An interpretable feature selection method integrating ensemble models for chiller fault diagnosis

Timely diagnosis of chiller faults is crucial for indoor comfort and building energy saving with the number of sensors being minimized. To address this challenge and select the top important features for chiller diagnosis (FD), a novel feature selection method (FSM) with interpretability is proposed for chiller FD. The proposed method integrates four ensemble models, namely, random forest, XGBoost, LightGBM, and CatBoost in the feature selection process. A feature sets fusion strategy is designed based on SHAP analysis and a novel normalized feature weight calculation (NFWC) method. An interpretability analysis is performed using SHAP. The proposed NFWC method integrates the weights of four feature subsets based on SHAP values. Subsequently, the method of joint correlation analysis of feature weights is leveraged to eliminate redundant features. To evaluate the effectiveness of the proposed FSM, ten models, including traditional machine learning and deep learning, are used for FD performance validation. The experiment results show that the top ten features selected by the proposed FSM have obvious advantages compared to existing methods, especially in the early stage of FD. This work effectively eliminates 84% of redundant features for chiller FD, significantly improving the efficiency of HVAC system maintenance.