An intelligent fault detection and diagnosis model for refrigeration systems with a comprehensive feature selection method

• Published in: International journal of refrigeration 2024-04, Vol.160, p.28-39
• Main Authors: Wang, Zi-Cheng, Wang, Si-Cheng, Li, Dong, Cao, Zhan-Wei, He, Ya-Ling
• Format: Article
• Language: English
• Subjects: Apprentissage profonde; Deep learning; Détection et diagnostic des défaillances; Fault detection and diagnosis; Feature selection; Refrigeration system; Système frigorifique; Sélection des caractéristiques
• ISSN: 0140-7007; 1879-2081
• DOI: 10.1016/j.ijrefrig.2024.01.006

•A comprehensive feature selection method is proposed.•One-dimensional convolution and self-attention neural network is used as FDD model.•Integrated optimization of the features and the model is carried out to achieve better performance.•Diagnostic accuracy of an experiment on miniature refrigeration system is 99.66 %, surpassing other popular FDD models. Feature selection and model establishment are two essential steps for fault detection and diagnosis (FDD) of refrigeration systems. A robust and powerful FDD model combined with a suitable feature selection method can exhibit excellent performance in FDD tasks for refrigeration systems. In this study, a novel FDD method that integrates a comprehensive feature selection method and a deep learning-based intelligent FDD model is proposed. Including three steps, the comprehensive feature selection method combines filter methods and wrapper methods. It can optimize the features and the model jointly by using the multi-objective optimization algorithm to achieve a better performance. In addition, a novel FDD model that combines one-dimensional convolutional neural network (1D-CNN) and self-attention (SA) mechanism is proposed based on the deep learning technology. To evaluate the proposed method, experiments are performed on a miniature refrigeration system under 4 situations with multiple working conditions, forming a dataset for the FDD study. The proposed three-step feature selection method is utilized to obtain the best feature subset. The 1D-CNN and SA FDD model is constructed and the model is jointly optimized with the features. Several comparisons are carried out to demonstrate the effectiveness and superiority of the proposed feature selection method and the FDD model. The results demonstrate that the presented integrated optimization achieved a test accuracy of around 99.66 %, surpassing other popular FDD models including MLP, CNN, and LSTM.