PREFACE
Chapter 1 Background of Systems Health Management
1.1 Introduction
1.2 Maintenance Strategy
1.3 From Maintenance to PHM
1.4 Definitions and Terms of Systems Health Management
1.5 Preface to Book Chapters
1.6 References
Chapter 2 Design Approach for Systems Health Management
2.1 Introduction
2.2 Systems Engineering
2.3 Systems Engineering, Dependability, and Health Management
2.4 SHM Lifecycle Stages
2.4.1 Research stage
2.4.2 Requirements development stage
2.4.3 System/functional analysis
2.4.4 Design, synthesis and integration
2.4.5 System test and evaluation
2.4.6 HM system maturation
2.5 A Systems-based Methodology for CBM/PHM Design
2.6 References
Chapter 3 Technical Approaches for Systems Health Management
3.1 Introduction
3.2 Data-Driven Approaches
3.3 Model-Based Approaches
3.4 Hybrid Approaches
3.5 OSA-CBM Architecture
3.6 Problems during Implementation
3.7 Related Techniques
3.8 References
Chapter 4 Sensors and Data Acquisition
4.1 Introduction
4.2 Data Acquisition
4.2.1 Selecting a proper measure
4.2.2 Vibration transducers
4.2.3 Transducer selection
4.2.4 Transducer mounting
4.2.5 Transducer location
4.2.6 Frequency spans
4.2.7 Data display
4.3 References
Chapter 5 Signal Processing and Feature Representation
5.1 Signal Processing
5.2 Feature Representation
5.2.1 Features in time domain
5.2.2 Features in frequency domain
5.2.3 Features in auto-regression domain
5.3 References
Chapter 6 Feature Extraction
6.1 Introduction
6.2 Basic Concepts
6.2.1 Pattern and feature vector
6.2.2 Class
6.3 Parameter Evaluation Technique
6.4 Principal Component Analysis (PCA)
6.5 Kernel PCA
6.6 Fisher Discriminant Analysis (FDA)
6.7 Linear Discriminant Analysis (LDA)
6.8 References
Chapter 7 Fault Diagnosis
7.1 Introduction
7.2 Data-Driven Diagnosis
7.2.1 Classifier concepts
7.2.2 k-nearest neighbors (k-NN)
7.2.3 Bayesian classifier
7.2.4 Support vector machines (SVMs)
7.2.5 Self-organizing feature map (SOFM) neural network
7.3 Model-Based Diagnosis
7.3.1 Classification methods
7.3.2 Inference methods
7.4 References
Chapter 8 Failure Prognosis
8.1 Introduction
8.2 Prognosis Approaches
8.2.1 Rule-based approaches
8.2.2 Fuzzy logic approaches
8.2.3 Model-based approaches
8.2.4 Trend-based evolutionary approaches
8.2.5 Data-driven model based approaches
8.2.6 State estimator-based approaches
8.2.7 Statistical reliability and usage-based approaches
8.2.8 Adaptive prognosis
8.2.9 Data mining and automated rule extraction
8.2.1 0 Distributed prognostic system architecture
8.3 Applications
8.3.1 Bearing prognosis
8.3.2 Gear prognosis
8.4 References
Chapter 9 Data Fusion
9.1 Introduction
9.2 Fusion Application Areas
9.3 Data Fusion Architectures
9.3.1 Data-level fusion
9.3.2 Feature-level fusion
9.3.3 Decision-level fusion
9.4 Data Fusion Techniques at Decision-Level
9.4.1 Voting method
9.4.2 Bayesian belief fusion
9.4.3 Multi-agent fusion
9.5 Data Fusion for Condition Monitoring
9.5.1 A proposed fusion system for condition monitoring
9.5.2 Degradation indicator using SOM neural network fusion
9.5.3 Automatic alarm setting strategy
9.5.4 Detection matrix
9.6 Data Fusion for Fault Diagnosis
9.6.1 Classifier selection
9.6.2 Decision fusion system
9.6.3 Faults diagnosis of test-rig motors using fusion techniques
9.7 Data Fusion for Failure Prognostics
9.7.1 A proposed fusion strategy for failure prognostics
9.7.2 Time series prediction
9.8 References
Chapter 10 Cases Study for Rail Vehicle Systems Health Management
10.1 Introduction
10.2 Health Management of Locomotive Roller Bearings
10.2.1 Fault diagnosis of roller bearings
10.2.2 Failure prognosis of roller bearings
10.3 Fault Diagnosis of Locomotive Elector-Pneumatic Brake
10.4 In Situ Health Monitoring for Bogie Systems of CRH 380 Train
10.5 Health Assessment and Prognosis for Point Machines
10.5.1 Health assessment of point machines
10.5.2 State-based prognosis for point machines
10.6 References
