Fault Diagnosis Based On One-Dimensional Deep Convolution Neural Network
作者单位：College of Information Science and Engineering Northeastern University
会议名称：《第32届中国控制与决策会议》
主办单位：IEEE Control Systems Society (CSS);Northeastern University;State Key Laboratory of Synthetical Automation for Process Industries;Technical Committee on Control Theory, Chinese Association of Automation
会议日期：2020年
学科分类：0710[理学-生物学] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 080401[工学-精密仪器及机械] 0804[工学-仪器科学与技术] 080402[工学-测试计量技术及仪器] 0838[工学-公安技术] 0835[工学-软件工程] 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：National Key R&D Program of China National Key Research and Development Program of China, NKRDPC, (2017YFB0304202)
关 键 词：ML Fault diagnosis Deep learning 1D-DCNN T-SNE
摘 要：Aiming at the problems of low accuracy and poor generalization ability of bearing fault diagnosis based on machine learning（ML）, this paper proposes the method of deep learning（DL） to solve the above problems. Combined with the bearing signal one-dimensional characteristics, this paper proposes a one-dimension deep convolutional neural network（1 D-DCNN）. First of all, the original bearing vibration signal is directly input the 1 D-DCNN frame structure, then 1 D-DCNN frame structure is used to automatic feature extraction. Next, we use softmax regression to classified fault samples and normal samples, the confusion matrix shows that the accuracy of the 1 D-DCNN model for fault diagnosis. Finally, T-SNE algorithm is used to reduce the dimension of extracted features and visualize data features, which proves that the 1 D-DCNN model has a good feature extraction ability. We use bearing data sets from Case Western Reserve University（CWRU） to verify the model of 1 D-DCNN. According to the result, we can see that the 1 D-DCNN frame structure not only effectively extracts and diagnoses the original signal, but also has high fault identification accuracy. It shows the advantages of the 1 D-DCNN model in extracting data features and fault diagnosis. The model of 1 D-DCNN is better than the mainstream fault diagnosis method of support vector machine（SVM） and probabilistic neural networks（PNN）.