A hybrid deep forest approach for outlier detection and fault diagnosis of variable refrigerant flow system

• Published in: International journal of refrigeration Vol. 120; pp. 104 - 118
• Main Authors: Zeng, Yuke, Chen, Huanxin, Xu, Chengliang, Cheng, Yahao, Gong, Qijian
• Format: Journal Article
• Language: English
• Published: Paris Elsevier Ltd 01.12.2020; Elsevier Science Ltd
• Subjects: Algorithms; Artificial neural networks; Back propagation; Correlation coefficients; Data analysis; Deep forest model; Deep learning; Defrosting; Diagnostic des défaillances; Diagnostic systems; Fault diagnosis; HVAC; HVAC equipment; Machine learning; Mathematical models; Model accuracy; Modèle de forêt neuronale profonde; Méthode de détection des valeurs aberrantes; Neural networks; Optimization; Outlier detection; Outliers (statistics); Parameters; Refrigerants; Système à débit de frigorigène variable; Variable refrigerant flow system; Fault diagnosis; Méthode de détection des valeurs aberrantes; Modèle de forêt neuronale profonde; Diagnostic des défaillances; Outlier detection; Variable refrigerant flow system; Deep forest model; Système à débit de frigorigène variable
• ISSN: 0140-7007; 1879-2081
• DOI: 10.1016/j.ijrefrig.2020.08.014

•An improved deep learning model based on tree structure is proposed in VRF system.•Pearson's correlation coefficient combines with isolation forest for data preprocessing•The physical significance of outliers in VRF system is explained.•The IF-CF model does not require complex hyper-parameter optimization strategy. This paper presents a hybrid deep forest approach for outlier detection and fault diagnosis. Isolation forest algorithm is combined with Pearson's correlation coefficient for outlier detection. The physical significance of outliers detected by the proposed algorithm is explained by origin analysis, which is rarely mentioned in existing studies. In addition, a novel non-neural network deep learning model-cascade forest model is proposed to fault diagnosis of HVAC system for the first time to achieve high precision accuracy in low-dimensional features. The proposed approach is validated with the refrigerant charge fault of VRF system. The results show that the isolation forest algorithm can improve the performance of fault diagnosis model and the mainly outliers of VRF system are defrosting data. The IF-CF model has short operation time, and high accuracy in low-dimensional features. When the dimension drops to 6, the accuracy of the IF-CF model is 94.16%, which is 5.26%, 10.02%, 5.87% and 3.34% higher than the IF-MLP, IF-BPNN, IF-SVM and IF-LSTM models, respectively. Moreover, IF-CF model does not require complex hyper-parameter optimization strategy because its maximum accuracy difference in different hyper-parameters is 2.04%. This study is enlightening which may inspire the potential of outlier detection technology and deep learning in HVAC field.