A Divisive Unsupervised Feature Selection Approach for Explainable Remaining Useful Life Prediction

Predicting the Remaining Useful Life (RUL) in maintenance
often encounters challenges such as high dimensionality, feature redundancy, and limited explainability. This paper presents a novel approach that combines Interpretable Divisive Feature Clustering (IDFC) with Long Short-Term Memory (LSTM) networks. The IDFC algorithm leverages the strengths of variable clustering methods (VARCLUS) and the Clustering of Variables around Latent Components (CLV) to identify significant features and non-orthogonal latent components. This method
enables effective dimensionality reduction by selecting key features rather than combining them. Integrating IDFC with a single-layer LSTM and Shapley Additive Explanations (SHAP) results in a robust and interpretable framework for RUL prediction, achieving a balance between accuracy and transparency. Experimental results on a bearing dataset
show that the IDFC + LSTM model outperforms traditional methods while enhancing interpretability through the identification of key energyrelated features which influence the RUL prediction more.