Physics-informed deep learning framework for explainable remaining useful life prediction

This study proposes a comprehensive framework of explainable remaining useful life (RUL) prediction. The proposed framework aims to not only enhance the accuracy and robustness of RUL estimation but also improve the interpretability of the estimated RUL. The proposed framework features three characteristics. First, raw measurements are transformed into informative features by accounting for the physics of degradation. This transformation results in five types of physics-informed features. The proposed method attenuates the adverse effect of distinct operational conditions while disclosing hidden information in the raw measurements. Second, a novel architecture of multi-scale deep convolutional neural network is addressed to extract temporal patterns from disparate time scales of transformed features, enabling accurate but robust prediction of RUL. Third, a novel interpretation method traces the root causes of the degradation. Specifically, layer-wise relevance propagation is deployed to create a relevance map, which provides fast but accurate identification of the failure modes regardless of the number of features. A systematic analysis on experiments with the commercial modular aeropropulsion system simulation dataset demonstrates the accuracy and interpretability of the proposed framework. The comparative study also confirms that the proposed framework would be effective in predicting and interpreting the RUL of systems in real-world applications, where disparate operational conditions and failure modes are complexly intertwined.