Application of adaptive convolutional neural network in rotating machinery fault diagnosis

被引：0

作者：

Li T. ^{[1
]}

Duan L. ^{[1
]}

Zhang D. ^{[2
]}

Zhao S. ^{[2
]}

Huang H. ^{[3
]}

Bi C. ^{[3
]}

Yuan Z. ^{[1
]}

机构：

[1] College of Safety and Ocean Engineering, China University of Petroleum, Beijing

[2] Petro China Beijing Gas Pipeline Co., Ltd., Beijing

[3] Exploration and Production Research Institute, Sinopec, Beijing

来源：

Zhendong yu Chongji/Journal of Vibration and Shock | 2020年 / 39卷 / 16期

关键词：

Convolutional neural network(CNN); Deep learning model; Fault diagnosis; Particle swarm optimization(PSO) algorithm; Rotating machinery;

D O I：

10.13465/j.cnki.jvs.2020.16.037

中图分类号：

学科分类号：

摘要：

Aiming at solving the problems of fault diagnosis based on machine learning model, such as relying on manual feature extraction quality, dimension disaster, lack of self-adaptation of convolutional neural network (CNN) model construction,a fault diagnosis method of adaptive CNN based on particle swarm optimization (PSO) was proposed and applied to fault diagnosis of rotating machinery. Firstly, one-dimensional time-domain signal was transformed into two-dimensional time-frequency image; Then, the PSO algorithm was employed to optimize the seven key parameters in the CNN model to construct a deep learning model. Finally, the two-dimensional time-frequency image was input into the optimized model to diagnose rotating machinery faults. The results show that the proposed method has high accuracy, stability and adaptability. © 2020, Editorial Office of Journal of Vibration and Shock. All right reserved.

引用

页码：275 / 282and288

共 28 条

[1] (2017)
[2] LEI Yaguo, JIA Feng, ZHOU Xin, Et al., A deep learning-based method for machinery health monitoring with big data, Journal of Mechanical Engineering, 51, 21, pp. 49-56, (2015)
[3] WANG Xin, YAN Wenyuan, Fault diagnosis of roller bearings based on the variational mode decomposition and SVM, Journal of Vibration and Shock, 36, 18, pp. 252-256, (2017)
[4] TANG Guiji, DENG Feiyue, HE Yuling, Rolling element bearing fault diagnosis based on time-wavelet energy spectrum entropy, Journal of Vibration and Shock, 33, 7, pp. 68-72, (2014)
[5] ZOU Longqing, CHEN Guijuan, XING Junjie, Et al., Fault diagnosis method based on LMD sample entropy and SVM for reciprocating compressors, Noise and Vibration Control, 34, 6, pp. 174-177, (2014)
[6] JIN Qi, WANG Youren, WANG Jun, Planetary gearbox fault diagnosis based on multiple feature extraction and information fusion combined with deep learning, China Mechanical Engineering, 30, 2, pp. 196-204, (2019)
[7] ZHANG Qingqing, LIU Yong, PAN Jielin, Et al., Continuous speech recognition based on convolutional neural network, Chinese Journal of Engineering, 37, 9, pp. 1212-1217, (2015)
[8] KRIZHEVSKY A, SUTSKEVER I, HINTON G E., Image net classification with deep convolutional neural networks, International Conference on Neural Information Processing Systems, (2012)
[9] SZEGEDY C, LIU W, JIA Y, Et al., Going deeper with convolutions, IEEE Conference on Computer Vision and Pattern Recognition, (2015)
[10] HE K, ZHANG X, REN S, Et al., Deep residual learning for image recognition, Computer Vision and Pattern Recognition, (2016)

← 1 2 3 →