A Remaining Useful Life Approach using an Ensemble Regressor enhanced with Hilbert Transform and CNN-LSTM Model

Abstract

In this study, we propose a hybrid approach that integrates signal-driven and knowledge-based techniques to estimate the Remaining Useful Life (RUL) of bearings. The experimental data for this research is sourced from the FEMTO-ST Institute. Firstly, the horizontal and vertical acceleration data is ordered chronologically by time, and a band-pass filter is used for early-stage preprocessing of the vibration signals below 20 kHz. Then, the overall behavior of the signal is characterized by Hilbert-Transform. For the feature extraction scheme, a model that integrates Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks is implemented. These features form historical data on health indexes describing fault stages and are as such used to fit a voting regressor yielding an extrapolated future. The voting regressor is based on support vector regression (SVR) and linear regressor methods and a fault threshold is determined as 0.8 based on prior experiments. Finally, the proposed methodology distinguishes itself by recording the smallest average percentage error on the FEMTO dataset. This method proves that early-stage predictions are possible with run-to-failure data provision ranging from 60% and above, averaging some 1400 seconds into the future implying its suitability and effectiveness for real industrial applications.

Keywords

• Predictive Maintenance
• CNN-LSTM
• Feature Extraction
• RUL
• Hilbert Transform

References

1. [1] Kaplan K., Kaya Y., Kuncan M., Mi̇naz M. R., Ertunç H. M., 2020. An improved feature extraction method using texture analysis with LBP for bearing fault diagnosis, Applied Soft Computing, 87, pp. 1-13.
2. [2] Kuncan M., Kaplan K., Mi̇naz M. R., Kaya Y., Ertunç H. M., 2020. A novel feature extraction method for bearing fault classification with one dimensional ternary pattern, ISA Transactions, 100, pp. 346-357.
3. [3] Kaya Y., Kuncan M., Kaplan K., Minaz M. R., Ertunç H. M., 2020. Classification of bearing vibration speeds under 1D-LBP based on eight local directional filters, Soft Computing, 24, pp. 12175–12186.
4. [4] Kaya Y., Kuncan M., Kaplan K., Minaz M. R., Ertunç H. M., 2021. A new feature extraction approach based on one dimensional gray level co-occurrence matrices for bearing fault classification, Journal of Experimental & Theoretical Artificial Intelligence, 33(1), pp. 161-178.
5. [5] Simani S et al., 2003. Model-based fault diagnosis in dynamic systems using identification techniques. Springer-Verlag, Secaucus, NJ, USA.
6. [6] Isermann R., 2005. Model-based fault-detection and diagnosis – status and applications, Annual Reviews in Control, 29, pp. 71-85.
7. [7] Bensaadi R., Mouss H., Mouss M.D., Benbouzid M., 2005. Fuzzy Pattern Recognition Based Fault Diagnosis. International Review on Modelling and Simulations, 4, pp. 347-356.
8. [8] Do V. T., Chong U., 2011. Signal model-based fault detection and diagnosis for induction motors using features of vibration signal in two-dimension domain. Strojniški vestnik - Journal of Mechanical Engineering, 57, pp. 655–666.

9. [9] Lei, Y., Li, N., Gontarz, S., Lin, J., Radkowski, S., & Dybala, J., 2016. A model-based method for remaining useful life prediction of machinery. IEEE Transactions on reliability, 65(3), pp. 1314-1326.
10. [10] M. Benbouzid et al., 1999. Induction motors’ faults detection and localization using stator current advanced signal processing techniques. IEEE Trans Power Electron, 14, pp. 14–22.
11. [11] A. Widodo et al., 2009. Intelligent fault diagnosis system of induction motor based on transient current signal. Mechatronics, 19, pp. 680–689.
12. [12] Wang R., Zhan X., Bai H., Dong E., Cheng Z., & Jia X., 2022. A Review of Fault Diagnosis Methods for Rotating Machinery Using Infrared Thermography. Micromachines, 13(10), pp. 1644.
13. [13] Witczak, M., Lipiec, B., Mrugalski, M., & Stetter, R., 2020. A fuzzy logic approach to remaining useful life estimation of ball bearings. In Advanced, Contemporary Control: Proceedings of KKA 2020—The 20th Polish Control Conference, Łódź, Poland, 22-25 June, pp. 1411-1423.
14. [14] Saon, S., & Hiyama, T., 2010. Predicting remaining useful life of rotating machinery based artificial neural network. Computers & Mathematics with Applications, 60(4), pp. 1078-1087.
15. [15] Chen Y., Peng G., Zhu Z., Li S., 2020. A novel deep learning method based on attention mechanism for bearing remaining useful life prediction, Applied Soft Computing, 86, pp. 1568-4946.
16. [16] Yan, M., Wang, X., Wang, B., Chang, M., & Muhammad, I., 2020. Bearing remaining useful life prediction using support vector machine and hybrid degradation tracking model. ISA transactions, 98, pp. 471-482.
17. [17] Wu J. Y., Wu M., Chen Z. H., Li X. L., & Yan R. Q., 2021. A joint classification-regression method for multi-stage remaining useful life prediction J. Manuf. Syst., 58, pp. 109-119.
18. [18] Li X., Elasha F., Shanbr S., and Mba D., 2019. Remaining useful life prediction of rolling element bearings using supervised machine learning Energies 12(14), pp. 2705.
19. [19] Wu J., Wu C. Y., Cao S., Or S. W., Deng C., and Shao X. Y., 2019. Degradation data-driven time-to-failure prognostics approach for rolling element bearings in electrical machines IEEE Trans. Ind. Electron, 66, pp. 529-539.
20. [20] Meng, Z., Li, J., Yin, N., & Pan, Z., 2020. Remaining useful life prediction of rolling bearing using fractal theory. Measurement, 156, pp. 0263-2241.
21. [21] Ahmad, W., Khan, S. A., Islam, M. M., & Kim, J. M. 2019. A reliable technique for remaining useful life estimation of rolling element bearings using dynamic regression models. Reliability Engineering & System Safety, 184, pp. 67-76.
22. [22] Soualhi A., Medjaher K., & Zerhouni N., 2014. Bearing health monitoring based on Hilbert–Huang transform, support vector machine, and regression. IEEE Transactions on instrumentation and measurement, 64(1), pp. 52-62.
23. [23] Ren, L., Sun, Y., Cui, J., & Zhang, L., 2018. Bearing remaining useful life prediction based on deep autoencoder and deep neural networks. Journal of Manufacturing Systems, 48, pp. 71-77.
24. [24] Lu Y. W., Hsu C. Y., and Huang K. C., 2020, An autoencoder gated recurrent unit for remaining useful life prediction Processes, 8, pp. 1155-1159.
25. [25] Peng K. X., Jiao R. H., Dong J., and Pi Y. T., 2019. A deep belief network based health indicator construction and remaining useful life prediction using improved particle filter. Neurocomputing, 361, pp. 19-28.
26. [26] Zhao C., Huang X., Li Y., & Li S., 2021. A novel cap-LSTM model for remaining useful life prediction. IEEE Sensors Journal, 21(20), 23498-23509.
27. [27] Li X., Zhang W., and Ding Q., 2019. Deep learning-based remaining useful life estimation of bearings using multi-scale feature extraction. Reliability Engineering & System Safety, 182, pp. 208-218.
28. [28] Wang B., Lei Y. G., Li N. P., and Yan T., 2019. Deep separable convolutional network for remaining useful life prediction of machinery. Mechanical Systems and Signal Processing, 134, pp. 106330.
29. [29] Lee K., Man Z., Wang D., & Cao Z., 2013. Classification of bioinformatics dataset using finite impulse response extreme learning machine for cancer diagnosis. Neural Computing and Applications, 22, pp. 457-468.
30. [30] Feldman, M., 2011. Hilbert transform applications in mechanical vibration. John Wiley & Sons, West Sussex, England.
31. [31] Yu Y., Si X., Hu C., & Zhang J., 2019. A review of recurrent neural networks: LSTM cells and network architectures. Neural Computation, 31(7), pp. 1235-1270.
32. [32] Awad M., Khanna R., Awad M., & Khanna R., 2015. Efficient learning machines: Theories, concepts, and applications for engineers and system designers. New York.
33. [33] Maulud D., & Abdulazeez A. M., 2020. A review on linear regression comprehensive in machine learning. Journal of Applied Science and Technology Trends, 1(4), pp. 140-147.
34. [34] Nectoux P., Gouriveau R., Medjaher K., Ramasso E., Chebel-Morello B., Zerhouni N., Varnier C., 2012. PRONOSTIA: An experimental platform for bearings accelerated degradation tests, IEEE International Conference on Prognostics and Health Management, June, pp. 1-8.
35. [35] Zhou W., Habetler T. G., & Harley R. G., 200, September). Bearing condition monitoring methods for electric machines: A general review. IEEE international symposium on diagnostics for electric machines, power electronics and drives, pp. 3-6.
36. [36] Akcan E., Kaya Y., 2023. A new approach for remaining useful life prediction of bearings using 1D-ternary patterns with LSTM. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 45, pp. 378.
37. [37] Rumelhart D. E., Hinton G. E., Williams R. J., 1986. Learning representations by back-propagating errors. Nature, 323, pp. 533-536.
38. [38] Sutrisno E., Oh H., Vasan A., Pecht M., 2012. Estimation of remaining useful life of ball bearings using data driven methodologies. IEEE Conference on Prognostics and Health Management, pp. 1-7.
39. [39] Hinchi Z., Tkiouat M., 2018. Rolling element bearing remaining useful life estimation based on a convolutional long-short-term memory network. Procedia Computer Science, 127, pp. 123–132.
40. [40] Lei Y., Li N., Gontarz S., Lin J., Radkowski S., Dybala J., 2016. A model-based method for remaining useful life prediction of machinery. IEEE Transactions on Reliability, 65(3), pp. 1314–1326.
41. [41] Hong S., Zhou Z., Zio E., Hong K., 2014. Condition assessment for the performance degradation of bearing based on a combinatorial feature extraction method. Digital Signal Process, 27, pp. 159–166.