Method to improve convolutional neural network in rolling bearing fault diagnosis with multi-state feature information

被引：0

作者：

Zhou C.-L. ^{[1
]}

Dong S.-J. ^{[1
]}

Li L. ^{[1
]}

Tang B.-P. ^{[2
]}

He K. ^{[1
]}

Mu S.-F. ^{[1
]}

Zhang X.-T. ^{[3
]}

机构：

[1] School of Mechanical and Vehicle Engineering, Chongqing Jiaotong University, Chongqing

[2] State Key Laboratory of Mechanical Transmission, Chongqing University, Chongqing

[3] Finance Department, Chongqing Jiaotong University, Chongqing

来源：

Dong, Shao-Jiang (913264318@qq.com) | 1600年 / Nanjing University of Aeronautics an Astronautics卷 / 33期

关键词：

Fault diagnosis; Improved convolutional neural network; Multi-state; Rolling bearing;

D O I：

10.16385/j.cnki.issn.1004-4523.2020.04.024

中图分类号：

学科分类号：

摘要：

An improved fault diagnosis model for multi-state faulty bearings by using convolutional neural network is proposed in this paper, aiming at the problems of the uncertainty in manual feature selection and the unspecific of existed fault diagnosis models. At first, according to the multi-state feature of the faulty bearings, a basic principle for designing an improved convolutional neural network (BPDICNN) is proposed by taking advantage of the sparse connection and weight sharing of convolutional neural network. Secondly, a convolutional neural network model is designed by using the BPDICNN design principle, and the "end-to-end" learning and training is carried out directly on the original vibration signal of faulty bearing. Multiple features including fault types, fault positions, fault damage degree and load state are extracted from the original signals. Finally, test data are used to verify the fault diagnosis of 30 types of faulty bearings with 100% accuracy. Test results verified the effectiveness of the proposed method. © 2020, Nanjing Univ. of Aeronautics an Astronautics. All right reserved.

引用

页码：854 / 860

页数：6

共 11 条

[1] Lei Ya-guo, 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)
[2] Tan J, Lu W, An J, Et al., Fault diagnosis method study in roller bearing based on wavelet transform and stacked auto-encoder, Control and Decision Conference, pp. 4608-4613, (2015)
[3] Gan M, Wang C., Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings, Mechanical Systems and Signal Processing, 72, pp. 92-104, (2016)
[4] Sun W, Shao S, Zhao R, Et al., A sparse auto-encode r-based deep neural network approach for induction motor faults classification, Measurement, 89, pp. 171-178, (2016)
[5] He M, He D., Deep learning based approach for bearing fault diagnosis, IEEE Transactions on Industry Applications, 53, 3, pp. 3057-3065, (2017)
[6] Jia F, Lei Y, Lin J, Et al., Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data, Mechanical Systems and Signal Processing, 72, pp. 303-315, (2016)
[7] YUAN Jianhu, HAN Tao, TANG Jian, Et al., An approach to intelligent fault diagnosis of rolling bearing using wavelet time-frequency representations and CNN, Machine Design and Research, 33, 2, pp. 93-97, (2017)
[8] Qu Tianling, Yu Lu, Yuan Tao, Et al., Adaptive fault diagonosis algorithm for rolling bearings based on one-dimensional convolutional neural network, Chinese Journal of Scientific Instrument, 39, 7, pp. 134-143, (2018)
[9] Zhang Wei, Study on bearing fault diagnosis algorithm based on convolutional neural network, pp. 21-23, (2017)
[10] Krizhevsky A, Sutskever I, Hinton G E., ImageNet classification with deep convolutional neural networks, Proceedings of the 25th International Conference on Neural Information Processing System, pp. 1097-1105, (2012)

← 1 2 →