SOC estimation of lithium-ion batteries based on Gaussprocess regression

doi:10.19799/j.cnki.2095-4239.2019.0189

Abstract

Abstract:

Battery state estimation (state of charge, SOC) is particularly important in a battery management system (BMS). It is difficult to ensure its accuracy because SOC estimation is vulnerable to temperature, load, charging and discharging efficiency, and other external factors. Currently, many scholars use machine learning algorithms to estimate the SOC. However, the estimation accuracy of a neural network (NN) is dependent on the number of samples. The support vector machine (SVM) falls into a local optimum in parameter optimization. An online estimation method is proposed based on Gaussian process regression (GPR) for lithium-ion batteries to improve the estimation accuracy of the SOC. Based on the battery measurement parameters, including current, voltage, and temperature, as input to the GPR model and the SOC as an output of the model, the model is trained, and the parameters are optimized using the gradient descent method. The validity of the model is verified by simulation and data collected from the constant current charging and discharging experiments. Compared with the SVM, LSSVM, and NN, the validity and feasibility of the model are verified.

Key words: SOC, Gauss process regression, lithium-ion battery

CLC Number:

TM 911

LI Jiabo, WEI Meng, YE Min, JIAO Shengjie, XU Xinxin. SOC estimation of lithium-ion batteries based on Gaussprocess regression[J]. Energy Storage Science and Technology, 2020, 9(1): 131-137.

Figures/Tables 23

Fig.1

Table 1

GPR-based SOC estimation algorithm"

算法流程
训练部分 Step1 通过不同的工况收集样本集； Step2 选取训练集D= (X,y)，其中X是电池的电压、电流和温度的测量值，y是相应的SOC值；
Step3 采用均值法，将所选的数据进行归一化处理； Step4 初始化GPR模型的超参数σ、σ_f和l；
Step5 利用梯度下降法，求解超参数的极大似然估计方程，得到最优超参数；
验证部分
Step6 在获取最优的超出参数σ、σ_f和l，选取验证集x，进行SOC估计， $μ$ 是SOC的估计值。 $μ = K x , X K X, X + σ n 2 I - 1 y$

Table 1

Fig. 2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Fig.10

Fig.11

Table 2

Fig.12

Fig.13

Fig.20

Fig. 4

Fig.15

Fig.16

Fig.17

Fig.18

Fig.19

Table 3

References 11

1	KLASS V, BEHM M, LINDBERGH G. A support vector machine-based state-of-health estimation method for lithium-ion batteries under electric vehicle operation[J]. Journal of Power Sources, 2014, 270: 262-272.
2	徐尖峰, 张颖, 甄玉, 等. 基于安时积分法的电池SOC估算[J]. 汽车实用技术, 2018, 273(18): 17-19+31.
	XU Jianfeng, ZHANG Ying, ZHEN Yu, et al. Lithium-ion battery SOC estimation based on Ahh-total integration method[J]. Automobile Applied Technology, 2018, 273(18): 17-19+31.
3	鲍慧, 于洋. 基于开路电压法的电池荷电状态估计误差校正[J]. 中国民航飞行学院学报, 2014, 25(5): 77-80.
	BAO Hui, YU Yang. State of charge estimation error correction of open circuit voltage method[J]. Journal of Civil Aviation Flight University of China, 2014, 25(5): 77-80.
4	MENG J, MEMBER S, IEEE, et al. A simplified model based state-of-charge estimation approach for lithium-ion battery with dynamic linear model[J]. IEEE Transactions on Industrial Electronics, 2019, 66(10): 7717-7727.
5	SUN Q, ZHANG H, ZHANG J, et al. Adaptive unscented Kalman filter with correntropy loss for robust state of charge estimation of lithium-ion battery[J]. Energies, 2018, 11(11): 1-20.
6	PARK C, RYU S J, JEONG B H, et al. Real-time noninvasive intracranial state estimation using unscented Kalman filter[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2019, 27(9): 1931-1938.
7	王震, 陆金桂. 改进的ACO-BP神经网络在锂离子电池SOC估算中的应用[J]. 轻工学报, 2019, 34(4): 81-86.
	WANG Zhen, LU Jingui. Estimation of SOC of lithium-ion battery based on ACO-BP neural network[J]. Journal of Light Industry, 2019, 34(4): 81-86.
8	LUZI M, MASCIOLI F M F, PASCHERO M, et al. A white-box equivalent neural network circuit model for SOC estimation of electrochemical cells[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019: doi: 10.1109/TNNLS.2019.2901062
9	邓建威, 章云. 基于扩展PSO优化的SVM铅酸蓄电池荷电状态估测[J]. 工业控制计算机, 2017, 30(3): 126-127+129.
	DENG Jianwei, ZHANG Yun. Lead-acid battery SOC estimation based on SVM optimized by extended PSO[J]. Industrial Control Computer, 2017, 30(3): 126-127+129.
10	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 Wen, CAI Chengguang, YANG Ping, et al. UKF estimation method incorporating Gaussian process regression[J]. Journal of Beijing University of Aeronautics and Astronautics, 2019, 45(6): 1081-1087.
11	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, 2016, 31(3): 2226-2238.

名称	参数值
额定容量/mA·h	2250
额定电压/V	3.7
最大电压/V	（4.5±0.05）
截止电压/V	2.8
最大放大电流/A	10
电池尺寸	?18.6 mm × 64.9 mm
阳极材料及厚度	Li_xC₆/0.165 mm
阴极材料及厚度	LiCoO₂/0.159 mm
重量/g	（43.6 ± 1.5）

方法	RMSE	MAE
GPR	1.24%	4.38%
LSSVM	2.03%	3.14%
SVM	4.26%	13.04%
NN	6.91%	40.28%

[1]	Shunmin YI, Linbo XIE, Li PENG. Remaining useful life prediction of lithium-ion batteries based on VF-DW-DFN [J]. Energy Storage Science and Technology, 2022, 11(7): 2305-2315.
[2]	Qingwei ZHU, Xiaoli YU, Qichao WU, Yidan XU, Fenfang CHEN, Rui HUANG. Semi-empirical degradation model of lithium-ion battery with high energy density [J]. Energy Storage Science and Technology, 2022, 11(7): 2324-2331.
[3]	Yuzuo WANG, Jin WANG, Yinli LU, Dianbo RUAN. Study on the effects of pore structure on lithium-storage performances for soft carbon [J]. Energy Storage Science and Technology, 2022, 11(7): 2023-2029.
[4]	Wei KONG, Jingtao JIN, Xipo LU, Yang SUN. Study on cooling performance of lithium ion batteries with symmetrical serpentine channel [J]. Energy Storage Science and Technology, 2022, 11(7): 2258-2265.
[5]	YAN Qiaoyi, WU Feng, CHEN Renjie, LI Li. Recovery and resource recycling of graphite anode materials for spent lithium-ion batteries [J]. Energy Storage Science and Technology, 2022, 11(6): 1760-1771.
[6]	WANG Yuzuo, DENG Miao, WANG Jin, YANG Bin, LU Yinli, JIN Ge, RUAN Dianbo. Study on the effects of carbonization temperature on lithium-storage kinetics for soft carbon [J]. Energy Storage Science and Technology, 2022, 11(6): 1715-1724.
[7]	YU Chunhui, HE Ziying, ZHANG Chenxi, LIN Xianqing, XIAO Zhexi, WEI Fei. The analyses and suppressing strategies of silicon anode with the electrolyte [J]. Energy Storage Science and Technology, 2022, 11(6): 1749-1759.
[8]	WANG Can, MA Pan, ZHU Guoliang, WEI Shuimiao, YANG Zhilu, ZHANG Zhiyu. Effect of lithium acrylic-coated nature graphite on its electrochemical properties [J]. Energy Storage Science and Technology, 2022, 11(6): 1706-1714.
[9]	LIU Hangxin, CHEN Xiantao, SUN Qiang, ZHAO Chenxi. Cycle performance characteristics of soft pack lithium-ion batteries under vacuum environment [J]. Energy Storage Science and Technology, 2022, 11(6): 1806-1815.
[10]	Guangyu CHENG, Xinwei LIU, Yueni MEI, Honghui GU, Cheng YANG, Ke WANG. Capacity fading analysis of lithium-ion battery after high temperature storage [J]. Energy Storage Science and Technology, 2022, 11(5): 1339-1349.
[11]	Yanwen DAI, Aiqing YU. Combined CNN-LSTM and GRU based health feature parameters for lithium-ion batteries SOH estimation [J]. Energy Storage Science and Technology, 2022, 11(5): 1641-1649.
[12]	Chunjing LIN, Danhua LI, Haoran WEN, Tianyi MA, Hong CHANG, Peixiang CHANG, Haiqiang LI, Shiqiang LIU. Research on swelling force characteristics of power battery during charging [J]. Energy Storage Science and Technology, 2022, 11(5): 1627-1633.
[13]	Qiaomin KE, Jian GUO, Yiwei WANG, Wenjiong CAO, Man CHEN, Fangming JIANG. The effect of liquid-cooled thermal management on thermal runaway of power battery [J]. Energy Storage Science and Technology, 2022, 11(5): 1634-1640.
[14]	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.
[15]	Zhenkai HU, Bo LEI, Yongqi LI, Youjie SHI, Qikai LEI, Zhipeng HE. Comparative study on safety test and evaluation methods of lithium-ion batteries for energy storage [J]. Energy Storage Science and Technology, 2022, 11(5): 1650-1656.