Fault diagnosis of HVAC system with imbalanced data using multi-scale convolution composite neural network

作     者：Rouhui Wu Yizhu Ren Mengying Tan Lei Nie Rouhui Wu;Yizhu Ren;Mengying Tan;Lei Nie

作者机构：School of Mechanical EngineeringHubei University of TechnologyWuhan430068China Industrial Research Institute of Xiangyang Hubei University of TechnologyXiangyang441100China 

出 版 物：《Building Simulation》 (建筑模拟（英文）)

年 卷 期：2024年第17卷第3期

页      面：371-386页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 081104[工学-模式识别与智能系统] 0807[工学-动力工程及工程热物理] 081404[工学-供热、供燃气、通风及空调工程] 0835[工学-软件工程] 0814[工学-土木工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：The authors of this paper acknowledge the support from the National Natural Science Foundation of China(No.51975191) the Funds for Science and Technology Creative Talents of Hubei,China(No.2023DJC048) This work was supported by the Xiangyang Hubei University of Technology Industrial Research Institute Funding Program(No.XYYJ2022B01) 

主　　题：fault diagnosis chiller imbalanced data SMOTETomek multi-scale neural networks 

摘      要：Accurate fault diagnosis of heating,ventilation,and air conditioning(HVAC)systems is of significant importance for maintaining normal operation,reducing energy consumption,and minimizing maintenance ***,in practical applications,it is challenging to obtain sufficient fault data for HVAC systems,leading to imbalanced data,where the number of fault samples is much smaller than that of normal ***,most existing HVAC system fault diagnosis methods heavily rely on balanced training sets to achieve high fault diagnosis ***,to address this issue,a composite neural network fault diagnosis model is proposed,which combines SMOTETomek,multi-scale one-dimensional convolutional neural networks(M1DCNN),and support vector machine(SVM).This method first utilizes SMOTETomek to augment the minority class samples in the imbalanced dataset,achieving a balanced number of faulty and normal ***,it employs the M1DCNN model to extract feature information from the augmented ***,it replaces the original Softmax classifier with an SVM classifier for classification,thus enhancing the fault diagnosis *** the SMOTETomek-M1DCNN-SVM method,we conducted fault diagnosis validation on both the ASHRAE RP-1043 dataset and experimental dataset with an imbalance ratio of 1:*** results demonstrate the superiority of this approach,providing a novel and promising solution for intelligent building management,with accuracy and F1 scores of 98.45%and 100%for the RP-1043 dataset and experimental dataset,respectively.