PE-TSFM: Self-Supervised Time-Series Learning for Generalizable Power Converter Health Monitoring under Unseen Conditions
Preprint
Abstract
Data-driven health monitoring of power converters remains limited by poor generalization to unseen operating conditions. This work addresses this out-of-distribution (OOD) challenge by building a domain-specific time-series foundation model (PE-TSFM) that learns representations directly from large-scale unlabeled converter data. Unlike generic TSFMs trained on broad time-series datasets, the proposed PE-TSFM is pre-trained entirely on domain data, enabling it to learn the physical relationships unique to power electronics. To further tailor the model to this domain, we introduce a dual-attention mechanism that captures both temporal patterns and inter-channel dependencies. While generic TSFMs primarily model temporal dependencies, the added channel attention captures inter-sensor physical relationships essential for converter degradation analysis. A dataset containing 141 million unlabeled timestamps from an operating power converter is used for pre-training. Experiments show that PE-TSFM achieves 92% accuracy under unseen operating conditions. In contrast, generic TSFMs achieve around 60% and conventional time-series models achieve around 40% accuracy. This result confirms the strong OOD generalization of the proposed PE-TSFM. Ablation studies further verify that the introduced channel attention mechanism significantly improves model performance. In addition, we conduct detailed studies on model scalability, hyperparameter sensitivity, and interpretability to provide a comprehensive understanding of the proposed approach.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Review on Condition Monitoring Methods of IGBT Power Device2025
- A Large Language Model based Multi-agent Framework for Goal Oriented Controller Design in Power Electronics2025
- Predicting DC-Link Capacitor Current Ripple in AC-DC Rectifier Circuits Using Fine-Tuned Large Language Models2024
- PE-GPT: A Physics-Informed Interactive Large Language Model for Power Converter Modulation Design2024
- PE-GPT: A New Paradigm for Power Electronics DesignIEEE Transactions on Industrial Electronics, 2024
- Applications of Unsupervised Deep Transfer Learning to Intelligent Fault Diagnosis: A Survey and Comparative StudyIEEE Transactions on Instrumentation and Measurement, 2021
- Fault Diagnosis of Inverter Current Sensor Using Artificial Neural Network Considering Out-of-distribution2021
- High-Voltage Hybrid IGBT Power Modules for Miniaturization of Rolling Stock Traction InvertersIEEE Transactions on Industrial Electronics, 2021
- InceptionTime: Finding AlexNet for time series classificationData Mining and Knowledge Discovery, 2020
- Reliability Improvement for a High-Power IGBT in Wind Energy ApplicationsIEEE Transactions on Industrial Electronics, 2018