改进PSO-RBF模型的分阶查表法荷电状态估计

doi:10.12028/j.issn.2095-4239.2019.0129

储能科学与技术 ›› 2019, Vol. 8 ›› Issue (6): 1190-1196.doi: 10.12028/j.issn.2095-4239.2019.0129

改进PSO-RBF模型的分阶查表法荷电状态估计

陈德海, 马原, 潘韦驰

江西理工大学电气工程与自动化学院, 江西赣州 341000

收稿日期:2019-06-11 修回日期:2019-08-07 出版日期:2019-11-01 发布日期:2019-11-01
通讯作者: 马原,硕士,研究方向为动力电池能量管理系统,E-mail:715663338@qq.com。
作者简介:陈德海(1978-),男,博士研究生,副教授,研究方向为动力电池能量管理系统及故障诊断技术,E-mail:643967664@qq.com
基金资助:
国家自然科学基金（61463020），江西省自然科学基金（20151BAB206034）项目。

Improved state-of-the-art look-up table method for charge state estimation of PSO-RBF model

CHEN Dehai, MA Yuan, PAN Weichi

School of Electrical Engineering and Automation, Jiangxi University of Science and Technology, Ganzhou 341000, Jiangxi, China

Received:2019-06-11 Revised:2019-08-07 Online:2019-11-01 Published:2019-11-01

摘要/Abstract

摘要： 为了解决纯电动汽车在SOC预测时易受电流波动、工况非线性等因素影响，提出了一种针对锂电池SOC进行动态预测的方法。首先，对粒子群聚类算法的参数组合进行优选并结合优选结果对径向基函数（RBF）神经网络进行改进。然后，通过分析电池在不同工作状态下的特性，将电池分为充电、静置、放电三个状态。针对电池所处的工作状态采取不同的策略对SOC进行预测。在电池放电阶段使用经过改进的PSO-RBF算法对SOC进行动态预测。在电池静置及充电状态使用二分查表法，将考虑温度漂移的开路电压曲线及充电时电流节点突变曲线制成二维数组表，利用制作的二维数组表对SOC的值进行修正。从而减小系统响应时间，同时预测提升精度。实验结果表明，该预测修正模型最大误差约为1.9%，验证了方法的有效性。

关键词: SOC, 粒子群算法, 径向基神经网络, 分阶段法

Abstract: In order to solve the problem that pure electric vehicles are susceptible to current fluctuations and non-linear conditions during SOC prediction, a method for dynamic prediction of lithium battery SOC is proposed. Firstly, the parameter combination of the particle swarm clustering algorithm is optimized and combined with the preferred results to improve the radial basis function (RBF) neural network. Then, by analyzing the characteristics of the battery under different working conditions, the battery is divided into charging and static. Set and discharge three states. Different strategies are used to predict the SOC for the working state of the battery. In the battery discharge phase, the improved PSO-RBF algorithm is used to dynamically predict the SOC. in the battery standing and charging state, the two-point look-up table method is used to make the open circuit voltage curve considering the temperature drift and the current node abrupt curve during charging into two dimensions. Array table, the value of SOC is corrected by using the created two-dimensional array table. Thereby reducing system response time while improving accuracy. The experimental results show that the maximum error of the prediction correction model is about 1.9%, which verifies the effectiveness of the method.

Key words: SOC, particle swarm optimization, radial basis neural network, staged method

中图分类号:

TM911

陈德海, 马原, 潘韦驰. 改进PSO-RBF模型的分阶查表法荷电状态估计[J]. 储能科学与技术, 2019, 8(6): 1190-1196.

CHEN Dehai, MA Yuan, PAN Weichi. Improved state-of-the-art look-up table method for charge state estimation of PSO-RBF model[J]. Energy Storage Science and Technology, 2019, 8(6): 1190-1196.

参考文献

[1] 武怿达,赵俊年,詹元杰,等.锂电池百篇论文点评(2018.10.1-2018.11.30)[J]. 储能科学与技术,2019, 8(1):14-25. WU Yida, ZHAO Junnian, ZHAN Yuanjie, et al. Reviews of selected 100 recent papers for lithium batteries(Oct. 12018 to Nov. 30, 2018)[J]. Energy Storage Science and Technology, 2019, 8(1):14-25.
[2] 杨云龙,徐自强,吴孟强,等.锂离子动力电池荷电状态联合估计[J]. 科学技术与工程,2018, 18(22):60-65. YANG Yunlong,XU Ziqiang, WU Mengqiang,et al. Joint estimation of state-of-charge for lithium ion power battery[J]. Science Technology and Engineering, 2019, 8(1):14-25.
[3] 张持健,陈航.锂电池SOC预测方法综述[J].电源技术,2016, 40(6):1318-1320. ZHANG Chijian, CHEN Hang. Review of state of charge estimation methods for lithium battery[J]. Chinese Journal of Power Sources, 2016, 40(6):1318-1320.
[4] 欧阳剑,李迪,刘俊城.电动汽车车用动力电池荷电状态估算方法研究综述[J]. 机电工程技术,2016, 45(1):52-56. OUYANG jian, LI Di, LIU Juncheng. The overview of research of power battery SOC estimation methods use for electric vehicle[J]. Mechanical & Electrical Engineering Technology, 2016, 45(1):52-56.
[5] 张方亮,黄泽波,李占锋.不同放电倍率下锂电池SOC估算分析研究[J].机械设计与制造,2018(6):262-265. ZHANG Fangliang, HUANG Zebo, LI Zhanfeng. The analysis of lithium battery soc estimation under different discharge rate[J].Machinery Design & Manufacture, 2018(6):262-265.
[6] 程泽, 杨磊, 孙幸勉. 基于自适应平方根无迹卡尔曼滤波算法的锂离子电池SOC和SOH估计[J]. 中国电机工程学报, 2018:doi:10.13334/j.0258-8013.pcsee.170992. CHENG Ze, YANG Lei, SUN Xingmian. State of charge and state of health estimation of Li-ion batteries based on adaptive square-root Unscented Kalman filters[J]. Proceedings of the CSEE, 2018:doi:10.13334/j.0258-8013.pcsee.170992.
[7] 罗勇, 赵小帅, 祁朋伟, 等. 车用动力电池二阶RC建模及参数辨识[J]. 储能科学与技术, 2019, 8(4):738-744. LUO Yong, ZHAO Xiaoshuai, QI Pengwei, et al. Second-order RC modeling and parameter identification of electric vehicle power battery[J]. Energy Storage Science and Technology, 2019, 8(4):738-744.
[8] 梁奇. 基于无迹卡尔曼滤波的锂电池SOC估算[D]. 绵阳:西南科技大学, 2018. LIANG Qi. SOC estimation of lithium battery based on Unscented Kalman filter[D]. Mianyang:Southwest University of Science and Technology, 2018.
[9] LEE K T, DAI M J, CHUANG C C, Temperature-compensated model for lithium-ion polymer batteries with extended Kalman filter state-ofcharge estimation for an implantable charger[J]. IEEE Transactions on Industrial Electronics, 2017(99):1.
[10] CHAOUI H, MEJDOUBI A E, OUKAOUR A, et al. State of charge estimation of LiFePO₄ batteries with temperature variations using neural networks[J]. IEEE International Symposium on Industrial Electronics, 2016.
[11] MSH Lipu, HUSSAIN A, SAAD M H, et al. Improved recurrent NARX neural network model for state of charge estimation of lithiumion battery using pso algorithm[J]. IEEE Symposium on Computer Applications & Industrial Electronics, 2018:354-359.
[12] 赵钢, 朱芳欣, 窦汝振. 基于PSO-BP的电动汽车锂离子电池SOC估算[J]. 电源技术, 2018, 42(9):1318-1320. ZHAO Gang, ZHU Fangxin, DOU Ruzhen. SOC estimation of lithium battery for electric vehicle based on PSO-BP neural network[J]. Chinese Journal of Power Sources, 2018, 42(9):1318-1320.
[13] 陈德海, 任永昌, 黄艳国, 等. 基于改进PSO-RBF算法的纯电动汽车剩余里程实时预测[J]. 汽车工程, 2018, 40(7):764-769. CHEN Dehai, REN Yongchang, HUANG Yanguo, et al. Real time prediction for remaining mileage of battery electric vehicle based on modified PSO-RBF algorithm[J]. Automotive Engineering, 2018, 40(7):764-769.
[14] 薛萍, 宋岩亮. 改进蚁群算法与BP网络融合预测铅酸蓄电池SOC[J]. 哈尔滨理工大学学报, 2016, 21(6):95-99. XUE Ping, SONG Yanliang. The prediction of lead-acid battery remaining capacity based on improved ant colony algorithm and bp network[J]. Journal of Harbin University of Science and Technology, 2016, 21(6):95-99.
[15] 谢文强. 遗传算法优化BP网络的锂电池剩余容量预测[J]. 仪表技术, 2019(1):35-37. XIE Wenqiang. A GA-based optimal algorithm for the bp network for forecasting remaining capacity of the lithium battery[J]. Instrument Technology, 2019(1):35-37.
[16] 陈德海, 华铭, 徐王娟, 等. 基于二分法查找-伪循环次数法的动力电池健康状态实时预测[J]. 汽车技术, 2019(4):29-33. CHEN Dehai, HUA Ming, XU Wangjuan, et al. Real-time prediction of power battery SOH based on dichotomy searching pseudo-cyclic number method[J]. Automotive Technology, 2019(4):29-33.
[17] 高云龙, 闫鹏. 基于多种群粒子群算法和布谷鸟搜索的联合寻优算法[J]. 控制与决策, 2016, 31(4):601-608. GAO Yunlong, YAN Peng. Unified optimization based on multi-swarm PSO algorithm and cuckoo search algorithm[J]. Control and Decision, 2016, 31(4):601-608.
[18] 王东风, 孟丽.粒子群优化算法的性能分析和参数选择[J]. 自动化学报, 2016(10):1552-1561. WANG Dongfeng, MENG Li. Performance analysis and parameter selection of PSO algorithms[J]. Acta Automatica Sinica, 2016(10):1552-1561.

改进PSO-RBF模型的分阶查表法荷电状态估计

Improved state-of-the-art look-up table method for charge state estimation of PSO-RBF model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	田峰, 程志江, 杨涵棣, 杨天翔. 模块化多电平复合变换器电池储能系统容错控制策略[J]. 储能科学与技术, 2022, 11(5): 1583-1591.
[2]	郭斌, 邢洁, 姚飞, 景小敏. 基于双层规划模型的用户侧混合储能优化配置[J]. 储能科学与技术, 2022, 11(2): 615-622.
[3]	孙爱芬, 赤娜. 基于改进的高斯过程回归的SOC估计算法[J]. 储能科学与技术, 2022, 11(1): 253-257.
[4]	罗恒, 严晓, 王钦, 胡波. 充电场站光储充控制策略[J]. 储能科学与技术, 2022, 11(1): 275-282.
[5]	谢克桓, 李传常, 陈荐, 余龙海, 谭准, 秦位海. 全钒液流电池储能仿真模型及荷电状态监测方法研究[J]. 储能科学与技术, 2021, 10(6): 2363-2372.
[6]	朱奕楠, 吕桃林, 赵芝芸, 杨文. 基于并行卡尔曼滤波器的锂离子电池荷电状态估计[J]. 储能科学与技术, 2021, 10(6): 2352-2362.
[7]	朱磊, 刘子博, 李路路, 潘庭龙, 杨玮林. 基于RLS-DLUKF算法的锂电池SOC预测方法研究[J]. 储能科学与技术, 2021, 10(3): 1137-1144.
[8]	付诗意, 吕桃林, 闵凡奇, 罗伟林, 罗承东, 吴磊, 解晶莹. 电动汽车用锂离子电池SOC估算方法综述[J]. 储能科学与技术, 2021, 10(3): 1127-1136.
[9]	朱元富, 贺文武, 李建兴, 李有财, 李培强. 基于Bi-LSTM/Bi-GRU循环神经网络的锂电池SOC估计[J]. 储能科学与技术, 2021, 10(3): 1163-1176.
[10]	杜帮华, 张宇, 吴铁洲, 何衍林, 李子龙. 梯次利用锂离子电池等效模型参数在线辨识方法[J]. 储能科学与技术, 2021, 10(1): 342-348.
[11]	张远进, 吴华伟, 叶从进. 基于AUKF-BP神经网络的锂电池SOC估算[J]. 储能科学与技术, 2021, 10(1): 237-241.
[12]	陈峥, 李磊磊, 舒星, 沈世全, 刘永刚, 申江卫. 基于特征处理与径向基神经网络的锂电池剩余容量估算方法[J]. 储能科学与技术, 2021, 10(1): 261-270.
[13]	王一全, 黄碧雄, 严晓, 刘新田, 王影, 刘双宇, 徐华源. 基于LSTM-DaNN的动力电池SOC估算方法[J]. 储能科学与技术, 2020, 9(6): 1969-1975.
[14]	何瑛, 钟根鹏, 陈翌. 基于特征组合堆叠融合集成学习的锂离子动力电池SOC估算[J]. 储能科学与技术, 2020, 9(5): 1548-1557.
[15]	郑涛, 张里, 侯杨成, 陈薇. 基于自适应CKF的老化锂电池SOC估计[J]. 储能科学与技术, 2020, 9(4): 1193-1199.