This paper proposes a new prognostics analysis approach for power electronics by combining physics-based and data-driven techniques. With Weibull degradation model as base, Machine learning (ML) techniques are applied to degradation data progressively for continuous reliability monitoring and predictive maintenance decision-making. No prior knowledge of components or mission profiles is required for model training and prediction. Another innovative advantage is abrupt change of operation condition can be captured through machine learning for predictive maintenance. Proposed method can be generalized to other hardware components beyond power electronics.
