Signal Processing Software
51(1)
2.2.4.5 Fast and Convenient Data Transmission
52(1)
2.2.5 Reliability
53(1)
2.2.6 Availability
53(1)
2.2.7 Cost
54(1)
2.3 Sensor Selection
54(1)
2.4 Examples of Sensor Systems for PHM Implementation
54(5)
2.5 Emerging Trends in Sensor Technology for PHM
59(1)
References
60(1)
3 Physics-of-Failure Approach to PHM 61(24)
Shunfeng Cheng
Nagarajan Raghavan
Jie Gu
Sony Mathew
Michael G. Pecht
3.1 PoF-Based PHM Methodology
61(1)
3.2 Hardware Configuration
62(1)
3.3 Loads
63(1)
3.4 Failure Modes, Mechanisms, and Effects Analysis (FMMEA)
64(7)
3.4.1 Examples of FMMEA for Electronic Devices
68(3)
3.5 Stress Analysis
71(2)
3.6 Reliability Assessment and Remaining-Life Predictions
73(4)
3.7 Outputs from PoF-Based PHM
77(1)
3.8 Caution and Concerns in the Use of PoF-Based PHM
78(2)
3.9 Combining PoF with Data-Driven Prognosis
80(1)
References
81(4)
4 Machine Learning: Fundamentals 85(26)
Myeongsu Kang
Noel Jordan Jameson
4.1 Types of Machine Learning
85(5)
4.1.1 Supervised, Unsupervised, Semi-Supervised, and Reinforcement Learning
86(2)
4.1.2 Batch and Online Learning
88(1)
4.1.3 Instance-Based and Model-Based Learning
89(1)
4.2 Probability Theory in Machine Learning: Fundamentals
90(3)
4.2.1 Probability Space and Random Variables
91(1)
4.2.2 Distributions, Joint Distributions, and Marginal Distributions
91(1)
4.2.3 Conditional Distributions
91(1)
4.2.4 Independence
92(1)
4.2.5 Chain Rule and Bayes Rule
92(1)
4.3 Probability Mass Function and Probability Density Function
93(1)
4.3.1 Probability Mass Function
93(1)
4.3.2 Probability Density Function
93(1)
4.4 Mean, Variance, and Covariance Estimation
94(2)
4.4.1 Mean
94(1)
4.4.2 Variance
94(1)
4.4.3 Robust Covariance Estimation
95(1)
4.5 Probability Distributions
96(1)
4.5.1 Bernoulli Distribution
96(1)
4.5.2 Normal Distribution
96(1)
4.5.3 Uniform Distribution
97(1)
4.6 Maximum Likelihood and Maximum A Posteriori Estimation
97(2)
4.6.1 Maximum Likelihood Estimation
97(1)
4.6.2 Maximum A Posteriori Estimation
98(1)
4.7 Correlation and Causation
99(1)
4.8 Kernel Trick
100(2)
4.9 Performance Metrics
102(5)
4.9.1 Diagnostic Metrics
102(3)
4.9.2 Prognostic Metrics
105(2)
References
107(4)
5 Machine Learning: Data Pre-processing 111(20)
Myeongsu Kang
Jing Tian
5.1 Data Cleaning
111(3)
5.1.1 Missing Data Handling
111(5)
5.1.1.1 Single-Value Imputation Methods
113(1)
5.1.1.2 Model-Based Methods
113(1)
5.2 Feature Scaling
114(2)
5.3 Feature Engineering
116(9)
5.3.1 Feature Extraction
116(5)
5.3.1.1 PCA and Kernel PCA
116(2)
5.3.1.2 LDA and Kernel LDA
118(1)
5.3.1.3 Isomap
119(1)
5.3.1.4 Self-Organizing Map (SOM)
120(1)
5.3.2 Feature Selection
121(4)
5.3.2.1 Feature Selection: Filter Methods
122(2)
5.3.2.2 Feature Selection: Wrapper Methods
124(1)
5.3.2.3 Feature Selection: Embedded Methods
124(1)
5.3.2.4 Advanced Feature Selection
125(1)
5.4 Imbalanced Data Handling
125(4)
5.4.1 Sampling Methods for Imbalanced Learning
126(7)
5.4.1.1 Synthetic Minority Oversampling Technique
126(1)
5.4.1.2 Adaptive Synthetic Sampling
126(1)
5.4.1.3 Effect of Sampling Methods for Diagnosis
127(2)
References
129(2)
6 Machine Learning: Anomaly Detection 131(32)
Myeongsu Kang
6.1 Introduction
131(2)
6.2 Types of Anomalies
133(3)
6.2.1 Point Anomalies
134(1)
6.2.2 Contextual Anomalies
134(1)
6.2.3 Collective Anomalies
135(1)
6.3 Distance-Based Methods
136(4)
6.3.1 MD Calculation Using an Inverse Matrix Method
137(1)
6.3.2 MD Calculation Using a Gram-Schmidt Orthogonalization Method
137(1)
6.3.3 Decision Rules
138(2)
6.3.3.1 Gamma Distribution: Threshold Selection
138(1)
6.3.3.2 Weibull Distribution: Threshold Selection
139(1)
6.3.3.3 Box-Cox Transformation: Threshold Selection
139(1)
6.4 Clustering-Based Methods
140(4)
6.4.1 k-Means Clustering
141(1)
6.4.2 Fuzzy c-Means Clustering
142(1)
6.4.3 Self-Organizing Maps (SOMs)
142(2)
6.5 Classification-Based Methods
144(9)
6.5.1 One-Class Classification
145(4)
6.5.1.1 One-Class Support Vector Machines
145(3)
6.5.1.2 k-Nearest Neighbors
148(1)
6.5.2 Multi-Class Classification
149(4)
6.5.2.1 Multi-Class Support Vector Machines
149(2)
6.5.2.2 Neural Networks
151(2)
6.6 Statistical Methods
153(3)
6.6.1 Sequential Probability Ratio Test
154(2)
6.6.2 Correlation Analysis
156(1)
6.7 Anomaly Detection with No System Health Profile
156(2)
6.8 Challenges in Anomaly Detection
158(1)
References
159(4)
7 Machine Learning: Diagnostics and Prognostics 163(30)
Myeongsu Kang
7.1 Overview of Diagnosis and Prognosis
163(2)
7.2 Techniques for Diagnostics
165(13)
7.2.1 Supervised Machine Learning Algorithms
165(4)
7.2.1.1 Naive Bayes
165(2)
7.2.1.2 Decision Trees
167(2)
7.2.2 Ensemble Learning
169(3)
7.2.2.1 Bagging
170(1)
7.2.2.2 Boosting: AdaBoost
171(1)
7.2.3 Deep Learning
172(6)
7.2.3.1 Supervised Learning: Deep Residual Networks
173(3)
7.2.3.2 Effect of Feature Learning-Powered Diagnosis
176(2)
7.3 Techniques for Prognostics
178(11)
7.3.1 Regression Analysis
178(7)
7.3.1.1 Linear Regression
178(2)
7.3.1.2 Polynomial Regression
180(1)
7.3.1.3 Ridge Regression
181(1)
7.3.1.4 LASSO Regression
182(1)
7.3.1.5 Elastic Net Regression
183(1)
7.3.1.6 k-Nearest Neighbors Regression
183(1)
7.3.1.7 Support Vector Regression
184(1)
7.3.2 Particle Filtering
185(14)
7.3.2.1 Fundamentals of Particle Filtering
186(1)
7.3.2.2 Resampling Methods-A Review
187(2)
References
189(4)
8 Uncertainty Representation, Quantification, and Management in Prognostics 193(28)
Shankar Sankararaman
8.1 Introduction
193(3)
8.2 Sources of Uncertainty in PHM
196(3)
8.3 Formal Treatment of Uncertainty in PHM
199(1)
8.3.1 Problem 1: Uncertainty Representation and Interpretation
199(1)
8.3.2 Problem 2: Uncertainty Quantification
199(1)
8.3.3 Problem 3: Uncertainty Propagation
200(1)
8.3.4 Problem 4: Uncertainty Management
200(1)
8.4 Uncertainty Representation and Interpretation
200(3)
8.4.1 Physical Probabilities and Testing-Based Prediction
201(1)
8.4.1.1 Physical Probability
201(1)
8.4.1.2 Testing-Based Life Prediction
201(1)
8.4.1.3 Confidence Intervals
202(1)
8.4.2 Subjective Probabilities and Condition-Based Prognostics
202(1)
8.4.2.1 Subjective Probability
202(1)
8.4.2.2 Subjective Probabilities in Condition-Based Prognostics
203(1)
8.4.3 Why is RUL Prediction Uncertain?
203(1)
8.5 Uncertainty Quantification and Propagation for RUL Prediction
203(7)
8.5.1 Computational Framework for Uncertainty Quantification
204(2)
8.5.1.1 Present State Estimation
204(1)
8.5.1.2 Future State Prediction
205(1)
8.5.1.3 RUL Computation
205(1)
8.5.2 RUL Prediction: An Uncertainty Propagation Problem
206(1)
8.5.3 Uncertainty Propagation Methods
206(5)
8.5.3.1 Sampling-Based Methods
207(2)
8.5.3.2 Analytical Methods
209(1)
8.5.3.3 Hybrid Methods
209(1)
8.5.3.4 Summary of Methods
209(1)
8.6 Uncertainty Management
210(1)
8.7 Case Study: Uncertainty Quantification in the Power System of an Unmanned Aerial Vehicle
211(4)
8.7.1 Description of the Model
211(1)
8.7.2 Sources of Uncertainty
212(1)
8.7.3 Results: Constant Amplitude Loading Conditions
213(1)
8.7.4 Results: Variable Amplitude Loading Conditions
214(1)
8.7.5 Discussion
214(1)
8.8 Existing Challenges
215(2)
8.8.1 Timely Predictions
215(1)
8.8.2 Uncertainty Characterization
216(1)
8.8.3 Uncertainty Propagation
216(1)
8.8.4 Capturing Distribution Properties
216(1)
8.8.5 Accuracy
216(1)
8.8.6 Uncertainty Bounds
216(1)
8.8.7 Deterministic Calculations
216(1)
8.9 Summary
217(1)
References
217(4)
9 PHM Cost and Return on Investment 221(40)
Peter Sandborn
Chris Wilkinson
Kiri Lee Sharon
Taoufik Jazouli
Roozbeh Bakhshi
9.1 Return on Investment
221(4)
9.1.1 PHM ROI Analyses
222(2)
9.1.2 Financial Costs
224(1)
9.2 PHM Cost-Modeling Terminology and Definitions
225(1)
9.3 PHM Implementation Costs
226(3)
9.3.1 Nonrecurring Costs
226(1)
9.3.2 Recurring Costs
227(1)
9.3.3 Infrastructure Costs
228(1)
9.3.4 Nonmonetary Considerations and Maintenance Culture
228(1)
9.4 Cost Avoidance
229(9)
9.4.1 Maintenance Planning Cost Avoidance
231(1)
9.4.2 Discrete-Event Simulation Maintenance Planning Model
232(1)
9.4.3 Fixed-Schedule Maintenance Interval
233(1)
9.4.4 Data-Driven (Precursor to Failure Monitoring) Methods
233(1)
9.4.5 Model-Based (LRU-Independent) Methods
234(2)
9.4.6 Discrete-Event Simulation Implementation Details
236(1)
9.4.7 Operational Profile
237(1)
9.5 Example PHM Cost Analysis
238(8)
9.5.1 Single-Socket Model Results
239(2)
9.5.2 Multiple-Socket Model Results
241(5)
9.6 Example Business Case Construction: Analysis for ROI
246(9)
9.7 Summary
255(1)
References
255(6)
10 Valuation and Optimization of PHM-Enabled Maintenance Decisions 261(18)
Xin Lei
Amir Reza Kashani-Pour
Peter Sandborn
Taoufik Jazouli
10.1 Valuation and Optimization of PHM-Enabled Maintenance Decisions for an Individual System
262(6)
10.1.1 A PHM-Enabled Predictive Maintenance Optimization Model for an Individual System
263(2)
10.1.2 Case Study: Optimization of PHM-Enabled Maintenance Decisions for an Individual System (Wind Turbine)
265(3)
10.2 Availability
268(4)
10.2.1 The Business of Availability: Outcome-Based Contracts
269(1)
10.2.2 Incorporating Contract Terms into Maintenance Decisions
270(1)
10.2.3 Case Study: Optimization of PHM-Enabled Maintenance Decisions for Systems (Wind Farm)
270(2)
10.3 Future Directions
272(5)
10.3.1 Design for Availability
272(3)
10.3.2 Prognostics-Based Warranties
275(1)
10.3.3 Contract Engineering
276(1)
References
277(2)
11 Health and Remaining Useful Life Estimation of Electronic Circuits 279(50)
Arvind Sai Sarathi Vasan
Michael G. Pecht
11.1 Introduction
279(2)
11.2 Related Work
281(4)
11.2.1 Component-Centric Approach
281(1)
11.2.2 Circuit-Centric Approach
282(3)
11.3 Electronic Circuit Health Estimation Through Kernel Learning
285(21)
11.3.1 Kernel-Based Learning
285(1)
11.3.2 Health Estimation Method
286(6)
11.3.2.1 Likelihood-Based Function for Model Selection
288(1)
11.3.2.2 Optimization Approach for Model Selection
289(3)
11.3.3 Implementation Results
292(14)
11.3.3.1 Bandpass Filter Circuit
293(7)
11.3.3.2 DC-DC Buck Converter System
300(6)
11.4 RUL Prediction Using Model-Based Filtering
306(16)
11.4.1 Prognostics Problem Formulation
306(1)
11.4.2 Circuit Degradation Modeling
307(3)
11.4.3 Model-Based Prognostic Methodology
310(3)
11.4.4 Implementation Results
313(21)
11.4.4.1 Low-Pass Filter Circuit
313(2)
11.4.4.2 Voltage Feedback Circuit
315(5)
11.4.4.3 Source of RUL Prediction Error
320(1)
11.4.4.4 Effect of First-Principles-Based Modeling
320(2)
11.5 Summary
322(2)
References
324(5)
12 PHM-Based Qualification of Electronics 329(20)
Preeti S. Chauhan
12.1 Why is Product Qualification Important?
329(2)
12.2 Considerations for Product Qualification
331(3)
12.3 Review of Current Qualification Methodologies
334(11)
12.3.1 Standards-Based Qualification
334(3)
12.3.2 Knowledge-Based or PoF-Based Qualification
337(3)
12.3.3 Prognostics and Health Management-Based Qualification
340(11)
12.3.3.1 Data-Driven Techniques
340(3)
12.3.3.2 Fusion Prognostics
343(2)
12.4 Summary
345(1)
References
346(3)
13 PHM of Li-ion Batteries 349(28)
Saurabh Saxena
Yinjiao Xing
Michael G. Pecht
13.1 Introduction
349(2)
13.2 State of Charge Estimation
351(14)
13.2.1 SOC Estimation Case Study I
352(5)
13.2.1.1 NN Model
353(1)
13.2.1.2 Training and Testing Data
354(1)
13.2.1.3 Determination of the NN Structure
355(1)
13.2.1.4 Training and Testing Results
356(1)
13.2.1.5 Application of Unscented Kalman Filter
357(1)
13.2.2 SOC Estimation Case Study II
357(8)
13.2.2.1 OCV-SOC-T Test
358(1)
13.2.2.2 Battery Modeling and Parameter Identification
359(1)
13.2.2.3 OCV-SOC-T Table for Model Improvement
360(2)
13.2.2.4 Validation of the Proposed Model
362(1)
13.2.2.5 Algorithm Implementation for Online Estimation
362(3)
13.3 State of Health Estimation and Prognostics
365(6)
13.3.1 Case Study for Li-ion Battery Prognostics
366(12)
13.3.1.1 Capacity Degradation Model
366(2)
13.3.1.2 Uncertainties in Battery Prognostics
368(1)
13.3.1.3 Model Updating via Bayesian Monte Carlo
368(1)
13.3.1.4 SOH Prognostics and RUL Estimation
369(2)
13.3.1.5 Prognostic Results
371(1)
13.4 Summary
371(1)
References
372(5)
14 PHM of Light-Emitting Diodes 377(54)
Moon-Hwan Chang
Jiajie Fan
Cheng Qian
Bo Sun
14.1 Introduction
377(1)
14.2 Review of PHM Methodologies for LEDs
378(10)
14.2.1 Overview of Available Prognostic Methods
378(1)
14.2.2 Data-Driven Methods
379(6)
14.2.2.1 Statistical Regression
379(2)
14.2.2.2 Static Bayesian Network
381(1)
14.2.2.3 Kalman Filtering
382(1)
14.2.2.4 Particle Filtering
383(1)
14.2.2.5 Artificial Neural Network
384(1)
14.2.3 Physics-Based Methods
385(2)
14.2.4 LED System-Level Prognostics
387(1)
14.3 Simulation-Based Modeling and Failure Analysis for LEDs
388(13)
14.3.1 LED Chip-Level Modeling and Failure Analysis
389(6)
14.3.1.1 Electro-optical Simulation of LED Chip
389(4)
14.3.1.2 LED Chip-Level Failure Analysis
393(2)
14.3.2 LED Package-Level Modeling and Failure Analysis
395(4)
14.3.2.1 Thermal and Optical Simulation for Phosphor-Converted White LED Package
395(2)
14.3.2.2 LED Package-Level Failure Analysis
397(2)
14.3.3 LED System-Level Modeling and Failure Analysis
399(2)
14.4 Return-on-Investment Analysis of Applying Health Monitoring to LED Lighting Systems
401(18)
14.4.1 ROI Methodology
403(3)
14.4.2 ROI Analysis of Applying System Health Monitoring to LED Lighting Systems
406(26)
14.4.2.1 Failure Rates and Distributions for ROI Simulation
407(3)
14.4.2.2 Determination of Prognostics Distance
410(2)
14.4.2.3 IPHM, CPHM, and Cu Evaluation
412(5)
14.4.2.4 ROI Evaluation
417(2)
14.5 Summary
419(1)
References
420(11)
15 PHM in Healthcare 431(20)
Mary Capelli-Schellpfeffer
Myeongsu Kang
Michael G. Pecht
15.1 Healthcare in the United States
431(1)
15.2 Considerations in Healthcare
432(6)
15.2.1 Clinical Consideration in Implantable Medical Devices
432(1)
15.2.2 Considerations in Care Bots
433(5)
15.3 Benefits of PHM
438(4)
15.3.1 Safety Increase
439(1)
15.3.2 Operational Reliability Improvement
440(1)
15.3.3 Mission Availability Increase
440(1)
15.3.4 System's Service Life Extension
441(1)
15.3.5 Maintenance Effectiveness Increase
441(1)
15.4 PHM of Implantable Medical Devices
442(2)
15.5 PHM of Care Bots
444(1)
15.6 Canary-Based Prognostics of Healthcare Devices
445(2)
15.7 Summary
447(1)
References
447(4)
16 PHM of Subsea Cables 451(28)
David Flynn
Christopher Bailey
Pushpa Rajaguru
Wenshuo Tang
Chunyan Yin
16.1 Subsea Cable Market
451(1)
16.2 Subsea Cables
452(2)
16.3 Cable Failures
454(3)
16.3.1 Internal Failures
455(1)
16.3.2 Early-Stage Failures
455(1)
16.3.3 External Failures
455(1)
16.3.4 Environmental Conditions
455(1)
16.3.5 Third-Party Damage
456(1)
16.4 State-of-the-Art Monitoring
457(1)
16.5 Qualifying and Maintaining Subsea Cables
458(2)
16.5.1 Qualifying Subsea Cables
458(1)
16.5.2 Mechanical Tests
458(1)
16.5.3 Maintaining Subsea Cables
459(1)
16.6 Data-Gathering Techniques
460(1)
16.7 Measuring the Wear Behavior of Cable Materials
461(2)
16.8 Predicting Cable Movement
463(3)
16.8.1 Sliding Distance Derivation
463(2)
16.8.2 Scouring Depth Calculations
465(1)
16.9 Predicting Cable Degradation
466(2)
16.9.1 Volume Loss due to Abrasion
466(1)
16.9.2 Volume Loss due to Corrosion
466(2)
16.10 Predicting Remaining Useful Life
468(3)
16.11 Case Study
471(1)
16.12 Future Challenges
471(3)
16.12.1 Data-Driven Approach for Random Failures
471(2)
16.12.2 Model-Driven Approach for Environmental Failures
473(8)
16.12.2.1 Fusion-Based PHM
473(1)
16.12.2.2 Sensing Techniques
474(1)
16.13 Summary
474(1)
References
475(4)
17 Connected Vehicle Diagnostics and Prognostics 479(24)
Yilu Zhang
Xinyu Du
17.1 Introduction
479(2)
17.2 Design of an Automatic Field Data Analyzer
481(5)
17.2.1 Data Collection Subsystem
482(1)
17.2.2 Information Abstraction Subsystem
482(1)
17.2.3 Root Cause Analysis Subsystem
482(4)
17.2.3.1 Feature-Ranking Module
482(2)
17.2.3.2 Relevant Feature Set Selection
484(2)
17.2.3.3 Results Interpretation
486(1)
17.3 Case Study: CVDP for Vehicle Batteries
486(12)
17.3.1 Brief Background of Vehicle Batteries
486(2)
17.3.2 Applying AFDA for Vehicle Batteries
488(1)
17.3.3 Experimental Results
489(17)
17.3.3.1 Information Abstraction
490(1)
17.3.3.2 Feature Ranking
490(5)
17.3.3.3 Interpretation of Results
495(3)
17.4 Summary
498(1)
References
499(4)
18 The Role of PHM at Commercial Airlines 503(32)
Rhonda Walthall
Ravi Rajamani
18.1 Evolution of Aviation Maintenance
503(3)
18.2 Stakeholder Expectations for PHM
506(7)
18.2.1 Passenger Expectations
506(1)
18.2.2 Airline/Operator/Owner Expectations
507(2)
18.2.3 Airframe Manufacturer Expectations
509(1)
18.2.4 Engine Manufacturer Expectations
510(1)
18.2.5 System and Component Supplier Expectations
511(1)
18.2.6 MRO Organization Expectations
512(1)
18.3 PHM Implementation
513(4)
18.3.1 SATAA
513(4)
18.4 PHM Applications
517(15)
18.4.1 Engine Health Management (EHM)
517(7)
18.4.1.1 History of EHM
518(1)
18.4.1.2 EHM Infrastructure
519(1)
18.4.1.3 Technologies Associated with EHM
520(3)
18.4.1.4 The Future
523(1)
18.4.2 Auxiliary Power Unit (APU) Health Management
524(1)
18.4.3 Environmental Control System (ECS) and Air Distribution Health Monitoring
525(1)
18.4.4 Landing System Health Monitoring
526(1)
18.4.5 Liquid Cooling System Health Monitoring
526(1)
18.4.6 Nitrogen Generation System (NGS) Health Monitoring
527(1)
18.4.7 Fuel Consumption Monitoring
527(1)
18.4.8 Flight Control Actuation Health Monitoring
528(1)
18.4.9 Electric Power System Health Monitoring
529(1)
18.4.10 Structural Health Monitoring (SHM)
529(2)
18.4.11 Battery Health Management
531(1)
18.5 Summary
532(1)
References
533(2)
19 PHM Software for Electronics 535(24)
Noel Jordan Jameson
Myeongsu Kang
Jing Tian
19.1 PHM Software: CALCE Simulation Assisted Reliability Assessment
535(5)
19.2 PHM Software: Data-Driven
540(17)
19.2.1 Data Flow
541(1)
19.2.2 Master Options
542(1)
19.2.3 Data Pre-processing
543(2)
19.2.4 Feature Discovery
545(1)
19.2.5 Anomaly Detection
546(2)
19.2.6 Diagnostics/Classification
548(4)
19.2.7 Prognostics/Modeling
552(2)
19.2.8 Challenges in Data-Driven PHM Software Development
554(3)
19.3 Summary
557(2)
20 eMaintenance 559(30)
Ramin Karim
Phillip Tretten
Uday Kumar
20.1 From Reactive to Proactive Maintenance
559(1)
20.2 The Onset of eMaintenance
560(1)
20.3 Maintenance Management System
561(3)
20.3.1 Life-cycle Management
562(2)
20.3.2 eMaintenance Architecture
564(1)
20.4 Sensor Systems
564(1)
20.4.1 Sensor Technology for PHM
565(1)
20.5 Data Analysis
565(1)
20.6 Predictive Maintenance
566(1)
20.7 Maintenance Analytics
567(3)
20.7.1 Maintenance Descriptive Analytics
568(1)
20.7.2 Maintenance Analytics and eMaintenance
568(1)
20.7.3 Maintenance Analytics and Big Data
568(2)
20.8 Knowledge Discovery
570(1)
20.9 Integrated Knowledge Discovery
571(1)
20.10 User Interface for Decision Support
572(1)
20.11 Applications of eMaintenance
572(13)
20.11.1 eMaintenance in Railways
572(2)
20.11.1.1 Railway Cloud: Swedish Railway Data
573(1)
20.11.1.2 Railway Cloud: Service Architecture
573(1)
20.11.1.3 Railway Cloud: Usage Scenario
574(1)
20.11.2 eMaintenance in Manufacturing
574(2)
20.11.3 MEMS Sensors for Bearing Vibration Measurement
576(1)
20.11.4 Wireless Sensors for Temperature Measurement
576(1)
20.11.5 Monitoring Systems
576(2)
20.11.6 eMaintenance Cloud and Servers
578(2)
20.11.7 Dashboard Managers
580(1)
20.11.8 Alarm Servers
580(1)
20.11.9 Cloud Services
581(2)
20.11.10 Graphic User Interfaces
583(2)
20.12 Internet Technology and Optimizing Technology
585(1)
References
586(3)
21 Predictive Maintenance in the loT Era 589(24)
Rashmi B. Shetty
21.1 Background
589(6)
21.1.1 Challenges of a Maintenance Program
590(1)
21.1.2 Evolution of Maintenance Paradigms
590(2)
21.1.3 Preventive Versus Predictive Maintenance
592(1)
21.1.4 P-F Curve
592(2)
21.1.5 Bathtub Curve
594(1)
21.2 Benefits of a Predictive Maintenance Program
595(1)
21.3 Prognostic Model Selection for Predictive Maintenance
596(2)
21.4 Internet of Things
598(1)
21.4.1 Industrial IoT
598(1)
21.5 Predictive Maintenance Based on IoT
599(1)
21.6 Predictive Maintenance Usage Cases
600(1)
21.7 Machine Learning Techniques for Data-Driven Predictive Maintenance
600(4)
21.7.1 Supervised Learning
602(1)
21.7.2 Unsupervised Learning
602(1)
21.7.3 Anomaly Detection
602(1)
21.7.4 Multi-class and Binary Classification Models
603(1)
21.7.5 Regression Models
604(1)
21.7.6 Survival Models
604(1)
21.8 Best Practices
604(6)
21.8.1 Define Business Problem and Quantitative Metrics
605(1)
21.8.2 Identify Assets and Data Sources
605(1)
21.8.3 Data Acquisition and Transformation
606(1)
21.8.4 Build Models
607(1)
21.8.5 Model Selection
607(1)
21.8.6 Predict Outcomes and Transform into Process Insights
608(1)
21.8.7 Operationalize and Deploy
609(1)
21.8.8 Continuous Monitoring
609(1)
21.9 Challenges in a Successful Predictive Maintenance Program
610(1)
21.9.1 Predictive Maintenance Management Success Key Performance Indicators (KPIs)
610(1)
21.10 Summary
611(1)
References
611(2)
22 Analysis of PHM Patents for Electronics 613(36)
Zhenbao Liu
Zhen Jia
Chi-Man Vong
Shuhui Bu
Michael G. Pecht
22.1 Introduction
613(3)
22.2 Analysis of PHM Patents for Electronics
616(3)
22.2.1 Sources of PHM Patents
616(1)
22.2.2 Analysis of PHM Patents
617(2)
22.3 Trend of Electronics PHM
619(19)
22.3.1 Semiconductor Products and Computers
619(3)
22.3.2 Batteries
622(4)
22.3.3 Electric Motors
626(3)
22.3.4 Circuits and Systems
629(2)
22.3.5 Electrical Devices in Automobiles and Airplanes
631(3)
22.3.6 Networks and Communication Facilities
634(2)
22.3.7 Others
636(2)
22.4 Summary
638(1)
References
639(10)
23 A PHM Roadmap for Electronics-Rich Systems 649(42)
Michael G. Pecht
23.1 Introduction
649(1)
23.2 Roadmap Classifications
650(13)
23.2.1 PHM at the Component Level
651(6)
23.2.1.1 PHM for Integrated Circuits
652(1)
23.2.1.2 High-Power Switching Electronics
652(1)
23.2.1.3 Built-In Prognostics for Components and Circuit Boards
653(1)
23.2.1.4 Photo-Electronics Prognostics
654(2)
23.2.1.5 Interconnect and Wiring Prognostics
656(1)
23.2.2 PHM at the System Level
657(6)
23.2.2.1 Legacy Systems
657(2)
23.2.2.2 Environmental and Operational Monitoring
659(1)
23.2.2.3 LRU to Device Level
659(1)
23.2.2.4 Dynamic Reconfiguration
659(1)
23.2.2.5 System Power Management and PHM
660(1)
23.2.2.6 PHM as Knowledge Infrastructure for System Development
660(1)
23.2.2.7 Prognostics for Software
660(1)
23.2.2.8 PHM for Mitigation of Reliability and Safety Risks
661(1)
23.2.2.9 PHM in Supply Chain Management and Product Maintenance
662(1)
23.3 Methodology Development
663(11)
23.3.1 Best Algorithms
664(6)
23.3.1.1 Approaches to Training
667(1)
23.3.1.2 Active Learning for Unlabeled Data
667(1)
23.3.1.3 Sampling Techniques and Cost-Sensitive Learning for Imbalanced Data
668(1)
23.3.1.4 Transfer Learning for Knowledge Transfer
668(1)
23.3.1.5 Internet of Things and Big Data Analytics
669(1)
23.3.2 Verification and Validation
670(1)
23.3.3 Long-Term PHM Studies
671(1)
23.3.4 PHM for Storage
671(1)
23.3.5 PHM for No-Fault-Found/Intermittent Failures
672(1)
23.3.6 PHM for Products Subjected to Indeterminate Operating Conditions
673(1)
23.4 Nontechnical Barriers
674(6)
23.4.1 Cost, Return on Investment, and Business Case Development
674(2)
23.4.2 Liability and Litigation
676(1)
23.4.2.1 Code Architecture: Proprietary or Open?
676(1)
23.4.2.2 Long-Term Code Maintenance and Upgrades
676(1)
23.4.2.3 False Alarms, Missed Alarms, and Life-Safety Implications
677(1)
23.4.2.4 Warranty Restructuring
677(1)
23.4.3 Maintenance Culture
677(1)
23.4.4 Contract Structure
677(1)
23.4.5 Role of Standards Organizations
678(2)
23.4.5.1 IEEE Reliability Society and PHM Efforts
678(1)
23.4.5.2 SAE PHM Standards
678(1)
23.4.5.3 PHM Society
679(1)
23.4.6 Licensing and Entitlement Management
680(1)
References
680(11)
Appendix A: Commercially Available Sensor Systems for PHM 691(30)
A.1 SmartButton-ACR Systems
691(2)
A.2 OWL 400-ACR Systems
693(2)
A.3 SAVER™ 3X90-Lansmont Instruments
695(2)
A.4 G-Link®-LXRS®-LORD MicroStrain® Sensing Systems
697(2)
A.5 V-Link®-LXRS®-LORD MicroStrain Sensing Systems
699(3)
A.6 3DM-GX4-25™-LORD MicroStrain Sensing Systems
702(2)
A.7 IEPE-Link™-LXRS®-LORD MicroStrain Sensing Systems
704(2)
A.8 ICHM® 20/20-Oceana Sensor
706(2)
A.9 Environmental Monitoring System 200™-Upsite Technologies
708(2)
A.10 S2NAP®-RLW Inc.
710(2)
A.11 SR1 Strain Gage Indicator-Advance Instrument Inc.
712(2)
A.12 P3 Strain Indicator and Recorder-Micro-Measurements
714(2)
A.13 Airscale Suspension-Based Weighing System-VPG Inc.
716(2)
A.14 Radio Microlog-Transmission Dynamics
718(3)
Appendix B: Journals and Conference Proceedings Related to PHM 721(4)
B.1 Journals
721(1)
B.2 Conference Proceedings
722(3)
Appendix C: Glossary of Terms and Definitions 725(6)
Index 731
MICHAEL G. PECHT, PHD, is Chair Professor in Mechanical Engineering and Professor in Applied Mathematics, Statistics and Scientific Computation at the University of Maryland, USA. He is the Founder and Director of the Center for Advanced Life Cycle Engineering (CALCE) at the University of Maryland, USA, which is funded by more than 150 leading electronics companies. Dr. Pecht is an IEEE, ASME, SAE, and IMAPS Fellow and serves as editor-in-chief of IEEE Access. He has written more than 30 books, 700 technical articles, and has 8 patents.

MYEONGSU KANG, PHD, is currently a Research Associate at the Center for Advanced Life Cycle Engineering (CALCE), University of Maryland, USA. His expertise is in data analytics, machine learning, system modeling, and statistics for prognostics and systems health management. He has authored/coauthored more than 60 publications in leading journals and conference proceedings.