An Efficient and Flexible Diagnostic Method for Machinery Fault Detection Based on Convolutional Neural Network

  • Geng Wang
  • Baolong GuoEmail author
  • Cheng Li
  • Zhe Huang
  • Jie Hu
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1107)


In the field of feature extraction and machinery fault detection, intelligent fault diagnosis of rotating machinery has drawn much attention. This paper proposes an efficient and flexible diagnostic method based on convolutional neural network (CNN). The method directly feeds the original one-dimensional signals into the formulated network, and adopts one-dimensional convolution kernels to extract representative features. This reduces complexity and time consumption. In the training process, the stochastic gradient descent (SGD) method with momentum is adopted to minimize the loss function of the formulated learning network, so that it could get rid of local minimum points and saddle points as well as speed up optimizing. The experimental results demonstrate that the proposed method effectively identifies the rolling bearing faults under different conditions.


Rolling bearing Fault diagnosis Feature extraction Convolutional neural network Deep learning 



This work is supported by the National Natural Science Foundation of China (61571346). The research is also supported by the Fundamental Research Funds for the Central Universities and the Innovation Fund of Xidian University. The authors also gratefully acknowledge the helpful comments and suggestions of the reviewers, which have improved the presentation.


  1. 1.
    Cui, L.L., Gong, X.Y., Zhang, J.Y., Wang, H.Q.: Double-dictionary matching pursuit for fault extent evaluation of rolling bearing based on the Lempel-Ziv complexity. J. Sound Vib. 385, 372–388 (2016)CrossRefGoogle Scholar
  2. 2.
    He, Q.B., Wu, E.H., Pan, Y.Y.: Multi-scale stochastic resonance spectrogram for fault diagnosis of rolling element bearings. J. Sound Vib. 420, 174–184 (2018)CrossRefGoogle Scholar
  3. 3.
    Tu, X.T., Hu, Y., Li, F., Abbas, S., Liu, Z., Bao, W.J.: Demodulated high-order synchrosqueezing transform with application to machine fault diagnosis. IEEE Trans. Ind. Electron. 66(4), 3071–3081 (2018)CrossRefGoogle Scholar
  4. 4.
    Cui, L.L., Huang, J.F., Zhang, F.B.: Quantitative and localization diagnosis of a defective ball bearing based on vertical-horizontal synchronization signal analysis. IEEE Trans. Ind. Electron. 64(11), 8695–8706 (2017)CrossRefGoogle Scholar
  5. 5.
    Xiang, J.W., Zhong, Y.T.: A novel personalized diagnosis methodology using numerical simulation and an intelligent method to detect faults in a shaft. Appl. Sci. 6(12), 414 (2016)CrossRefGoogle Scholar
  6. 6.
    He, W.P., Wang, G., Hu, J., Li, C., Guo, B.L., Li, F.P.: Simultaneous human health monitoring and time-frequency sparse representation using EEG and ECG signals. IEEE Access 7, 85986–85994 (2019)Google Scholar
  7. 7.
    Liu, R.N., Yang, B.Y., Zio, E., Chen, X.F.: Artificial intelligence for fault diagnosis of rotating machinery: a review. Mech. Syst. Signal Process. 108, 33–47 (2018)CrossRefGoogle Scholar
  8. 8.
    He, W.P., Huang, Z., Wei, Z.F., Li, C., Guo, B.L.: TF-YOLO: an improved incremental network for real-time object detection. Appl. Sci. 9(16), 3225 (2019)CrossRefGoogle Scholar
  9. 9.
    Zhao, R., Yan, R.Q., Chen, Z.H., Mao, K.Z., Wang, P., Gao, R.: Deep learning and its applications to machine health monitoring. Mech. Syst. Signal Process. 115, 213–237 (2019)CrossRefGoogle Scholar
  10. 10.
    Jing, L.Y., Zhao, M., Li, P., Xu, X.Q.: A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox. Measurement 111, 1–10 (2017)CrossRefGoogle Scholar
  11. 11.
    Liu, R.N., Meng, G.T., Yang, B.Y., Sun, C., Chen, X.F.: Dislocated time series convolutional neural architecture: an intelligent fault diagnosis approach for electric machine. IEEE Trans. Ind. Inform. 13(3), 1310–1320 (2016)CrossRefGoogle Scholar
  12. 12.
    Xia, M., Li, T., Lin, X., Liu, L.Z., De Silva, C.: Fault diagnosis for rotating machinery using multiple sensors and convolutional neural networks. IEEE/ASME Trans. Mechatron. 23(1), 101–110 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Geng Wang
    • 1
  • Baolong Guo
    • 1
    Email author
  • Cheng Li
    • 1
  • Zhe Huang
    • 1
  • Jie Hu
    • 1
  1. 1.School of Aerospace Science and TechnologyXidian UniversityXi’anChina

Personalised recommendations