SS 09
Against the global drive for sustainable energy transition and intelligent reliability engineering, nuclear and renewable energy systems demand high-fidelity, real-time, and physically consistent reliability assessment to ensure safety, resilience, and efficient operation. Traditional reliability methods face bottlenecks in handling multi-physics coupling, uncertainty propagation, and sparse noisy data in complex energy systems. Physics-informed digital twin (PIDT) integrates first-principle physical laws, real-time monitoring data, and data-driven models to construct high-confidence virtual replicas, enabling online state awareness, remaining useful life prediction, fault early warning, and risk-informed decision-making for nuclear reactors, wind farms, solar systems, and other critical energy facilities. This special session aims to gather global scholars and engineers to exchange frontier theories, key technologies, and industrial applications of PIDT in reliability engineering, promote the integration of physical modeling, digital twin, and intelligent algorithms, and support the safe, reliable, and sustainable development of next-generation energy systems.
面向全球能源可持续转型与可靠性工程智能化发展趋势，核电与可再生能源系统亟需高保真、实时化、物理一致的可靠性评估方法，以保障系统安全、韧性与高效运行。传统可靠性手段在应对复杂能源系统的多物理场耦合、不确定性传播、稀疏噪声数据等难题时存在明显瓶颈。基于物理信息的数字孪生（PIDT）融合第一性原理物理规律、实时监测数据与数据驱动模型，构建高置信度虚拟映射，可实现核反应堆、风电场、光伏系统等关键能源装备的在线状态感知、剩余寿命预测、故障早期预警与风险决策优化。本专题旨在汇聚全球学者与工程专家，交流物理信息数字孪生在可靠性领域的前沿理论、关键技术与工程实践，推动物理建模、数字孪生与智能算法深度融合，支撑新一代能源系统的安全、可靠与可持续发展。
Topics:
Physics-Informed Modeling and Digital Twin Construction for Nuclear and Renewable Energy Systems
Remaining Useful Life Prediction and Reliability Assessment Enhanced by Digital Twins
Uncertainty Quantification and Propagation in Physics-Informed Digital Twins
Risk-Informed Decision-Making and Maintenance Optimization
Sensor fusion, online monitoring, and early fault warning based on physics-informed learning and digital twin technologies
Industrial Applications and Case Studies
核电与可再生能源系统的物理建模与孪生构建
数字孪生驱动的剩余寿命预测与可靠性评估
基于物理信息的数字孪生中的不确定性量化与传播
风险决策与维修优化
基于物理信息学习与数字孪生技术的传感器融合、在线监测与早期故障预警
工业应用与案例研究
Modern complex engineering systems, such as aerospace systems, autonomous intelligent systems, industrial equipment, and cyber-physical systems, are becoming increasingly sophisticated and interconnected. Ensuring their reliability and operational safety requires advanced techniques for timely fault detection, accurate diagnosis, and reliable prognostics.
Recent advances in artificial intelligence (AI), machine learning, and data-driven modeling have significantly improved the capability of intelligent fault diagnosis and prognostics. AI-based approaches enable systems to learn complex patterns from large volumes of operational data, providing enhanced capabilities for fault detection, fault isolation, health assessment, and remaining useful life prediction. Despite these advances, many challenges remain, including limited labeled fault data, system complexity, heterogeneous sensing information, and the need for robust and interpretable diagnostic models. Addressing these challenges is critical for improving the reliability and resilience of complex engineering systems.
This special session aims to provide a platform for researchers and practitioners to present recent advances in intelligent fault diagnosis and prognostics. The session will highlight novel AI-driven methods, theoretical developments, and practical applications that enhance the reliability and health monitoring capabilities of complex engineering systems.
Topics of interest include, but are not limited to:
Artificial Intelligence for Fault Diagnosis and Prognostics
Data-driven Fault Detection and Diagnosis
Testing, Sensing and Diagnosis
Remaining Useful Life (RUL) Prediction
Intelligent Health State Assessment
Hybrid Model-based and Data-driven Fault Diagnosis and Tolerant Control Methods
Multisensor Data Fusion for Intelligent Fault Detection
Explainable AI for Fault Diagnosis and Prognostics
Robust and Uncertainty-aware Diagnosis and Prognostics Methods
Intelligent Monitoring of Complex Engineering Systems
Applications in Aerospace, Autonomous Systems, and Industrial Equipment
