基于机器学习的钠离子电池健康状态估计研究

钠离子电池由于其丰富的资源和低成本而成为锂离子电池的有前途的替代品。然而，钠离子电池的老化机制复杂且尚未被完全理解，这限制了它们的实际应用。 本文提出了一种提取钠离子电池健康因素的方法，并使用多种机器学习方法来估 计钠离子电池的健康状况，这可以对其剩余使用寿命提供可靠和准确的评估。论 文的具体研究如下：本文从理论层面出发分析钠离子电池衰减机理，并对电池循环实验数据进行 详细分析。首先分析了钠离子电池衰建的内部机制，并与锂离子电池进行了比较。在此基础上，对钠离子电池循环数据进行分析，确立健康因素提取的基本方法，为 后续工作提供理论和数据支撑。在此基础上，本文提出一种新的提取健康因素的方法。该方法基于增量容量分析，并改进了该方法，仅通过充电电流的部分数据提取钠离子电池的健康因素。 同时，本文还介绍了一种确定提取健康因素所需要的电压上限和下限的方法，方便了后续快速确定电池健康因素，提高了估计钠离子健康状态的精度。本文主要工作是寻找一种与钠离子电池健康状态高度相关的健康因素，并通过堆叠双向长短期记忆网络进行建模预测。本文分别使用了多种机器学习算法构建了用于估计钠离子电池的健康状态的预测模型，并进行了实验以评估模型的性能。实验结果表明，该方法可以准确估计钠离子电池的健康状态，这对钠离子电池商业化使用具有一定参考价值。

[1] CHAYAMBUKA K, JIANG M, MULDER G, et al. Physics-based modeling of sodium-ionbatteries part I: Experimental parameter determination[J]. Electrochimica Acta, 2022, 404:139726.
[2] LARCHER D, TARASCON J M. Towards greener and more sustainable batteries for electricalenergy storage[J]. Nature chemistry, 2015, 7(1): 19-29.
[3] KUBOTA K, DAHBI M, HOSAKA T, et al. Towards K-ion and Na-ion batteries as “beyondLi-ion”[J]. The chemical record, 2018, 18(4): 459-479.
[4] EVARTS E C. Lithium batteries: To the limits of lithium[J]. Nature, 2015, 526(7575): S93-S95.
[5] GOODENOUGH J B, PARK K S. The Li-ion rechargeable battery: a perspective[J]. Journalof the American Chemical Society, 2013, 135(4): 1167-1176.
[6] LIU T, ZHANG Y, JIANG Z, et al. Exploring competitive features of stationary sodium ionbatteries for electrochemical energy storage[J]. Energy & Environmental Science, 2019, 12(5):1512-1533.
[7] KUNDU D, TALAIE E, DUFFORT V, et al. The emerging chemistry of sodium ion batteriesfor electrochemical energy storage[J]. Angewandte Chemie International Edition, 2015, 54(11):3431-3448.
[8] SAWICKI M, SHAW L L. Advances and challenges of sodium ion batteries as post lithium ionbatteries[J]. RSC Advances, 2015, 5(65): 53129-53154.
[9] VAALMA C, BUCHHOLZ D, WEIL M, et al. A cost and resource analysis of sodium-ionbatteries[J]. Nature reviews materials, 2018, 3(4): 1-11.
[10] TARASCON J M, ARMAND M. Issues and challenges facing rechargeable lithium batteries[J]. nature, 2001, 414(6861): 359-367.
[11] XU H, YAN Q, YAO W, et al. Mainstream Optimization Strategies for Cathode Materials ofSodium-Ion Batteries[J]. Small Structures, 2022, 3(4): 2100217.
[12] HANSEN T, WANG C J. Support vector based battery state of charge estimator[J]. Journal ofPower Sources, 2005, 141(2): 351-358.
[13] WEN J, CHEN X, LI X, et al. SOH prediction of lithium battery based on IC curve feature andBP neural network[J]. Energy, 2022, 261: 125234.
[14] TRAN M K, CUNANAN C, PANCHAL S, et al. Investigation of individual cells replacementconcept in lithium-ion battery packs with analysis on economic feasibility and pack design requirements[J]. Processes, 2021, 9(12): 2263.
[15] SUI X, HE S, VILSEN S B, et al. A review of non-probabilistic machine learning-based stateof health estimation techniques for Lithium-ion battery[J]. Applied Energy, 2021, 300: 117346.
[16] SUBRAMANIAN V R, DIWAKAR V D, TAPRIYAL D. Effffcient macro-micro scale coupledmodeling of batteries[J]. Journal of The Electrochemical Society, 2005, 152(10): A2002.55
[17] PRASAD G K, RAHN C D. Model based identification of aging parameters in lithium ionbatteries[J]. Journal of power sources, 2013, 232: 79-85.
[18] HU X, LI S, PENG H. A comparative study of equivalent circuit models for Li-ion batteries[J].Journal of Power Sources, 2012, 198: 359-367.
[19] CACCIATO M, NOBILE G, SCARCELLA G, et al. Real-time model-based estimation of SOCand SOH for energy storage systems[J]. IEEE Transactions on Power Electronics, 2016, 32(1):794-803.
[20] XIONG R, TIAN J, MU H, et al. A systematic model-based degradation behavior recognitionand health monitoring method for lithium-ion batteries[J]. Applied energy, 2017, 207: 372-383.
[21] STROE D I, ŚWIERCZYŃSKI M, STAN A I, et al. Accelerated lifetime testing methodologyfor lifetime estimation of lithium-ion batteries used in augmented wind power plants[J]. IEEETransactions on Industry Applications, 2014, 50(6): 4006-4017.
[22] BROUSSELY M, BIENSAN P, BONHOMME F, et al. Main aging mechanisms in Li ion batteries[J].Journal of power sources, 2005, 146(1-2): 90-96.
[23] GALEOTTI M, CINÀ L, GIAMMANCO C, et al. Performance analysis and SOH (state ofhealth) evaluation of lithium polymer batteries through electrochemical impedance spectroscopy[J]. Energy, 2015, 89: 678-686.
[24] GAO Y, LIU K, ZHU C, et al. Co-estimation of state-of-charge and state-of-health for lithiumion batteries using an enhanced electrochemical model[J]. IEEE Transactions on Industrial Electronics, 2021, 69(3): 2684-2696.
[25] ANSELMA P G, KOLLMEYER P, LEMPERT J, et al. Battery state-of-health sensitive energymanagement of hybrid electric vehicles: Lifetime prediction and ageing experimental validation[J]. Applied Energy, 2021, 285: 116440.
[26] ZHENG L, ZHU J, LU D D C, et al. Incremental capacity analysis and differential voltageanalysis based state of charge and capacity estimation for lithium-ion batteries[J]. Energy, 2018,150: 759-769.
[27] DUBARRY M, SVOBODA V, HWU R, et al. Incremental capacity analysis and close-toequilibriumOCV measurements to quantify capacity fade in commercial rechargeable lithiumbatteries[J]. Electrochemical and solid-state letters, 2006, 9(10): A454.
[28] YAZAMI R, TOUZAIN P. A reversible graphite-lithium negative electrode for electrochemicalgenerators[J]. Journal of Power Sources, 1983, 9(3): 365-371.
[29] YAZAMI R, REYNIER Y. Thermodynamics and crystal structure anomalies in lithiumintercalatedgraphite[J]. Journal of Power Sources, 2006, 153(2): 312-318.
[30] DUBARRY M, SVOBODA V, HWU R, et al. A roadmap to understand battery performance inelectric and hybrid vehicle operation[J]. Journal of Power Sources, 2007, 174(2): 366-372.
[31] DUBARRY M, LIAW B Y. Identify capacity fading mechanism in a commercial LiFePO4 cell[J]. Journal of power sources, 2009, 194(1): 541-549.
[32] STROE D I, SCHALTZ E. Lithium-ion battery state-of-health estimation using the incrementalcapacity analysis technique[J]. IEEE Transactions on Industry Applications, 2019, 56(1): 678-685.56
[33] ZHANG Y, LIU Y, WANG J, et al. State-of-health estimation for lithium-ion batteries by combining model-based incremental capacity analysis with support vector regression[J]. Energy, 2022, 239: 121986.
[34] DUBARRY M, LIAW B Y, CHEN M S, et al. Identifying battery aging mechanisms in large format Li ion cells[J]. Journal of Power Sources, 2011, 196(7): 3420-3425.
[35] YOU G W, PARK S, OH D. Real-time state-of-health estimation for electric vehicle batteries:A data-driven approach[J]. Applied energy, 2016, 176: 92-103.
[36] BAI G, WANG P, HU C, et al. A generic model-free approach for lithium-ion battery healthmanagement[J]. Applied Energy, 2014, 135: 247-260.
[37] PASTOR-FERNÁNDEZ C, WIDANAGE W, CHOUCHELAMANE G, et al. A soh diagnosis and prognosis method to identify and quantify degradation modes in li-ion batteries using the ic/dv technique[C]//6th Hybrid and Electric Vehicles Conference (HEVC 2016). IET, 2016:1-6.
[38] 冯志伟. 神经网络, 深度学习与自然语言处理[J]. 上海师范大学学报 (哲学社会科学版), 2021, 2: 110-122.
[39] 徐冰冰, 岑科廷, 黄俊杰, 等. 图卷积神经网络综述[J]. 计算机学报, 2020, 43(5): 755-780.
[40] 王红霞, 周家奇, 辜承昊, 等. 用于图像分类的卷积神经网络中激活函数的设计[J]. 浙江大学学报 (工学版), 2019, 53(7): 1363-1373