研究生: |
Zemenu Endalamaw Amogne Zemenu Endalamaw Amogne |
---|---|
論文名稱: |
線上和遷移學習的深度學習模型預測鋰離子電池的剩餘使用壽命 Online and Transfer Learning Based Deep Learning Models for Remaining Useful Life Prediction of Li-ion Batteries |
指導教授: |
王福琨
Fu-Kwun Wang |
口試委員: |
林則孟
J.-T Lin 徐世輝 S.-H Sheu 林義貴 Y.-K Lin 葉瑞徽 R.-H Yeh 王孔政 K.-J Wang 王福琨 Fu-K Wang |
學位類別: |
博士 Doctor |
系所名稱: |
管理學院 - 工業管理系 Department of Industrial Management |
論文出版年: | 2023 |
畢業學年度: | 111 |
語文別: | 英文 |
論文頁數: | 93 |
中文關鍵詞: | 剩餘使用壽命 、健康狀況 、電池管理系統 、遷移學習 、帶有註意力的 BiLSTM 、滑動窗 |
外文關鍵詞: | Remaining useful life, State of health, Battery management system, Transfer learning, BiLSTM with attention, Sliding window |
相關次數: | 點閱:423 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
鋰離子 (Li-ion) 電池是生物醫學、汽車和電子應用的理想能源,因為與市場上的其他電池相比,它具有更小的尺寸、更低的自放電率、更高的能量和功率密度。 許多工業中的應用都使用鋰離子電池,但缺乏維護、惡劣的使用環境和不良的充電操作加速了它們的退化。 因此,即時線上剩餘使用壽命(RUL)預測是一個熱門的研究課題。 本論文整合了兩項使用標準化後的電池容量作為離子電池健康狀態 (SOH) 剩餘壽命預測研究。 使用滑動窗口方法的多步超前預測用於獲得SOH估計。 第一項研究使用六個圓柱形和棱柱形鋰離子 (Li-ion) 電池來評估所提出模型的性能。 使用所提出的即時在線 RUL 預測模型,六種鋰離子電池的相對誤差分別為 0.57%、0.54%、0.56%、0%、1.27% 和 1.41%。 為了評估所提出模型的可靠性,還使用 Monte Carlo dropout 方法提供了 RUL 預測的預測區間。 對於遷移學習方法,總共使用了 6 個電池(3 個作為來源數據集,3 個作為目標數據集)。 通過考慮來源數據集與目標數據集之間差異,使用可轉移性測量來識別來源域和目標域。 四個目標數據集的 RMSE 值分別為 0.0108, 0.0172, 和0.0201。
A lithium-ion (Li-ion) battery is an ideal energy source for biomedical, automotive, and electronics applications because of its smaller size, lower self-discharge rate, higher energy, and power density than other available batteries in the market. Many industrial applications use lithium-ion batteries, but lack of maintenance, harsh use environments, and poor charging operations accelerate their degradation. Therefore, online remaining useful lifetime (RUL) prediction is a hot research topic. This dissertation integrates two studies that use normalized capacity as a state of health (SOH) for RUL prediction of Lithium-ion batteries. Multi-step ahead prediction using a sliding window method is used to obtain the SOH estimates. The first study uses six cylindrical and prismatic lithium-ion (Li-ion) batteries to evaluate the proposed model's performance. Using the proposed online RUL prediction model, the relative errors for the six Li-ion batteries are 0.57%, 0.54%, 0.56%, 0%, 1.27 %, and 1.41 %, respectively. To evaluate the reliability of the proposed model, the prediction interval for the RUL prediction is also provided using the Monte Carlo dropout approach. For the transfer learning approach, a total of six batteries ( three as a source dataset and three as a target dataset) are used. The source domain and target domain are identified using transferability measurement by considering the cell-to-cell difference of the dataset. The RMSE values for the SOH prediction of three target datasets are 0.0108, 0.0172, and 0.0201.
References
[1] R.Irle. Global EV Sales for 2022 H1, https://www.ev-volumes.com/; 2022 [ accessed 06 January 2023].
[2] U.S Department of Energy. Batteries for hybrid and plug-in electric vehicles, https://afdc.energy.gov/vehicles/electric_batteries.html/;2021. [accessed 19 Augest, 2022].
[3] Wu J, Zhang C, Chen Z. An online method for lithium-ion battery remaining useful life estimation using importance sampling and neural networks. Appl Energy 2016;173:134-40. https://doi.org/10.1016/j.apenergy.2016.04.057.
[4] Ali M, Zafar A, Nengroo SH, Hussain S, Park GS, Kim HJ. Online remaining useful life prediction for lithium-ion batteries using partial discharge data features. Energies 2019;12:4366. https://doi.org/10.3390/en12224366.
[5] Chen L, Wang H, Chen J, An J, Ji B, Lyu Z, Cao W, Pan H. A novel remaining useful life prediction framework for lithium‐ion battery using grey model and particle filtering. Int J Energy Res 2020;44:7435-49. https://doi.org/10.1002/er.5464.
[6] Ge MF, Liu Y, Jiang X, Liu J. A review on state of health estimations and remaining useful life prognostics of lithium-ion batteries. Measurement. 2021;174:109057. https://doi.org/10.1016/j.measurement.2021.109057.
[7] Hasib SA, Islam S, Chakrabortty RK, et al. A comprehensive review of available battery datasets, RUL prediction approaches, and advanced battery management. IEEE Access 2021;9:86166–93. https://doi.org/10.1109/ACCESS.2021.3089032.
[8] Kim S, Choi YY, Kim KJ, Choi JI. Forecasting state-of-health of lithium-ion batteries using variational long short-term memory with transfer learning. J Energy Storage 2021;41:102893. https://doi.org/10.1016/j.est.2021.102893.
[9] Guo Y, Shi H, Kumar A, Grauman K, Rosing T, Feris R. SpotTune: Transfer Learning through Adaptive Fine-tuning, https://doi.org/10.48550/arXiv.1811.08737/; 2018 [accessed 19 Augest 2022].
[10] Neyshabur B, Sedghi H, Zhang C. What is being transferred in transfer learning?, https://doi.org/10.48550/arXiv.2008.11687/;2020 [accessed 19 Augest 2022].
[11] Pan S J, Yang Q. A Survey on Transfer Learning. IEEE Trans. Knowl. Data Eng. 2010;22:1345–59. https://doi.org/10.1109/TKDE.2009.191.
[12] Tan C, Sun F, Kong T, Zhang W, Yang C, Liu C. A Survey on Deep Transfer Learning, https://doi.org/10.48550/arXiv.1808.01974/;2018 [accessed 19 Augest 2022].
[13] Weiss K, Khoshgoftaar TM, Wang D, A survey of transfer learning. J. Big Data 2016;3:9. https://doi.org/10.1186/s40537-016-0043-6.
[14] Zhuang F, Qi Z, Duan K, Xi D, Zhu Y, Zhu H et al. A Comprehensive Survey on Transfer Learning. Proc. IEEE 2021;109:43–76. https://doi.org/10.1109/JPROC.2020.3004555.
[15] Li Y, Li K. Liu X, Wang Y, Zhang L. Lithium-ion battery capacity estimation — A pruned convolutional neural network approach assisted with transfer learning. Appl. Energy 2021;285. https://doi.org/10.1016/j.apenergy.2020.116410.
[16] Wang S, Jin S, Deng D, Fernandez C. A critical review of online battery remaining useful lifetime prediction methods. Front Mech Eng 2021;7:719718. https://doi.org/10.3389/fmech.2021.719718.
[17] Lin X, Tang Y, Ren J, Wei Y. State of charge estimation with the adaptive unscented Kalman filter based on an accurate equivalent circuit model. J Energy Storage 2021;41:102840. https://doi.org/10.1016/j.est.2021.102840.
[18] Wu M, Qin L, Wu G, Huang Y, Shi C. State of charge estimation of power lithium-ion battery based on a variable forgetting factor adaptive Kalman filter. J Energy Storage 2021; 41:102841. https://doi.org/10.1016/j.est.2021.102841.
[19] Guha A, Patra A. Online estimation of the electrochemical impedance spectrum and remaining useful life of lithium-ion batteries. IEEE Trans Instrum Meas 2018;67:1836-49. https://doi.org/10.1109/TIM.2018.2809138.
[20] Dong H, Jin X, Lou Y, Wang C. Lithium-ion battery state of health monitoring and remaining useful life prediction based on support vector regression-particle filter. J. Power Sources 2014;271:114-23. https://doi.org/10.1016/j.jpowsour.2014.07.176.
[21] Peng W, Ye ZS, Chen N. Joint online RUL prediction for multivariate deteriorating systems. IEEE Trans Ind Inform 2019;15:2870-78. https://doi.org/10.1109/TII.2018.2869429.
[22] Zhang S, Zhai B, Guo X, Wang K, Peng N, Zhang X. Synchronous estimation of state of health and remaining useful lifetime for lithium-ion battery using the incremental capacity and artificial neural networks. J Energy Storage 2019;26:100951. https://doi.org/10.1016/j.est.2019.100951.
[23] Li X, Shu X, Shen J, Xiao R, Yan W, Chen Z. An on-board remaining useful life estimation algorithm for lithium-ion batteries of electric vehicles. Energies 2017;10:691. https://doi.org/10.3390/en10050691.
[24] Tao T, Zio E, Zhao W. A novel support vector regression method for online reliability prediction under multi-state varying operating conditions. Reliab Eng Syst Saf 2018;177:35-49. https://doi.org/10.1016/j.ress.2018.04.027.
[25] Zhao Q, Qin X, Zhao H, Feng W. A novel prediction method based on the support vector regression for the remaining useful life of lithium-ion batteries. Microelectron Reliab 2018;85:99-108. https://doi.org/10.1016/j.microrel.2018.04.007.
[26] Tan X, Zhan D, Lyu P, Rao J, Fan Y. Online state-of-health estimation of lithium-ion battery based on dynamic parameter identification at multi timescale and support vector regression. J Power Sources 2021;484:229233. https://doi.org/10.1016/j.jpowsour.2020.229233.
[27] Liu Y, Zhao G, Peng X. Deep learning prognostics for lithium-ion battery based on ensembled long short-term memory networks. IEEE Access 2019;7:155130-42. https://doi.org/10.1109/ACCESS.2019.2937798.
[28] Fan Y, Xiao F, Li C, Yang G, Tang X. A novel deep learning framework for state of health estimation of lithium-ion battery. J Energy Storage 2020;32:101741. https://doi.org/10.1016/j.est.2020.101741.
[29] Lyu Z, Wang G, Gao R. Li-ion battery prognostic and health management through an indirect hybrid model. J. Energy Storage 2021;42:102990. https://doi.org/10.1016/j.est.2021.102990.
[30] Ungurean L, Micea MV, Cârstoiu G. Online state of health prediction method for lithium‐ion batteries, based on gated recurrent unit neural networks. Int J Energy Res 2020;44:6767-77. https://doi.org/10.1002/er.5413.
[31] Li Y, Li K, Liu X, Wang Y, Zhang L. Lithium-ion battery capacity estimation - a pruned convolutional neural network approach assisted with transfer learning. Appl Energy 2021;285:116410. https://doi.org/10.1016/j.apenergy.2020.116410.
[32] Fan L, Wang P, Cheng Z. A remaining capacity estimation approach of lithium-ion batteries based on partial charging curve and health feature fusion. J Energy Storage 2021;43:103115. https://doi.org/10.1016/j.est.2021.103115.
[33] Hosen MS, Youssef R, Kalogiannis T, Van Mierlo J, Berecibar M. Battery cycle life study through relaxation and forecasting the lifetime via machine learning. J Energy Storage 2021;40:102726. https://doi.org/10.1016/j.est.2021.102726.
[34] Pan W, Luo X, Zhu M, Ye J, Gong L, Qu H. A health indicator extraction and optimization for capacity estimation of Li-ion battery using incremental capacity curves. J Energy Storage 2021;42:103072. https://doi.org/10.1016/j.est.2021.103072.
[35] Xu X, Yu C, Tang S, Sun X, Si X, Wu L. Remaining useful life prediction of lithium- ion batteries based on Wiener processes with considering the relaxation effect. Energies 2019;12:1685. https://doi.org/10.3390/en12091685.
[36] Shen D, Wu L, Kang G, Guan Y, Peng Z. A novel online method for predicting the remaining useful life of lithium-ion batteries considering random variable discharge current. Energy. 2021;218:119490. https://doi.org/10.1016/j.energy.2020.119490.
[37] Jia, J, Liang J, Shi Y, Wen J, Pang X, Zeng J. SOH and RUL Prediction of lithium-ion batteries based on Gaussian process regression with indirect health indicators. Energies 2020:13:375. https://doi.org/10.3390/en13020375.
[38] Wu Y, Li W, Wang Y, Zhang K. Remaining useful life prediction of lithium-ion batteries using neural network and bat-based particle filter. IEEE Access 2019;7:54843-54. https://doi.org/10.1109/ACCESS.2019.2913163.
[39] Li X, Zhang L, Wang Z, Dong P. Remaining useful life prediction for lithium-ion batteries based on a hybrid model combining the long short-term memory and Elman neural networks. J Energy Storage 2019;21:510-18. https://doi.org/10.1016/j.est.2018.12.011.
[40] Gou B, Xu Y, Feng X. State-of-health estimation and remaining-useful-life prediction for lithium- ion battery using a hybrid data-driven method. IEEE Trans Veh Technol 2020;69:10854-67. https://doi.org/10.1109/TVT.2020.3014932.
[41] Che Y , Deng Z, Lin X, Hu L, Hu X. Predictive battery health management with transfer learning and online model correction. IEEE Trans. Veh. Technol 2021;70: 1269-77.https://doi.org/10.1109/TVT.2021.3055811.
[42] Chehade AA, Hussein AA. A collaborative Gaussian process regression model for transfer learning of capacity trends between li-ion battery cells. IEEE Trans. Veh. Technol. 2020;69: 9542-52. https://doi.org/10.1109/TVT.2020.3000970.
[43] Chehade AA, Hussein AA. A Multioutput convolved Gaussian process for capacity forecasting of li-ion battery cells. IEEE Trans. Power Electron 2022;37: 896-909. https://doi.org/10.1109/TPEL.2021.3096164.
[44] El-Dalahmeh M, Al-Greer M, El-Dalahmeh M, Short M. Time-frequency image analysis and transfer learning for capacity prediction of lithium-ion batteries. Energies 2020;13(20): 5447. https://doi.org/10.3390/en13205447.
[45] Li Y, Tao J. CNN and transfer learning based online SOH estimation for lithium-ion battery. Chinese Control And Decision Conference (CCDC) 2020: 5489-5494. https://doi.org/10.1109/CCDC49329.2020.9164208.
[46] Shen S, Sadoughi M, Hu C. Online estimation of lithium-ion battery capacity using transfer learning. IEEE Transportation Electrification Conference and Expo (ITEC) 2019;1-4. https://doi.org/10.1109/ITEC.2019.8790606.
[47] Shen S, Sadoughi M, Li M, Wang Z, Hu C. “Deep convolutional neural networks with ensemble learning and transfer learning for capacity estimation of lithium-ion batteries. Appl. Energy 2020; 260: 114296. https://doi.org/10.1016/j.apenergy.2019.114296.
[48] Jia B, Guan Y, Wu L. A state of health estimation framework for lithium-ion batteries using transfer components analysis. Energies 2019;12(13): 2524. https://doi.org/10.3390/en12132524.
[49] Kim S, Choi YY, Kim KJ, Choi J-I. “Forecasting state-of-health of lithium-ion batteries using variational long short-term memory with transfer learning. J. Energy Storage 202;41: 102893.https://doi.org/10.1016/j.est.2021.102893.
[50] Ye Z, Yu J. State-of-health estimation for lithium-ion batteries using domain adversarial transfer learning. IEEE Trans. Power Electron 2021;37:3528-43. https://doi.org/10.1109/TPEL.2021.3117788.
[51] Ye Z, Yu J, Mao L. Multisource domain adaption for health degradation monitoring of lithium-ion batteries. IEEE Trans. Transp. Electrif. 2021;7: 2279-92. https://doi.org/10.1109/TTE.2021.3085430.
[52] Qin Y, Adams S, Yuen C. Transfer learning-based state of charge estimation for lithium-ion battery at varying ambient temperatures. IEEE Trans. Ind. Informatics 2021;17: 7304-15. https://doi.org/10.1109/TII.2021.3051048.
[53] Kong J, Yang F, Zhang X, Pan E, Peng Z, Wang D. Voltage-temperature health feature extraction to improve prognostics and health management of lithium-ion batteries. Energy 2021;223: 120114. https://doi.org/ 10.1016/j.energy.2021.120114.
[54] Tan Y, Zhao G. Transfer learning with long short-term memory network for state-of-health prediction of lithium-ion batteries. IEEE Trans. Ind. Electron. 2020;67: 8723-31. https://doi.org/10.1109/TIE.2019.2946551.
[55] Wang C, Lu N, Wang S, Cheng Y, Jiang B. Dynamic long short-term memory neural-network- based indirect remaining-useful-life prognosis for satellite lithium-ion battery. Appl. Sci.2018;8(11):2078. https://doi.org/ 10.3390/app8112078.
[56] Che Y, Deng Z, Lin X, Hu L, Hu X. Predictive battery health management with transfer learning and online model correction. IEEE Trans. Veh. Technol.202;70: 1269-77. https://doi.org/10.1109/TVT.2021.3055811.
[57] Liu Y, Shu X, Yu H, Shen J, Zhang Y, Liu Y, Chen Z. State of charge prediction framework for lithium-ion batteries incorporating long short-term memory network and transfer learning. J. Energy Storage. 2021;37: 102494 https://doi.org/10.1016/j.est.2021.102494.
[58] Chen Z, Chen L, Shen W, Xu K. Remaining useful life prediction of lithium-ion battery via a sequence decomposition and deep learning integrated approach. IEEE Trans. Veh. Technol. 2022;71:1466–79. https://doi.org/ 10.1109/TVT.2021.3134312.
[59] Diao W, Saxena S, Han B, Pecht M. Algorithm to determine the knee point on capacity fade curves of lithium-ion cells. Energies 2019;12:2910. https://doi.org/ 10.3390/en12152910.
[60] Diao W, Saxena S, Pecht M.Accelerated cycle life testing and capacity degradation modeling of LiCoO2-graphite cells. J. Power Sources 2019; 435: 226830. https://doi.org/10.1016/j.jpowsour.2019.226830.
[61] Zhang C, Wang Y, Gao Y, Wang F, Mu B, Zhang W. Accelerated fading recognition for lithium-ion batteries with Nickel-Cobalt-Manganese cathode using quantile regression method. Appl. Energy 2019;256:113841. https://doi.org/10.1016/j.apenergy.2019.113841.
[62] Fermín-Cueto P, McTurk E, Allerhand M, Medina-Lopez E, F.Anjos M, Sylvester J, et al. Identification and machine learning prediction of knee-point and knee-onset in capacity degradation curves of lithium-ion cells. Energy AI 2020;1:100006. https://doi.org/10.1016/j.egyai.2020.100006.
[63] Bacon WD, Watts GD. Estimating the transition between two intersecting straight lines. Biometrika 1971;58:525–34. https://doi.org/10.1093/biomet/58.3.525.
[64] Strange C, Li S, Gilchrist R, dosReis G. Elbows of Internal Resistance Rise Curves in Li-Ion Cells. Energies 2021;14:1206. https://doi.org/10.3390/en14041206.
[65] Greenbank S, Howey D. Automated feature extraction and selection for data-driven models of rapid battery capacity fade and end of life. IEEE Trans. Ind. Informatics 2022;18:2965–73. https://doi.org/10.1109/TII.2021.3106593.
[66] Harris SJ, Harris DJ, Li C. Failure statistics for commercial lithium ion batteries: A study of 24 pouch cells. J. Power Sources 2017;342:589–97. https://doi.org/10.1016/j.jpowsour.2016.12.083.
[67] Li W, Sengupta N, Dechent P, Howey D, Annaswamy A. Sauer DU. One-shot battery degradation trajectory prediction with deep learning. J. Power Sources 2021;506:230024 https://doi.org/10.1016/j.jpowsour.2021.230024.
[68] Satopaa V. Albrecht J. Irwin D. Raghavan B. Finding a ‘Kneedle’ in a Haystack: detecting knee points in system behavior. in 2011 31st international conference on distributed computing systems workshops 2011:166–171. https://doi.org/ 10.1109/ICDCSW.2011.20.
[69] Liu Y, Liu Z, Zuo H, Jiang H, Li P, Li X. A DLSTM-network-based approach for mechanical remaining useful life prediction. Sensors 2022;22:5680. https://doi.org/doi: 10.3390/s22155680.
[70] Ma J, Shang P, Zou X, Ma N, Ding Y, Sun Y, et al. A hybrid transfer learning scheme for remaining useful life prediction and cycle life test optimization of different formulation Li-ion power batteries. Appl. Energy 2020;282:116167 https://doi.org/10.1016/j.apenergy.2020.116167.
[71] Severson KA, Attia PM, Jin N, Jin N, Perkins N, Jiang B, Yang Z, et al. Data-driven prediction of battery cycle life before capacity degradation. Nat Energy 2019;4:383–91. https://doi.org/10.1038/s41560-019-0356-8.
[72] Ma J, Shang P, Zou X, Ma N, Ding Y, Sun Y, et al. A hybrid transfer learning scheme for remaining useful life prediction and cycle life test optimization of different formulation Li-ion power batteries. Appl. Energy 2020;282:116167 https://doi.org/10.1016/j.apenergy.2020.116167.
[73] Karunasingha DSK. Root mean square error or mean absolute error? Use their ratio as well. Inf. Sci. (Ny). 2022;585:609–29. https://doi.org/10.1016/j.ins.2021.11.036.
[74] Feng H, Song D. A health indicator extraction based on surface temperature for lithium-ion batteries remaining useful life prediction. J. Energy Storage 2021;34:102118. https://doi.org/10.1016/j.est.2020.102118.
[75] Wei M, Ye M, Wang Q, Xu X, Twajamahoro JP. Remaining useful life prediction of lithium-ion batteries based on stacked autoencoder and gaussian mixture regression. J. Energy Storage 2022.47:103558. https://doi.org/10.1016/j.est.2021.103558.
[76] Pang X, Liu X, Jia J, Wen J, Shi Y, Zeng J, Zhao Z. A lithium-ion battery remaining useful life prediction method based on the incremental capacity analysis and Gaussian process regression. Microelectron. Reliab. 2021;127:114405. https://doi.org/10.1016/j.microrel.2021.114405.
[77] Taylor ME, Stone P. Transfer learning for reinforcement learning domains: A survey. In: The Journal of Machine Learning Research; 2009,p.1633–1685. https://dl.acm.org/doi/10.5555/1577069.1755839
[78] Yosinski J, Clune J, Bengio Y, Lipson H. How transferable are features in deep neural networks?, https://doi.org/10.48550/arXiv.1411.1792/; 2014 [accessed 15 October 2022].