针对退役电池老化程度较高,在动力电池上采用的健康特征无法满足退役电池实际工作时的荷电状态（SOC）的范围的问题,提出在退役电池实际使用时SOC的主要分布范围内获取电池充电数据,通过获取的数据预测SOH,提升算法运用的实用性。在此基础上,针对传统SOH估计算法提取能反映电池老化特性的特征较困难,且无法完全利用数据的问题,提出利用一维深度卷积神经网络（CNN）提取电池特征,再将特征输入到长短期神经网络（LSTM）中预测SOH。利用美国国家航空航天局（NASA）锂离子电池随机数据集对算法进行验证,该方法能采取较少的电池片段来实现准确的SOH估算,且相较于传统的SOH算法,更能贴合退役电池实际使用需求。
Abstract
Regarding the issue of retired batteries having a higher degree of aging, the health characteristics used in power batteries are insufficient to meet the actual state of charge （SOC） range during the operation of retired batteries, it is proposed to obtain battery charging data within the main distribution range of SOC during actual use of decommissioned batteries, and predict SOH through the obtained data, which improves the practicality of the algorithm. On this basis, aiming at the problem that it is difficult for traditional SOH estimation algorithm to extract the features that can reflect the aging characteristics of batteries, and the data cannot be fully utilized, a one-dimensional deep convolutional neural network （CNN） is proposed to extract the battery features, and then the features are input into the long and short term neural network （LSTM） to predict SOH. The algorithm was verified on the NASA random data set of lithium-ion batteries, and the method can achieve accurate SOH estimation with fewer battery fragments, and is more suitable for the actual use of decommissioned batteries than the traditional SOH algorithm.
关键词
退役电池 /
电池健康状态 /
电池荷电状态 /
卷积神经网络 /
长短期神经网络 /
充电数据片段
Key words
decommissioned battery /
battery health status /
state of charge /
convolutional neural network /
long and short term neural networks /
charging data segment
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 孙国跃, 陈勇. 退役动力电池梯次利用筛选指标的实验研究[J]. 电源技术, 2018, 42(12): 1818-1821.
SUN G Y, CHEN Y.Experimental study on the screening criteria of echelon use of returned power battery[J]. Chinese journal of power sources, 2018, 42(12): 1818-1821.
[2] 马玲, 魏成伟, 谢丽蓉, 等. 基于退役动力电池的风储有功功率协调控制策略[J]. 太阳能学报, 2021, 42(10): 437-443.
MA L, WEI C W, XIE L R, et al.Coordinated control strategy for wind storage active power of decommissioned power battery[J]. Acta energiae solaris sinica, 2021, 42(10): 437-443.
[3] 李建林, 王哲, 李雅欣, 等. 退役动力电池梯级利用分选技术研究[J]. 太阳能学报, 2023, 44(1): 418-425.
LI J L, WANG Z, LI Y X, et al.Research on sorting technology of cascade utilization of retired power batteries[J]. Acta energiae solaris sinica, 2023, 44(1): 418-425.
[4] 魏梓轩, 韩晓娟, 李炫. 基于深度神经网络的梯次利用电池健康状态评估[J]. 太阳能学报, 2022, 43(5): 518-524.
WEI Z X, HAN X J, LI X.State of health assessment for echelon utilization batteries based on deep neural network[J]. Acta energiae solaris sinica, 2022, 43(5): 518-524.
[5] LU J, WU T P, AMINE K.State-of-the-art characterization techniques for advanced lithium-ion batteries[J]. Nature energy, 2017, 2(3): 17011.
[6] DOYLE M, NEWMAN J.Modeling the performance of rechargeable lithium-based cells: design correlations for limiting cases[J]. Journal of power sources, 1995, 54(1): 46-51.
[7] WANG D, MIAO Q, PECHT M.Prognostics of lithium-ion batteries based on relevance vectors and a conditional three-parameter capacity degradation model[J]. Journal of power sources, 2013, 239: 253-264.
[8] 刘婷婷, 朱文东, 刘广一. 基于深度学习的文本分类研究进展[J]. 电力信息与通信技术, 2018, 16(3): 1-7.
LIU T T, ZHU W D, LIU G Y.Advances in deep learning based text classification[J]. Electric power information and communication technology, 2018, 16(3): 1-7.
[9] 李超然, 肖飞, 樊亚翔, 等. 基于卷积神经网络的锂离子电池SOH估算[J]. 电工技术学报, 2020, 35(19): 4106-4119.
LI C R, XIAO F, FAN Y X, et al.An approach to lithium-ion battery SOH estimation based on convolutional neural network[J]. Transactions of China Electrotechnical Society, 2020, 35(19): 4106-4119.
[10] 杨胜杰, 罗冰洋, 王菁, 等. 基于容量增量曲线峰值区间特征参数的锂离子电池健康状态估算[J]. 电工技术学报, 2021, 36(11): 2277-2287.
YANG S J, LUO B Y, WANG J, et al.State of health estimation for lithium-ion batteries based on peak region feature parameters of incremental capacity curve[J]. Transactions of China Electrotechnical Society, 2021, 36(11): 2277-2287.
[11] MAWONOU K R, EDDAHECH A, DUMUR D, et al.State-of-health estimators coupled to a random forest approach for lithium-ion battery aging factor ranking[J]. Journal of power sources, 484: 229154
[12] 韩乔妮, 姜帆, 程泽. 变温度下IHF-IGPR框架的锂离子电池健康状态预测方法[J]. 电工技术学报, 2021, 36(17): 3705-3720.
HAN Q N, JIANG F, CHENG Z.State of health estimation for lithium-ion batteries based on the framework of IHF-IGPR under variable temperature[J]. Transactions of China Electrotechnical Society, 2021, 36(17): 3705-3720.
[13] MIAO Q, XIE L, CUI H J, et al.Remaining useful life prediction of lithium-ion battery with unscented particle filter technique[J]. Microelectronics reliability, 2013, 53(6): 805-810.
[14] 王育飞, 叶俊斌, 薛花, 等. 基于改进雨流计数法的梯次利用电池储能系统优化控制[J]. 电力系统自动化, 2022, 46(8): 39-49.
WANG Y F, YE J B, XUE H, et al.Optimal control for energy storage system with echelon utilization batteries based on improved rain-flow counting method[J]. Automation of electric power systems, 2022, 46(8): 39-49.
[15] 周頔, 宋显华, 卢文斌, 等. 基于日常片段充电数据的锂电池健康状态实时评估方法研究[J]. 中国电机工程学报, 2019, 39(1): 105-111, 325.
ZHOU D, SONG X H, LU W B, et al.Real-time SOH estimation algorithm for lithium-ion batteries based on daily segment charging data[J]. Proceedings of the CSEE, 2019, 39(1): 105-111, 325.
[16] 周飞燕, 金林鹏, 董军. 卷积神经网络研究综述[J]. 计算机学报, 2017, 40(6): 1229-1251.
ZHOU F Y, JIN L P, DONG J.Review of convolutional neural network[J]. Chinese journal of computers, 2017, 40(6): 1229-1251.
[17] 杨丽, 吴雨茜, 王俊丽, 等. 循环神经网络研究综述[J]. 计算机应用, 2018, 38(增刊2): 1-6, 26.
YANG L, WU Y Q, WANG J L, et al.A survey of research on circulatory neural network[J]. Journal of computer applications, 2018, 38(S2): 1-6, 26.
[18] SONG X B, YANG F F, WANG D, et al.Combined CNN-LSTM network for state-of-charge estimation of lithium-ion batteries[J]. IEEE access, 2019, 7: 88894-88902.
基金
合肥综合性国家科学中心能源研究院重大培育项目（21KZS210）; 校级研究生质量工程项目（2021YJG113）
PDF(2333 KB)
