簡易檢索 / 詳目顯示

研究生: 羅仁成
Luo, Ren-Cheng
論文名稱: 結合貝葉斯優化與LSTM之延長鋰離子電池壽命充電策略
Charging Strategy for Lithium-Ion Battery Lifetime Extension Using LSTM and Bayesian Optimization
指導教授: 楊宏澤
Yang, Hong-Tzer
學位類別: 碩士
Master
系所名稱: 電機資訊學院 - 電機工程學系
Department of Electrical Engineering
論文出版年: 2026
畢業學年度: 114
語文別: 中文
論文頁數: 84
中文關鍵詞: 早期壽命預測鋰離子電池深度學習循環壽命
外文關鍵詞: Early Life Prediction, Lithium-ion battery, Deep Learning, Cycle Life
相關次數: 點閱:53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
  • 隨著台灣再生能源比例逐漸提升,以及台電電力交易平台與輔助服務機制的推動,儲能系統(ESS)在電力調度中的角色日益重要。另一方面,鋰離子電池因具備高能量密度與良好的循環性能,已廣泛應用於電動車與儲能場域;然而,其回收率仍有限,若能透過更合理的充電策略延長使用週期,將有助於降低電池汰換與資源消耗。因此,本研究嘗試結合貝葉斯優化與 LSTM,建立鋰離子電池充電控制模型,並於低成本嵌入式平台上進行實作與初步驗證,以評估智慧充電策略在實務應用中的可行性及其限制。
    本研究使用專業充放電測試機台,收集不同充電條件下的電壓與電流變化與容量,進行評估鋰電池的壽命。採用RNN-LSTM序列模型,針對電流與電壓等因素進行評估,並透過模型的預測結果,調整電流大小以減少消耗並提升鋰離子電池的循環壽命。
    實驗中透過多次循環測試,觀察每組充電電流對於容量的損失的影響,評估最有效的充電方式,期望能有效延緩電池老化,降低電池報廢的數量,減少對環境的污染並為實現淨零碳排放的目標盡一份力量。

    With the increasing penetration of renewable energy in Taiwan and the development of Taiwan Power Company’s electricity trading platform and ancillary service mechanisms, energy storage systems(ESS) have become increasingly important in power system operation. Meanwhile, lithium-ion batteries are widely used in electric vehicles and energy storage applications due to their high energy density and long cycle life. However, their limited recycling rate highlights the need for strategies that can extend battery lifespan and reduce resource consumption.
    This study combines Bayesian Optimization and Long Short-Term Memory(LSTM) networks to develop a charging control model for lithium-ion batteries. A professional battery cycler was used to collect charging and discharging data under different operating conditions, including voltage, current, and capacity variations. An RNN-LSTM model was then employed to evaluate battery conditions and dynamically adjust charging current based on prediction results.
    Through repeated cycling tests, the effects of different charging currents on capacity degradation were analyzed to identify more effective charging methods. The proposed strategy was implemented on a low-cost embedded platform for preliminary validation. The ultimate goal of this research is to mitigate battery aging, reduce battery waste, decrease environmental impact, and contribute to the achievement of net-zero carbon emissions.

    摘要 I EXTENDED ABSTRACT II 誌謝 VII 目錄 VIII 圖目錄 XII 表目錄 XV 第一章 緒論 1 1.1 研究背景 1 1.2 研究動機及目的 2 1.3 文獻回顧 3 1.3.1 鋰離子電池種類 3 1.3.2 名詞定義 4 1.3.3 循環充放電耗損 7 1.3.4 充電行為 10 1.3.5 電池老化研究[29] 14 1.4 研究方法與目的 14 1.5 論文架構 16 第二章 系統架構與現況 17 2.1 簡介 17 2.2 早期壽命預測 18 2.3 貝葉斯優化 19 2.4 LSTM[37][38] 21 2.5 鋰離子電池需求 23 2.6 鋰離子電池產量 24 2.7 本章結論 25 第三章 鋰離子電池最佳充放電策略 26 3.1 簡介 26 3.1.1 CALCE數據集[43] 27 3.1.2 豐田研究所數據集[44][45] 28 3.1.3 訓練數據集 29 3.2 最佳化流程說明 29 3.2.1 目標函數 30 3.3 最佳化流程架構 32 3.3.1 資料準備 32 3.3.2 資料處理 36 3.3.3 訓練LSTM模組 36 3.3.4 實際作業 39 3.3.5 測試架構 40 3.3.6 測試流程 43 第四章 實驗結果 46 4.1 簡介 46 4.2 早期壽命預測結果 47 4.3 實際充放電結果 49 4.4 當前問題 50 4.4.1 頻繁電流變化 50 4.4.2 未考慮SOC範圍 50 4.4.3 量測數據不足或不正確 51 4.4.4 電流大小影響電壓數據 51 4.5 改善方法 52 4.6 加速驗證對策 54 4.6.1 實驗條件 54 4.7 導入對策後充放電結果 54 4.8 實驗設計彙整 56 4.9 量測誤差與研究限制分析 56 4.9.1 誤差來源分析 56 4.9.2 資料雜訊分析 57 4.9.3 溫度影響 57 4.9.4 硬體限制 57 第五章 結論與未來研究方向 58 5.1 結論 58 5.2 未來研究方向 59 參考文獻 60

    [1] 中華民國經濟部,「經濟部淨零關鍵戰略厚植產業綠色成長力,擘劃2030年電力配比願景」,Online Available: https://www.moea.gov.tw/MNS/populace/news/News.aspx?kind=1&menu_id=40&news_id=104155,2022年12月28日。(Accessed: Jun. 2, 2026.)
    [2] 維基百科,「鴨子曲線」,Online Available: https://zh.wikipedia.org/zh-tw/%E9%B4%A8%E5%AD%90%E6%9B%B2%E7%B7%9A,2020年12月3日。(Accessed: Jun. 2, 2026.)
    [3] 王釿鋊與劉致峻,「電力系統運轉與再生能源併網的影響」,能源教育資源總中心,Online Available: https://learnenergy.tw/index.php?inter=knowledge&caid=4&id=439,2019年11月21日。(Accessed: Jun. 2, 2026.)
    [4] 維基百科,「儲能技術」,Online Available: https://zh.wikipedia.org/zh-tw/%E5%82%A8%E8%83%BD%E6%8A%80%E6%9C%AF,2025年1月13日。(Accessed: Jun. 2, 2026.)
    [5] M. S. Whittingham, “Lithium Batteries and Cathode Materials,” Chemical Reviews, vol. 104, no. 10, pp. 4271–4302, 2004.
    [6] T. Möller, C. Cepnik, M. Azevedo, N. Campagnol, and Y. Kinzel, “The Battery Chemistries Powering the Future of Electric Vehicles,” [Online] Available: https://www.mckinsey.com/industries/automotive-and-assembly/our-insights/the-battery-chemistries-powering-the-future-of-electric-vehicles. McKinsey & Company, Dec. 17, 2024. (Accessed: Jun. 2, 2026.)
    [7] W. M. Haynes, Ed., CRC Handbook of Chemistry and Physics, 97th ed., Boca Raton, FL: CRC Press, 2016, sec. 14, pp. 17.
    [8] U.S. Energy Information Administration, “U.S. Battery Capacity Increased 66% in 2024,” [Online] Available: https://www.eia.gov/todayinenergy/detail.php?id=64705. Today in Energy, Mar. 12, 2025. (Accessed: Jun. 2, 2026.).
    [9] CAS Insights, “Innovations in Lithium-Ion Battery Recycling,” [Online] Available: https://www.cas.org/resources/cas-insights/innovations-in-lithium-ion-battery-recycling. Mar. 7, 2025. (Accessed: Jun. 2, 2026.)
    [10] Y. He, X. Ren, Y. Xu, M. H. Engelhard, X. Li, J. Xiao, J. Liu, J.-G. Zhang, W. Xu, and C. Wang, “Origin of lithium whisker formation and growth under stress,” Nature Nanotechnology, vol. 14, no. 11, pp. 1042–1047, 2019.
    [11] R. Tian, S.-H. Park, P. J. King, G. Cunningham, J. Coelho, V. Nicolosi, and J. N. Coleman, “Quantifying the Factors Limiting Rate Performance in Battery Electrodes,” Nature Communications, vol. 10, Art. no. 1933, 2019.
    [12] Y. Wang and H.-Y. S. Huang, “An Overview of Lithium-Ion Battery Cathode Materials,” MRS Online Proceedings Library, vol. 1363, Art. no. 530, 2011.
    [13] U.-H. Kim, L.-Y. Kuo, P. Kaghazchi, C. S. Yoon, and Y.-K. Sun, “Quaternary Layered Ni-Rich NCMA Cathode for Lithium-Ion Batteries,” ACS Energy Letters, vol. 4, no. 2, pp. 576–582, 2019.
    [14] University of Oxford, “Professor John Goodenough Wins 2019 Nobel Prize in Chemistry for Lithium-Ion Battery Research,” [Online] Available: https://staff.admin.ox.ac.uk/article/professor-john-goodenough-wins-2019-nobel-prize-in-chemistry-for-lithium-ion-battery-researc, Oct. 9, 2019. (Accessed: Jun. 2, 2026.)
    [15] C. M. Julien and A. Mauger, “Fabrication of Li₄Ti₅O₁₂ (LTO) as Anode Material for Li-Ion Batteries,” Micromachines (Basel), vol. 15, no. 3, Art. no. 310, Feb. 23, 2024.
    [16] Y. Lyu, X. Wu, K. Wang, Z. Feng, T. Cheng, Y. Liu, M. Wang, R. Chen, L. Xu, J. Zhou, Y. Lu, and B. Guo, “An Overview on the Advances of LiCoO₂ Cathodes for Lithium-Ion Batteries,” Advanced Energy Materials, vol. 11, no. 2, Art. no. 2000982, 2021.
    [17] Y. Preger, H. M. Barkholtz, A. Fresquez, D. L. Campbell, B. W. Juba, J. R. Kustas, S. R. Ferreira, and B. J. Chalamala, “Degradation of Commercial Lithium-Ion Cells as a Function of Chemistry and Cycling Conditions,” Journal of The Electrochemical Society, vol. 167, no. 12, Art. no. 120532, 2020.
    [18] P. Bugryniec, J. Davidson, D. Cumming, and S. F. Brown, “Pursuing Safer Batteries: Thermal Abuse of LiFePO₄ Cells,” Journal of Power Sources, vol. 414, pp. 557–568, Feb. 2019.
    [19] M. V. Reddy, A. Mauger, C. M. Julien, A. Paolella, and K. Zaghib, “Brief History of Early Lithium-Battery Development,” Materials (Basel), vol. 13, no. 8, Art. no. 1884, Apr. 2020.
    [20] V. M. Leal, J. S. Ribeiro, E. L. D. Coelho, and M. B. J. G. Freitas, “Recycling of Spent Lithium-Ion Batteries as a Sustainable Solution to Obtain Raw Materials for Different Applications,” Journal of Energy Chemistry, vol. 79, pp. 118–134, Apr. 2023.
    [21] C. Hu, M. Geng, H. Yang, M. Fan, Z. Sun, R. Yu, and B. Wei, “A Review of Capacity Fade Mechanism and Promotion Strategies for Lithium Iron Phosphate Batteries,” Coatings, vol. 14, no. 7, Art. no. 832, 2024.
    [22] J. S. Edge, S. O’Kane, R. Prosser, N. D. Kirkaldy, A. N. Patel, A. Hales, A. Ghosh, W. Ai, J. Chen, J. Jiang, S. Li, M.-C. Pang, L. Bravo Diaz, A. Tomaszewska, M. W. Marzook, K. N. Radhakrishnan, H. Wang, Y. Patel, B. Wu, and G. J. Offer, “Lithium-Ion Battery Degradation: What You Need to Know,” Physical Chemistry Chemical Physics, vol. 23, pp. 8200–8221, 2021.
    [23] PyBaMM Team, “PyBaMM Documentation,” version 25.4.2, [Online] Available: https://docs.pybamm.org/en/stable/, Mar. 12, 2025. (Accessed: Jun. 2, 2026.)
    [24] L. Xia, E. Najafi, H. J. Bergveld, and M. C. F. Donkers, “A Computationally Efficient Implementation of an Electrochemistry-Based Model for Lithium-Ion Batteries,” IFAC-PapersOnLine, vol. 50, no. 1, pp. 2169–2174, 2017.
    [25] 陳沛琳,「磷酸鋰鐵電池之電壓微分充放電策略」,碩士論文,國立中山大學電機工程學系研究所,2017年。
    [26] Y. Fan, Y. Qiao, D. Gan, Q. Wang, and W. Chen, “Lithium-Ion Battery Polarization Characteristics at Different Charging Modes,” Transactions of China Electrotechnical Society, vol. 32, no. 12, pp. 171–178, 2017.
    [27] Y. Huang, S. Wang, Z. Wang, and G. Xu, “Investigation of Lithium-Ion Battery Negative Pulsed Charging Strategy Using Non-Dominated Sorting Genetic Algorithm II,” Electronics, vol. 13, no. 11, Art. no. 2178, 2024.
    [28] X. Huang, Y. Li, A. B. Acharya, X. Sui, J. Meng, R. Teodorescu, and D.-I. Stroe, “A Review of Pulsed Current Technique for Lithium-Ion Batteries,” Energies, vol. 13, no. 10, Art. no. 2458, 2020.
    [29] 蔡汶峰,「鋰離子電池儲存老化與鋰金屬沉積之探討」,碩士論文,國立臺灣大學應用力學研究所,2019年。
    [30] X. Sun, Y. Zhang, Y. Zhang, L. Wang, and K. Wang, “Summary of Health-State Estimation of Lithium-Ion Batteries Based on Electrochemical Impedance Spectroscopy,” Energies, vol. 16, no. 15, Art. no. 5682, 2023.
    [31] L. Yao, S. Xu, A. Tang, F. Zhou, J. Hou, Y. Xiao, and Z. Fu, “A Review of Lithium-Ion Battery State of Health Estimation and Prediction Methods,” World Electric Vehicle Journal, vol. 12, no. 3, Art. no. 113, 2021.
    [32] W. Xiong, G. Xu, Y. Li, F. Zhang, P. Ye, and B. Li, “Early Prediction of Lithium-Ion Battery Cycle Life Based on Voltage-Capacity Discharge Curves,” Journal of Energy Storage, vol. 62, Art. no. 106790, 2023.
    [33] J. Snoek, H. Larochelle, and R. P. Adams, “Practical Bayesian Optimization of Machine Learning Algorithms,” arXiv preprint, arXiv:1206.2944, 2012.
    [34] P. Liashchynskyi and P. Liashchynskyi, “Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS,” arXiv preprint, arXiv:1912.06059, 2019.
    [35] J. Bergstra and Y. Bengio, “Random Search for Hyper-Parameter Optimization,” Journal of Machine Learning Research, vol. 13, pp. 281–305, 2012.
    [36] R. Turner, D. Eriksson, M. McCourt, J. Kiili, E. Laaksonen, Z. Xu, and I. Guyon, “Bayesian Optimization Is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020,” arXiv preprint, arXiv:2104.10201, 2021.
    [37] S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, Nov. 1997.
    [38] B. Ghojogh and A. Ghodsi, “Recurrent Neural Networks and Long Short-Term Memory Networks: Tutorial and Survey,” arXiv preprint, arXiv:2304.11461, 2023.
    [39] International Energy Agency, “Global Lithium Demand in the Net Zero Scenario, 2023–2040,” [Online] Available: https://www.iea.org/data-and-statistics/charts/global-lithium-demand-in-the-net-zero-scenario-2023-2040. 2024. (Accessed: Jun. 2, 2026.)
    [40] G. Harper, R. Sommerville, E. Kendrick, L. Driscoll, P. Slater, R. Stolkin, A. Walton, P. Christensen, O. Heidrich, S. Lambert, A. Abbott, K. Ryder, L. Gaines, and P. Anderson, “Recycling Lithium-Ion Batteries from Electric Vehicles,” Nature, vol. 575, no. 7781, pp. 75–86, Nov. 2019.
    [41] International Energy Agency, “Global EV Outlook 2024,” [Online] Available: https://www.iea.org/reports/global-ev-outlook-2024. 2024. (Accessed: Jun. 2, 2026.)
    [42] McKinsey & Company, “Toward Security in Sustainable Battery Raw Material Supply,” [Online] Available: https://www.mckinsey.com/industries/metals-and-mining/our-insights/toward-security-in-sustainable-battery-raw-material-supply. Dec. 19, 2024. (Accessed: Jun. 2, 2026.)
    [43] Center for Advanced Life Cycle Engineering (CALCE), “A123 Battery Data,” [Online] Available: https://calce.umd.edu/battery-data#A123. University of Maryland, College Park, Maryland, USA. (Accessed: Jun. 2, 2026.)
    [44] K. A. Severson, P. M. Attia, N. Jin, N. Perkins, B. Jiang, Z. Yang, M. H. Chen, M. Aykol, P. K. Herring, D. Fraggedakis, M. Z. Bazant, S. J. Harris, W. C. Chueh, and R. D. Braatz, “Data-driven prediction of battery cycle life before capacity degradation,” Nature Energy, vol. 4, no. 5, pp. 383–391, 2019.
    [45] P. M. Attia, A. Grover, N. Jin, K. A. Severson, T. Markov, Y.-H. Liao, M. H. Chen, B. Cheong, N. Perkins, Z. Yang, P. K. Herring, M. Aykol, S. J. Harris, R. D. Braatz, S. Ermon, and W. C. Chueh, “Closed-loop optimization of fast-charging protocols for batteries with machine learning,” Nature, vol. 578, pp. 397–402, 2020.
    [46] 陳明達,「基於使用者特性之鋰離子電池充電程序最佳化」,碩士論文,國立交通大學,2010年。
    [47] Wikipedia, “Inverse Function,” [Online] Available: https://en.wikipedia.org/wiki/Inverse_function. Mar. 12, 2025. (Accessed: Jun. 2, 2026.)
    [48] W. Xia, Y. Zhang, Y. Yang, J.-H. Xue, B. Zhou, and M.-H. Yang, “GAN Inversion: A Survey,” arXiv preprint, arXiv:2101.05278v5, Mar. 2022.
    [49] 林宗賢,「自適應脈衝電流電池充電器之研製」,碩士論文,國立雲林科技大學電機工程系,2019年。
    [50] S. Lee, W. Cho, V. Do, and W. Choi, “Effects of Pulse Current Charging on the Aging Performance of Commercial Cylindrical Lithium-Ion Batteries,” Applied Sciences, vol. 11, no. 11, Art. no. 4918, Jun. 2021.
    [51] Y. Tian, L. Wang, C. Liao, and G. Yan, “Comprehensive Investigation of the Durability of Lithium-Ion Batteries Under Frequency Regulation Conditions,” Batteries, vol. 11, no. 2, Art. no. 75, 2025.
    [52] Z. Rao, J. Wu, G. Li, and H. Wang, “Voltage Abnormity Prediction Method of Lithium-Ion Energy Storage Power Station Using Informer Based on Bayesian Optimization,” Scientific Reports, vol. 14, Art. no. 21404, Sep. 2024.
    [53] L. He, Y. Lee, E. Kim, and K. G. Shin, “Environment-Aware Estimation of Battery State-of-Charge for Mobile Devices,” in Proceedings of the 10th ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS), 2019, pp. 227–236..
    [54] H. Xu, T. Yu, C. Chen, and X. Wu, “State-of-Charge Prediction Model for Ni-Cd Batteries Considering Temperature and Noise,” Applied Sciences, vol. 13, no. 11, Art. no. 6494, 2023.
    [55] Y. Song, J. Lu, H. Zhang, and G. Liu, “SOC and SOH Prediction of Lithium-Ion Batteries Based on LSTM–AUKF Joint Algorithm,” Energy Science & Engineering, vol. 13, pp. 240–254, 2024.
    [56] M. U. Tahir, A. Sangwongwanich, D.-I. Stroe, and F. Blaabjerg, “Multi-Objective Optimization for Multi-Stage Constant Current Charging for Li-Ion Batteries,” Journal of Energy Storage, vol. 86, Part A, Art. no. 111313, 2024.
    [57] M. Yuan and C. Zou, “Lifelong Reinforcement Learning for Health-Aware Fast Charging of Lithium-Ion Batteries,” arXiv preprint, arXiv:2505.11061, 2025.
    [58] IEST, “High-Precision Battery Cycler Systems: Analysis of Accuracy and Stability Verification Methods,” [Online] Available: https://iestbattery.com/battery-cycler-system-accuracy-stability-methods/. (Accessed: Jun. 2, 2026.)
    [59] Arbin Instruments, “The Impact of Temperature on Battery Testing,” [Online] Available: https://www.arbin.com/the-impact-of-temperature-on-battery-testing.html. Nov. 12, 2021. (Accessed: Jun. 2, 2026.)
    [60] B. Schweighofer, D. Schürholz, M. Neumayer, and H. Wegleiter, “Uncertainty Analysis of Selected Standard Methods in Battery Measurement Technology,” Journal of Power Sources, vol. 561, Art. no. 232749, 2023.
    [61] BioLogic, “Resolution, Precision, Accuracy, Temperature Stability and Time Base: The Five to Watch (Electrochemistry Basics Series),” [Online] Available: https://www.biologic.net/topics/resolution-precision-accuracy-temperature-stability-and-time-base-the-five-to-watch/. (Accessed: Jun. 2, 2026.)
    [62] D. C. Montgomery, E. A. Peck, and G. G. Vining, Introduction to Linear Regression Analysis, 5th ed. Hoboken, NJ, USA: John Wiley & Sons, 2012. [Online] Available: https://www.kwcsangli.in/uploads/3--Introduction_to_Linear_Regression_Analysis__5th_ed._Douglas_C._Montgomery__Elizabeth_A._Peck__and_G._.pdf. (Accessed: Jun. 2, 2026.)

    下載圖示
    校外:立即公開
    QR CODE