Prognostics and Health Management in Energy and Power Systems

Ryad M. Zemouri, Ph.D, is a Data Scientist at Hydro-Québec’s Research Institute (IREQ), Canada. Previously, he was an Associate Professor at the University of Cnam, Paris. His research interests include machine learning and artificial neural networks, with a particular interest in industrial applications of machine learning to prognosis and health management (PHM). He has published nearly 100 papers in various international conferences and journals. Jean Raymond, ing., Ph.D., M.Sc.A., is a RAMS Engineer in Hydro-Québec’s Expertise, Engineering and Standardization, Canada. He has over 34 years of experience as a telecom network and systems engineer. He was responsible for the long-term development of its transport and power systems. He actively contributes to international standards groups (IEC, IEEE), and leads several committees. He has authored over twenty publications. Jean is involved in modernizing university programs in RAMS and Asset Management. Dragan Komljenovic, ing., Ph.D, is a Senior Research Scientist at Hydro-Québec’s Research Institute (IREQ), specializing in reliability, resilience, asset management, and risk analysis. He previously served as a reliability and nuclear safety engineer at the Gentilly-2 nuclear power plant, also part of Hydro-Québec. Dragan actively collaborates with several universities and has authored over 120 peer-reviewed journal and conference papers. He is a Fellow of the International Society of Engineering Asset Management (ISEAM).

• List of Figures xiList of Tables xviiAbstract xixAbout the Authors xxiPreface xxiiiAcknowledgments xxvNotations xxviiAbout the Companion Website xxix1 Introduction 11.1 The Energy Transition: Toward a Highly Interconnected System of Systems 11.2 The Power Plant and Substation of the Future: Toward Situational Awareness 21.3 The New Paradigm in AI: The Emergence of the Large-scale Foundation Models 31.4 Topics and Organization of the Book 4Part I Challenges, Trends, and Asset Management Requirements for the Energy Transition 72 Energy Transition and Digital Transformation 92.1 Introduction 92.2 Digital Transformation 112.3 Energy Transition 122.4 Arrival of DERs 132.5 Lifecycle Requirements, Expectations, and Speed of New Technologies, Introduction in the Electric System 143 Asset Management and Resilience 153.1 Introduction 153.2 Asset Management 153.3 Resilience 173.4 Combining AM and Resilience: Resilience-based AM 183.5 Key Differences Between Reliability and Resilience 203.6 The Link Between DTs, Reliability, LCM, and AM 214 Challenges and Issues Surrounding the Operation of Current and Future Power Plants and Substations 254.1 Introduction 254.2 Reliability and Asset Management 274.3 Different Designs 294.4 Sensor Proliferation 294.5 Dynamic Systems 294.6 Cohabitation of Current and New-generation Technologies 294.7 Software 304.8 Complexity 324.9 Behavioral Nonlinearity of Components and Systems 354.10 System of Systems 354.11 Human Factors 364.12 Data 374.13 Different Operational Time Ranges of the Electric Network 374.14 Possible Multistates of a Component 384.15 Maintenance 384.16 Hidden Failures 394.17 Degradation Process and Obsolescence of Electric and Mechanical Components or Systems 404.18 Climate Change, Extreme Weather Events, and Others 404.19 Complete Life Cycle of Component/System 434.20 Prescriptive Maintenance or Knowledge-based Maintenance 434.21 Regulation Evolution 444.22 Prosumers 454.23 Potential Consequences of Energy Transition 464.24 Remaining Technical Gaps for Electric Power Utilities 47Part II Large-scale Foundation Models 515 From Shallow Machine Learning to the Requirements of Large-scale Foundation Models 535.1 Introduction 535.2 ANNs: Theoretical Foundations 545.3 A Brief History of AI: The Main Developments 575.4 Trustworthiness of AI Systems 616 Main Elements of Large-scale Foundation Models: Theoretical Backgrounds 776.1 Introduction 776.2 Modular Learning 786.3 Transformer-based DNNs 826.4 Self-supervised Learning 876.5 Multimodal Fusion 906.6 Multitask Learning 936.7 Graph-oriented Approaches 936.8 Conclusion 997 Main Elements of Large-scale Foundation Models: A Practical and Literature Review 1017.1 Introduction 1017.2 Transformer Architecture-based Deep Neural Network 1017.3 Self-supervised Learning 1047.4 Multimodal Fusion 1077.5 Multitask Learning 1097.6 Graph-oriented Approaches 1107.6.1 Anomaly Detection 1147.6.2 Diagnostics 1147.6.3 Prognostics 1147.7 Conclusion and Synthesis 1168 Combining Situational Awareness and LSF Models to Support the Energy Transition 1198.1 Introduction 1198.2 The Target of Future Power Plants and Substations 1208.3 What Is the Situational Awareness? 1218.4 Incorporating the SA to the Power Plant/Substation of the Future 1228.5 Conclusion 1249 Toward a New PHM Process 1259.1 The Concept of PHM Process 1259.2 Integrating ML into the PHM Process 1269.3 The Situational Awareness Integrated to the PHM Process 1289.4 Conclusion 130Part III Industrial Case Study 13110 Hydro-generators Prognostics and Health Management 13310.1 Introduction 13310.2 Description of the Case Study 13310.3 Overview of the Global Methodology 14211 Set of Deep Learning Models for Feature Extraction 14511.1 Introduction 14511.2 Feature Extraction from Visual Inspection Data 14511.3 Feature Extraction from Text Data 14911.4 Feature Extraction from PD 15211.5 Conclusion 15512 Set of AI-Experts with Deep Modular Learning 15712.1 Introduction 15712.2 Description of the AI-Experts 15812.3 Managing the Mixture-of-AI-Experts 16112.4 Experimental Results 16412.5 Conclusion 16912.6 Appendix 16913 Graph-based Approach for Prognostics of Complex Machinery with Sparse Run-to-failure Data 17513.1 Introduction 17513.2 Preliminaries and Assumptions 17613.3 Diagnostics Feature Extraction 17713.4 Graph Structure Definition 17813.5 Graph Dataset Generation for the Prognostics Considering the Sparse RTF Data 17913.6 Assigning a Likelihood for Each Edge 18013.7 Graph-based Forecasting Model 18113.8 Experimental Results 18413.9 Conclusion 190Part IV Conclusion 19114 Conclusion 19314.1 What to Keep in Mind 19314.2 Future Directions 195Acronyms 199Glossary 203References 205