基于EKF-SVM算法的动力电池SOC估计*

doi:10.19562/j.chinasae.qcgc.2020.11.010

摘要/Abstract

摘要： 针对单一SOC估计算法无法同时满足多项指标要求的问题,提出一种扩展卡尔曼滤波(EKF)与支持向量机(SVM)相结合的算法。通过动态跟踪模型参数和对开路电压(OCV)的实时估计,由EKF算法得到初步SOC估计值;通过对EKF算法滤波输出的DST工况数据进行训练,得到SVM模型,并利用其回归预测能力对初步估计值进行误差补偿,进一步地降低了估计误差。仿真结果表明,相比EKF算法和EKF-BP算法,所提EKF-SVM算法具有良好鲁棒性和泛化性,可实现电池SOC的准确估计,其最大绝对误差为1%左右。

关键词: 锂离子电池, 荷电状态, 扩展卡尔曼滤波, 支持向量机, 组合算法

Abstract: In view of that　the single SOC estimation algorithm cannot concurrently meet the requirements of multi-indicators, an algorithm combining the extended Kalman filtering (EKF) and support vector machine (SVM) is proposed. By dynamically tracking the model parameters and estimating the open-circuit voltage in real-time, the preliminary SOC estimation is obtained by using EKF algorithm. Furthermore, by training the DST condition data output from EKF algorithm, SVM model is obtained and its regression prediction ability is utilized to perform error compensation on preliminary estimation, further reducing the error of SOC estimation. The results of simulation show that compared with EKF and EKF-BP algorithms,the proposed EKF-SVM algorithm has better robustness and adaptability and can achieve accurate estimation of battery SOC,with the maximum absolute error of about 1%

Key words: lithium-ion battery, SOC, extended Kalman filtering, support vector machine, combination algorithm

刘兴涛, 李坤, 武骥, 何耀, 刘新天. 基于EKF-SVM算法的动力电池SOC估计^*[J]. 汽车工程, 2020, 42(11): 1522-1528.

Liu Xingtao, Li Kun, Wu Ji, He Yao, Liu Xintian. State of Charge Estimation for Traction Battery Based on EKF-SVM Algorithm[J]. Automotive Engineering, 2020, 42(11): 1522-1528.

参考文献

[1] CHEN X, LEI H, XIONG R, et al. A novel approach to reconstr-uct open circuit voltage for state of charge estimation of lithium ion batteries in electric vehicles[J]. Applied Energy, 2019, 255:341-348.
[2] 陈宗海, 钟良, 何耀, 等. 基于充电方式的锂电池SOC校准和估计方法[J]. 控制与决策, 2014, 29(6):1148-1152.
CHEN Zonghai, ZHONG Liang, HE Yao, et al. Lithium battery SOC calibration and estimation method based on charging method[J]. Control and Decision, 2014, 29(6):1148-1152.
[3] XIONG R, YU Q, LIN C. A novel method to obtain the open circuit voltage for the state of charge of lithium ion batteries in electric vehicles by using H infinity filter[J]. Applied Energy, 2017, 207:346-353.
[4] 刘东, 黄碧雄, 王一全, 等. 锂电池SOC拐点修正安时积分实时估算方法[J]. 储能科学与技术, 2019,8(5):850-855.
LIU Dong, HUANG Bixiong, WANG Yiquan, et al. Real-time estimation method of lithium battery SOC inflection point corrected ampere-hour integral[J]. Energy Storage Science and Technology, 2019,8(5):850-855.
[5] 刘新天, 李涵琪, 魏增福, 等. 基于Drift-Ah积分法的 CKF 估算锂电池SOC[J]. 控制与决策, 2019, 34(3):535-541.
LIU Xintian, LI Hanqi, WEI Zengfu, et al. CKF estimation of lithium battery SOC based on Drift-Ah integral method[J]. Control and Decision, 2019, 34(3):535-541.
[6] GUO Y, ZHAO Z, HUANG L. SOC estimation of Lithium battery based on improved BP neural network[J]. Energy Procedia, 2017, 105:4153-4158.
[7] GUO N, FANG Y, TIAN Z, et al. Research on SOC fuzzy weight-ed algorithm based on GA-BP neural network and ampere integral method[J]. The Journal of Engineering, 2019, 19(15):576-580.
[8] ANTÓN J C Á, NIETO P J G, de COS JUEZ F J, et al. Battery state-of-charge estimator using the SVM technique[J]. Applied Mathematical Modelling, 2013, 37(9):6244-6253.
[9] CHENG B, BAI Z, CAO B. State of charge estimation based on evolutionary neural network[J]. Energy Conversion & Management, 2008, 49(10):2788-2794.
[10] 杨海学, 张继业, 张晗. 基于改进Sage-Husa的自适应无迹卡尔曼滤波的锂离子电池SOC估计[J]. 电工电能新技术, 2016, 35(1):30-35.
YANG Haixue, ZHANG Jiye, ZHANG Han. Lithium-ion battery SOC estimation based on improved Sage-Husa adaptive unscented Kalman filter[J]. Advanced Technology of Electrical Engineering and Energy, 2016, 35(1):30-35.
[11] 谈发明, 赵俊杰, 王琪. 动力电池SOC估计的一种新型鲁棒 UKF算法[J]. 汽车工程, 2019, 41(8):944-952.
TAN Faming, ZHAO Junjie, WANG Qi. A new robust UKF algorithm for power battery SOC estimation[J]. Automotive Engineering, 2019, 41(8):944-952.
[12] 刘新天, 刘兴涛, 何耀, 等. 基于V_min-EKF 的动力锂电池组 SOC 估计[J]. 控制与决策, 2010, 25(3):445-448.
LIU Xintian, LIU Xingtao, HE Yao, et al. SOC estimation of power lithium battery pack based on V_min-EKF[J]. Control and Decision, 2010, 25(3):445-448.
[13] WANG Q, KANG J, TAN Z, et al. An online method to simultaneously identify the parameters and estimate states for lithium ion batteries[J]. Electrochimica Acta, 2018, 289:376-388.
[14] CHEN X, SHEN W, CAO Z, et al. A novel approach for state of charge estimation based on adaptive switching gain sliding mode observer in electric vehicles[J]. Journal of Power Sources, 2014, 246:667-678.
[15] MA Y, LI B, XIE Y, et al. Estimating the state of charge of lithium-ion battery based on sliding mode observer[J]. IFAC-Papers Online, 2016, 49(11):54-61.
[16] 皮钒, 王耀南, 孟步敏. 基于扩展 PSO 和离散 PI 观测器的电池 SOC估计[J]. 电子测量与仪器学报, 2016, 30(1):11- 19.
PI Fan, WANG Yaonan, MENG Bumin. Battery SOC estimation based on extended PSO and discrete PI observer[J]. Journal of Electronic Measurement and Instrument, 2016, 30(1):11-19.
[17] LAI X, ZHENG Y, SUN T. A comparative study of different equivalent circuit models for estimating state-of-charge of lithium-ion batteries[J]. Electrochimica Acta, 2018, 259:566-577.
[18] 孔祥创, 赵万忠, 王春燕. 基于BP-EKF算法的锂电池 SOC 联合估计[J]. 汽车工程, 2017, 39(6):648-652.
KONG Xiangchuang, ZHAO Wanzhong, WANG Chunyan. Joint estimation of lithium battery SOC based on BP-EKF algorithm[J]. Automotive Engineering, 2017, 39(6):648-652.
[19] LI Z, Xiong R, MU H, et al. A novel parameter and state-of-charge determining method of lithium-ion battery for electric vehicles[J]. Applied Energy, 2017, 207:363-371.
[20] 朱江, 张伟, 马嵩. 基于在线支持向量回归的锂离子电池 SOC 估计[J]. 电源技术, 2019,43(10):1611-1614.
ZHU Jiang, ZHANG Wei, MA Song. Lithium-ion battery SOC estimation based on online support vector regression[J]. Chinese Journal of Power Sources, 2019,43(10):1611-1614.
[21] 刘志强, 吴雪刚, 倪捷, 等. 基于 HMM 和 SVM 级联算法的驾驶意图识别[J]. 汽车工程, 2018,40(7):858-864.
LIU Zhiqiang, WU Xuegang, NI Jie, et al. Driving intention recognition based on the cascade algorithm of HMM and SVM[J]. Automotive Engineering, 2018,40(7):858-864.
[22] ANTON J C A, NIETO P J G, VIEJO C B, et al. Support vector machines used to estimate the battery state of charge[J]. IEEE Transactions on Power Electronics, 2013, 28(12):5919-5926.
[23] ZHENG F, XING Y, JIANG J, et al. Influence of different open circuit voltage tests on state of charge online estimation for lithium-ion batteries[J]. Applied Energy, 2016, 183:513-525.

基于EKF-SVM算法的动力电池SOC估计^*

State of Charge Estimation for Traction Battery Based on EKF-SVM Algorithm

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 10

[1]	张念忠,宋强,王冠峰,王明生. 车用永磁同步电机无电流传感器控制研究[J]. 汽车工程, 2024, 46(2): 281-289.
[2]	陈飞,孔祥栋,孙跃东,韩雪冰,卢兰光,郑岳久,欧阳明高. 锂离子电池制造工艺仿真技术进展[J]. 汽车工程, 2023, 45(9): 1516-1529.
[3]	胡明辉,朱广曜,刘长贺,唐国峰. 考虑迟滞特性的卡尔曼滤波和门控循环单元神经网络的锂离子电池SOC联合估计[J]. 汽车工程, 2023, 45(9): 1688-1701.
[4]	梁海强,何洪文,代康伟,庞博,王鹏. 融合经验老化模型和机理模型的电动汽车锂离子电池寿命预测方法研究[J]. 汽车工程, 2023, 45(5): 825-835.
[5]	王春,唐滔,张永志. 考虑环境温度影响的超级电容SOC加权融合估计方法[J]. 汽车工程, 2023, 45(4): 627-636.
[6]	廉玉波,凌和平,马晴婵,任强,贺斌. 电动汽车锂离子电池脉冲加热技术研究进展[J]. 汽车工程, 2023, 45(2): 169-174.
[7]	吕又付,罗卫明,陈荐,吴锡鸿,李传常. 分层优化测定锂离子电池比热容参数的实验研究[J]. 汽车工程, 2023, 45(2): 183-190.
[8]	张健豪,高兴奇,张莉. 基于容量增量曲线与充电容量差的电池组微短路诊断方法[J]. 汽车工程, 2023, 45(2): 191-198.
[9]	李贵敬,谷青锴,杨昊鑫,黄健齐,邸立明. PA/EG耦合风冷电池热管理系统轻量研究[J]. 汽车工程, 2023, 45(2): 209-218.
[10]	王萍,弓清瑞,程泽,张吉昂. 基于AUKF的锂离子电池SOC估计方法[J]. 汽车工程, 2022, 44(7): 1080-1088.
[11]	彭宇明,袁明晓,敬卓鑫,张永林,黄港. 汇流排产热影响下的电池模组冷却系统改进设计[J]. 汽车工程, 2022, 44(6): 859-867.
[12]	毕贵红,谢旭,蔡子龙,骆钊,陈臣鹏,赵鑫. 动态条件下基于深度学习的锂电池容量估计[J]. 汽车工程, 2022, 44(6): 868-878.
[13]	张哲雨,吕超,李景行,熊光明,吴绍斌,龚建伟. 基于车辆视角数据的行人轨迹预测与风险等级评定[J]. 汽车工程, 2022, 44(5): 675-683.
[14]	马彦,李佳怡,马乾,陈明超. 基于迭代动态规划的动力电池组热管理优化策略[J]. 汽车工程, 2022, 44(5): 709-721.
[15]	刘首彤,黄沛丰,白中浩. 锂离子电池机械滥用失效机理及仿真模型研究进展[J]. 汽车工程, 2022, 44(4): 465-475.