Fault Diagnosis of Aeroengine Gear Based on Deep Learning

被引：0

作者：

Wan A. ^{[1
]}

Yang J. ^{[2
]}

Wang J. ^{[3
]}

Chen T. ^{[1
]}

Miao X. ^{[1
]}

Huang J. ^{[1
]}

Du X. ^{[1
]}

机构：

[1] Department of Mechanical and Electrical Engineering, Zhejiang University City College, Hangzhou

[2] School of Mechanical Engineering, Zhejiang University, Hangzhou

[3] Key Laboratory of Aviation Science and Technology for Fault Diagnosis and Health Management Technology, Shanghai

来源：

Zhendong Ceshi Yu Zhenduan/Journal of Vibration, Measurement and Diagnosis | 2022年 / 42卷 / 06期

关键词：

Aircraft engines - Backpropagation - Classification (of information) - Convolution - Fault detection - Neural networks - Signal processing - Support vector machines;

D O I：

10.16450/j.cnki.issn.1004-6801.2022.06.002

中图分类号：

学科分类号：

摘要：

Traditional mechanical fault diagnosis methods often need to handle the collected fault wave signals， and then combine neural network to extract and classify the features. It is not only complex in process， time consuming， but also low in recognition accuracy. Therefore， this paper uses one-dimensional convolutional neural network （1D-CNN） to extract and classify the experimental vibration data of gear fault of an aeroengine， for establishing the 1D-CNN model of gear fault and diagnosing the bearing fault. From the test and analysis results， the accuracy of gear classification by using the neural network model is up to 80%， which is 15.07% higher than that of 63.9% of the traditional back propagation neural network， and the accuracy of this method is improved by 15.89% compared with the classification by support vector machine （SVM）. This method can directly use the wave vibration signal as input， and output the final classification results through a series of operations such as convolution and pooling. It simplifies the traditional tedious steps of signal processing and machine learning diagnosis， which provides a feasible method for aeroengine fault diagnosis. © 2022 Journal of Vibration,Measurement & Diagnosis. All rights reserved.

引用

页码：1062 / 1067

页数：5

共 19 条

[1] JIANG Dongxiang, WANG Fengyu, ZHOU Ming, Et al., Application of fuzzy self-organizing neural network in aero-engine fault diagnosis［J］, Journal of Aerospace Power, 16, 1, pp. 80-82, (2001)
[2] TIAN Jing, LI Youru, AI Yanting, A fault diagnosis method for aero engine intermediate bearing based on deep GBM［J］, Journal of Aerospace Power, 34, 4, pp. 756-763, (2019)
[3] JIAO J Y，, ZHAO M，, LIN J，, Et al., Hierarchical discriminating sparse coding for weak fault feature extraction of rolling bearings［J］, Reliability Engineering and System Safety, 184, pp. 41-54, (2019)
[4] ZHAO M，, JIA X D., A novel strategy for signal denoising using reweighted SVD and its applications to weak fault feature enhancement of rotating machinery ［J］, Mechanical Systems and Signal Processing, 94, pp. 129-147, (2017)
[5] (2020)
[6] LIU W Y, ZHANG W H, HAN J G，, Et al., A new wind turbine fault diagnosis method based on the local mean decomposition［J］, Renewable Energy, 48, pp. 411-415, (2012)
[7] ZHU Wenying, FENG Zhipeng, Fault diagnosis of planetary gearbox based on improved empirical wavelet transform［J］, Chinese Journal of Scientific Instrument, 37, 10, pp. 2193-2201, (2016)
[8] LECUN Y，, BOTTOU L., Gradient-based learning applied to document recognition［J］, Proceedings of the IEEE, 86, 11, pp. 2278-2324, (1998)
[9] HAN Tao, YUAN Jianhu, TANG Jian, Et al., Intelli⁃ gent composite fault diagnosis method of rolling bearing based on MWT and CNN［J］, Journal of Mechanical Transmission, 40, 12, pp. 139-143, (2016)
[10] ZHANG Xining, XIANG Zhou, TANG Chunhua, A deep convolutional self coding network and its applica⁃ tion in rolling bearing fault diagnosis［J］, Journal of Xi'an Jiaotong University, 52, 7, pp. 1-8, (2018)

← 1 2 →