Linked e-resources
Details
Table of Contents
Foreword; Acknowledgements; Contents; Trends and Applications; 1 Probabilistic Prognostics and Health Management: A Brief Summary; Abstract; 1 Introduction; 2 Methodology; 3 The Way Forward; References; 2 Introduction to Data-Driven Methodologies for Prognostics and Health Management; Abstract; 1 Overview of Prognostics and Health Management (PHM); 1.1 Definition and the Value of Prognostics and Health Management; 1.2 Research in Data-Driven Prognostics and Health Management; 1.3 Methodology; 1.3.1 Algorithms; 1.3.2 Data Pre-processing Algorithms; 1.3.3 Feature Extraction Algorithms
1.3.4 Health Assessment and Anomaly Detection Algorithms1.3.5 Health Diagnostic Algorithms; 1.3.6 Prognostics Algorithms; 2 Case Study in Wind Turbine Monitoring System; 2.1 Project Background; 2.2 Benefits to Users; 2.3 Method Development; 2.3.1 Identify Critical Subsystems/Components; 2.3.2 Data Acquisition/Signal Selection; 2.3.3 Multi-regime Modeling for Turbine Global Health Assessment; 2.3.4 The Proposed Approach to Assessing Turbine Performance; 2.3.5 Vibration-Based Condition Monitoring for Drivetrain System; 3 Industrial Implementation and Gaps; 3.1 Available Software and Platforms
3.2 Gaps and Future Directions3.2.1 Preprocessing; 3.2.2 Fleet-Based PHM; 3.2.3 General PHM Platform; References; 3 Prognostics and Health Management of Wind Turbines-Current Status and Future Opportunities; Abstract; 1 Introduction; 2 Typical Practices in Utility-Scale Wind Turbines; 2.1 SCADA Data Mining; 2.2 Condition Monitoring; 2.2.1 Vibration Analysis; 2.2.2 Oil Debris Monitoring; 2.2.3 Discussions; 3 Future R&D Opportunities; Acknowledgements; References; 4 Overview on Gear Health Prognostics; Abstract; 1 Introduction; 2 Gear Health Prognostics Methods
2.1 Gear Fatigue Life Statistical Models2.2 Physics-Based Gear Prognostics; 2.2.1 Tooth Fracture; 2.2.2 Sliding Wear; 2.3 Data-Driven Gear Prognostics; 2.3.1 Data-Driven Methods: Statistical Matching Learning Methods; 2.3.2 Data-Driven Methods: Dynamic System; 2.4 Integrated Gear Prognostics; 3 Opportunities and Challenges in Gear Prognostics; 4 Conclusions; References; 5 Probabilistic Model-Based Prognostics Using Meshfree Modeling; Abstract; 1 Introduction; 1.1 Prognostics and Health Management; 1.2 Modeling; 1.3 Filtering; 1.4 Degradation Models; 1.5 Probabilistic Analysis
1.6 Remaining Useful Life Prediction1.7 Motivation; 1.8 Research Question and Specific Aims; 2 Methodology; 2.1 Efficient Modeling; 2.2 RUL Prediction; 2.2.1 Deterministic RUL Prediction; 2.2.2 Probabilistic RUL Prediction; 3 Results and Discussion; 3.1 RUL Prediction; 3.1.1 Deterministic RUL Prediction; 3.1.2 Probabilistic RUL Prediction; Loadings of Single Mean Value; Loadings of Multiple Mean Values; Single Uninterrupted Loading Application; Multiple Uninterrupted Loading Application; 3.1.3 Conclusions; References; 6 Cognitive Architectures for Prognostic Health Management; Abstract
1.3.4 Health Assessment and Anomaly Detection Algorithms1.3.5 Health Diagnostic Algorithms; 1.3.6 Prognostics Algorithms; 2 Case Study in Wind Turbine Monitoring System; 2.1 Project Background; 2.2 Benefits to Users; 2.3 Method Development; 2.3.1 Identify Critical Subsystems/Components; 2.3.2 Data Acquisition/Signal Selection; 2.3.3 Multi-regime Modeling for Turbine Global Health Assessment; 2.3.4 The Proposed Approach to Assessing Turbine Performance; 2.3.5 Vibration-Based Condition Monitoring for Drivetrain System; 3 Industrial Implementation and Gaps; 3.1 Available Software and Platforms
3.2 Gaps and Future Directions3.2.1 Preprocessing; 3.2.2 Fleet-Based PHM; 3.2.3 General PHM Platform; References; 3 Prognostics and Health Management of Wind Turbines-Current Status and Future Opportunities; Abstract; 1 Introduction; 2 Typical Practices in Utility-Scale Wind Turbines; 2.1 SCADA Data Mining; 2.2 Condition Monitoring; 2.2.1 Vibration Analysis; 2.2.2 Oil Debris Monitoring; 2.2.3 Discussions; 3 Future R&D Opportunities; Acknowledgements; References; 4 Overview on Gear Health Prognostics; Abstract; 1 Introduction; 2 Gear Health Prognostics Methods
2.1 Gear Fatigue Life Statistical Models2.2 Physics-Based Gear Prognostics; 2.2.1 Tooth Fracture; 2.2.2 Sliding Wear; 2.3 Data-Driven Gear Prognostics; 2.3.1 Data-Driven Methods: Statistical Matching Learning Methods; 2.3.2 Data-Driven Methods: Dynamic System; 2.4 Integrated Gear Prognostics; 3 Opportunities and Challenges in Gear Prognostics; 4 Conclusions; References; 5 Probabilistic Model-Based Prognostics Using Meshfree Modeling; Abstract; 1 Introduction; 1.1 Prognostics and Health Management; 1.2 Modeling; 1.3 Filtering; 1.4 Degradation Models; 1.5 Probabilistic Analysis
1.6 Remaining Useful Life Prediction1.7 Motivation; 1.8 Research Question and Specific Aims; 2 Methodology; 2.1 Efficient Modeling; 2.2 RUL Prediction; 2.2.1 Deterministic RUL Prediction; 2.2.2 Probabilistic RUL Prediction; 3 Results and Discussion; 3.1 RUL Prediction; 3.1.1 Deterministic RUL Prediction; 3.1.2 Probabilistic RUL Prediction; Loadings of Single Mean Value; Loadings of Multiple Mean Values; Single Uninterrupted Loading Application; Multiple Uninterrupted Loading Application; 3.1.3 Conclusions; References; 6 Cognitive Architectures for Prognostic Health Management; Abstract