SOC estimation algorithm based on improved Gaussian process regression

doi:10.19799/j.cnki.2095-4239.2021.0297

Abstract

Abstract:

A data-driven method based on Gaussian process regression (GPR) machine learning is adopted herein to improve the estimation accuracy of the state of charge (SOC) of lithium-ion batteries. The current and the voltage measured by the battery are taken as the input vectors of the model, while the SOC is taken as the output vector of the model for model training. The GPR model is improved to improve the model accuracy. The SOC-estimated values are then added to the moving window and used as the input vectors together with the current and the voltage. A high-precision SOC estimation model is trained by updating the training set with the window size. Compared with the GPR, least square support vector machine, support vector machine, and neural network, the root mean square error of the SOC estimated by the proposed model is controlled within 1.5%, verifying the effectiveness of the proposed method.

Key words: SOC, gauss process regression, voltage, current

CLC Number:

TM 911

Aifen SUN, Na CHI. SOC estimation algorithm based on improved Gaussian process regression[J]. Energy Storage Science and Technology, 2022, 11(1): 253-257.

Figures/Tables 11

Fig. 1

Table 1

SOC estimation algorithm based on GPR framework"

算法1：GPR算法SOC估计流程

Step1. 选择工况获取训练集D(X,y)，X包括电池参数的测量值电压和电流，y表示相应的SOC

Step2. 将选择的数据进行归一化处理

Step3. 选择协方差函数，并将相应的超参数 $θ$ 完成初始化。

Step4. 使用共轭梯度法求解对数似然函数，获取最优超参数值

Step5. 验证模型：给定预测的输入x，获得相应的估计值，

$μ ε = k ε T K + σ n 2 I - 1 y$

$∑ ε = σ n 2 + k ε ε - k ε T K + σ n 2 I - 1 k ε$

其中 $μ ε$ 为SOC的估计值。

Table 1

Fig. 2

Table 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Fig. 8

Table 3

References 10

1	张小利, 王玥童, 夏金松, 等. 基于改进的CDKF锂电池SOC估计方法[J]. 储能科学与技术, 2021, 10(4): 1454-1462.
	ZHANG X L, WANG Y T, XIA J S, et al. Estimation of the SOC of lithium batteries based on an improved CDKF algorithm[J]. Energy Storage Science and Technology, 2021, 10(4): 1454-1462.
2	吴海东, 任晓明, 那伟, 等. 改进安时法结合神经网络估算锂离子电池SOC[J]. 电池, 2016, 46(1): 16-19.
	WU H D, REN X M, NA W, et al. Estimating SOC of Li-ion battery by improved AH combined with neural network[J]. Battery Bimonthly, 2016, 46(1): 16-19.
3	邹琳, 刘佳俊, 马国庆, 等. 基于双无迹卡尔曼滤波的锂电池SOC估算[J]. 电源技术, 2021, 45(4): 450-454.
	ZOU L, LIU J J, MA G Q, et al. Estimation of state of charge of lithium battery based on dual unscented Kalman filter[J]. Chinese Journal of Power Sources, 2021, 45(4): 450-454.
4	齐延兴, 杨雪银, 王增玉. 基于STM32的蓄电池内阻测量系统设计[J]. 汽车实用技术, 2021, 46(2): 41-43.
	QI Y X, YANG X Y, WANG Z Y. Design of battery internal resistance measurement system based on STM32[J]. Automobile Applied Technology, 2021, 46(2): 41-43.
5	HUANG Z J, FANG Y S, XU J J. SOC estimation of Li-ion battery based on improved EKF algorithm[J]. International Journal of Automotive Technology, 2021, 22(2): 335-340.
6	孙万里. 基于EKF算法的车载电池SOC估算研究[J]. 电子测试, 2021(9): 59-60.
	SUN W L. Research on SOC estimation of vehicle battery based on EKF algorithm[J]. Electronic Test, 2021(9): 59-60.
7	李岩, 韩志刚, 蒋乙未, 等. 基于改进UKF算法的锂电池SOC精准估算[J]. 传感器与微系统, 2021, 40(6): 126-128, 132.
	LI Y, HAN Z G, JIANG Y W, et al. Accurate estimation of lithium battery SOC based on improved UKF algorithm[J]. Transducer and Microsystem Technologies, 2021, 40(6): 126-128, 132.
8	TALHA M, ASGHAR F, KIM S H. A neural network-based robust online SOC and SOH estimation for sealed lead-acid batteries in renewable systems[J]. Arabian Journal for Science and Engineering, 2019, 44(3): 1869-1881.
9	ZHANG L, LI K, DU D J, et al. A sparse least squares support vector machine used for SOC estimation of Li-ion batteries[J]. IFAC-PapersOnLine, 2019, 52(11): 256-261.
10	李超然, 肖飞, 樊亚翔, 等. 基于高斯过程回归的锂电池SOC估算方法[J]. 海军工程大学学报, 2021, 33(1): 55-59.
	LI C R, XIAO F, FAN Y X, et al. State of charge estimation method for lithium battery based on Gaussian process regression[J]. Journal of Naval University of Engineering, 2021, 33(1): 55-59.

方法	RMSE/%	MAE/%
GPR	1.56	4.12
改进的GPR	0.93	1.69

方法	RMSE/%	MAE/%
SVM	5.88	18.45
LSSVM	3.12	7.23
GPR	1.79	6.54
改进的GPR	1.15	1.49

[1]	Zhiying LU, Shan JIANG, Quanlong LI, Kexin MA, Teng FU, Zhigang ZHENG, Zhicheng LIU, Miao LI, Yongsheng LIANG, Zhifei DONG. Open-circuit voltage variation during charge and shelf phases of an all-vanadium liquid flow battery [J]. Energy Storage Science and Technology, 2022, 11(7): 2046-2050.
[2]	WU Yida, ZHANG Yi, ZHAN Yuanjie, GUO Yaqi, ZHANG liao, LIU Xingjiang, YU Hailong, ZHAO Wenwu, HUANG Xuejie. The effect of B₂O₃ modification on the electrochemical properties of LiCoO₂ cathode [J]. Energy Storage Science and Technology, 2022, 11(6): 1687-1692.
[3]	Feng TIAN, Zhijiang CHENG, Handi YANG, Tianxiang YANG. Fault-tolerant control strategy for modular multi-level hybrid converter battery energy storage system [J]. Energy Storage Science and Technology, 2022, 11(5): 1583-1591.
[4]	Suhang WANG, Jianlin LI, Yaxin LI, Junjie XIONG, Wei ZENG. Research on charging strategy of lithium-ion battery system at low temperature [J]. Energy Storage Science and Technology, 2022, 11(5): 1537-1542.
[5]	Haiyan HU, Shulei CHOU, Yao XIAO. Layered oxide cathode materials based on molecular orbital hybridization for high voltage sodium-ion batteries [J]. Energy Storage Science and Technology, 2022, 11(4): 1093-1102.
[6]	Dongge QIAO, Xunliang LIU, Zhi WEN, Ruifeng DOU, Wenning ZHOU. Numerical analysis of inhibition of lithium dendrite growth by heating and pulse charging [J]. Energy Storage Science and Technology, 2022, 11(3): 1008-1018.
[7]	Pengchao HUANG, Jiaqiang E. State estimation of lithium-ion battery based on dual adaptive Kalman filter [J]. Energy Storage Science and Technology, 2022, 11(2): 660-666.
[8]	Xiaozhi GAO, Lei WANG, Jin TIAN, Jialu LIU, Qinghua LIU. Research on hybrid energy storage power distribution strategy based on parameter optimization variational mode decomposition [J]. Energy Storage Science and Technology, 2022, 11(1): 147-155.
[9]	Weicheng SHEN, Wenxi ZHEN, Chong SHAO, Qi XIE. Coordinated fault ride through strategy for doubly fed induction generator using a superconducting magnetic energy storage system [J]. Energy Storage Science and Technology, 2022, 11(1): 136-146.
[10]	Lianbing LI, Sijia LI, Jie LI, Kun SUN, Zhengping WANG, Haiyue YANG, Bing GAO, Shaobo YANG. RUL prediction of lithium-ion battery based on differential voltage and Elman neural network [J]. Energy Storage Science and Technology, 2021, 10(6): 2373-2384.
[11]	Yi'nan ZHU, Taolin LÜ, Zhiyun ZHAO, Wen YANG. State of charge estimation of lithium ion battery based on parallel Kalman filter [J]. Energy Storage Science and Technology, 2021, 10(6): 2352-2362.
[12]	Xinyu CAO, Fei PENG, Liwei LI, Jianguang YIN. SOC estimation of lithium battery based on IBAS-NARX neural network model [J]. Energy Storage Science and Technology, 2021, 10(6): 2342-2351.
[13]	Kehuan XIE, Chuanchang LI, Jian CHEN, Longhai YU, zhun TAN, Weihai QIN. Simulation model advances in vanadium redox flow battery energy storage and monitoring method for state of charge [J]. Energy Storage Science and Technology, 2021, 10(6): 2363-2372.
[14]	Fan WANG, Yongsheng SHI, Boqin LIU, Yujie ZUO, Zheng FU, Jamsher ALI. Health state estimation of lithium-ion batteries based on attention augmented BiGRU [J]. Energy Storage Science and Technology, 2021, 10(6): 2326-2333.
[15]	Zeng'ang JIA, Zhibin LING, Xuguang LI. Thermal characteristics of lithium-ion battery with sinusoidal charge and discharge pulsating current [J]. Energy Storage Science and Technology, 2021, 10(6): 2260-2268.