Remaining Useful Life Prediction Method For Different Types Of Rolling Bearings Based On Bi-Lstm Quantification
DOI:
https://doi.org/10.5890/DNC.2025.03.012Abstract
The remaining Useful Life (RUL) forecast for rolling bearings is still a crucial part of condition-based maintenance (CBM) for mechanical systems. To predict the RUL, the existing research utilized traditional Deep Learning techniques, however, it has trouble quantifying uncertainty. Therefore, this research suggested a novel deep learning (DL) model to improve RUL prediction. Initially, to define the degree of rolling bearing deterioration and comprehend the non-linear qualities, time domain features, frequency domain features, and time-frequency domain features are removed. Then, this study suggested using a Bi-LSTM - RF framework to predict the RUL, this framework has an LSTM layer in a combination of forward and backward motion, a fully connected layer, an RF classifier, and a dropout layer. As a result, our proposed deep learning-based RUL prediction obtains the Accuracy of 0.9845, Precision of 0.93, Recall of 1.0, and F1-score of 0.9656.References
[1] de Pater, I., Reijns, A., and Mitici, M. (2022), Alarm-based predictive maintenance scheduling for aircraft engines with imperfect Remaining Useful Life prognostics, Reliability Engineering and System Safety, 221, 108341.
[2] Kondhalkar, G.E. and Diwakar, G. (2020), Crest factor measurement by experimental vibration analysis for preventive maintenance of bearing, In ICRRM 2019--System Reliability, Quality Control, Safety, Maintenance, and Management: Applications to Civil, Mechanical and Chemical Engineering, Springer Singapore, 133-138.
[3] Kondhalka, G. and Diwakar, E. (2019), Effect of various defects in roller bearings and ball bearings on vibration, International Journal of Innovative Technology and Exploring Engineering, 8(12), 5137-5141.
[4] Zhang, P., Gao, Z., Cao, L., Dong, F., Zou, Y., Wang, K., and Sun, P. (2022), Marine systems and equipment prognostics and health management: a systematic review from health condition monitoring to maintenance strategy, Machines, 10(2), 72.
[5] Cao, Y., Ding, Y., Jia, M., and Tian, R. (2021), A novel temporal convolutional network with residual self-attention mechanism for remaining useful life prediction of rolling bearings, Reliability Engineering and System Safety, 215, 107813.
[6] Cao, Y., Jia, M., Ding, P., and Ding, Y. (2021), Transfer learning for remaining useful life prediction of multi-conditions bearings based on bidirectional-GRU network, Measurement, 178, 109287.
[7] Chen, C., Liu, Y., Wang, S., Sun, X., Di Cairano-Gilfedder, C., Titmus, S., and Syntetos, A.A. (2020), Predictive maintenance using Cox proportional hazard deep learning, Adv Eng Informatics, 44, p.101054.
[8] Aremu, O.O., Hyland-Wood, D., McAree, P.R. (2019), A Relative Entropy Weibull-SAX framework for health indices construction and health stage division in degradation modeling of multivariate time series asset data, Advanced Engineering Informatics, 40, 121-134.
[9] Caravaca, C.F., Flamant, Q., Anglada, M., Gremillard, L., and Chevalier, J. (2018), Impact of sandblasting on the mechanical properties and aging resistance of alumina and zirconia-based ceramics, Journal of the European Ceramic Society, 38(3), 915-925.
[10] Ding, P., Jia, M., and Yan, X. (2021), Stationary subspaces-vector autoregressive with exogenous terms methodology for degradation trend estimation of rolling and slewing bearings, Mechanical Systems and Signal Processing, 150, p.107293.
[11] Ding, P., Jia, M., and Wang, H. (2020), A dynamic structure-adaptive symbolic approach for slewing bearings' life prediction under variable working conditions, Structural Health Monitoring, 20(1), 273-302.
[12] Meissner, R., Rahn, A., and Wicke, K. (2021), Developing prescriptive maintenance strategies in the aviation industry based on a discrete-event simulation framework for post-prognostics decision-making, Reliability Engineering and System Safety, 214, 107812.
[13] Ordo'nez, C., Lasheras, F.S, Roca-Pardinas, J., and de Cos Juez, F.J. (2019), A hybrid arima--svm model for the study of the remaining useful life of aircraft engines, Journal of Computational and Applied Mathematics, 346, 184-191.
[14] Chen, Z., Li, Y., Xia, T., and Pan, E. (2019), Hidden Markov model with auto-correlated observations for remaining useful life prediction and optimal maintenance policy, Reliability Engineering and System Safety, 184, 123-136.
[15] Yang, B., Liu, R., and Zio, E. (2019), Remaining useful life prediction based on a double-convolutional neural network architecture, IEEE Transactions on Industrial Electronics, 66(12), 9521-9530.
[16] Liu, Z., Cheng, Y., Wang, P., Yu, Y., and Long, Y. (2018), A method for remaining useful life prediction of crystal oscillators using the Bayesian approach and extreme learning machine under uncertainty, Neurocomputing, 305, 27-38.
[17] Hu, Y., Li, H., Shi, P., Chai, Z., Wang, K., Xie, X., and Chen, Z. (2018), A prediction method for the real-time remaining useful life of wind turbine bearings based on the Wiener process, Renewable Energy, 127, 452-460.
[18] Wu, J., Su, Y., Cheng, Y., Shao, X., Deng, C., and Liu, C. (2018), Multi-sensor information fusion for remaining useful life prediction of machining tools by adaptive network-based fuzzy inference system, Applied Soft Computing, 68, 12-23.
[19] Kundu, P., Darpe, A.K., and Kulkarni, M.S. (2019), Weibull accelerated failure time regression model for remaining useful life prediction of bearing working under multiple operating conditions, Mechanical Systems and Signal Processing, 134, p.106302.
[20] Cheng, Y., Hu, K., Wu, J., Zhu, H., and Shao, X. (2021), Auto-encoder quasi-recurrent neural networks for remaining useful life prediction of engineering systems, IEEE/ASME Transactions on Mechatronics, 27(2), 1081-1092.
[21] Hu, C., Pei, H., Si, X., Du, D., Pang, Z., and Wang, X. (2020), A prognostic model based on DBN and diffusion process for degrading bearing, IEEE Transactions on Industrial Electronics, 67(10), 8767-8777.
[22] Cheng, H., Kong, X., Chen, G., Wang, Q., and Wang, R. (2020), Transferable convolutional neural network based remaining useful life prediction of bearing under multiple failure behaviors, Measurement, 168, 108286.
[23] Zhao, C., Huang, X., Li, Y., and Yousaf Iqbal, M. (2020), A double-channel hybrid deep neural network based on CNN and Bi-LSTM for remaining useful life prediction, Sensors, 20, 7109.
[24] Zhu, X., Zhang, P., and Xie, M. (2020), A joint long short-term memory and Adaboost regression approach with application to remaining useful life estimation, Measurement, 170, 108707.
[25] Biggio, L., Wieland, A., Chao, M.A., Kastanis, I., and Fink, O. (2021), Uncertainty-aware remaining useful life predictor. arXiv, arXiv:2104.03613.
[26] Li, G., Yang, L., Lee, C.G., Wang, X., and Rong, M. (2020), A Bayesian deep learning rul framework integrating epistemic and aleatoric uncertainties, IEEE Transactions on Industrial Electronics, 68(9), 8829-8841.
[27] Eknath, K.G. and Diwakar, G. (2022), Prediction of remaining useful life of rolling bearing using hybrid DCNN-BiGRU model, Journal of Vibration Engineering and Technologies, 11(3), 997-1010.
[28] Schimmack, M., Nguyen, S., and Mercorelli, P. (2016), Anatomy of Haar wavelet filter and its implementation for signal processing, IFAC-PapersOnLine, 49(6), 99-104.
[29] Yang, J., Peng, Y., Xie, J., and Wang, P. (2022), Remaining useful life prediction method for bearings based on LSTM with uncertainty quantification, Sensors, 22(12), 4549.
[30] Qiu, H., Lee, J., Lin, J., and Yu, G. (2006), Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics, Journal of Sound and Vibration, 289(4-5), 1066-1090.
Article Metrics
Usage tracking begins September 1, 2026.