基于GRNN-GSA-ELM的在线锂离子电池RUL多步预测

doi:10.3901/JME.2024.24.296

摘要/Abstract

摘要： 考虑到锂离子电池剩余寿命在线预测能力不足，以及基于极限学习机网络模型对小样本训练数据学习能力不强的问题，提出构建连续的健康因子的方法，使用广义回归神经网络与改进极限学习机(Extreme learning machine，ELM)融合的方法对锂电池剩余寿命进行多步预测。首先，提取锂电池等压降放电时间作为健康因子，利用插值补充的方法将离散的电池运行参数重构为连续的健康因子，然后，使用广义回归神经网络对锂离子电池早期剩余寿命进行预测，引入引力搜索算法对极限学习机进行优化，建立具有实时更新能力的锂离子电池中后期剩余寿命预测(Remaining useful life，RUL)多步预测模型，最后，基于马里兰高级生命周期工程中心的CS2-35～CS2-38号以及CS2-7号电池数据对模型进行验证。试验结果表明，基于广义回归神经网络与引力搜索算法优化极限学习机融合的锂电池在线RUL多步预测模型具有较高的预测精度，与其他模型相比鲁棒性与适用性较好。

关键词: 等压降放电时间, 广义回归神经网络, 引力搜索算法, 极限学习机, 多步预测

Abstract: Considering the problems of insufficient online prediction capability of the residual life of Li-ion batteries and the poor learning capability of the extreme learning machine based network model for small sample training data, a method of constructing continuous health factors is proposed to perform multi-step prediction of the residual life of Li-ion batteries using generalized regression neural network fused with an improved ELM. Firstly, the iso-voltage drop discharge time of Li-ion batteries is extracted as the health factor, and the discrete battery operating parameters are reconstructed into continuous health factors using the interpolation complementary method. Then, the generalized regression neural network is used to predict the early remaining life of Li-ion batteries, and the gravitational search algorithm is introduced to optimize the limit learning machine to build a mid-late RUL multi-step Li-ion battery multi-step with real-time update capability Finally, the model is validated based on the data of CS2-35～CS2-38 and CS2-7 batteries from the Maryland advanced life cycle engineering center. The experimental results show that the online RUL multi-step prediction model for Li-ion batteries based on the fusion of GRNN and GSA-ELM has high prediction accuracy and better robustness and applicability compared with other models.

Key words: equal voltage discharging time, general regression neural network, gravity search algorithm, extreme learning machine, multi-step online prediction

中图分类号:

TM912

蔡艳平, 王新军, 姜柯, 韩德帅, 赵沁峰. 基于GRNN-GSA-ELM的在线锂离子电池RUL多步预测[J]. 机械工程学报, 2024, 60(24): 296-308.

CAI Yanping, WANG Xinjun, JIANG Ke, HAN Deshuai, ZHAO Qinfeng. Multi-step Prediction of Online Lithium Battery Remaining Useful Life Based on GRNN-GSA-ELM[J]. Journal of Mechanical Engineering, 2024, 60(24): 296-308.

参考文献

[1] 陈龙，池上森，董源，等. 全固态锂电池关键材料—固态电解质研究进展[J]. 硅酸盐学报，2018，46(1)：21-34. CHEN Long，CHI Shangsen，DONG Yuan，et al. Research progress of key materials for all-solid-state lithium batteries[J]. Journal of the Chinese Ceramic Society，2018，46(1)：21-34.
[2] 李维聪，穆浩，沈恒龙，等. 固态锂电池在载运工具中的应用前景分析[J]. 电气工程学报，2022，17(4)：88-102. LI Weicong，MU Hao，SHEN Henglong，et al. Application prospect analysis of solid-state lithium battery in vehicle[J]. Journal of Electrical Engineering，2022，17(4)：88-102.
[3] 杨淞元，田勇，田劲东. 基于iCEEMDAN和迁移学习的锂离子电池SOH估计[J]. 电气工程学报，2022，17(4)：2-10. YANG Songyuan，TIAN Yong，TIAN Jindong. State of health estimation of lithium-ion batteries based on iCEEMDAN and transfer learning[J]. Journal of Electrical Engineering，2022，17(4)：2-10.
[4] 鲁南，欧阳权，黄俍卉，等. 基于注意力机制和多任务LSTM的锂电池容量预测方法[J]. 电气工程学报，2022，17(4)：41-50. LU Nan，OUYANG Quan，HUANG Lianghui，et al. Capacity prediction of lithium-ion batteries based on multi-task LSTM with attention mechanism[J]. Journal of Electrical Engineering，2022，17(4)：41-50.
[5] 方德宇，楚潇，刘涛，等. 基于数据-模型驱动的锂离子电池健康状态估计[J]. 电气工程学报，2022，17(4)：20-31. FANG Deyu，CHU Xiao，LIU Tao，et al. Research on health assessment method of lithium-ion battery based on data-model hybrid drive[J]. Journal of Electrical Electrical Engineering，2022，17(4)：20-31.
[6] 郑志坤，赵光金，金阳，等. 基于库仑效率的退役锂离子动力电池储能梯次利用筛选[J]. 电工技术学报，2019，34(增刊1)：388-395. ZHENG Zhikun，ZHAO Guangjin，JIN Yang，et al. The reutilization screening of retired electric vehicle Lithium-ion battery based on coulombic efficiency[J]. Transactions of China Electrotechnical Society，2019，34(Suppl.1)：388-395.
[7] 全睿，全书海，黄亮，等. 基于模糊故障树的燃料电池发动机氢安全[J]. 上海交通大学学报，2010，44(7)：951-956. QUAN Rui，QUAN Shuhai，HUANG Liang，et al. Study on hydrogen safety of fuel cell engine based on fuzzy fault tree[J]. Journal of Shanghai Jiaotong University，2010，44(7)：951-956.
[8] 郭永芳，黄凯，李志刚. 基于短时搁置端电压压降的快速锂离子电池健康状态预测[J]. 电工技术学报，2019，34(19)：3968-3978. GUO Yongfang，HUANG Kai，LI Zhigang. Fast state of health prediction of lithium-ion battery based on terminal voltage drop during rest for short time[J]. Transactions of China Electrotechnical Society，2019，34(19)：3968-3978.
[9] 谢长君，费亚龙，曾春年，等. 基于无迹粒子滤波的车载锂离子电池状态估计[J]. 电工技术学报，2018，33(17)：3958-3964. XIE Changjun，FEI Yalong，ZENG Chunnian，et al. Sta-te-of-charge estimation of lithium-ion battery using unscented particle filter in vehicle[J]. Transactions of China Electrotechnical Society，2018，33(17)： 3958-3964.
[10] 易灵芝，张宗光，范朝冬，等. 基于EEMD-GSGRU的锂电池寿命预测[J]. 储能科学与技术，2020，9(5)：1566-1573. YI Lingzhi，ZHANG Zongguang，FAN Chaodong，et al. Life prediction of lithium battery based on EEMD- GSGRU[J]. Energy Storage Science and Technology，2020，9(5)：1566-1573.
[11] 王竹晴，郭阳明，徐聪. 基于SAE-VMD的锂离子电池健康因子提取方法[J]. 西北工业大学学报，2020，38(4)：814-821. WANG Zhuqing，GUO Yangming，XU Cong. An HI extraction framework for lithium-Ion battery prognostics based on SAE-VMD[J]. Journal of Northwestern Polytechnical University，2020，38(4)：814-821.
[12] 宋哲，高建平，潘龙帅，等. 基于主成分分析和改进支持向量机的锂离子电池健康状态预测[J]. 汽车技术，2020(11)：21-27. SONG Zhe，GAO Jianping，PAN Longshuai，et al. Prediction for the state of health of lithium-ion batteries based on PCA and improved SVR[J]. Automobile Te-chnology，2020(11)：21-27.
[13] FANG Y，DONG W，FAN X，et al. Lifespan prediction of lithium-ion batteries based on various extracted features and gradient boosting regression tree model[J]. Journal of Power Sources，2020，476：228654.
[14] WANG R，FENG H. Remaining useful life prediction of lithium-ion battery using a novel health indicator[J]. Quality and Reliability Engineering International，2021，37(3)：1232-1243.
[15] 庞晓琼，王竹晴，曾建潮，等. 基于PCA-NARX的锂离子电池剩余使用寿命预测[J]. 北京理工大学学报，2019，39(4)：406-412. PANG Xiaoqiong，WANG Zhuqing，ZENG Jianchao，et al. Prediction for remaining useful life of lithium-ion battery based on PCA-NARX[J]. Transactions of Beijing Institute of Technology，2019，39(4)：406-412.
[16] 陈则王，李福胜，林娅，等. 基于GA-ELM的锂离子电池RUL间接预测方法[J]. 计量学报，2020，41(6)：735-742. CHEN Zewang，LI Fusheng，LIN Ya，et al. Indirect prediction method of RUL for lithium-ion battery based on GA-ELM[J]. Acta Metrologica Sinica，2020，41(6)：735-742.
[17] 彭宇，刘大同. 数据驱动故障预测和健康管理综述[J]. 仪器仪表学报，2014，35(3)：481-495. PENG Yu，LIU Datong. Data-driven prognostics and health management：A review of recent advances[J]. Chinese Journal of Scientific Instrument，2014，35(3)：481-495.
[18] SPECHT D F. A general regression neural network[J]. IEEE Transactions on Neural Networks，1991，2(6)：568-576.
[19] 冯志鹏，宋希庚，薛冬新，等. 基于广义回归神经网络的时间序列预测研究[J]. 振动、测试与诊断，2003(2)：29-33，68. FENG Zhipeng，SONG Xigeng，XUE Dongxin，et al. General regression neural network based prediction of time series[J]. Journal of Vibration，Measurement & Diagnosis，2003(2)：29-33，68.
[20] 张淑清，任爽，姜安琦，等. PCA-GRNN在综合气象短期负荷预测中的应用[J]. 计量学报，2017，38(3)：340-344. ZHANG Shuqing，REN Shuang，JIANG Anqi，et al. Application of PCA-GRNN in integrated meteorological short-term load forecasting[J]. Acta Metrologica Sinica，2017，38(3)：340-344.
[21] GUANGBIN Huang，QINYU Zhu，CHEEKHEONG S. Extreme learning machine：Theory and applications[J]. Neurocomputing，2006，70(1-3)：489-501.
[22] RASHEDI E，NEZAMABADI-POUR H，SARYAZDI S. GSA：A Gravitational search algorithm[J]. Information Sciences，2009，179(13)：2232-2248.
[23] 蔡改贫，赵小涛，张丹荣，等. 基于ASOS-ELM的湿式球磨机负荷软测量方法[J]. 振动. 测试与诊断，2020，40(1)：184-192，211. CAI Gaipin，ZHAO Xiaotao，ZHANG Danrong，et al. Soft measurement method of wet ball mill load based on ASOS-ELM[J]. Journal of Vibration，Measurement & Diagnosis，2020，40(1)：184-192，211.
[24] JINGSEN L，YUHAO X，YU L. A gravitational search algorithm with adaptive mixed mutation for function optimization[J]. International Journal of Performability Engineering，2018，14(4)：681-690.
[25] 姜媛媛，刘柱，罗慧，等. 锂电池剩余寿命的ELM间接预测方法[J]. 电子测量与仪器学报，2016，30(2)：179-185. JIANG Yuanyuan，LIU Zhu，LUO Hui，et al. ELM indirect prediction method for the remaining life of lithium-ion battery[J]. Journal of Electronic Measurement and Instrumentation，2016，30(2)：179-185.
[26] 邵良杉，李臣浩. 基于改进花粉算法的极限学习机分类模型[J]. 计算机工程与应用，2020，56(1)：172-179. SHAO Liangshan，LI Chenhao. Improved flower pollination algorithm extreme learning machine classification model[J]. Computer Engineering and Applications，2020，56(1)：172-179.
[27] 王瀛洲，倪裕隆，郑宇清，等. 基于ALO-SVR的锂离子电池剩余使用寿命预测[J]. 中国电机工程学报，2021，41(4)：1445-1457，1550. WANG Yingzhou，NI Yulong，ZHENG Yuqing，et al. Remaining useful life prediction of lithium-ion batteries based on support vector regression optimized and ant lion optimizations[J]. Proceedings of the CSEE，2021，41(4)：1445-1457，1550.
[28] WU Peihao，LYU Nawei，SONG Yuhang，et al. Li-ion battery failure warning methods for energy-storage systems[J]. Chinese Journal of Electrical Engineering，2024，10(1)：86-100.
[29] LI Kuijie，LI Yalun，RUI Xinyu，et al. Experimental study on the effect of state of charge on failure propagation characteristics within battery modules[J]. Chinese Journal of Electrical Engineering，2023，9(3)：3-14.
[30] LIU Z，SUN G，BU S，et al. Particle learning framework for estimating the remaining useful life of lithium-ion batteries[J]. IEEE Transactions on Instrumentation and Measurement，2016(99)：1-14.