基于数据驱动模型融合的锂离子电池多时间尺度状态联合估计方法

doi:10.19562/j.chinasae.qcgc.2022.03.007

摘要/Abstract

摘要：

本文提出一种基于数据驱动法（data driven method， DDM）-等效电路模型（equivalent circuit model， ECM）融合的锂离子电池多时间尺度状态联合估计方法。首先提取内阻作为健康特征（health factor， HF），利用最小二乘支持向量机（least squares support vector machine， LSSVM）建立电池老化模型实现健康状态（state of health， SOH）估计；根据阻容参数辨识值和容量估计值建立电池状态空间方程，结合无迹卡尔曼滤波算法（unscented Kalman filter， UKF）进行荷电状态（state of charge， SOC）估计；用高斯过程回归（Gaussian process regression， GPR）对HF随循环次数的变化进行映射，预测HF的变化趋势，并结合LSSVM模型实现长期剩余使用使命（remaining useful life， RUL）预测。实验结果表明，所提方法具有较高精度和鲁棒性。

关键词: 锂离子电池, 多时间尺度, 联合估计, 融合方法

Abstract:

This paper proposes a multi-time scale joint state estimation method for lithium-ion batteries based on the fusion of data driven method （DDM） and equivalent circuit model （ECM）. Firstly， the internal resistance is extracted as the health factor （HF）， and the least squares support vector machine （LSSVM） is used to establish the battery aging model to estimate state of health （SOH）. Subsequently， the battery state space equation is established according to the RC parameter identification values and the capacity estimation values， and then the Unscented Kalman Filter （UKF） algorithm is used to estimate state of charge （SOC）. Then， Gaussian process regression （GPR） is used to map the change of HF with the number of cycles to predict the trend of HF change， and long-term remaining useful life （RUL） prediction is realized combined with the LSSVM model. The experimental results show that the proposed method has high accuracy and robustness.

Key words: lithium-ion battery, multi-time scale, joint estimation, fusion method

王萍,彭香园,程泽,张吉昂. 基于数据驱动模型融合的锂离子电池多时间尺度状态联合估计方法[J]. 汽车工程, 2022, 44(3): 362-371.

Ping Wang,Xiangyuan Peng,Ze Cheng,Ji’ang Zhang. A Multi-time Scale Joint State Estimation Method for Lithium-ion Batteries Based on Data-driven Model Fusion[J]. Automotive Engineering, 2022, 44(3): 362-371.

图/表 9

图1

图2

图3

表1

阻容参数与SOH的Pearson和GRC系数"

电池	Pearson系数				GRC系数
电池	$R$	$R 0$	$R p$	$C p$	$R$	$R 0$	$R p$	$C p$
Cell1	-0.998 0	-0.985 2	-0.996 0	0.957 8	0.933 3	0.933 3	0.933 3	0.646 0
Cell2	-0.986 3	-0.964 1	-0.981 8	0.964 1	0.879 0	0.879 0	0.879 0	0.734 8
Cell3	-0.998 2	-0.989 3	-0.997 5	0.973 8	0.934 4	0.934 4	0.934 4	0.763 6
Cell4	-0.998 6	-0.980 2	-0.997 8	0.975 9	0.939 0	0.938 9	0.938 9	0.708 4
Cell5	-0.998 9	-0.993 7	-0.998 7	0.984 9	0.947 2	0.947 2	0.947 2	0.662 5
Cell6	-0.992 6	-0.989 3	-0.988 2	0.977 8	0.928 0	0.928 0	0.928 0	0.742 6
Cell7	-0.998 3	-0.991 2	-0.997 2	0.981 4	0.942 1	0.942 0	0.942 0	0.687 6
Cell8	-0.997 0	-0.991 2	-0.995 5	0.979 9	0.930 2	0.930 2	0.930 2	0.759 3

表1

图4

图5

表2

图6

图7

参考文献 19

1	LIN C P， LIN C P， CABRERA J， et al. Battery state of health modeling and remaining useful life prediction through time series model［J］. Applied Energy， 275.P115338.
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］. Journal of Cleaner Production，2020，261：120813.
3	HU Xiaosong， FENG Fei， LIU Kailong， et al. State estimation for advanced battery management： key challenges and future trends［J］. Renewable and Sustainable Energy Reviews，2019，114：109334.
4	CHEN C， XIONG R， SHEN W. A Lithium-ion battery-in-the-loop approach to test and validate multiscale dual h infinity filters for state-of-charge and capacity estimation［J］. IEEE Transactions on Power Electronics， 2018：1-1.
5	XIA B， CHEN G， ZHOU J， et al. Online parameter identification and joint estimation of the state of charge and the state of health of lithium-ion batteries considering the degree of polarization［J］. Energies， 2019， 12（15）：2939.
6	JAMOOS A， GRIVEL E， SHAKARNEH N， et al. Dual optimal filters for parameter estimation of a multivariate autoregressive process from noisy observations［J］. Iet Signal Processing， 2011， 5（5）：471-479.
7	CHEN Z， SUN H， DONG G， et al. Particle filter-based state-of-charge estimation and remaining- dischargeable-time prediction method for lithium-ion batteries［J］. Journal of Power Sources， 2019， 414：158-166.
8	DUONG V H， BASTAWROUS H A， LIM K C， et al. Online state of charge and model parameters estimation of the LiFePO4 battery in electric vehicles using multiple adaptive forgetting factors recursive least-squares［J］. Journal of Power Sources， 2015， 296：215-224.
9	SUN F， XIONG R， HE H. A systematic state-of-charge estimation framework for multi-cell battery pack in electric vehicles using bias correction technique［J］. Applied Energy， 2016， 162：1399-1409.
10	HUA Y， CORDOBA-ARENAS A， WARNER N， et al. A multi time-scale state-of-charge and state-of-health estimation framework using nonlinear predictive filter for lithium-ion battery pack with passive balance control［J］. Journal of Power Sources， 2015， 280：293-312.
11	LEE S， KIM J， LEE J， et al. State-of-charge and capacity estimation of lithium-ion battery using a new open-circuit voltage versus state-of-charge［J］. Journal of Power Sources， 2009，2：1367-1373.
12	WEI Z， TSENG K J， WAI N， et al. Adaptive estimation of state of charge and capacity with online identified battery model for vanadium redox flow battery［J］. Journal of Power Sources， 2016， 332：389-398.
13	YANG Q， XU J， CAO B， et al. State-of-health estimation of lithium-ion battery based on interval capacity［J］. Energy Procedia， 2017， 105：2342-2347.
14	GUO P， CHENG Z， YANG L. A data-driven remaining capacity estimation approach for lithium-ion batteries based on charging health feature extraction［J］. Journal of Power Sources， 2019， 412：442-450.
15	HOSSAIN L， HANNAN M A， AINI H， et al. A review of state of health and remaining useful life estimation methods for lithium-ion battery in electric vehicles： Challenges and recommendations［J］. Journal of Cleaner Production， 2018， 205：115-133.
16	XING Y， MA E， TSUI K L， et al. An ensemble model for predicting the remaining useful performance of lithium-ion batteries［J］. Microelectronics Reliability， 2013， 53（6）：811-820.
17	WANG S， ZHAO L， SU X， et al. Prognostics of lithium-ion batteries based on flexible support vector regression［C］. Proceedings of Prognostics & System Health Management Conference. Zhangiiaijie： IEEE， 2014，7（10）：6492-6508.
18	REZVANI M， LEE S， LEE J. A comparative analysis of techniques for electric vehicle battery prognostics and health management （PHM）［C］. SAE Paper 2011-01-2247.
19	LIU D T， ZHOU J B， LIAO H T，et al．A health indicator extraction and optimization framework for lithium-ion battery degradation modeling and prognostics［J］.IEEE Transactions on Systems，Man，and Cybernetics：Systems，2015，45（6）：915-928．

电池	SOH		RUL
电池	MAE	RMSE	MAE	RMSE
Cell 1	0.003 8	0.004 3	0.666 7	0.866 0
Cell 2	0.002 9	0.003 4	0.333 3	0.577 4
Cell 3	0.003 6	0.004 1	0.413 8	0.694 8
Cell 4	0.002 9	0.003 5	0.454 5	0.738 5
Cell 5	0.001 7	0.002 3	0.285 7	0.534 5
Cell 6	0.002 1	0.002 7	0.565 2	0.751 8
Cell 7	0.003 4	0.003 8	0.975 0	1.172 6
Cell 8	0.003 9	0.004 4	0.166 7	0.408 2

[1]	陈飞,孔祥栋,孙跃东,韩雪冰,卢兰光,郑岳久,欧阳明高. 锂离子电池制造工艺仿真技术进展[J]. 汽车工程, 2023, 45(9): 1516-1529.
[2]	胡明辉,朱广曜,刘长贺,唐国峰. 考虑迟滞特性的卡尔曼滤波和门控循环单元神经网络的锂离子电池SOC联合估计[J]. 汽车工程, 2023, 45(9): 1688-1701.
[3]	梁海强,何洪文,代康伟,庞博,王鹏. 融合经验老化模型和机理模型的电动汽车锂离子电池寿命预测方法研究[J]. 汽车工程, 2023, 45(5): 825-835.
[4]	廉玉波,凌和平,马晴婵,任强,贺斌. 电动汽车锂离子电池脉冲加热技术研究进展[J]. 汽车工程, 2023, 45(2): 169-174.
[5]	吕又付,罗卫明,陈荐,吴锡鸿,李传常. 分层优化测定锂离子电池比热容参数的实验研究[J]. 汽车工程, 2023, 45(2): 183-190.
[6]	张健豪,高兴奇,张莉. 基于容量增量曲线与充电容量差的电池组微短路诊断方法[J]. 汽车工程, 2023, 45(2): 191-198.
[7]	李贵敬,谷青锴,杨昊鑫,黄健齐,邸立明. PA/EG耦合风冷电池热管理系统轻量研究[J]. 汽车工程, 2023, 45(2): 209-218.
[8]	王萍,弓清瑞,程泽,张吉昂. 基于AUKF的锂离子电池SOC估计方法[J]. 汽车工程, 2022, 44(7): 1080-1088.
[9]	彭宇明,袁明晓,敬卓鑫,张永林,黄港. 汇流排产热影响下的电池模组冷却系统改进设计[J]. 汽车工程, 2022, 44(6): 859-867.
[10]	毕贵红,谢旭,蔡子龙,骆钊,陈臣鹏,赵鑫. 动态条件下基于深度学习的锂电池容量估计[J]. 汽车工程, 2022, 44(6): 868-878.
[11]	马彦,李佳怡,马乾,陈明超. 基于迭代动态规划的动力电池组热管理优化策略[J]. 汽车工程, 2022, 44(5): 709-721.
[12]	刘首彤,黄沛丰,白中浩. 锂离子电池机械滥用失效机理及仿真模型研究进展[J]. 汽车工程, 2022, 44(4): 465-475.
[13]	孙涛,郑侠,郑岳久,卢宇芳,匡柯,韩雪冰. 基于电化学热耦合模型的锂离子电池快充控制[J]. 汽车工程, 2022, 44(4): 495-504.
[14]	程夕明,胡薇,翟钧,罗荣华,张盼,徐野. 纯电动汽车低压电气系统效率研究[J]. 汽车工程, 2022, 44(4): 601-608.
[15]	刘红锐,古栋华,李海瑞,张彬,钱晶. 一种串联锂离子电池组P-C-C-P均衡器及其控制方法[J]. 汽车工程, 2022, 44(3): 372-378.