Skip to main content
SpringerLink
Log in

A sparse denoising deep neural network for improving fault diagnosis performance

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

Deep neural network (DNN) has been recently used in the field of fault diagnosis, but still their applicability is restricted to high computational complexity. In addition, useless information transformation between adjacent layers of the network could have a negative influence on the diagnosis accuracy. In this paper, a new DNN structure with sparse gate is designed to highlight the role of neurons contributed more by making it directly transfer through layers rather than transfer via an activation function. So it can reduce the computational complexity of network training since only those contributed less are required to be transferred via a nonlinear transformation. The proposed sparse denoising DNN (SD-DNN)-based fault diagnosis method can achieve more accurate diagnosis result with less computational complexity. It shows significant superiority to other-related methods in the case when only small size of training samples polluted by strong noise is available, which is very common for the engineering field of fault diagnosis. The experimental testing of fault diagnosis for rolling bearings verifies the effectiveness of the proposed method.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

References:

  1. Zhang, D., Chen, Y., Guo, F., Karimi, H.R., Dong, H., Xuan, Q.: A New Interpretable Learning Method for Fault Diagnosis of Rolling Bearings. IEEE Trans.Instrum. Meas. 70, 1–10 (2021)

    Google Scholar 

  2. Hoanga, D., Kang, H.: Survey on Deep Learning based bearing fault diagnosis. Neurocomput. 335, 327–335 (2019)

    Article  Google Scholar 

  3. Sun, M., Wang, H., Liu, P., Huang, S., Fan, P.: A sparse stacked denoising autoencoder with optimized transfer learning applied to the fault diagnosis of rolling bearings. Meas. 146, 305–314 (2019)

    Article  Google Scholar 

  4. Cerrada, M., Sánchez, R.-V., Li, C., et al.: A review on data-driven fault severity assessment in rolling bearings. Mechl. Syst. Signal Process. 99, 169–196 (2018)

    Article  Google Scholar 

  5. Li, Y., Xu, M., Wei, Y., Huang, W.: A new rolling bearing fault diagnosis method based on multiscale permutation entropy and improved support vector machine based binary tree. Meas. 77, 80–94 (2016)

    Article  Google Scholar 

  6. Dhamande, L.S., Chaudhari, M.B.: Bearing fault diagnosis based on statistical feature extraction in time and frequency domain and neural network. Int. J. Veh. Struct. Syst. 8(4), 229–240 (2016)

    Google Scholar 

  7. 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. Mech. Syst. Signal Process. 72–73, 303–315 (2016)

    Article  Google Scholar 

  8. Duan, L., Xie, M., Wang, J., Bai, T.: Deep learning enabled intelligent fault diagnosis: Overview and applications. J. Intell. Fuzzy Syst. 35, 5771–5784 (2018)

    Article  Google Scholar 

  9. Janssens, O., Slavkovikj, V., Vervisch, B., Stockman, K., Loccufier, M., Verstockt, S., Walle, R.V., Hoecke, S.V.: Convolutional neural network based fault detection for rotating machinery. J. Sound Vib. 377(1), 331–345 (2016)

    Article  Google Scholar 

  10. Shao, H., Jiang, H., Wang, F., Wang, Y.: Rolling bearing fault diagnosis using adaptive deep belief network with dual-tree complex wavelet packet. ISA Trans. 69, 187–201 (2017)

    Article  Google Scholar 

  11. Cao L., Zhang J., Wang J. and Qian Z., (2019) Intelligent fault diagnosis of wind turbine gearbox based on Long short-term memory networks. Proceeding of 2019 IEEE 28th International Symposium on Industrial Electronics (ISIE), Vancouver, B.C., Canada, 890-895

  12. Yu, J.: Evolutionary manifold regularized stacked denoising autoencoders for gearbox fault diagnosis. Knowl.-Based Syst. 178, 111–122 (2019)

    Article  Google Scholar 

  13. Wen, L., Li, X., Gao, L., Zhang, Y.: A New convolutional neural network-nased data-driven fault diagnosis method. IEEE Trans. Industr. Electron. 65(7), 5990–5998 (2018)

    Article  Google Scholar 

  14. Shao, H., Jiang, H., Zhang, X., et al.: Rolling bearing fault diagnosis using an optimization deep belief network. Meas. Sci. Technol. 26(11), 115–123 (2015)

    Article  Google Scholar 

  15. Yu, L., Qu, J., Gao, F., Tian, Y., Mucchi, E.: A Novel Hierarchical Algorithm for Bearing Fault Diagnosis Based on Stacked LSTM. Shock Vib. 2019, 1–10 (2019)

    Google Scholar 

  16. Lei, Y., Karimi, H.R., Cen, L., Chen, X., Xie, Y.: Processes soft modeling based on stacked autoencoders and wavelet extreme learning machine for aluminum plant-wide application. Control Eng. Prac. 108, 104706 (2021)

    Article  Google Scholar 

  17. Zhao, M., Kang, M., Tang, B., Pecht, M.: Deep Residual Networks With Dynamically Weighted Wavelet Coeffificients for Fault Diagnosis of Planetary Gearboxes. IEEE Trans. Industr. Electron. 65(5), 4290–4300 (2018)

    Article  Google Scholar 

  18. Wang, J., Mo, Z., Zhang, H., Miao, Q.: A Deep Learning Method for Bearing Fault Diagnosis Based on Time-Frequency Image. IEEE Access 7, 42373–42383 (2019)

    Article  Google Scholar 

  19. Tang J., Lu W., An J. and Wan X., (2015) Fault diagnosis method study in roller bearing based on wavelet transform and stacked auto-encoder. Proceeding of 27th Chinese Control and Decision Conference, 4608–4613.

  20. M.Heydarzadeh, S. H. Kia, M. Nourani, H. Henao and G. Capolino, (2016) Gear fault diagnosis using discrete wavelet transform and deep neural networks. Proceeding of 42nd Annual Conference of the IEEE Industrial Electronics Society, 1494–1500.

  21. Zarei, J., Tajeddini, M.A., Karimi, H.R.: Vibration analysis for bearing fault detection and classification using an intelligent filter. Mechatron. 24(2), 151–157 (2014)

    Article  Google Scholar 

  22. Qian, W., Li, S., Wang, J., Wu, Q.: A novel supervised sparse feature extraction method and its application on rotating machine fault diagnosis. Neurocomput. 320, 129–140 (2018)

    Article  Google Scholar 

  23. Meng, Z., Zhan, X., Li, J., Pan, Z.: An enhancement denoising autoencoder for rolling bearing fault diagnosis. Meas. 130, 448–454 (2018)

    Article  Google Scholar 

  24. Lu, C., Wang, Z., Qin, W., Ma, J.: Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification. Signal Process. 130, 377–388 (2017)

    Article  Google Scholar 

  25. Wang Y., Han M. and Liu W., (2019) Rolling Bearing Fault Diagnosis Method Based on Stacked Denoising Autoencoder and Convolutional Neural Network, Proceeding of 2019 International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering, 833–838.

  26. Zhang, J., Chen, Z., Du, X., Yu, M.: Application of stack marginalised sparse denoising auto-encoder in fault diagnosis of rolling bearing. J. Eng. 16, 1772–1777 (2018)

    Article  Google Scholar 

  27. Li, Y., Lei, Y., Wang, P., Jiang, M., Liu, Y.: Embedded stacked group sparse autoencoder ensemble with L1 regularization and manifold reduction. Appl. Soft Comput. J. 101, 107003 (2021)

    Article  Google Scholar 

  28. Sun, W., Shao, S., Zhao, R., Yan, R., Zhang, X., Chen, X.: A sparse auto-encoder-based deep neural network approach for induction motor faults classification. Meas. 89, 171–178 (2016)

    Article  Google Scholar 

  29. Sohaib, M., Kim, J.-M.: Reliable Fault Diagnosis of Rotary Machine Bearings Using a Stacked Sparse Autoencoder-Based Deep Neural Network. Shock Vib. 2018, 1–11 (2018)

    Article  Google Scholar 

  30. Qi, Y., Shen, C., Wang, D.: Stacked sparse autoencoder-based deep network for fault diagnosis of rotating machinery. IEEE Access 5, 15066–15079 (2017)

    Article  Google Scholar 

  31. Zhang, J., Chen, Z., Du, X., Xu, X., Yu, M.: Application of stack marginalised sparse denoising auto-encoder in fault diagnosis of rolling bearing. J. Eng. 2018(16), 1772–1777 (2018)

    Article  Google Scholar 

  32. Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Sci. 313(5786), 504–507 (2006)

    Article  MathSciNet  Google Scholar 

  33. Bengio Y, Lamblin P, Popovici D, et al., (2007) Greedy layer-wise training of deep networks.Advances in Neural Information Processing Systems 19, Proceedings of the Twentieth Annual Conference on Neural Information Processing Systems:153–160.

  34. Bearing data Centre, Case Western Reserve University, Available: http://csegroups.case.edu/bearingdatacenter/home

Download references

Acknowledgements

This research was supported in part by the Natural Science Fund of China (Grant No.62073213, U1604158, U1804163, 61751304, 61673160).

Author information

Authors and Affiliations

  1. School of Logistic Engineering, Shanghai Maritime University, Shanghai, 201306, China

    Funa Zhou, Tong Sun, Xiong Hu & Tianzhen Wang

  2. Institute of Automation, Guangdong University of Petrochemical Technology, Maoming, China

    Chenglin Wen

Authors
  1. Funa Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tong Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiong Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Tianzhen Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Chenglin Wen
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Funa Zhou or Tong Sun.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhou, F., Sun, T., Hu, X. et al. A sparse denoising deep neural network for improving fault diagnosis performance. SIViP 15, 1889–1898 (2021). https://doi.org/10.1007/s11760-021-01939-w

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-021-01939-w

Keywords

Search

Navigation