为解决退役电池梯次利用过程中单体剩余使用寿命估计困难、测试流程复杂与能耗高等问题,提出迁移学习与GRU网络结合的锂离子电池健康状态估计方法;设计的基础模型结构为输入层+GRU层+全连接层+输出层;根据健康因子的得分,选择训练基础模型的数据集、划分电池相似度等级并制定对应的迁移学习策略。实验结果表明：与其他模型相比,分别使用数据集的前40%与前25%训练得到的基础模型与迁移学习模型,两者的精度分别最大提高42.48%与95.28%,而预测稳定性分别最大提高55.38%与93.55%。
Abstract
In order to solve the problems of difficulty in estimating the remaining service life of cells, complex testing process and high energy consumption in the cascade utilization of retired batteries. The designed basic model structure is input layer + GRU layer + full connection （full connect, FC） layer+output layer. According to the score of the health factor, the dataset for training the basic model is selected, the battery similarity level is divided, and the corresponding migration learning strategy is formulated. The experimental results show that compared with other models, the accuracy of the basic model and transfer learning model trained by using the first 40% and the first 25% of the dataset respectively increased by 42.48% and 95.28%, and the prediction stability Respectively the maximum increase of 55.38% and 93.55%.
关键词
机器学习 /
迁移学习 /
锂电池 /
门控循环单元神经网络 /
健康状态估计
Key words
machine learning /
transfer learning /
lithium batteries /
GRU neural network /
state of health estimation
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] YANG S J, ZHANG C P, JIANG J C, et al.Review on state-of-health of lithium-ion batteries: characterizations, estimations and applications[J]. Journal of cleaner production, 2021, 314: 128015.
[2] MOVASSAGH K, RAIHAN A, BALASINGAM B, et al.A critical look at coulomb counting approach for state of charge estimation in batteries[J]. Energies, 2021, 14(14): 4074.
[3] WENG C H, SUN J, PENG H E.A unified open-circuit-voltage model of lithium-ion batteries for state-of-charge estimation and state-of-health monitoring[J]. Journal of power sources, 2014, 258: 228-237.
[4] HOSSEININASAB S, LIN C W, PISCHINGER S, et al.State-of-health estimation of lithium-ion batteries for electrified vehicles using a reduced-order electrochemical model[J]. Journal of energy storage, 2022, 52: 104684.
[5] SANKARASUBRAMANIAN S, KRISHNAMURTHY B.A capacity fade model for lithium-ion batteries including diffusion and kinetics[J]. Electrochimica acta, 2012, 70: 248-254.
[6] SINGH P, CHEN C, TAN C M, et al.Semi-empirical capacity fading model for SoH estimation of Li-ion batteries[J]. Applied sciences, 2019, 9(15): 3012.
[7] FENG X N, LI J Q, OUYANG M G, et al.Using probability density function to evaluate the state of health of lithium-ion batteries[J]. Journal of power sources, 2013, 232: 209-218.
[8] ZHANG S Z, ZHAI B Y, GUO X, et al.Synchronous estimation of state of health and remaining useful lifetime for lithium-ion battery using the incremental capacity and artificial neural networks[J]. Journal of energy storage, 2019, 26: 100951.
[9] GUHA A, PATRA A.Particle filtering based estimation of remaining useful life of lithium-ion batteries employing power fading data[C]//2017 IEEE International Conference on Prognostics and Health Management (ICPHM). Dallas, TX, USA, 2017: 193-198.
[10] 戴海峰, 姜波, 魏学哲, 等. 基于充电曲线特征的锂离子电池容量估计[J]. 机械工程学报, 2019, 55(20): 52-59.
DAI H F, JIANG B, WEI X Z, et al.Capacity estimation of lithium-ion batteries based on charging curve features[J]. Journal of mechanical engineering, 2019, 55(20): 52-59.
[11] KIM S J, KIM S H, LEE H M, et al.State of health estimation of Li-ion batteries using multi-input LSTM with optimal sequence length[C]//2020 IEEE 29th International Symposium on Industrial Electronics (ISIE). Delft, Netherlands, 2020: 1336-1341.
[12] SAHA B, GOEBEL K. Battery Data Set, Moffett Field, CA, USA: NASA Ames Res. Center, 2007.[DB/OL]. Available: https://download.csdn.net/download/m0_53407570/85258209.
[13] MICHAEL P, et al.Battery Data Set, USA: University of Maryland, CALCE, 2010.[DB/OL]. Available:https://web.calce.umd.edu/batteries/data.htm.
[14] ABHANG L B, HAMEEDULLAH M.Determination of optimum parameters for multi-performance characteristics in turning by using grey relational analysis[J]. The international journal of advanced manufacturing technology, 2012, 63(1/2/3/4): 13-24.
[15] LEE J H, KIM H S, LEE I S.State of charge estimation and state of health diagnostic method using multilayer neural networks[C]//2021 International Conference on Electronics, Information, and Communication (ICEIC). Jeju, South Korea, 2021: 1-4.
[16] ZHAO Q, QIN X L, ZHAO H B, et al.A novel prediction method based on the support vector regression for the remaining useful life of lithium-ion batteries[J]. Microelectronics reliability, 2018, 85: 99-108.
[17] YANG D, ZHANG X, PAN R, et al.A novel Gaussian process regression model for state-of-health estimation of lithium-ion battery using charging curve[J]. Journal of power sources, 2018, 384: 387-395.
PDF(2207 KB)
