剩餘使用壽命之預測，對於重要機械零件的故障預測與健康管理，是很重要的環節，若能準確且即時地的預測，將有助於提早安排適當的維修或更換零件，以提高設備運行的可靠性和操作安全性。近年來由於資訊技術的大幅度進步，造就機器學習的興起，以數據驅動的剩餘使用壽命預測方法受到研究者的重視。機器學習被廣泛應用於許多跨領域科學研究中，然而複雜的神經網路難以從外部去了解其中的原理，為了讓深度學習有更好的表現，許多學者們從許多方面著手試圖改善模型的效果，其中特徵萃取和組合學習模型是常見的兩種改善方法。本研究提出一個混合型集成模型來預測剩餘使用壽命，首先根據資料集的特性進行資料處理，再導入Stacking 集成學習的概念，利用深度學習進行特徵萃取，並混合Bagging 或Boosting 學習，進行預測模型的訓練，以提升預測的準確率。實驗中針對多種不同的學習模型進行實驗，並比較分析預測的結果。

Remaining useful life prediction of important mechanical parts is an important part of Prognostics and Health Management. Being able to make accurate predictions will help to schedule repairs or replace parts in advance, as well as improving the reliability and safety of equipment operation. With the rapid progress of information technology in recent years, machine learning and deep learning have emerged as the times require. Deep learning is widely used in many cross-disciplinary scientific researches. However, it is difficult for complex neural networks to understand the principles from the outside. In order to make deep learning have a better performance, many scholars have tried to improve the effect of the model from many aspects, among which feature extraction and combinatorial learning models are two common improvement methods. This study proposes a hybrid ensemble model to predict remaining useful life. Firstly, data preprocessing is carried out according to the characteristics of the data set. Second, import the concept of Stacking learning, use deep learning for feature extraction, which is then mixed Bagging or Boosting learning to train the prediction model to improve the accuracy of prediction. In the experiment, different learning models are tested and the prediction results are compared and analyzed.

[1] M. S. R. Mohd Saufi and K. A. Hassan, “Remaining useful life prediction using an integrated laplacian-lstm network on machinery components,” Applied Soft Computing, vol. 112, p. 107817, 2021.
[2] G. Ahn, H. Yun, S. Hur, and S. Lim, “A time-series data generation method to predict remaining useful life,” Processes, vol. 9, no. 7, 2021.
[3] X.-S. Si, W. Wang, C.-H. Hu, and D.-H. Zhou, “Remaining useful life estimation - A review on the statistical data driven approaches,” European Journal of Operational Research, vol. 213, no. 1, pp. 1–14, Aug. 2011.
[4] C. W. Hong, C. Lee, K. Lee, M.-S. Ko, D. E. Kim, and K. Hur, “Remaining useful life prognosis for turbofan engine using explainable deep neural networks with dimensionality reduction,” Sensors, vol. 20, no. 22, 2020.
[5] S. Zheng, K. Ristovski, A. Farahat, and C. Gupta, “Long short-term memory network for remaining useful life estimation,” in 2017 IEEE International Conference on Prognostics and Health Management (ICPHM), 2017, pp. 88–95.
[6] L. Ren, Y. Liu, X. Wang, J. Lü, and M. J. Deen, “Cloud–edge-based lightweight temporal convolutional networks for remaining useful life prediction in iiot,” IEEE Internet of Things Journal, vol. 8, no. 16, pp. 12 578–12 587, 2021.
[7] A. Muneer, S. M. Taib, S. Naseer, R. F. Ali, and I. A. Aziz, “Data-driven deep learning based attention mechanism for remaining useful life prediction: Case study application to turbofan engine analysis,” Electronics, vol. 10, no. 20, 2021.
[8] Y. Tian, M. A. Chao, C. Kulkarni, K. Goebel, and O. Fink, “Real-time model calibration with deep reinforcement learning,” Mechanical Systems and Signal Processing, vol. 165, p. 108284, 2022.
[9] A. Saxena, K. Goebel, D. Simon, and N. Eklund, “Damage propagation modeling for aircraft engine run-to-failure simulation,” in 2008 International Conference on Prognostics and Health Management, 2008, pp. 1–9.
[10] D. Wang, K.-L. Tsui, and Q. Miao, “Prognostics and health management: A review of vibration based bearing and gear health indicators,” IEEE Access, vol. 6, pp. 665–676, 2018.
[11] R. Zhao, R. Yan, Z. Chen, K. Mao, P. Wang, and R. X. Gao, “Deep learning and its applications to machine health monitoring,” Mechanical Systems and Signal Processing, vol. 115, pp. 213–237, 2019.
[12] A. Mosallam, K. Medjaher, and N. Zerhouni, “Data-driven prognostic method based on bayesian approaches for direct remaining useful life prediction,” Journal of Intelligent Manufacturing, vol. 27, pp. 1037–1048, 2016.
[13] Y. Fan, S. Nowaczyk, and T. Rögnvaldsson, “Transfer learning for remaining useful life prediction based on consensus self-organizing models,” Reliability Engineering & System Safety, vol. 203, p. 107098, 2020.
[14] Z. Zhao, Bin Liang, X. Wang, and W. Lu, “Remaining useful life prediction of aircraft engine based on degradation pattern learning,” Reliability Engineering & System Safety, vol. 164, pp. 74–83, 2017.
[15] C. Ordóñez, F. Sánchez Lasheras, J. Roca-Pardiñas, and F. J. de Cos Juez, “A hybrid arima–svm model for the study of the remaining useful life of aircraft engines,” Journal of Computational and Applied Mathematics, vol. 346, pp. 184–191, 2019.
[16] H. Cai, J. Feng, W. Li, Y.-M. Hsu, and J. Lee, “Similarity-based particle filter for remaining useful life prediction with enhanced performance,” Applied Soft Computing, vol. 94, p. 106474, 2020.
[17] A. Listou Ellefsen, E. Bjørlykhaug, V. Æsøy, S. Ushakov, and H. Zhang, “Remaining useful life predictions for turbofan engine degradation using semi-supervised deep architecture,” Reliability Engineering & System Safety, vol. 183, pp. 240–251, 2019.
[18] Y. Wu, M. Yuan, S. Dong, L. Lin, and Y. Liu, “Remaining useful life estimation of engineered systems using vanilla lstm neural networks,” Neurocomputing, vol. 275, pp. 167–179, 2018.
[19] J. Wu, K. Hu, Y. Cheng, H. Zhu, X. Shao, and Y. Wang, “Data-driven remaining useful life prediction via multiple sensor signals and deep long short-term memory neural network,” ISA Transactions, vol. 97, pp. 241–250, 2020.
[20] Y.-W. Lu, C.-Y. Hsu, and K.-C. Huang, “An autoencoder gated recurrent unit for remaining useful life prediction,” Processes, vol. 8, no. 9, 2020.
[21] X. Li, Q. Ding, and J.-Q. Sun, “Remaining useful life estimation in prognostics using deep convolution neural networks,” Reliability Engineering & System Safety, vol. 172, pp. 1–11, 2018.
[22] G. Babu, P. Zhao, and X. Li, “Deep convolutional neural network based regression approach for estimation of remaining useful life,” in Database Systems for Advanced Applications. Springer International Publishing, Mar. 2016, pp. 214–228.
[23] X. Li, “Fault diagnosis and prediction of rolling bearings based on deep learning,” IOP Conference Series: Earth and Environmental Science, vol. 769, no. 3, p. 032051, May 2021.
[24] C. Peng, Z. Tang, W. Gui, Q. Chen, and J. He, “A bidirectional weighted boundary distance algorithm for time series similarity computation based on optimized sliding window size,” Journal of Industrial and Management Optimization, vol. 17, no. 1, pp. 205–220, 2021.
[25] C. Peng, Z. Tang, W. Gui, Q. Chen, L. Zhang, X. Yuan, and X. Deng, “Review of key technologies and progress in industrial equipment health management,” IEEE Access, vol. 8, pp. 151 764–151 776, 2020.
[26] L. Wen, X. Li, L. Gao, and Y. Zhang, “A new convolutional neural network-based datadriven fault diagnosis method,” IEEE Transactions on Industrial Electronics, vol. 65, no. 7, pp. 5990–5998, 2018.
[27] J. Li, X. Li, and D. He, “A directed acyclic graph network combined with cnn and lstm for remaining useful life prediction,” IEEE Access, vol. 7, pp. 75 464–75 475, 2019.
[28] K. T. Chui, B. B. Gupta, and P. Vasant, “A genetic algorithm optimized rnn-lstm model for remaining useful life prediction of turbofan engine,” Electronics, vol. 10, no. 3, 2021.
[29] F. Amato, N. Mazzocca, F. Moscato, and E. Vivenzio, “Multilayer perceptron: An intelligent model for classification and intrusion detection,” in 2017 31st International Conference on Advanced Information Networking and Applications Workshops (WAINA), 2017, pp. 686–691.
[30] C. Nwankpa, W. L. Ijomah, A. Gachagan, and S. Marshall, “Activation functions: Comparison of trends in practice and research for deep learning,” ArXiv, vol. abs/1811.03378, 2018.
[31] E. Chemali, P. J. Kollmeyer, M. Preindl, R. Ahmed, and A. Emadi, “Long short-term memory networks for accurate state-of-charge estimation of li-ion batteries,” IEEE Transactions on Industrial Electronics, vol. 65, no. 8, pp. 6730–6739, 2018.
[32] K. Greff, R. K. Srivastava, J. Koutník, B. R. Steunebrink, and J. Schmidhuber, “Lstm: A search space odyssey,” IEEE Transactions on Neural Networks and Learning Systems, vol. 28, no. 10, pp. 2222–2232, 2017.
[33] S. Bloehdorn and A. Hotho, “Text classification by boosting weak learners based on terms and concepts,” in Fourth IEEE International Conference on Data Mining (ICDM’04), 2004, pp. 331–334.
[34] T. G. Dietterich, “Ensemble methods in machine learning,” in Multiple Classifier Systems. Berlin, Heidelberg: Springer Berlin Heidelberg, 2000, pp. 1–15.
[35] I. Syarif, E. Zaluska, A. Prugel-Bennett, and G. Wills, “Application of bagging, boosting and stacking to intrusion detectiong,” in Machine Learning and Data Mining in Pattern Recognition. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012, pp. 593–602.
[36] B. Efron, “Bootstrap methods: Another look at the jackknife,” The Annals of Statistics,
vol. 7, no. 1, pp. 1 – 26, 1979.
[37] L. Breiman, “Hierarchical symbolic analysis and particle swarm optimization based fault diagnosis model for rotating machineries with deep neural networks,” Machine Learning, vol. 24, p. 123–140, 1996.
[38] C. Sammut and G. I. Webb, Eds., Random Forests. Boston, MA: Springer US, 2010, pp. 828–828.
[39] T. K. Ho, “A data complexity analysis of comparative advantages of decision forest constructors,” Pattern Analysis and Applications, vol. 5, no. 2, pp. 102–112, 2002.
[40] T. Chen and C. Guestrin, “Xgboost: A scalable tree boosting system,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ser. KDD ’16. New York, NY, USA: Association for Computing Machinery, 2016, p. 785–794.
[41] J. Wei, X. Chu, X.-Y. Sun, K. Xu, H.-X. Deng, J. Chen, Z. Wei, and M. Lei, “Machine learning in materials science,” InfoMat, vol. 1, no. 3, pp. 338–358, 2019.
[42] C. Zhang, P. Lim, A. K. Qin, and K. C. Tan, “Multiobjective deep belief networks ensemble for remaining useful life estimation in prognostics,” IEEE Transactions on Neural Networks and Learning Systems, vol. 28, no. 10, pp. 2306–2318, 2017.