Anti‐noise diesel engine misfire diagnosis using a multi‐scale CNN‐LSTM neural network with denoising module

作     者：Chengjin Qin Yanrui Jin Zhinan Zhang Honggan Yu Jianfeng Tao Hao Sun Chengliang Liu 

作者机构：State Key Laboratory of Mechanical System and VibrationSchool of Mechanical EngineeringShanghai Jiao Tong UniversityShanghaiChina 

出 版 物：《CAAI Transactions on Intelligence Technology》 (智能技术学报（英文）)

年 卷 期：2023年第8卷第3期

页      面：963-986页

核心收录：

学科分类：081203[工学-计算机应用技术] 08[工学] 0835[工学-软件工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Key R&D Program of China(Grant No.2020YFB1709604) Shanghai Municipal Science and Technology Major Project(Grant No.2021SHZDZX0102) 

主　　题：fault diagnosis machine learning neural network 

摘      要：Currently,accuracy of existing diesel engine fault diagnosis methods under strong noise and generalisation performance between different noise levels are still limited.A novel multi‐scale CNN‐LSTM neural network(MSCNN‐LSTMNet)is proposed with a residual‐CNN denoising module for anti‐noise diesel engine misfire ***,a residual‐CNN module is designed for denoising the original vibration signal measured from the diesel engine cylinder and residual loss for constructing a new loss function is *** the essential characteristics of measured vibration signals at different scales,a multi‐scale convolutional NN(CNN)block is designed to realize multi‐scale feature ***,multiple convolution layers with different branches and different convolution kernel sizes are utilised to extract different time scales features,enhancing the robustness of the *** this basis,the LSTM is utilised to further extract sequential features for improving anti‐noise and generalisa-tion *** effectiveness of MSCNN‐LSTMNet is validated by experi-mental results of both one‐and hybrid‐cylinder diesel engine misfires diagnosis under various noise levels and working *** results demonstrate that MSCNN‐LSTMNet achieved much better anti‐noise and generalisation performances than the existing *** strong noise conditions(−10 dB signal‐to‐noise ratio)for four datasets,MSCNN‐LSTMNet obtained 97.561%average accuracy,while average accuracy for random forest,deep neural network,CNN and MSCNNNet were 73.828%,79.544%,82.247%,and 89.741%,***,for 11 noise generalisation tasks between different noise levels,MSCNN‐LSTMNet obtained at least 96.679%,97.849%,98.892%,and 94.010%accuracy on the four datasets,which are much higher than those of the existing methods.