1 Introduction 1.1 Overview of Intelligent Electromechanical System 1.1.1 High-Speed Trains 1.1.2 Robots 1.1.3 New Energy Vehicles 1.2 Research Status of Prognostics and Health Management in Intelligent Electromechanical System 1.2.1 Fault Diagnosis 1.2.2 Remaining Useful Life Prediction 1.3 Methodology of Prognostics and Health Management in Intelligent Electromechanical System 1.3.1 Feature Extraction Method 1.3.2 Prediction Model 1.3.3 Error Modification Model 1.4 The Necessity of Big Data Embedding in Prognostics and Health Management for Intelligent Electromechanical Systems 1.5 Scope of the Book References 2 Feature Extraction of Bearing Vibration Signal 2.1 Introduction 2.2 Data Acquisition 2.3 Frequency Domain Feature Extraction 2.3.1 The Theoretical Basis of Continuous Wavelet Transform 2.3.2 Feature Extraction 2.3.3 Feature Evaluation 2.4 Decomposition-Based Feature Extraction 2.4.1 The Theoretical Basis of Variational Modal Decomposition 2.4.2 Feature Extraction 2.4.3 Feature Evaluation 2.5 Deep Learning Feature Extraction 2.5.1 The Theoretical Basis of Convolutional Neural Network 2.5.2 Feature Extraction 2.5.3 Feature Evaluation References 3 Ensemble Intelligent Diagnosis for Bearing Faults 3.1 Introduction 3.2 Data Acquisition 3.3 Ensemble Diagnostic Model Based on Multi-objective Grey Wolf Optimizer for Bearing Faults 3.3.1 The Theoretical Basis of Empirical Wavelet Transform 3.3.2 The Theoretical Basis of Random Tree 3.3.3 The Theoretical Basis of Multi-objective Grey Wolf Optimizer 3.3.4 Experimental Result and Analysis 3.4 Boosting Ensemble Diagnostic Model for Bearing Faults 3.4.1 The Theoretical Basis of Empirical Mode Decomposition 3.4.2 The Theoretical Basis of Boosting 3.4.3 The Theoretical Basis of the Osprey-Cauchy-Sparrow Search Algorithm 3.4.4 Experimental Result and Analysis 3.5 Model Performance Comparison 3.6 Conclusions References 4 Deep Learning Prediction for Bearing Remaining Useful Life 4.1 Introduction 4.2 Data Acquisition
4.3 BiLSTM-Based Predictive Model for Bearing Remaining Useful Life 4.3.1 The Theoretical Basis Convolutional Neural Network 4.3.2 The Theoretical Basis Bidirectional Long Short-Term Memory 4.3.3 Experimental Result and Analysis 4.4 GRU-Based Predictive Model for Bearing Remaining Useful Life 4.4.1 The Theoretical Basis Gate Recurrent Unit 4.4.2 The Theoretical Basis Attention 4.4.3 Experimental Result and Analysis 4.5 Model Performance Comparison 4.6 Conclusions References 5 Optimization Based Prediction for IGBT Remaining Useful Life 5.1 Introduction 5.2 Data Acquisition 5.3 Predictive Model for IGBT Remaining Useful Life Based on Particle Swarm Optimization 5.3.1 Health Indicator Based on Particle Swarm Optimization 5.3.2 RUL Prediction Based on the Similarity 5.4 Predictive Model for IGBT Remaining Useful Life Based on Bat Optimization 5.5 Model Performance Comparison 5.6 Application in Front-Wheel Steering Mobile Robot Fault-Tolerant Control 5.6.1 Front-Wheel Steering Mobile Robot System 5.6.2 Control Design 5.6.3 Simulation Results 5.7 Conclusions References 6 Decomposition Based Prediction for MOSFET Remaining Useful Life 6.1 Introduction 6.2 Data Acquisition 6.3 Predictive Model for MOSFET Remaining Useful Life Based on Wavelet Packet Decomposition 6.3.1 Feature Extraction Based on Wavelet Packet Decomposition 6.3.2 The Theoretical Basis of Autoregressive Integrated Moving Average Model 6.3.3 Experimental Result and Analysis 6.4 Predictive Model for MOSFET Remaining Useful Life Based on Complete Ensemble Empirical Mode Decomposition 6.4.1 Feature Extraction Based on Complete Ensemble Empirical Mode Decomposition 6.4.2 The Theoretical Basis of Long Short-Term Memory Model 6.4.3 Experimental Result and Analysis 6.5 Model Performance Comparison 6.6 Applications in Wheeled Mobile Robot Fault-Tolerant Control 6.6.1 Fault-Tolerant Control 6.6.2 Applications in Wheeled Mobile Robot 6.6.3 Performance Analysis 6.7 Conclusions References 7 Linear Networks and Temporal Convolution Based Prediction for Capacitor Remaining Useful Life 7.1 Introduction 7.2 Data Acquisition 7.3 Predictive Model for Capacitor Remaining Useful Life Based on MSD-Mixer 7.3.1 The Theoretical Basis Linear Network 7.3.2 The Theoretical Basis of MSD-Mixer 7.3.3 Experimental Result and Analysis
7.4 Predictive Model for Capacitor Remaining Useful Life Based on TimesNet 7.4.1 The Theoretical Basis of Temporal Convolutional Networks 7.4.2 The Theoretical Basis of TimesNet 7.4.3 Experimental Result and Analysis 7.5 Model Performance Comparison 7.6 Conclusions References 8 Remaining Useful Life Prediction of Power Supply Based on Range-Extended New Energy Vehicles 8.1 Introduction 8.2 Data Acquisition 8.3 Predictive Model for Power Supply Remaining Useful Life Based on FEDformer 8.3.1 The Theoretical Basis of Transformer 8.3.2 The Theoretical Basis of FEDformer 8.3.3 Experimental Result and Analysis 8.4 Predictive Model for Power Supply Remaining Useful Life Based on Preformer 8.4.1 The Theoretical Basis of Multi-scale Time–Frequency Analysis of Power Batteries 8.4.2 The Theoretical Basis of Preformer 8.4.3 Experimental Result and Analysis 8.5 Model Performance Comparison 8.6 Conclusions References 9 Big Data Embedding in PHM for Electromechanical System 9.1 Introduction 9.2 Construction of Big Data Storage Platform 9.2.1 Data Source and Acquisition 9.2.2 Data Storage and Management Technology 9.3 Distributed Predictive Model for Electromechanical System 9.3.1 Distributed Computing Framework 9.3.2 Case Study 9.3.3 Challenges and Analysis 9.4 Conclusions References
[