1D-Convolutional Neural Network based Vibration Signal Fault Detection
作者单位：Machine Learning and I-health International Cooperation Base of Zhejiang Provinceand with the Artificial Intelligence InstituteHangzhou Dianzi University
会议名称：《第32届中国过程控制会议(CPCC2021)》
会议日期：2021年
学科分类：12[管理学] 07[理学] 08[工学] 0711[理学-系统科学] 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] 080401[工学-精密仪器及机械] 080203[工学-机械设计及理论] 0804[工学-仪器科学与技术] 080402[工学-测试计量技术及仪器] 0835[工学-软件工程] 0802[工学-机械工程] 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）]
关 键 词：Fault detection One-Dimensional Convolutional Neural Network Domain adaptation Rotating machinery
摘 要：Convolutional neural networks(CNNs) are very good at picking up on patterns in the input image and have become widely used in computer *** the help of the excellent structured data processing ability of CNNs,a one-dimensional convolutional neural network(1 D-CNN) is constructed for fault detection and classification of time series data from vibration system of rotating machinery under various operating ***,a compact 1 D-CNN model with a wide convolution kernel is proposed in the first layer,and Dropout technology is used in the convolution layer to simulate training interference to enhance the anti-noise ***,a double 1 D-CNN model is proposed for cross-condition fault ***,the effectiveness of the method is verified by simulation of compressor instability data.