基于改进灰狼算法优化GPR模型的动力电池RUL预测方法

doi:10.19799/j.cnki.2095-4239.2024.0717

摘要/Abstract

摘要：

可靠准确地预测动力电池剩余使用寿命(remaining useful life，RUL)可以缓解用户对里程和安全的焦虑。为了提升RUL预测精度，基于NASA数据集，本工作提出了一种改进的灰狼算法来优化高斯过程回归(Gaussian process regression, GPR)模型。本工作从以下三方面开展研究。首先，基于电池的充放电数据，提取了五种间接健康因子，包括充电电压饱和间隔(CVSI，HI1)、充电峰值温度间隔(CPTI，HI2)、恒流充电间隔(CCCI，HI3)、放电峰值温度区间(DPTI，HI4)和放电恒流间隔(DCCI，HI5)，并采用灰色关联方法分析健康因子和容量的相关性。其次，本工作选取GPR方法作为动力电池RUL预测模型，针对传统模型参数辨识已陷入局部最优问题，提出了基于差分算法改进的灰狼算法，提升模型预测能力。最后，利用NASA数据集对本工作所提方法进行验证。实验结果表明，所提算法预测RUL误差控制在2%以内。

关键词: 动力电池, 剩余使用寿命, 高斯过程回归, 灰狼算法

Abstract:

Accurate and reliable prediction of remaining useful life (RUL) of power batteries is crucial for mitigating user concerns regarding mileage and safety. To improve the accuracy of RUL prediction, we propose an improved grey wolf algorithm to optimize the GPR model, based on the NASA dataset. This study focuses on three aspects. First, five indirect health factors were extracted based on battery charging and discharging data including charging voltage saturation interval (CVSI, HI1), charging peak temperature interval (CPTI, HI2), constant current charging interval (CCCI, HI3), discharging peak temperature interval (DPTI, HI4), and discharging constant current interval (DCCI, HI5). The grey correlation method was used to analyze the correlation between health factors and capacity. Second, GPR method was selected as the RUL prediction model for power batteries. In response to the problem of traditional model parameter identification falling into local optima, an improved grey wolf algorithm based on a differential algorithm is proposed to enhance the model's prediction ability. Finally, the proposed method was validated using the NASA dataset. The experimental results showed that the proposed algorithm can control the RUL prediction error within 2%.

Key words: power battery, remaining useful life, Gaussian process regression, grey wolf optimization algorithm

中图分类号:

TM 911

吴旭志, 郭健. 基于改进灰狼算法优化GPR模型的动力电池RUL预测方法[J]. 储能科学与技术, 2025, 14(2): 728-736.

Xuzhi WU, Jian GUO. An approach for remaining useful life prediction of power battery with improved grey wolf optimized GPR model[J]. Energy Storage Science and Technology, 2025, 14(2): 728-736.

图/表 8

图1

图2

表1

图3

图4

表2

图5

表3

参考文献 14

1	刘康, 康龙云, 岳睿, 等. 基于门控循环单元编解码器的锂离子电池荷电状态估计[J]. 电网技术, 2024, 48(5): 2161-2169. DOI: 10.13335/j.1000-3673.pst.2023.0882
	LIU K, KANG L Y, YUE R, et al. Lithium-ion battery state of charge estimation based on gated recurrent unit encoder-decoder[J]. Power System Technology, 2024, 48(5): 2161-2169. DOI: 10.13335/j.1000-3673.pst.2023.0882
2	PANG X Q, LIU X Y, JIA J F, et al. A lithium-ion battery remaining useful life prediction method based on the incremental capacity analysis and Gaussian process regression[J]. Microelectronics Reliability, 2021, 127: 114405. DOI:10.1016/j.microrel. 2021.114405.
3	DUAN B, ZHANG Q, GENG F, et al. Remaining useful life prediction of lithium-ion battery based on extended Kalman particle filter[J]. International Journal of Energy Research, 2020, 44(3): 1724-1734. DOI:10.1002/er.5002.
4	MA Y, CHEN Y, ZHOU X W, et al. Remaining useful life prediction of lithium-ion battery based on Gauss-Hermite particle filter[J]. IEEE Transactions on Control Systems Technology, 2019, 27(4): 1788-1795. DOI:10.1109/TCST.2018.2819965.
5	DONG H C, JIN X N, LOU Y B, et al. Lithium-ion battery state of health monitoring and remaining useful life prediction based on support vector regression-particle filter[J]. Journal of Power Sources, 2014, 271: 114-123. DOI:10.1016/j.jpowsour. 2014.07.176.
6	HUANG C G, YIN X H, HUANG H Z, et al. An enhanced deep learning-based fusion prognostic method for RUL prediction[J]. IEEE Transactions on Reliability, 2020, 69(3): 1097-1109. DOI:10.1109/TR.2019.2948705.
7	LIU H, SONG W Q, NIU Y H, et al. A generalized cauchy method for remaining useful life prediction of wind turbine gearboxes[J]. Mechanical Systems and Signal Processing, 2021, 153: 107471. DOI:10.1016/j.ymssp.2020.107471.
8	SUN Y Q, HAO X L, PECHT M, et al. Remaining useful life prediction for lithium-ion batteries based on an integrated health indicator[J]. Microelectronics Reliability, 2018, 88: 1189-1194. DOI:10.1016/j.microrel.2018.07.047.
9	WU J, ZHANG C B, CHEN Z H. An online method for lithium-ion battery remaining useful life estimation using importance sampling and neural networks[J]. Applied Energy, 2016, 173: 134-140. DOI:10.1016/j.apenergy.2016.04.057.
10	LI L L, LIU Z F, TSENG M L, et al. Enhancing the Lithium-ion battery life predictability using a hybrid method[J]. Applied Soft Computing, 2019, 74: 110-121. DOI:10.1016/j.asoc.2018.10.014.
11	WANG F K, MAMO T. A hybrid model based on support vector regression and differential evolution for remaining useful lifetime prediction of lithium-ion batteries[J]. Journal of Power Sources, 2018, 401: 49-54. DOI:10.1016/j.jpowsour.2018.08.073.
12	王萍, 范凌峰, 程泽. 基于健康特征参数的锂离子电池SOH和RUL联合估计方法[J]. 中国电机工程学报, 2022, 42(4): 1523-1534. DOI: 10.13334/j.0258-8013.pcsee.202368.
	WANG P, FAN L F, CHENG Z. A joint state of health and remaining useful life estimation approach for lithium-ion batteries based on health factor parameter[J]. Proceedings of the CSEE, 2022, 42(4): 1523-1534. DOI: 10.13334/j.0258-8013.pcsee. 202368.
13	刘志文. 基于变分模态分解的锂离子电池剩余使用寿命预测方法研究[D]. 重庆: 重庆大学, 2022. DOI: 10.27670/d.cnki.gcqdu. 2022.000122.
	LIU Z W. Research on prediction method of remaining service life of lithium-ion battery based on variational modal decomposition[D]. Chongqing: Chongqing University, 2022. DOI: 10.27670/d.cnki.gcqdu.2022.000122.
14	向铭, 何怡刚, 张慧. 基于改进集成经验模态分解和高斯过程回归的锂离子电池剩余容量及寿命预测方法[J]. 电测与仪表, 2023, 60(9): 27-33. DOI: 10.19753/j.issn1001-1390.2023.09.005.
	XIANG M, HE Y G, ZHANG H. Capacity and remaining useful life prediction of lithium-ion battery based on MEEMD and GPR[J]. Electrical Measurement & Instrumentation, 2023, 60(9): 27-33. DOI: 10.19753/j.issn1001-1390.2023.09.005.

GRA	电池5#	电池6#	电池7#
HI1	0.81	0.66	0.85
HI2	0.80	0.67	0.85
HI3	0.73	0.82	0.89
HI4	0.90	0.92	0.92
HI5	0.89	0.93	0.95

方法	电池	RMSE/%	MAE/%	MAPE/%
所提模型	5#	1.35	1.28	0.96
	6#	1.97	1.75	1.35
	7#	1.75	1.38	1.17

GWO-GPR	5#	1.89	1.54	1.28
	6#	2.95	2.31	1.77
	7#	2.55	1.93	1.45

GPR	5#	1.98	1.61	1.34
	6#	3.19	2.56	1.98
	7#	2.72	2.09	1.58

方法	电池	RMSE/%	MAE/%	MAPE/%
NN-GWO	5#	3.84	3.51	2.82
	6#	4.97	3.88	2.92
	7#	4.42	3.61	2.95

NARX-GWO	5#	2.76	2.35	1.73
	6#	4.15	3.29	2.63
	7#	3.85	2.77	2.25

LSSVM-GWO	5#	2.11	1.72	1.43
	6#	3.65	2.71	2.13
	7#	3.31	2.43	1.75

LSTM-GWO	5#	1.91	1.57	1.32
	6#	2.43	1.99	.1.96
	7#	2.19	1.69	1.55

[1]	李嘉波, 王志璇, 田迪, 孙中麟. 变模态分解下SSA-LSTM组合的锂离子电池剩余使用寿命预测方法[J]. 储能科学与技术, 2025, 14(2): 659-670.
[2]	李春生, 王生春, 宋驰, 刘立海, 颜宁. 基于多状态耦合的退役动力电池模组双阶段分选方法[J]. 储能科学与技术, 2025, 14(2): 822-830.
[3]	刘勇, 于怀汶, 刘大鹏, 穆勇, 王瀛洲, 张秀宇. 基于ABC-LSTM模型的锂离子电池剩余使用寿命预测[J]. 储能科学与技术, 2025, 14(1): 331-345.
[4]	陈峥, 彭月, 胡竞元, 申江卫, 肖仁鑫, 夏雪磊. 基于短期充电数据和增强鲸鱼优化算法的锂离子电池容量预测[J]. 储能科学与技术, 2025, 14(1): 319-330.
[5]	刘迎迎, 张孝远, 刘梦楠, 孙俊章, 张艳. 基于自适应最优组合核函数高斯过程回归的锂电池健康状态区间估计[J]. 储能科学与技术, 2025, 14(1): 346-357.
[6]	孙中麟, 李嘉波, 田迪, 王志璇, 邢晓静. 基于COA-LSTM和VMD的锂离子电池剩余寿命预测[J]. 储能科学与技术, 2024, 13(9): 3254-3265.
[7]	刘定宏, 董文楷, 李召阳, 张红烛, 齐昕. 基于RUN-GRU-attention模型的实车动力电池健康状态估计方法[J]. 储能科学与技术, 2024, 13(9): 3042-3058.
[8]	宋旭, 孙楠楠, 曹恒超, 朱桂香, 李孟涵, 刘晓日, 饶中浩. 基于并联蛇形流道的动力电池冷媒直冷热管理系统研究[J]. 储能科学与技术, 2024, 13(8): 2726-2736.
[9]	李臣, 张会林, 张建平. 基于核函数和超参数优化的退役锂电池健康状态估计[J]. 储能科学与技术, 2024, 13(6): 2010-2021.
[10]	冯娜娜, 杨明, 惠周利, 王瑞洁, 宁弘扬. 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.
[11]	田根源. 云计算技术在新能源汽车智能制造中的应用与发展[J]. 储能科学与技术, 2024, 13(5): 1748-1750.
[12]	罗泽飞, 覃元庆. 新能源汽车电池智能制造工艺的创新与优化研究[J]. 储能科学与技术, 2024, 13(5): 1751-1753.
[13]	李炳金, 韩晓霞, 张文杰, 曾伟国, 武晋德. 锂离子电池剩余使用寿命预测方法综述[J]. 储能科学与技术, 2024, 13(4): 1266-1276.
[14]	柯奥, 阳如坤, 吴学科. 动力电池智能卷绕技术[J]. 储能科学与技术, 2024, 13(4): 1176-1187.
[15]	刘佳, 马志强, 刘广忱, 高俊东, 李宏勋. 多尺度分解下GRU-TCN集成的动力电池剩余使用寿命预测方法[J]. 储能科学与技术, 2024, 13(3): 1009-1018.