Skip to main content
SpringerLink
Log in

Machinery Fault Diagnosis Based on Deep Learning for Time Series Analysis and Knowledge Graphs

  • Published:
Journal of Signal Processing Systems Aims and scope Submit manuscript

Abstract

With the rapid development of modern industrial production, mechanical equipment plays an increasingly important role, and its fault diagnosis is therefore critical. Traditional fault diagnosis generally needs a manual selection of features and a large amount of labeled data for training. In addition, diagnosis results are often too isolated and cannot provide a complete fault diagnosis process. In this paper, we propose a fault diagnosis approach for mechanical equipment, which combines one-dimensional CNN (Convolutional Neural Network), GRU (Gated Recurrent Unit), attention mechanism, and KG (knowledge graph). We first construct an ATT-1D CNN-GRU model by the serial merger of the one-dimensional CNN and GRU. The CNN model is used for feature extraction, and GRU and attention mechanism are applied for more accurate feature extraction. To prevent overfitting, we add the BN (Batch Normalization) before each pooling layer input. Then, we train the ATT-1D CNN-GRU model according to the existing fault data and obtain a precise prediction of the fault diagnosis results. Furthermore, we match the prediction results by searching through the knowledge graph and obtaining more relevant information about this fault. We verify our attention-based 1D CNN-GRU model over rolling bearing datasets under different loads. The results show that the accuracy of our proposed model is up to 99%.

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

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11
Figure 12
Figure 13
Figure 14
Figure 15
Figure 16
Figure 17
Figure 18
Figure 19
Figure 20
Figure 21
Figure 22
Figure 23
Figure 24
Figure 25
Figure 26
Figure 27
Figure 28
Figure 29
Figure 30
Figure 31
Figure 32
Figure 33
Figure 34
Figure 35

Similar content being viewed by others

Notes

  1. http://www.ebusiness-unibw.org/tools/rdf2rdfa/

  2. http://csegroups.case.edu/bearingdatacenter/pages/welcome-case-western-reserve-university-bearing-data-center-website

References

  1. Hebda-Sobkowicz, J., Zimroz, R., Pitera, M., & Wyłomańskac, A. (2020). Informative frequency band selection in the presence of non-Gaussian noise – a novel approach based on the conditional variance statistic with application to bearing fault diagnosis. Mechanical Systems and Signal Processing, 145(0888–3270), 106971.

  2. Xu, L., Steven, C., & Paolo, P. (2021). Rolling element bearing diagnosis based on singular value decomposition and composite squared envelope spectrum. Mechanical Systems and Signal Processing, 148, 107174.

  3. Zhao, D. F., Liu, S. L., Cheng, S. G., Sun, X., Wang, L., Wei, Y., & Zhang, H. L. (2021). Parallel multi-scale entropy and it's application in rolling bearing fault diagnosis. Measurement, 168, 108333.

  4. Xu, X. J., Yan, X. P., Sheng, C. X., Yuan, C. Q., & Yang, J. B. (2017). A belief rule-based expert system for fault diagnosis of marine diesel engines. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 50, 1–17.

    Google Scholar 

  5. Cao, C. P., Li, M., Li, Y., & Sun, Y. (2018). Intelligent fault diagnosis of hot die forging press based on binary decision diagram and fault tree analysis. Procedia Manufacturing, 15, 459–466.

    Article  Google Scholar 

  6. Huang, H. R., Li, K., Su, W. S., Bai, J. Y., & Pecht, M. (2020). An improved empirical wavelet transform method for rolling bearing fault diagnosis. Science China Technological Sciences, 63.

  7. Krishnannair, S., & Aldrich, C. (2019). Process monitoring and fault detection using empirical mode decomposition and singular spectrum analysis. IFAC PapersOnLine, 52(14), 219–224.

    Article  Google Scholar 

  8. Wang, T., Liu, W., Zhao, J. B., Guo, X. K., & Terzija, V. (2020). A rough set-based bio-inspired fault diagnosis method for electrical substations. International Journal of Electrical Power and Energy Systems, 119, 105961.

  9. Hu, W. F., Chang, H., & Gu, X. S. (2019). A novel fault diagnosis technique for wind turbine gearbox. Applied Soft Computing, 82.

  10. Wang, J. J., Chen, X. Y., & Ji, L. (2019). Research on fault diagnosis of DC charging pile power device based on wavelet packet and elman neural network. IOP Conference Series Materials Science and Engineering, 486, 012086.

  11. Liu, C. Y., & Gryllias, K. (2020). A semi-supervised Support Vector data description-based fault detection method for rolling element bearings based on cyclic spectral analysis. Mechanical Systems and Signal Processing, 140, 106682.

  12. Long, J. B., Wang, H. B., & Li, P. (2019). Applications of fractional lower order frequency spectrum technologies to bearing fault analysis. Mathematical Problems in Engineering, 2019, 1–24.

    Article  MathSciNet  Google Scholar 

  13. Geng, C. Y., & Gao, F. I. (2016). Embedded fault diagnosis expert system on weapon equipment. Proceedings of the 2016 International Conference on Mechatronics.

  14. Saari, J., Stombergsson, D., Lundberg, J., & Thomson, A. (2019). Detection and identification of windmill bearing faults using a one-class support vector machine (SVM). Measurement, 137, 287–301.

    Article  Google Scholar 

  15. Li, X. Q., Jiang, H. K., Niu, M. G., & Wang, R. X. (2020). An enhanced selective ensemble deep learning method for rolling bearing fault diagnosis with beetle antennae search algorithm. Mechanical Systems and Signal Processing, 142, 106752.

  16. Liang, P. F., Deng, C., Wu, J., & Yang, Z. (2020). Intelligent fault diagnosis of rotating machinery via wavelet transform, generative adversarial nets and convolutional neural network. Measurement, 159(0263–2241), 107768.

  17. Zhou, Q., Li, Y. B., Tian, Y., & Jiang, L. (2020). A novel method based on nonlinear auto-regression neural network and convolutional neural network for imbalanced fault diagnosis of rotating machinery. Measurement, 161(0263–2241), 107880.

  18. Sheng, G., Tao, Y., Gao, W., & Zhang, C. (2018). A novel fault diagnosis method for rotating machinery based on a convolutional neural network. Sensors, 18(5), 1429.

    Article  Google Scholar 

  19. Shao, H. D., Jiang, H. K., Zhang, H. Z., & Liang, T. (2017). Electric locomotive bearing fault diagnosis using novel convolution al deep belief network. IEEE Transactions on Industrial Electronics, 65(3), 2727–2736.

    Article  Google Scholar 

  20. Khodja, A. Y., Guersi, N., Saadi, M. N., & Boutasseta, N. (2020). Rolling element bearing fault diagnosis for rotating machinery using vibration spectrum imaging and convolutional neural networks. The International Journal of Advanced Manufacturing Technology, 106(5), 1737–1751.

    Article  Google Scholar 

  21. Vishal, C., & Kishor U. (2020). E-ProSRNet: An enhanced progressive single image super-resolution approach. Computer Vision and Image Understanding, 200, 103038.

  22. Roy, S. K., Dubey, S. R., Chatterjee, S., & Chaudhuri, B. B. (2020). FuSENet: Fused squeeze-and-excitation network for spectral-spatial hyperspectral image classification. IET Image Processing, 8(14), 1653–1661.

    Article  Google Scholar 

  23. Lecun, Y., & Bengio, Y. (1998). Convolutional Networks for Images, Speech, and Time Series. MIT Press.

  24. Che, C. C., Wang, H. W., Fu, Q., & Ni, X. M. (2019). Combining multiple deep learning algorithms for prognostic and health management of aircraft. Aerospace Science and Technology, 94, 105423.

  25. Li, Y., Cheng, G., Chen, X. H., & Pang, Y. S. (2019). Research on bearing fault diagnosis method based on filter features of MOMLMEDA and LSTM. Entropy, 21, 1025.

    Article  MathSciNet  Google Scholar 

  26. An, Z., Li, S. M., Wang, J. R., & Jiang, X. X. (2020). A novel bearing intelligent fault diagnosis framework under time-varying working conditions using recurrent neural network. ISA Transactions, 100, 155–170.

  27. Yuan, J., & Tian, Y. (2019). An intelligent fault diagnosis method using GRU neural network towards sequential data in dynamic processes. Processes, 7(3), 152.

    Article  Google Scholar 

  28. Bahdanau, D., Cho, K., & Bengio, Y. (2015). Neural machine translation by jointly learning to align and translate. Proceedings of the 3rd International Conference on Learning Representations.

  29. Fahim, S. R., Sarker, Y., Sarker, S. K., Sheikh, M. R. I., & Das, S. K. (2020). Self attention convolutional neural network with time series imaging based feature extraction for transmission line fault detection and classification. Electric Power Systems Research, 187, 106437.

  30. Yao, Y., Zhang, S., Yang, S. X., & Gui, G. (2020). Learning attention representation with a multi-scale CNN for gear fault diagnosis under different working conditions. Sensors., 20(4), 1233.

    Article  Google Scholar 

  31. Chen, R., Zhou, Z., Liu, Q., & Pham, D. T. (2015). Knowledge modeling of fault diagnosis for rotating machinery based on ontology. Proceedings of the 2015 International Conference on Industrial Informatics, 1050–1055.

  32. Zhang, Y. J., Shi, J. L., & Chen, G. R. (2012). A knowledge modeling method of blast furnace fault diagnosis based on ontology. Electronic and Mechanical Engineering and Information Technology.

  33. Xu, F. X., Liu, X. H., Chen, W., Zhou, C., & Cao, B. W. (2018). Ontology-based method for fault diagnosis of loaders. Sensors, 18(3), 729.

    Article  Google Scholar 

  34. Zhou, Q., Ping, Y., Liu, H. Y., & Xin, Y. (2019). A hybrid fault diagnosis method for mechanical components based on ontology and signal analysis. Journal of Intelligent Manufacturing, 30(4), 1693–1715.

    Article  Google Scholar 

  35. Zhou, A., Yu, D. J., & Zhang, W. Y. (2015). A research on intelligent fault diagnosis of wind turbines based on ontology and FMECA. Advanced Engineering Informatics, 29(1), 115–125.

    Article  Google Scholar 

  36. Ioffe, S., & Szegedy, C. (2015). Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv: Learning.

  37. Kingma, D. P., & Ba, J. (2015). Adam: a method for stochastic optimization. Proceedings of the 3rd International Conference on Learning Representations.

  38. Wang, D. C., Guo, Q. W., Song, Y., Gao, S. Y., & Li, Y. B. (2019). Application of multiscale learning neural network based on CNN in bearing fault diagnosis. Journal of Signal Processing Systems, 91(10), 1205–1217.

    Article  Google Scholar 

  39. Levent, E., Turker, I., & Serkan, K. (2019). A generic intelligent bearing fault diagnosis system using compact adaptive 1D CNN classifier. Journal of Signal Processing Systems, 91(2), 179–189.

    Article  Google Scholar 

  40. Xu, B. B., Wang, T. Z., Luo, K., & Gao, D. J. (2020). A fault diagnosis method based on Wavelet Singular Entropy and SVM for VSC-HVDC Converter. Wuhan University Journal of Natural Sciences, 25(04), 359–368.

    Google Scholar 

  41. Lei, J. H., Liu, C., & Jiang, D. X. (2019). Fault diagnosis of wind turbine based on Long Short-term memory networks. Renewable Energy, 133, 422–432.

    Article  Google Scholar 

  42. Li, J. M., Yao, X. F., Wang, X. D., Yu, Q. W., & Zhang, Y. G. (2020). Multiscale local features learning based on BP neural network for rolling bearing intelligent fault diagnosis. Measurement, 153, 107419.

  43. Li, H. K., Yang, R., Ren, Y. J., He, D. L., & Guo, B. (2017). Rolling element bearing diagnosis using particle filter and kurtogram. Journal of mechanical engineering, 53(03), 63–72.

    Article  Google Scholar 

  44. Lei, Y. G., Jia, F., Lin, J., & Xing, S. B. (2016). An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data. IEEE Transactions on Industrial Electronics, 63(10), 3137–3147.

    Article  Google Scholar 

  45. Zhou, J. M., Wang, F., Zhang, C. C., & Zhang, L. (2019). Evaluation of rolling bearing performance degradation using wavelet packet energy entropy and RBF neural network. Symmetry, 11(8), 1064.

    Article  Google Scholar 

  46. Cheng, C., Zhou, B. T., Ma, G. J., Wu, D. R., & Yuan, Y. (2019). Wasserstein distance based deep adversarial transfer learning for intelligent fault diagnosis. arxiV: 1903.06753.

  47. Castejón, C., Gómez, M. J., García-Prada, J. C., Ordonez, A. J., & Rubio, H. (2015). Automatic selection of the WPT decomposition level for condition monitoring of rotor elements based on the sensitivity analysis of the wavelet energy. International Journal of Acoustics and Vibrations, 20(2), 95–100.

    Google Scholar 

  48. Bhandari, S., Zhao, H. P., Kim, H., Khan, P., & Ullah, S. (2019). Packet scheduling using SVM models in wireless communication networks. Journal of Internet Technology, 20(5), 1505–1512.

    Google Scholar 

  49. Shen, F., Chen, C., Yan, R. Q., & Gao, R. X. (2015). Bearing fault diagnosis based on SVD feature extraction and transfer learning classification. Prognostics and System Health Management Conference (PHM), 2015, 1–6.

    Google Scholar 

  50. Zhang, A., Li, S. B., Cui, Y. X., Yang, W. L., Dong, R. Z., & Hu, J. J. (2019). Limited data rolling bearing fault diagnosis with few-shot learning. IEEE Access, 7, 110895–110904.

    Article  Google Scholar 

Download references

Acknowledgements

The authors wish to thank the anonymous referees for their valuable comments and suggestions, which greatly improved the technical content and the presentation of the paper. The work was supported in part by the National Natural Science Foundation of China (U1931207).

Author information

Authors and Affiliations

  1. College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, 211106, China

    Haiying Liu, Daiyi Li, Li Yan & Zongmin Ma

  2. Department of Computer Science, University of Massachusetts Lowell, Lowell, MA, 01854, USA

    Ruizhe Ma

Authors
  1. Haiying Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ruizhe Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Daiyi Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Li Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zongmin Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ruizhe Ma.

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

Liu, H., Ma, R., Li, D. et al. Machinery Fault Diagnosis Based on Deep Learning for Time Series Analysis and Knowledge Graphs. J Sign Process Syst 93, 1433–1455 (2021). https://doi.org/10.1007/s11265-021-01718-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11265-021-01718-3

Keywords

Search

Navigation