Session 25: Advanced Condition Monitoring and Health Management for Power Electronic Converters and Components

Advanced Condition Monitoring and Health Management for Power Electronic Converters and Components
“电力电子变换器及其关键元件的先进状态监测与健康管理”

Power electronic converters are the critical enabler for high-efficiency energy conversion in renewable energy systems, electric vehicles, industrial drives, and modern power grids. The reliability of these converters is paramount, and it is often dictated by the health of their key components, such as power semiconductor devices (e.g., IGBTs, SiC/GaN FETs) and passive components (e.g., DC-link capacitors). Unexpected failures can lead to significant economic losses and even safety hazards.
This special session focuses on the paradigm shift from traditional reactive maintenance to proactive and predictive health management for power electronic systems. We aim to bring together leading researchers and engineers to share the latest advancements in condition monitoring, fault diagnosis, and prognosis techniques. The session will explore novel methods, including online parameter estimation, data-driven approaches empowered by AI and machine learning, and physics-of-failure-based modeling, to achieve real-time health awareness, accurate fault identification, and reliable remaining useful life (RUL) prediction. We welcome contributions that address the challenges and opportunities in enhancing the reliability, availability, and safety of power electronic converters through innovative monitoring and health management strategies.

Topics (Including but not limited to)  

• Condition monitoring and RUL prediction for power semiconductor devices (IGBTs, MOSFETs, SiC, GaN).
  功率半导体器件（IGBT、MOSFET、SiC、GaN）的状态监测与剩余使用寿命预测
• Health monitoring and lifetime estimation for DC-link capacitors and other passive components.
  直流支撑电容及其他无源器件的健康监测与寿命评估
• Online parameter extraction and identification techniques for health indicators (e.g., Vce(on), Rds(on), ESR, C).
  用于健康指标（如Vce(on)、Rds(on)、ESR、C）的在线参数提取与辨识技术
• Advanced sensor technologies and sensor-less monitoring methods.
  先进传感技术与无传感器监测方法
• Data-driven methods (AI, machine learning, deep learning) for fault diagnosis and prognosis.
  用于故障诊断与预测的数据驱动方法（人工智能、机器学习、深度学习）
• Digital twin technologies for power electronics reliability and health management.
  用于电力电子可靠性与健康管理的数字孪生技术
• Physics-of-Failure (PoF) models and hybrid approaches for lifetime prediction.
  用于寿命预测的失效物理（PoF）模型与混合方法
• Fault diagnosis, isolation, and fault-tolerant control strategies.
  故障诊断、隔离与容错控制策略
• Reliability modeling and assessment of power converter systems.
  电力电子变换器系统的可靠性建模与评估
• Monitoring of gate drivers, cooling systems, and packaging-related failures (e.g., bond-wire fatigue).
  门极驱动、冷却系统及封装相关失效（如键合线疲劳）的监测