Estimation on state of health of lithium battery based on Gaussian process quantile regression model

doi:10.3969/j.issn.1674-8484.2024.06.010

Abstract

Abstract:

To improve the safety of lithium batteries and delay their life degradation, a Gaussian process quantile regression model was proposed for estimating the state of health (SOH) of lithium batteries. The model combined the advantages of quasi-Gaussian process regression with non-stationary time series analysis and quantile regression, which can effectively deal with the nonlinear and time-varying problem of health characteristic data, and had the ability of adaptive adjustment of model parameters, thus improving the accuracy and robustness of SOH estimation. The validity of the proposed model was verified by the NASA battery dataset based on different temperatures. The results show that the mean absolute error (MAE)、root mean square error (RMSE) and mean absolute percentage error (MAPE) of the SOH estimation results of the model are 0.002 8, 0.003 8, and 0.003 4, respectively, and the model runtime is 0.008 1 s. Comparing the results with the Gray Wolf Optimization Guassian process regression model and three typical model estimation in the literature, the accuracy of RMSE is improved by 0.019 9, 0.003 0, 0.019 6, and 0.002 0, respectively, proving that the proposed model is more robust and has high accuracy in estimation results.

Key words: lithium-ion battery, Gaussian process quantile regression, state of health (SOH), non-stationary features, parameter tuning

CLC Number:

TM921.0

ZHANG Jinxiu, YAN Caihong, REN Guizhou. Estimation on state of health of lithium battery based on Gaussian process quantile regression model[J]. Journal of Automotive Safety and Energy, 2024, 15(6): 886-894.

Figures/Tables 12

References 25

[1]	CHEN Haiji, Abidi A, Hussein A K, et al. Investigation of the use of extended surfaces in paraffin wax phase change material in thermal management of a cylindrical lithium-ion battery: Applicable in the aerospace industry[J]. J Energ Stor, 2022, 45: 103685.
[2]	TIAN Huixin, QIN Pengliang, LI Kun, et al. A review of the state of health for lithium-ion batteries: Research status and suggestions[J]. J Clean Product, 2020, 261: 120813.
[3]	沈思远, 刘亚坤, 罗栋煌, 等. 储能锂离子电池模组暂态过电压防护设计与电路研发[J]. 储能科学与技术, 2024, 9(13): 3277-3286.
	SHEN siyuan, LIU yakun, LUO donghuang, et al. The design and circuit development for transient overvoltage protection in energy storage lithium-ion battery modules[J]. Energ Stor Sci Tech, 2024, 9(13): 3277-3286. (in Chinese)
[4]	黎冲, 王成辉, 王高, 等. 锂电池SOC估计的实现方法分析与性能对比[J]. 储能科学与技术, 2022, 11(10): 3328-3344. doi: 10.19799/j.cnki.2095-4239.2022.0078
	LI Chong, WANG Chenghui, WANG Gao, et al. Analysis and performance comparison of implementation methods for lithium battery soc estimation[J]. Energ Stor Sci Tech, 2022, 11(10): 3328-3344. (in Chinese)
[5]	李军, 李虎林. 电动汽车锂离子电池荷电状态估算方法综述[J]. 科学技术与工程, 2022, 22(6): 2147-2158.
	LI Jun, LI Hulin. A review of state of charge estimation methods for lithium-ion batteries in electric vehicles[J]. Sci Tech Engi, 2022, 22(6): 2147-2158. (in Chinese)
[6]	熊庆, 邸振国, 汲胜昌. 锂离子电池健康状态估计及寿命预测研究进展综述[J]. 高电压技术, 2024, 50(3): 1182-1195.
	XIONG Qing, DI Zhenguo, JI Shengchang. Review of research progress on health state estimation and lifetime prediction of lithium-ion batteries[J]. High Volt Tech, 2024, 50(3): 1182-1195. (in Chinese)
[7]	FU Juncheng, WU Chunling, WANG Jiwei, et al. Lithium-ion battery SOH prediction based on VMD-PE and improved DBO optimized temporal convolutional network model[J]. J Energy Storage, 2024, 87: 111392.
[8]	LI Hao, CHEN Chao, WEI Jie, et al. State of health (SOH) estimation of lithium-ion batteries based on ABC-BiGRU[J]. Electronics, 2024, 13(9): 1675.
[9]	CAI Nian, QUE Xiaoping, ZHANG Xu, et al. A deep learning framework for the joint prediction of the SOH and RUL of lithium-ion batteries based on bimodal images[J]. Energy, 2024, 302: 131700.
[10]	WANG Qilin, XIE Song, GUO Wenqi, et al. State of health estimation of lithium-ion batteries based on multiple health factors and BO-Seq2Seq model[J]. Comput Elect Engi, 2024, 116: 109167.
[11]	CHEN Z ewang, ZHANG Songyuan, SHI Na, et al. Online state-of-health estimation of lithium-ion battery based on relevance vector machine with dynamic integration[J]. Appl Soft Comput, 2022, 129: 109615.
[12]	HU Xiaosong, JANG Haifu, FENG Fei, et al. An enhanced multi-state estimation hierarchy for advanced lithium-ion battery management[J]. Appl Energ, 2020, 257: 114019.
[13]	XU Zhicun, XIE Naiming, DIAO Huakong, et al. Lithium-ion battery state of health monitoring based on an adaptive variable fractional order multivariate grey model[J]. Energy, 2023, 283: 129167.
[14]	ZHANG Chaolong, LUO Laijin, YANG Zhong, et al. Battery SOH estimation method based on gradual decreasing current, double correlation analysis and GRU[J]. Green Energ Intel Transport, 2023, 2: 100108.
[15]	TIAN Jinpeng, XIONG Rui, SHEN Weixiang, et al. Flexible battery state of health and state of charge estimation using partial charging data and deep learning[J]. Energ Stor Mate, 2023, 51: 372-381.
[16]	LI Penghua, ZHANG Zijian, Grosu R D, et al. An end-to-end neural network framework for state-of-health estimation and remaining useful life prediction of electric vehicle lithium batteries[J]. Renew Sustain Energ Rev, 2022, 156: 111843.
[17]	LI Xiaoyu, YUAN Changgui, WANG Zhenpo, et al. Lithium battery state-of-health estimation and remaining useful lifetime prediction based on non-parametric aging model and particle ﬁlter algorithm[J]. eTransportation, 2022, 11: 100156.
[18]	DUAN Wenxian, SONG Shixin, XIAO Feng, et al. Battery SOH estimation and RUL prediction framework based on variable forgetting factor online sequential extreme learning machine and particle filter[J]. Energy, 2023, 65: 107322.
[19]	张韬, 王阳, 王言子, 等. 蜻蜓算法优化的高斯过程回归对锂电池健康状态预测[J]. 重庆理工大学学报(自然科学), 2023, 37(11): 352-361.
	ZHANG tao, WANG yang, WANG yanzi, et al. Prediction of lithium battery health state using gaussian process regression optimized by dragonfly algorithm[J]. J Chongqing Univ Sci Tech (Nat Sci), 2023, 37(11): 352-361. (in Chinese)
[20]	XIANG Ming, HE Yiyang, ZHANG Hui, et al. State-of-health prognosis for lithium-ion batteries considering the limitations in measurements via maximal information entropy and collective sparse variational gaussian process[J]. IEEE Access, 2020, 8: 188199-188217.
[21]	邓鸿枥, 吴松荣, 刘齐, 等. 基于改进高斯过程回归的锂离子电池健康状态估计[J/OL]. 电源学报, 2024. (2024-04-26) https://link.cnki.net/urlid/12.1420.TM.20240426.0915.008.
	DENG Hongli, WU Songrong, LIU Qi, et al. Health state estimation of lithium-ion batteries based on improved gaussian process regression[J/OL]. J Power Supply, 2024. (2024-04-26) https://link.cnki.net/urlid/12.1420.TM.20240426.0915.008. (in Chinese)
[22]	HE Ye, BAI Wenyuan, WANG Lulu, et al. SOH estimation for lithium-ion batteries:An improved GPR optimization method based on the developed feature extraction[J]. J Energ Stor, 2024, 83: 110678.
[23]	李放, 闵永军, 王琛, 等. 基于充电过程的锂电池SOH估计和RUL预测[J]. 储能科学与技术, 2022, 11(10): 3316-3327. doi: 10.19799/j.cnki.2095-4239.2022.0165
	LI Fang, MIN Yongjun, WANG Chen, et al. Estimation of lithium battery state of health (SOH) and prediction of remaining useful life (RUL) based on charging processes[J]. Energ Stor Sci Tech, 2022, 11(10): 3316-3327. (in Chinese)
[24]	冯娜娜, 杨明, 惠周利, 等. 基于蚁狮优化高斯过程回归的锂电池剩余使用寿命预测[J]. 储能科学与技术, 2024, 13(5): 1643-1652. doi: 10.19799/j.cnki.2095-4239.2023.0865
	FENG nana, YANG ming, HUI zhouli, et al. Prediction of lithium battery remaining useful life based on ant-lion optimized gaussian process regression[J]. Energ Stor Sci Tech, 2024, 13(5): 1643-1652. (in Chinese)
[25]	王琛, 闵永军. 基于容量增量曲线与GWO-GPR的锂离子电池SOH估计[J]. 储能科学与技术, 2023, 12(11): 3508-3518. doi: 10.19799/j.cnki.2095-4239.2023.0458
	WANG chen, MIN yongjun. State of Health (SOH) Estimation of Lithium-ion Batteries Based on Capacity Increment Curve and GWO-GPR[J]. Energ Stor Sci Tech, 2023, 12(11): 3508-3518. (in Chinese)

健康特征	r	ρ	τ
H1	0.958 3	0.974 7	0.877 6
H2	0.982 0	0.983 0	0.898 7
H3	-0.918 8	-0.917 4	-0.742 4
H4	0.996 6	0.996 0	0.957 4

健康特征	r	ρ	τ
H1	0.958 3	0.974 7	0.877 6
H2	0.982 0	0.983 0	0.898 7
H3	-0.918 8	-0.917 4	-0.742 4
H4	0.996 6	0.996 0	0.957 4

模型	MAE	RMSE	MAPE	t / s
GPRQ训练集	0.003 6	0.005 8	0.004 7	0.008 1
GPRQ测试集	0.002 8	0.003 8	0.003 4	0.008 1
GWO-GPR测试集	0.005 4	0.006 7	0.006 7	0.008 8

模型	MAE	RMSE	MAPE	t / s
GPRQ训练集	0.003 6	0.005 8	0.004 7	0.008 1
GPRQ测试集	0.002 8	0.003 8	0.003 4	0.008 1
GWO-GPR测试集	0.005 4	0.006 7	0.006 7	0.008 8

电池	GPRQ	CSVGPR^[20]	IGPR^[21]	ALO-GPR^[24]	GWO-GPR^[25]
B0005	0.006 5	0.007 8	0.012 7	0.009 3	0.006 7
B0007	0.004 3	0.023 9	0.024 2	0.006 3	0.007 3