This book unifies existing and emerging concepts concerning state estimation, fault detection, fault isolation and fault estimation on industrial systems with an emphasis on a variety of network-induced phenomena, fault diagnosis and remaining useful life for industrial equipment. It covers state estimation/monitor, fault diagnosis and remaining useful life prediction by drawing on the conventional theories of systems science, signal processing and machine learning.
Features
Unifies existing and emerging concepts concerning robust filtering and fault diagnosis with an emphasis on a variety of network-induced complexities.
Explains theories, techniques, and applications of state estimation as well as fault diagnosis from an engineering-oriented perspective.
Provides a series of latest results in robust/stochastic filtering, multidate sample, and time-varying system.
Captures diagnosis (fault detection, fault isolation and fault estimation) for time-varying multi-rate systems.
Includes simulation examples in each chapter to reflect the engineering practice.
This book aims at graduate students, professionals and researchers in control science and application, system analysis, artificial intelligence, and fault diagnosis.
Author(s): Yong Zhang, Zidong Wang, Ye Yuan
Publisher: CRC Press
Year: 2023
Language: English
Pages: 289
City: Boca Raton
Cover
Half Title
Title Page
Copyright Page
Dedication
Contents
Preface
Acknowledgements
Author Biographies
List of Figures
List of Tables
Symbols
1. Introduction
1.1. Introduction
1.2. Fault Diagnosis
1.2.1. Filter-Based Fault Diagnosis
1.2.2. Data-Driven Fault Diagnosis
1.3. Remaining Useful Life Prediction
1.3.1. Data-Driven Remaining Useful Life Prediction
1.3.2. Filter-Based Remaining Useful Life Prediction
1.4. Outline of This Book
2. Filter/Estimator Design of Networked Multi-rate Sampled Systems with Network-Induced Phenomena
2.1. Estimator Design with Measurement Quantization and Sensor Failures
2.1.1. Problem Formulation
2.1.2. Variance-Constrained Estimator Design
2.1.3. Illustrative Examples
2.2. Finite-Time Filter Design with Event-Based Relay and Fading Channels
2.2.1. Problem Formulation
2.2.2. Finite-Time Filter Design
2.2.3. Illustrative Examples
2.3. Conclusion
3. Fault Detection of Networked Multi-rate Systems with Filter-Based Methods
3.1. Fault Detection with Fading Measurements and Randomly Occurring Faults
3.1.1. Problem Formulation
3.1.2. Detection of Randomly Occurring Faults
3.1.3. Illustrative Examples
3.2. Fault Detection with Dynamic Quantization and Intermittent Faults
3.2.1. Problem Formulation
3.2.2. Detection of Intermittent Faults
3.2.3. Illustrative Example
3.3. Conclusion
4. Fault Diagnosis of Multi-rate Time-Varying Systems with Filter-Based Methods
4.1. Event-Based Fault Diagnosis with Constrained Fault
4.1.1. Problem Formulation
4.1.2. Fault Detection and Fault Isolation
4.1.3. Illustrative Examples
4.2. Event-Based Fault Diagnosis with Bounded Unknown Fault
4.2.1. Problem Formulation
4.2.2. Fault Diagnosis and Fault Estimation
4.2.3. Illustrative Examples
4.3. Conclusion
5. Fault Diagnosis of Modular Multilevel Converters with Machine Learning Methods
5.1. Fault Diagnosis with Mixed Kernel Support Tensor Machine
5.1.1. Operating Principles of Modular Multilevel Converters
5.1.2. Mixed Kernel Support Tensor Machine
5.1.3. Fault Diagnosis
5.1.4. Illustrative Examples
5.2. Fault Diagnosis with Synchrosqueezing Transform and Optimized Deep CNN
5.2.1. Synchrosqueezing Transform
5.2.2. Optimized Deep Convolutional Neural Network
5.2.3. Fault Diagnosis
5.2.4. Illustrative Examples
5.3. Conclusion
6. Remaining Useful Life Prediction of Industrial Components with Filter-Based Methods
6.1. Remaining Useful Life Prediction with Adaptive UKF and SVR
6.1.1. Genetic Algorithm Optimized Support Vector Regression
6.1.2. Remaining Useful Life Prediction of Lithium-Ion Batteries
6.1.3. Illustrative Examples
6.2. Remaining Useful Life Prediction with ALF-Optimized PF and LSTM
6.2.1. Adaptive Levy Flight Optimized Particle Filter
6.2.2. Remaining Useful Life Prediction of Lithium-Ion Batteries
6.2.3. Illustrative Examples
6.3. Remaining Useful Life Prediction with Degradation Point Detection and EKF
6.3.1. Degradation Point Detection
6.3.2. Health Indicator Construction
6.3.3. Remaining Useful Life Prediction of Bearings
6.3.4. Illustrative Examples
6.4. Conclusion
7. Remaining Useful Life Prediction of Industrial Components with Machine Learning Methods
7.1. Remaining Useful Life Prediction with WPT and Optimized SVR
7.1.1. Degenerate Point Detection
7.1.2. Remaining Useful Life Prediction of Turbine Engines
7.1.3. Illustrative Examples
7.2. Remaining Useful Life Prediction with Complete Ensemble EMD and GRU
7.2.1. Health Indicator Construction
7.2.2. Remaining Useful Life Prediction of Bearings
7.2.3. Illustrative Examples
7.3. Remaining Useful Life Prediction with PSR and Error Compensation
7.3.1. Health Indicator Construction
7.3.2. Remaining Useful Life Prediction of Lithium-Ion Batteries
7.3.3. Illustrative Examples
7.4. Conclusion
8. Conclusions and Future Topics
Bibliography
Index
