Convolutional neural network diagnosis method of rolling bearing fault based on casing signal

被引：0
|
作者：
Zhang X. [1 ]
Chen G. [1 ]
Hao T. [2 ]
He Z. [1 ]
Li X. [1 ]
Cheng Z. [1 ]
机构：
[1] College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing
[2] School of Automotive and Rail Transit, Nanjing Institute of Technology, Nanjing
来源：
Hangkong Dongli Xuebao/Journal of Aerospace Power | 2019年 / 34卷 / 12期
关键词：
Casing signal; Convolutional neural network(CNN); Fault diagnosis; Rolling bearing; Wavelet scale spectrum;
D O I：
10.13224/j.cnki.jasp.2019.12.022
中图分类号：
学科分类号：
摘要：
A fault diagnosis method based on convolutional neural network (CNN) was proposed for the weak fault of the engine casing under the rolling bearing fault excitation. The one-dimensional original signal was converted into image signal by using three preprocessing methods: matrix graph method, kurtosis graph method and wavelet scale spectrum. Then the convolutional neural network was used to identify the fault. Through comparative analysis, the fault identification rate of rolling bearing was 95.82%, which was higher than other vibration signal pretreatment methods. At the same time, the fault recognition rate of convolutional neural network was about 7% higher than that of traditional support vector machine (SVM) because it can use deep network structure to extract the fault characteristics of rolling bearing adaptively. The results show that the proposed method is feasible and effective, and has a good generalization ability and robustness. © 2019, Editorial Department of Journal of Aerospace Power. All right reserved.
引用
收藏
页码：2729 / 2737
页数：8
相关论文
共 17 条
  • [1] Randall R.B., Antoni J., Roling element bearing diagnostics: a tutorial, Mechanical Systems and Signal Procesing, 25, 2, pp. 485-520, (2011)
  • [2] Chen Z.Q., Li C., Sanchez R.V., Gearbox fault identification and classification with convolutional neural networks, Shock and Vibration, 2015, pp. 1-10, (2015)
  • [3] Zhang Q., Chen G., Et al., State evaluation method of rolling bearing based on self-organizing neural network, China Mechanical Engineering, 28, 5, pp. 550-558, (2017)
  • [4] Chen G., Feature extraction and intelligent diagnosis of early faults in rolling bearings, Acta Aeronautica Sinica, 30, 2, pp. 362-367, (2009)
  • [5] Saidi L., Ben A.J., Fnaiech F., Application of higher order spectral features and support vector machines for bearing faults classification, ISA(International Society of Automation) Transactions, 54, pp. 193-206, (2015)
  • [6] Socher R., Huval B., Bath B.P., Et al., Convolutional-recursive deep learning for 3D object classification, (2012)
  • [7] Lecun Y., Bengio Y., Hinton G., Deep learning, Nature, 521, pp. 436-444, (2015)
  • [8] Chen R., Yang X., Yang L., Et al., Diagnosis of rolling bearing damage degree by stack sparse noise-added self-coded deep neural network, Journal of Vibration and Shock, 36, 21, (2017)
  • [9] Lei Y., Jia F., Zhou X., Et al., The big data health monitoring method for mechanical equipment based on deep learning theory, Journal of Mechanical Engineering, 51, 21, pp. 49-56, (2015)
  • [10] Sun W., Shao S., Zhao R., Et al., A sparse auto-encoder-based deep neural network approach for induction motor faults classification, Measurement, 89, pp. 171-178, (2016)
12