Interpretable Degradation Tensor Modeling Through Multi-scale and Multi-level Time-Frequency Feature Fusion for Machine Health Monitoring

T Yan, X Xing, D Wang, KL Tsui, M Xia - Information Fusion, 2025 - Elsevier
A health indicator (HI) is crucial for comprehensively characterizing degradation processes
influenced by multiple factors. However, HIs derived from physical features typically capture …

Relation between fault characteristic frequencies and local interpretability shapley additive explanations for continuous machine health monitoring

T Yan, X Xing, T Xia, D Wang - Engineering Applications of Artificial …, 2024 - Elsevier
Recently, the Shapley additive explanations models have been extensively studied to
enhance explainability of artificial intelligence algorithms, while most of them simply use …