基于高斯过程回归的UKF锂离子电池SOC估计

doi:10.19799/j.cnki.2095-4239.2020.0003

储能科学与技术 ›› 2020, Vol. 9 ›› Issue (4): 1206-1213.doi: 10.19799/j.cnki.2095-4239.2020.0003

基于高斯过程回归的UKF锂离子电池SOC估计

魏孟¹(), 李嘉波¹, 李忠玉², 叶敏¹(), 徐信芯¹

^1.长安大学公路养护装备国家工程实验室，陕西西安 710064
^2.河南省高远公路养护技术有限公司，河南新乡 453000

收稿日期:2020-01-05 修回日期:2020-01-15 出版日期:2020-07-05 发布日期:2020-06-30
通讯作者: 叶敏 E-mail:wm13484520242@163.com;minye@chd.cn
作者简介:魏孟（1997—），男，博士研究生，研究方向为新能源汽车，E-mail：wm13484520242@163.com；联系人：
基金资助:
国家自然科学基金青年项目(51805041);河南省交通运输厅科技计划项目(2019J3)

SOC estimation of Li-ion batteries based on Gaussian process regression and UKF

WEI"Meng¹(), LI"Jiabo¹, LI"Zhongyu², YE"Min¹(), XU"Xinxin¹

^1.Highway Maintenance Equipment National Engineering Laboratory, Changan University, Xi’an 710064, Shaanxi, China
^2.Henan Gaoyuan Highway Maintenance Technology Co. Ltd. , Xinxiang 453000, Henan, China

Received:2020-01-05 Revised:2020-01-15 Online:2020-07-05 Published:2020-06-30
Contact: Min YE E-mail:wm13484520242@163.com;minye@chd.cn

摘要/Abstract

摘要：

高精度的电池荷电状态估计是电动汽车电池管理系统的关键技术之一，其估计精度直接影响能量管理效率和汽车的续航里程。传统的滤波方法基于模型来估计电池SOC，但难以建立锂离子电池精确的数学模型。针对此问题，提出一种基于高斯过程回归的无迹卡尔曼滤波(UKF)锂离子电池SOC估计方法，使用高斯过程回归在有限的训练数据下建立等效电路模型的测量方程，在UKF和高斯过程回归之间建立关联。该模型能够充分联合利用现有实验数据和被预测实时状态数据，实现SOC估计。结果表明，与传统UKF相比，基于高斯过程回归的UKF算法具有较高精确性。

关键词: 动力电池, 荷电状态, 高斯过程回归, UKF

Abstract:

The high-precision state-of-charge (SOC) estimation of battery power capacity is the key technology associated with a battery management system, and its estimation accuracy directly influences the energy management efficiency and endurance mileage of electric vehicles. The traditional filter estimation method uses an estimation model and does not consider the accuracy model of a Li-ion battery. To solve this problem, an unscented Kalman filter (UKF) estimation method based on Gaussian process regression (GPR) is presented. GPR can be used to establish a measurement equation for an equivalent circuit model with limited training data, resulting in the connection of UKF and GPR. The proposed model optimally uses the data obtained via the tests and the current to estimate the SOC. The experimental results and comparative analysis of the UKF estimation method based on Gaussian process regression demonstrate the high prediction accuracy of the proposed algorithm during SOC estimation.

Key words: power battery, state of charge, Gaussian process regression, UKF

中图分类号:

TM 911

魏孟, 李嘉波, 李忠玉, 叶敏, 徐信芯. 基于高斯过程回归的UKF锂离子电池SOC估计[J]. 储能科学与技术, 2020, 9(4): 1206-1213.

WEI Meng, LI Jiabo, LI Zhongyu, YE Min, XU Xinxin. SOC estimation of Li-ion batteries based on Gaussian process regression and UKF[J]. Energy Storage Science and Technology, 2020, 9(4): 1206-1213.

图/表 19

图1

表1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

图12

图13

图14

图15

图16

图17

表2

参考文献 16

1	LI Y W, WANG C, GONG J F. A wavelet transform-adaptive unscented Kalman filter approach for state of charge estimation of LiFePO₄ battery[J]. International Journal of Energy Research, 2018, 42(11)： doi: 10.1002/er.3842.
2	LI B, BEI S. Estimation algorithm research for lithium battery SOC in electric vehicles based on adaptive unscented Kalman filter[J]. Neural Computing and Applications, 2019, 31: 8171-8183.
3	GUANG Zhong, ZONG Hai, JING Wei, et al. An online model-based method for state of energy estimation of lithium-ion batteries using dual filters[J]. Journal of Power Sources, 2016, 301: 277-286.
4	OZCAN G, PAJOVIC M, SAHINOGLU Z, et al. Online battery state-of-charge estimation based on sparse gaussian process regression[C]//2016 IEEE Power and Energy Society General Meeting (PESGM)， IEEE, 2016.
5	MENG J, LUO G, GAO F. Lithium polymer battery state-of-charge estimation based on adaptive unscented Kalman filter and support vector machine[J]. IEEE Transactions on Power Electronics, 2015， 31(3): 1.
6	宁博, 徐俊, 曹秉刚, 等. 采用等效电路的参数自适应电池模型及电池荷电状态估计方法[J].西安交通大学学报, 2015, 49(10): 67-71.
	NING B, XU J, CAO B G, et al. A battery model with adaptive parameters based on equivalent circuit for state of charge estimation [J]. Journal of Xi 'an Jiaotong University, 2015, 49(10): 67-71.
7	颜湘武,邓浩然, 郭琪, 等. 基于自适应无迹卡尔曼滤波的动力电池健康状态检测及梯次利用研究[J].电工技术学报, 2019, 34(18): 3937-3948.
	YAN X W, DENG H R, GUO Q, et al. Study on the state of health detection of power batteries based on adaptive unscented Kalman filters and the battery echelon utilization[J]. Transactions of China Electrotechnical Society, 2019, 34(18): 3937-3948.
8	安治国, 田茂飞, 赵琳, 等. 基于自适应无迹卡尔曼滤波的锂电池SOC估计[J]. 储能科学与技术, 2019, 8(5): 856-861.
	AN Z G, TIAN M F, ZHAO L, et al. SOC estimation of lithium battery based on adaptive untracked Kalman filter[J]. Energy Storage Science and Technology, 2019, 8(5): 856-861.
9	刘伟龙, 王丽芳, 廖承林, 等. 基于模型融合与自适应无迹卡尔曼滤波算法的锂离子电池SOC估计[J]. 汽车工程, 2017, 39(9): 997-1003.
	LIU W L, WANG L F, LIAO C L, et al. Estimation of Li-ion battery SOC based on model fusion and adaptive unscented Kalman filtering algorithm[J]. Automotive Engineering, 2017, 39(9): 997-1003.
10	魏克新, 陈峭岩. 基于自适应无迹卡尔曼滤波算法的锂离子动力电池状态估计[J]. 中国电机工程学报, 2014, 34(3): 445-452.
	WEI K X, CHEN Q Y. States estimation of Li-ion power batteries based on adaptive unscented Kalman filters [J]. Proceedings of the CSEE, 2014, 34(3): 445-452.
11	YUE L, CHATTOPADHYAY P, XIONG S, et al. Dynamic data-driven and model-based recursive analysis for estimation of battery state-of-charge[J]. Applied Energy, 2016, 184: 266-275.
12	CHENG C, RUI X, SHEN W. A lithium-ion battery-in-the-loop approach to test and validate multi-scale dual H infinity filters for state of charge and capacity estimation[J]. IEEE Transactions on Power Electronics, 2018(99): 1.
13	苏振浩, 李晓杰, 秦晋, 等. 基于BP人工神经网络模型的动力电池SOC估计方法[J]. 储能科学与技术, 2019, 8(5): 868-873.
	SU Z H, LI X J, QIN J, et al. SOC estimation method of power battery based on BP artificial neural network [J]. Energy Storage Science and Technology, 2019, 8(5): 868-873.
14	戴庚, 耿诗尧.基于最小二乘支持向量机的SOC估计方法[J].信息与电脑(理论版), 2018, 396(2): 36-37.
	DAI G, GENG S Y. SOC estimation based on least aquares support vector machines[J].China Computer & Communication, 2018, 396(2): 36-37.
15	李嘉波, 魏孟, 叶敏, 等. 基于高斯过程回归的锂离子电池SOC估计[J]. 储能科学与技术, 2020, 9(1): 131-137.
	LI J B, WEI M, YE M, et al. SOC estimation of lithium-ion batteries based on gauss process regression[J]. Energy Storage Science and Technology, 2020, 9(1): 131-137.
16	叶文, 蔡晨光, 杨平, 等. 融合高斯过程回归的UKF估计方法[J]. 北京航空航天大学学报, 2019, 45(6): 1081-1087.
	YE W, CAI C G, YANG P, et al. UKF estimation method incorporating Gaussian process regression[J]. Journal of Beijing University of Aeronautics and Astronautics, 2019, 45(6): 1081-1087.

SOC/%	R₀	R₁	R₂	C₁	C₂
10	0.0249	0.0189	0.0038	481.13	27.797
20	0.0217	0.0142	0.0067	637.41	21.198
30	0.0249	0.0126	0.0037	610.7	17.04
40	0.0243	0.0119	0.0046	629.43	16.709
50	0.0246	0.0146	0.0051	741.15	17.825
60	0.0237	0.0125	0.0055	622.14	14.426
70	0.0263	0.0139	0.0043	600.09	13.872
80	0.0246	0.0152	0.0043	438.51	15.042
90	0.028	0.016	0.0043	516.05	28.705
100	0.263	0.0161	0.0043	477.78	28.705

方法	RMSE/%	MAPE/%
UKF (UDDS)	1.93	2.50
GPR-UKF (UDDS)	1.57	2.24
UKF (DST)	1.81	3.73
GPR-UKF (DST)	1.48	3.52

[1]	吴田, 林闽城, 海浩, 孙海渔, 温兆银, 马福元. 面向一次调频的镍氢电池系统开发[J]. 储能科学与技术, 2022, 11(7): 2213-2221.
[2]	常泽宇, 张之琦, 张晓东, 李丽, 郁亚娟. 基于数据驱动的动力电池健康状态评估平台[J]. 储能科学与技术, 2022, 11(6): 1847-1853.
[3]	周伟, 符冬菊, 刘伟峰, 陈建军, 胡照, 曾燮榕. 废旧磷酸铁锂动力电池回收利用研究进展[J]. 储能科学与技术, 2022, 11(6): 1854-1864.
[4]	张孝远, 张金浩, 蒋亚俊. 基于改进TCN模型的动力电池健康状态评估[J]. 储能科学与技术, 2022, 11(5): 1617-1626.
[5]	王芳, 王峥, 林春景, 张国振, 张贵平, 马天翼, 刘磊, 刘仕强. 新能源汽车动力电池安全失效潜在原因分析[J]. 储能科学与技术, 2022, 11(5): 1411-1418.
[6]	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.
[7]	王苏杭, 李建林, 李雅欣, 熊俊杰, 曾伟. 锂离子电池系统低温充电策略[J]. 储能科学与技术, 2022, 11(5): 1537-1542.
[8]	刘春辉, 任宏斌. 基于SOC的动力电池组主动均衡研究[J]. 储能科学与技术, 2022, 11(2): 667-672.
[9]	黄鹏超, 鄂加强. 基于双自适应卡尔曼滤波的锂电池状态估算[J]. 储能科学与技术, 2022, 11(2): 660-666.
[10]	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.
[11]	马天翼, 王伟哲, 林春景, 白广利, 韦振, 刘仕强. 磷酸铁锂电池多阶段利用可行性[J]. 储能科学与技术, 2022, 11(1): 119-126.
[12]	王帅, 马鸿雁, 窦嘉铭, 张英达, 李晟延, 胡璐锦. 基于UGOA-BP的锂电池SOC估算[J]. 储能科学与技术, 2022, 11(1): 258-264.
[13]	高晓芝, 王磊, 田晋, 刘佳璐, 刘庆华. 基于参数优化变分模态分解的混合储能功率分配策略[J]. 储能科学与技术, 2022, 11(1): 147-155.
[14]	胡建, 林春景, 郝维健, 郑天雷. 动力电池标准体系建设现状及建议[J]. 储能科学与技术, 2022, 11(1): 313-320.
[15]	曹新宇, 彭飞, 李立伟, 尹建光. 基于IBAS-NARX神经网络的锂电池荷电状态估计[J]. 储能科学与技术, 2021, 10(6): 2342-2351.

基于高斯过程回归的UKF锂离子电池SOC估计

SOC estimation of Li-ion batteries based on Gaussian process regression and UKF

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 19

参考文献 16

相关文章 15

编辑推荐

Metrics

本文评价