在工業設備持續朝自動化與智慧化發展的趨勢下，設備健康監測（PHM）與剩餘使
用壽命（RUL）預測已成為提升工廠效率與安全性的重要工具。儘管傳統統計方法與機
器學習模型已被廣泛應用於此類任務，然而在處理高變異性、非線性退化與資料不平衡
問題時，常面臨準確度不足與泛化能力薄弱的挑戰。近年來，深度學習方法雖展現優異
表現，卻普遍仰賴大量完整退化資料，且缺乏明確的解釋性與物理對應性。
本研究針對此問題提出一套創新的資料生成與預測架構 —— WTTELSTMGAN（Wavelet-Temporal-Transformer Enhanced LSTM GAN）。本方法整合小波轉換的時
頻解析特性、雙向 LSTM 的時序記憶能力與多頭注意力機制的特徵聚焦優勢，能有效
模擬機械退化過程中的 RMS 演變趨勢，並補足原始資料不足所造成的學習落差。進一
步應用於結合 Weibull Distribution 與動態閾值之預測模型中，可預測失效點與剩餘壽命，
提升預測系統的實用性與準確性。

In the context of continuous advancements in industry and technology, Prognostics and
Health Management (PHM) and Remaining Useful Life (RUL) prediction have become
essential tools for enhancing operational efficiency and safety. Although traditional statistical
methods and machine learning models have been widely applied to such tasks, they often
struggle with high variability, nonlinear degradation, and imbalanced data, leading to limited
prediction accuracy and weak generalization capabilities. In recent years, deep learning
approaches have shown promising results, yet they typically rely on large amounts of complete
degradation data and often lack interpretability and physical correspondence.
To address these challenges, this study proposes an innovative data generation and
prediction framework—WTTELSTM-GAN (Wavelet-Temporal-Transformer Enhanced LSTM
GAN). The proposed model integrates wavelet transform for time-frequency feature extraction,
bidirectional LSTM for temporal memory modeling, and multi-head attention for enhancing
feature focus. This architecture effectively simulates the degradation trends of RMS sequences
in mechanical systems and compensates for data insufficiency during model training.
Furthermore, the generated data is incorporated into a prediction model that combines Weibull
distribution fitting and dynamic thresholding, enabling accurate prediction of failure points and
remaining useful life, thereby improving the practicality and reliability of the prognostic
system.

1. Ali, J. B., Chebel-Morello, B., Saidi, L., Malinowski, S., & Fnaiech, F. (2015). Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network. Mechanical Systems and Signal Processing, 56–57, 150–172.
2. Bustillo, A., Urbikain, G., Perez, J. M., Pereira, O. M., & de Lacalle, L. N. L. (2018). Smart optimization of a friction-drilling process based on boosting ensembles. Journal of Manufacturing Systems, 48, 108–121.
3. Caesarendra, W., Widodo, A., & Yang, B. S. (2010). Application of relevance vector machine and logistic regression for machine degradation assessment. Mechanical Systems and Signal Processing, 24(4), 1161–1171.
4. Ding, Y., & Jia, M. (2022). Convolutional transformer: An enhanced attention mechanism architecture for remaining useful life estimation of bearings. IEEE Transactions on Instrumentation and Measurement, 71, Article 3515010.
5. Fang, H., Deng, J., Bai, Y., & Feng, B. (2021). CLFormer: A lightweight transformer based on convolutional embedding and linear self-attention with strong robustness for bearing fault diagnosis under limited sample conditions. IEEE Transactions on Instrumentation and Measurement, PP(99), 1–1.
6. Gebraeel, N. Z., Lawley, M. A., Li, R., & Ryan, J. K. (2005). Residual-life distributions from component degradation signals: A Bayesian approach. IIE Transactions, 37(6), 543–557.
7. Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., & Courville, A. (2017). Improved training of Wasserstein GANs. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NeurIPS) (pp. 5767–5777).
8. Han, T., Ding, L., Qi, D., Li, C., Fu, Z., & Chen, W. (2022). Compound faults diagnosis method for wind turbine mainshaft bearing with Teager and second-order stochastic resonance. Measurement, 202, Article 111931.
9. He, Z., Sun, C., & Zhang, Z. (2011). Research on bearing life prediction based on support vector machine and its application. Journal of Physics: Conference Series, 305, Article 012028.
10. Huang, G. B. (2014). An insight into extreme learning machines: Random neurons, random features and kernels. Cognitive Computation, 6(2), 376–390.
11. Kacprzynski, G. J., Sarlashkar, A., Roemer, M. J., Hess, A., & Hardman, B. (2004). Predicting remaining life by fusing the physics of failure modeling with diagnostics. JOM, 56(3), 29–35.
12. Kan, M. S., Tan, A. C. C., & Mathew, J. (2015). A review on prognostic techniques for non-stationary and non-linear rotating systems. Mechanical Systems and Signal Processing, 62–63, 1–20.
13. Li, Y., Billington, S., Zhang, C., Kurfess, T., Danyluk, S., & Liang, S. (1999). Adaptive prognostics for rolling element bearing condition. Mechanical Systems and Signal Processing, 13(1), 103–113.
14. Li, Z., Zheng, T., Wang, Y., Cao, Z., Guo, Z., & Fu, H. (2020). A novel method for imbalanced fault diagnosis of rotating machinery based on generative adversarial networks. IEEE Transactions on Instrumentation and Measurement, 70, Article 3500417.
15. Liao, H., Zhao, W., & Guo, H. (2006, January 23–26). Predicting remaining useful life of an individual unit using proportional hazards model and logistic regression model. In Proceedings of the Reliability and Maintainability Symposium (RAMS’06) (pp. 127–132). IEEE.
16. Liu, F., Liu, Y., Chen, F., & He, B. (2015). Residual life prediction for ball bearings based on joint approximate diagonalization of eigen matrices and extreme learning machine. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 231(8), 1699–1711.
17. Liu, H., Zhao, H., Wang, J., Yuan, S., & Feng, W. (2022). LSTM-GAN-AE: A promising approach for fault diagnosis in machine health monitoring. IEEE Transactions on Instrumentation and Measurement, 71, Article 3503113.
18. Liu, Y., He, B., Liu, F., Lu, S., Zhao, Y., & Zhao, J. (2016). Remaining useful life prediction of rolling bearings using PSR, JADE, and extreme learning machine. Mathematical Problems in Engineering, 2016, Article 8623530.
19. Maio, F. D., Ng, S. S. Y., Tsui, K. L., & Zio, E. (2011). Naive Bayesian classifier for on-line remaining useful life prediction of degrading bearings. https://hal-supelec.archives-ouvertes.fr/hal-00658069/document.
20. Mahamad, A. K., Saon, S., & Hiyama, T. (2010). Predicting remaining useful life of rotating machinery based artificial neural network. Computers & Mathematics with Applications, 60(4), 1078–1087.
21. Oppenheimer, C. H., & Loparo, K. A. (2002). Physically based diagnosis and prognosis of cracked rotor shafts. In Component and systems diagnostics, prognostics, and health management II (Vol. 4733, pp. 122–132). SPIE.
22. Qiu, H., Lee, J., Lin, J., & Yu, G. (2003). Robust performance degradation assessment methods for enhanced rolling element bearing prognostics. Advanced Engineering Informatics, 17(1–2), 127–140.
23. Ratanamahatana, C. A., & Gunopulos, D. (2002). Scaling up the naive Bayesian classifier: Using decision trees for feature selection.
24. 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.
25. Shiroishi, J., Li, Y., Liang, S., Kurfess, T., & Danyluk, S. (1997). Bearing condition diagnostics via vibration and acoustic emission measurements. Mechanical Systems and Signal Processing, 11(5), 693–705.
26. Sikorska, J. Z., Hodkiewicz, M., & Ma, L. (2011). Prognostic modelling options for remaining useful life estimation by industry. Mechanical Systems and Signal Processing, 25(5), 1803–1836.
27. Sun, J., Xu, W., & Zhao, X. (2012). A hybrid algorithm of PSO and SVM for rolling element bearing fault diagnosis. In Proceedings of the 2012 International Conference on System Science and Engineering (ICSSE) (pp. 133–137). IEEE.
28. Soomro, A. A., Muhammad, M. B., Mokhtar, A. A., Md Saad, M. H., Lashari, N., Hussain, M., Sarwar, U., & Palli, A. S. (2024). Insights into modern machine learning approaches for bearing fault classification: A systematic literature review. Research in Engineering, 102700.
29. Wu, Z., Lin, W., Fu, B., Guo, J., Ji, Y., & Pecht, M. (2020). A local adaptive minority selection and oversampling method for class-imbalanced fault diagnostics in industrial systems. IEEE Transactions on Reliability, 69(4), 1195–1206.
30. Zhang, X., Zhu, J., Wu, Y., Zhen, D., & Zhang, M. (2020). Feature extraction for bearing fault detection using wavelet packet energy and fast kurtogram analysis. Applied Sciences, 10(21), 7715.
31. Zhao, X., Jia, M., Bin, J., Wang, T., & Liu, Z. (2021). Multiple-order graphical deep extreme learning machine for unsupervised fault diagnosis of rolling bearing. IEEE Transactions on Instrumentation and Measurement, 70, Article 3506012.
32. Zhao, Z., Zhang, Q., Yu, X., Sun, C., Wang, S., Yan, R., & Chen, X. (2021). Applications of unsupervised deep transfer learning to intelligent fault diagnosis: A survey and comparative study. IEEE Transactions on Instrumentation and Measurement, 70, Article 3525828.