近年來，鋰離子電池的預測性維護問題為熱門的研究項目之一，鋰離子電池可以作為工業設備像是自動搬運車的能源供應，預測性維護在智慧製造應用中扮演相當重要的角色，可對機台或元件提供不同層次的預診斷，對於預測性維護而言有兩種應用型式，如故障檢測和剩餘使用壽命預估，剩餘使用壽命指在機器經過一定時間的運作之後，預估其在無法運作之前所剩餘使用壽命。此研究利用深度學習模型，萃取時間序列資料的特徵並使用資料科學的方法來建立完整的鋰離子電池的預測性維護架構。本篇論文以NASA PCoE所提供鋰離子電池資料集為實驗案例，以所提的方法預估鋰離子電池的電池健康狀態與剩餘使用壽命。此外，本研究進行不同實驗，使用貝葉斯優化方法找出最佳的模型超參數。實驗結果找出了四個可以準確預測鋰離子電池健康狀態的特徵，並將實驗結果與文獻中的其他方法作為比較，驗證本研究的架構與方法可以更準確地預測鋰離子電池的剩餘使用壽命。

In recent years, predictive maintenance of the lithium-ion battery has been one of the popular research projects. Lithium-ion batteries can be used as the energy supply for industrial equipment such as automated guided vehicles (AGV). Predictive maintenance plays a very important role in the application of smart manufacturing. It can provide different levels of pre-diagnosis for the machine or components. There are two types of applications for predictive maintenance, such as fault detection and remaining useful life (RUL) prediction. RUL refers to the estimated useful life remaining before the machine cannot operate after a certain period of operation. This research uses deep learning models to extract the characteristics of time series data and uses data science methods to establish a complete predictive maintenance framework for lithium-ion batteries. This research uses the lithium-ion battery dataset provided by the NASA PCoE as an experimental case and uses the proposed models to estimate the state of health (SOH) and RUL of the lithium-ion battery. In addition, this research conducts different experiments and uses Bayesian optimization to find the best model hyperparameters. The experimental results show four characteristics that can accurately predict the SOH of lithium-ion batteries, and this research compares the experimental results with other methods in the literature to verify that the architecture and methods of this research can more accurately predict the RUL of lithium-ion batteries.

Contents
摘要 I
Abstract II
致謝 III
Contents IV
List of Tables VI
List of Figures VII
Chapter 1 Introduction 1
1.1 Background and Motivation 1
1.2 Research Objective 4
1.3 Research Method 4
1.4 Organization of Thesis 6
Chapter 2 Literature Review 7
2.1 Remaining Useful Life (RUL) Problem 7
2.1.1 Types of RUL Prediction Method 7
2.2 Deep Learning Model for RUL Prediction 9
2.2.1 RNN, LSTM, and GRU Model 9
2.3 Applications of RUL Problem in Lithium-Ion Battery 11
Chapter 3 Data Science Framework 14
3.1 Dataset Description 15
3.2 Problem Definition 18
3.3 Data Preprocessing 18
3.3.1 Feature Extraction 19
3.3.2 Feature Selection 28
3.3.3 Data Normalization 29
3.3.4 Data Segmentation 29
3.4 Prediction Model 31
3.4.1 Model Description 31
3.4.2 Model Parameter Setting 32
3.4.3 SOH Prediction Model (Phase I) 35
3.4.4 RUL Prediction Model (Phase II) 37
3.4.5 Evaluation Metrics 39
3.5 System Configuration 40
Chapter 4 Experimental Results 41
4.1 SOH Prediction Model Results (Phase I) 41
4.1.1 BLSTM Model 44
4.1.2 LSTM Model 45
4.1.3 GRU Model 46
4.1.4 RNN Model 47
4.1.5 Summary 48
4.2 RUL Prediction Model Results (Phase II) 53
4.2.1 BLSTM Model 55
4.2.2 LSTM Model 56
4.2.3 GRU Model 57
4.2.4 RNN Model 58
4.2.5 Summary 59
Chapter 5 Conclusion 68
Reference 70
Appendix 75
Appendix A: Model Loss of Deep Learning Models in Phase I Experiment 75
Appendix B: Model Loss of Deep Learning Models in Phase II Experiment 78
Appendix C: Phase I model results without Bayesian optimization 81
Appendix D: Phase II model results without Bayesian optimization 82
Appendix E: Phase II model results without EMD noise reduction method 83
Appendix F: Figure of Prediction Results in Phase I Experiment 84
Appendix G: Figure of Prediction Results in Phase II Experiment 87

An, D., Kim, N. H., & Choi, J. H. (2015). Practical options for selecting data-driven or physics-based prognostics algorithms with reviews. Reliability Engineering & System Safety, 133, 223-236.
Asmai, S. A., Hussin, B., & Yusof, M. M. (2010, May). A framework of an intelligent maintenance prognosis tool. In 2010 Second International Conference on Computer Research and Development (pp. 241-245). IEEE.
Da Costa, P. R. D. O., Akçay, A., Zhang, Y., & Kaymak, U. (2020). Remaining useful lifetime prediction via deep domain adaptation. Reliability Engineering & System Safety, 195, 106682.
Deutsch, J., & He, D. (2017). Using deep learning-based approach to predict remaining useful life of rotating components. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 48(1), 11-20.
Gugulothu, N., TV, V., Malhotra, P., Vig, L., Agarwal, P., & Shroff, G. (2017). Predicting remaining useful life using time series embeddings based on recurrent neural networks. arXiv preprint arXiv:1709.01073.
Jia, J., Liang, J., Shi, Y., Wen, J., Pang, X., & Zeng, J. (2020). SOH and RUL Prediction of Lithium-Ion Batteries Based on Gaussian Process Regression with Indirect Health Indicators. Energies, 13(2), 375.
Kordestani, M., Saif, M., Orchard, M. E., Razavi-Far, R., & Khorasani, K. (2019). Failure prognosis and applications—A survey of recent literature. IEEE transactions on reliability.
Kraus, M., & Feuerriegel, S. (2019). Forecasting remaining useful life: Interpretable deep learning approach via variational Bayesian inferences. Decision Support Systems, 125, 113100.
Lee, J., Wu, F., Zhao, W., Ghaffari, M., Liao, L., & Siegel, D. (2014). Prognostics and health management design for rotary machinery systems—Reviews, methodology and applications. Mechanical systems and signal processing, 42(1-2), 314-334.
Lei, Y., Li, N., Guo, L., Li, N., Yan, T., & Lin, J. (2018). Machinery health prognostics: A systematic review from data acquisition to RUL prediction. Mechanical Systems and Signal Processing, 104, 799-834.
Lipu, M. H., Hannan, M. A., Hussain, A., Hoque, M. M., Ker, P. J., Saad, M. H. M., & Ayob, A. (2018). A review of state of health and remaining useful life estimation methods for lithium-ion battery in electric vehicles: Challenges and recommendations. Journal of cleaner production, 205, 115-133.
Li, X., Zhang, L., Wang, Z., & Dong, P. (2019). Remaining useful life prediction for lithium-ion batteries based on a hybrid model combining the long short-term memory and Elman neural networks. Journal of Energy Storage, 21, 510-518.
Li, Z. (2018). Deep Learning Driven Approaches for Predictive Maintenance: A Framework of Intelligent Fault Diagnosis and Prognosis in the Industry 4.0 Era.
Liu, K., Shang, Y., Ouyang, Q., & Widanage, W. D. (2020). A Data-driven Approach with Uncertainty Quantification for Predicting Future Capacities and Remaining Useful Life of Lithium-ion Battery. IEEE Transactions on Industrial Electronics.
Nguyen, K. T., & Medjaher, K. (2019). A new dynamic predictive maintenance framework using deep learning for failure prognostics. Reliability Engineering & System Safety, 188, 251-262.
Okoh, C., Roy, R., Mehnen, J., & Redding, L. (2014). Overview of remaining useful life prediction techniques in through-life engineering services. Procedia CIRP, 16, 158-163.
Qu, J., Liu, F., Ma, Y., & Fan, J. (2019). A neural-network-based method for RUL prediction and SOH monitoring of lithium-ion battery. IEEE access, 7, 87178-87191.
Ren, L., Cui, J., Sun, Y., & Cheng, X. (2017). Multi-bearing remaining useful life collaborative prediction: A deep learning approach. Journal of Manufacturing Systems, 43, 248-256.
Ren, L., Zhao, L., Hong, S., Zhao, S., Wang, H., & Zhang, L. (2018). Remaining useful life prediction for lithium-ion battery: A deep learning approach. IEEE Access, 6, 50587-50598.
Ruiz-Sarmiento, J. R., Monroy, J., Moreno, F. A., Galindo, C., Bonelo, J. M., & Gonzalez-Jimenez, J. (2020). A predictive model for the maintenance of industrial machinery in the context of industry 4.0. Engineering Applications of Artificial Intelligence, 87, 103289.
Saha, B & Goebel, K (2007). "Battery Data Set", NASA Ames Prognostics Data Repository (http://ti.arc.nasa.gov/project/prognostic-data-repository), NASA Ames Research Center, Moffett Field, CA
Si, X. S., Wang, W., Hu, C. H., & Zhou, D. H. (2011). Remaining useful life estimation–a review on the statistical data driven approaches. European journal of operational research, 213(1), 1-14.
Si, X. S., Zhang, Z. X., & Hu, C. H. (2017). Data-Driven Remaining Useful Life Prognosis Techniques. Springer Series in Reliability Engineering.
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.
Wang, Y., Ni, Y., Lu, S., Wang, J., & Zhang, X. (2019). Remaining useful life prediction of lithium-ion batteries using support vector regression optimized by artificial bee colony. IEEE Transactions on Vehicular Technology, 68(10), 9543-9553.
Wu, J., Hu, K., Cheng, Y., Zhu, H., Shao, X., & Wang, Y. (2020). Data-driven remaining useful life prediction via multiple sensor signals and deep long short-term memory neural network. ISA transactions, 97, 241-250.
Wu, Y., Yuan, M., Dong, S., Lin, L., & Liu, Y. (2018). Remaining useful life estimation of engineered systems using vanilla LSTM neural networks. Neurocomputing, 275, 167-179.
Xiongzi, C., Jinsong, Y., Diyin, T., & Yingxun, W. (2011, August). Remaining useful life prognostic estimation for aircraft subsystems or components: A review. In IEEE 2011 10th International Conference on Electronic Measurement & Instruments (Vol. 2, pp. 94-98). IEEE.
Yuan, M., Wu, Y., & Lin, L. (2016, October). Fault diagnosis and remaining useful life estimation of aero engine using LSTM neural network. In 2016 IEEE International Conference on Aircraft Utility Systems (AUS) (pp. 135-140). IEEE.
Yu, J. (2018). State of health prediction of lithium-ion batteries: Multiscale logic regression and Gaussian process regression ensemble. Reliability Engineering & System Safety, 174, 82-95.
Yu, Y., Hu, C., Si, X., Zheng, J., & Zhang, J. (2020). Averaged Bi-LSTM networks for RUL prognostics with non-life-cycle labeled dataset. Neurocomputing.
Zeming, L., Jianmin, G., & Hongquan, J. (2019). A maintenance support framework based on dynamic reliability and remaining useful life. Measurement, 147, 106835.
Zenisek, J., Holzinger, F., & Affenzeller, M. (2019). Machine learning based concept drift detection for predictive maintenance. Computers & Industrial Engineering, 137, 106031.
Zhang, J., Wang, P., Yan, R., & Gao, R. X. (2018). Long short-term memory for machine remaining life prediction. Journal of manufacturing systems, 48, 78-86.
Zhang, W., Yang, D., & Wang, H. (2019). Data-Driven Methods for Predictive Maintenance of Industrial Equipment: A Survey. IEEE Systems Journal.
Zhang, Y., Xiong, R., He, H., & Pecht, M. G. (2018). Long short-term memory recurrent neural network for remaining useful life prediction of lithium-ion batteries. IEEE Transactions on Vehicular Technology, 67(7), 5695-5705.
Zheng, S., Ristovski, K., Farahat, A., & Gupta, C. (2017, June). Long short-term memory network for remaining useful life estimation. In 2017 IEEE International Conference on Prognostics and Health Management (ICPHM) (pp. 88-95). IEEE.
Zhou, D., Li, Z., Zhu, J., Zhang, H., & Hou, L. (2020). State of Health Monitoring and Remaining Useful Life Prediction of Lithium-Ion Batteries Based on Temporal Convolutional Network. IEEE Access, 8, 53307-53320.
Zhou, D. P., Hu, Q., & Tomlin, C. J. (2017, May). Quantitative comparison of data-driven and physics-based models for commercial building HVAC systems. In 2017 American Control Conference (ACC) (pp. 2900-2906). IEEE.