PERTANIKA JOURNAL OF SCIENCE AND TECHNOLOGY

Predicting bearing degradation is crucial for precise maintenance. However, accurately predicting the degradation stages of bearings to achieve appropriate maintenance has always been challenging. To address this problem, we propose a network architecture based on automatic label assignment called FAEK and a multi-scale channel-attention classification (MCC) prediction model to predict the degradation stage of bearings at a given time. Our method achieved outstanding performance on the FEMTO dataset with an accuracy of 0.9665. This approach provides an efficient and reliable solution for the predictive maintenance of bearings.

• Aggab, T., Vrignat, P., Avila, M., & Kratz, F. (2022). Remaining useful life estimation based on the joint use of an observer and a hidden Markov model. Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability, 236(5), 676–695. https://doi.org/10.1177/1748006X211044343
  
  Cao, Y., Jia, M., Ding, P., & Ding, Y. (2021). Transfer learning for remaining useful life prediction of multi-conditions bearings based on bidirectional-GRU network. Measurement, 178, Article 109287. https://doi.org/10.1016/j.measurement.2021.109287
  
  Chen, Y., Duan, W., Ding, Z., & Li, Y. (2022). Battery life prediction based on a hybrid support vector regression model. Frontiers in Energy Research, 10, Article 899804.
  
  Cui, L., & Su, Y. (2021). Contact fatigue life prediction of rolling bearing considering machined surface integrity. Industrial Lubrication and Tribology, 74(1), 73–80. https://doi.org/10.1108/ILT-08-2021-0345
  
  Gamanayake, C., Qin, Y., Yuen, C., Jayasinghe, L., Tan, D.-E., & Low, J. (2023). A hybrid deep learning model-based remaining useful life estimation for reed relay with degradation pattern clustering. IEEE Transactions on Industrial Informatics, 19(6), 7401–7413. https://doi.org/10.1109/TII.2022.3210250
  
  Gu, M. Y., Ge, J. Q., & Li, Z. N. (2023). Improved similarity-based residual life prediction method based on grey Markov model. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 45(6), Article 294. https://doi.org/10.1007/s40430-023-04176-z
  
  Hong, S., Zhou, Z., Zio, E., & Wang, W. (2014). An adaptive method for health trend prediction of rotating bearings. Digital Signal Processing, 35, 117–123. https://doi.org/10.1016/j.dsp.2014.08.006
  
  Hu, J., Shen, L., Albanie, S., Sun, G., & Wu, E. (2019). Squeeze-and-Excitation Networks (arXiv:1709.01507). arXiv. https://doi.org/10.48550/arXiv.1709.01507
  
  Juodelyte, D., Cheplygina, V., Graversen, T., & Bonnet, P. (2022). Predicting bearings degradation stages for predictive maintenance in the pharmaceutical industry. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (pp. 3107-3115). ACM Publishing. https://doi.org/10.1145/3534678.3539057
  
  Kou, L., Chu, B., Chen, Y., & Qin, Y. (2022). An automatic partition time-varying markov model for reliability evaluation. Applied Sciences, 12(12), Article 12. https://doi.org/10.3390/app12125933
  
  Li, H. F., Wei, J. L., Li, S. H., Liu, Y. Q., Gu, X. H., Liu, Z. C., & Yang, S. P. (2023). Fatigue life prediction of high-speed train bearings based on the generalized linear cumulative damage theory. Fatigue & Fracture of Engineering Materials & Structures, 46(6), 2112–2120. https://doi.org/10.1111/ffe.13984
  
  Li, X., Zhang, W., & Ding, Q. (2019). Deep learning-based remaining useful life estimation of bearings using multi-scale feature extraction. Reliability Engineering & System Safety, 182, 208–218. https://doi.org/10.1016/j.ress.2018.11.011
  
  Liao, D., Yin, M., Luo, H., Li, J., & Wu, N. (2022). Machine vision system based on a coupled image segmentation algorithm for surface-defect detection of a Si3N4 bearing roller. JOSA A, 39(4), 571–579. https://doi.org/10.1364/JOSAA.449088
  
  Mylonas, C., & Chatzi, E. (2020). Remaining Useful Life Estimation Under Uncertainty with Causal GraphNets (arXiv:2011.11740; Version 1). arXiv. http://arxiv.org/abs/2011.11740
  
  Qiu, S., Cui, X., Ping, Z., Shan, N., Li, Z., Bao, X., & Xu, X. (2023). Deep learning techniques in intelligent fault diagnosis and prognosis for industrial systems: A review. Sensors, 23(3), Article 3. https://doi.org/10.3390/s23031305
  
  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, 71–77. https://doi.org/10.1016/j.jmsy.2018.04.008
  
  Ruan, D., Han, J., Yan, J., & Gühmann, C. (2023). Light convolutional neural network by neural architecture search and model pruning for bearing fault diagnosis and remaining useful life prediction. Scientific Reports, 13(1), Article 1. https://doi.org/10.1038/s41598-023-31532-9
  
  Sanakkayala, D. C., Varadarajan, V., Kumar, N., Karan, Soni, G., Kamat, P., Kumar, S., Patil, S., & Kotecha, K. (2022). Explainable AI for bearing fault prognosis using deep learning techniques. Micromachines, 13(9), Article 9. https://doi.org/10.3390/mi13091471
  
  Sutrisno, E., Oh, H., Vasan, A. S. S., & Pecht, M. (2012). Estimation of remaining useful life of ball bearings using data driven methodologies. In 2012 IEEE Conference on Prognostics and Health Management (pp. 1-7). IEEE Publishing. https://doi.org/10.1109/ICPHM.2012.6299548
  
  Wang, B., Pan, H., & Yang, W. (2017). Robust bearing degradation assessment method based on improved CVA. IET Science, Measurement & Technology, 11(5), 637-645. https://doi.org/10.1049/iet-smt.2016.0391
  
  Wang, C., Jiang, W., Yang, X., & Zhang, S. (2021). RUL prediction of rolling bearings based on a DCAE and CNN. Applied Sciences, 11(23), Article 23. https://doi.org/10.3390/app112311516
  
  Wang, F., Liu, X., Deng, G., Yu, X., Li, H., & Han, Q. (2019). Remaining life prediction method for rolling bearing based on the long short-term memory network. Neural Processing Letters, 50(3), 2437–2454. https://doi.org/10.1007/s11063-019-10016-w
  
  Wang, Y., Deng, L., Zheng, L., & Gao, R. X. (2021). Temporal convolutional network with soft thresholding and attention mechanism for machinery prognostics. Journal of Manufacturing Systems, 60, 512–526. https://doi.org/10.1016/j.jmsy.2021.07.008
  
  Xia, T., & Xi, L. (2019). Manufacturing paradigm-oriented PHM methodologies for cyber-physical systems. Journal of Intelligent Manufacturing, 30(4), 1659–1672. https://doi.org/10.1007/s10845-017-1342-2
  
  Zhang, C., Pan, L., Wang, S., Wang, X., & Tomovic, M. (2018). An accelerated life test model for solid lubricated bearings used in space based on time-varying dependence analysis of different failure modes. Acta Astronautica, 152, 352–359. https://doi.org/10.1016/j.actaastro.2018.08.027
  
  Zhou, Q., Shen, H., Zhao, J., Liu, X., & Xiong, X. (2019). Degradation state recognition of rolling bearing based on K-means and CNN algorithm. Shock and Vibration, 2019, Article e8471732. https://doi.org/10.1155/2019/8471732
  
  Zhu, G., Zhu, Z., Xiang, L., Hu, A., & Xu, Y. (2023). Prediction of bearing remaining useful life based on DACN-ConvLSTM model. Measurement, 211, Article 112600. https://doi.org/10.1016/j.measurement.2023.112600
  
  Zhu, J., Nostrand, T., Spiegel, C., & Morton, B. (2014). Survey of condition indicators for condition monitoring systems. Annual Conference of the PHM Society, 6(1), Article 1. https://doi.org/10.36001/phmconf.2014.v6i1.2514