基于LE -ELM的锂电池热过程时空建模方法

doi:10.19799/j.cnki.2095-4239.2022.0030

储能科学与技术 ›› 2022, Vol. 11 ›› Issue (10): 3200-3208.doi: 10.19799/j.cnki.2095-4239.2022.0030

基于LE -ELM的锂电池热过程时空建模方法

吕洲¹(), 何波¹, 黄镇泽²(), 梁志勇²

^1.广州港科大技术有限公司，广东广州 511458
^2.广东产品质量监督检测研究院，广东广州 510670

收稿日期:2022-01-14 修回日期:2022-03-01 出版日期:2022-10-05 发布日期:2022-10-10
通讯作者: 黄镇泽 E-mail:lvzhoubang@163.com;363611009@qq.com
作者简介:吕洲（ 1986－），男，硕士，高级工程师，研究方向为锂电池管理技术及动力电池系统， E-mail：lvzhoubang@163.com；

LE-ELM-based spatiotemporal modeling method of lithium battery thermal process

Zhou LYU¹(), Bo HE¹, Zhenze HUANG²(), Zhiyong LIANG²

^1.Guangzhou Hong Kong University of Science and Technology Co. , Ltd, Guangzhou 511458, Guangdong, China
^2.Guangdong Testing Institute of Product Quality Supervision, Guangzhou 510670, Guangdong, China

Received:2022-01-14 Revised:2022-03-01 Online:2022-10-05 Published:2022-10-10
Contact: Zhenze HUANG E-mail:lvzhoubang@163.com;363611009@qq.com

摘要/Abstract

摘要：

锂电池管理系统对于锂电池的效率、寿命和安全至关重要，而电池管理系统对电池的控制、热管理和故障诊断等都需要依赖于准确的电池热过程模型。然而锂电池热过程属于一种具有强非线性特征的分布参数系统，电池内部的温度分布是时空耦合的，并且具有无限维的特性，使得建模存在很大的困难。针对上述问题，本工作提出了一种基于LE-ELM的锂离子电池热过程建模方法。首先使用基于拉普拉斯特征映射（laplacian eigenmaps，LE）的局部非线性降维方法构建空间基函数，以表征系统固有的非线性拓扑特征；利用所得的基函数进行时空分离，获得原始数据的低阶时序表达；然后用极限学习机（extreme learning machine，ELM）以时间系数和对应的电流电压输入信号来近似低阶时序模型。最后集成辨识出的ELM模型与空间基函数，通过时空综合重构出锂离子电池的全局时空模型。为验证算法的有效性，使用所提出的方法对三元软包锂电池热过程进行建模。

关键词: 分布参数系统, 锂电池热过程, 拉普拉斯特征映射, 极限学习机

Abstract:

The efficiency, life, and safety of lithium batteries are influenced by the lithium battery management system. The control, thermal management, and fault diagnosis of the battery management system depend on the accuracy of the battery's thermal process model. However, the thermal process of the lithium battery is a distributed parameter system with strong nonlinear characteristics. The temperature distribution inside the battery is spatiotemporally coupled and has infinite dimension characteristics, making modeling extremely challenging. To solve these problems, a Laplacian eigenmaps-extreme learning machine (LE-ELM)-based spatiotemporal modeling method for the thermal process of lithium batteries is proposed. First, a local nonlinear dimension reduction method based on LE is developed to learn the spatial basis function to represent the inherent nonlinear topological feature of the original system. Second, a low-dimensional representation of the original data can be generated using time/space separation and the spatial basis functions. Then, ELM is used to approximate the low-order time-series model with the low-dimensional representation and the corresponding current and voltage input signals. Finally, the spatiotemporal temperature distribution can be reconstructed using time/space synthesis. A thermal process of ternary soft-pack lithium battery was modeled using our proposed algorithm to verify the proposed method.

Key words: distributed parameter system, lithium battery thermal process, laplacian eigenmaps (LE), extreme learning machine (ELM)

中图分类号:

TM 912.9

吕洲, 何波, 黄镇泽, 梁志勇. 基于LE -ELM的锂电池热过程时空建模方法[J]. 储能科学与技术, 2022, 11(10): 3200-3208.

Zhou LYU, Bo HE, Zhenze HUANG, Zhiyong LIANG. LE-ELM-based spatiotemporal modeling method of lithium battery thermal process[J]. Energy Storage Science and Technology, 2022, 11(10): 3200-3208.

图/表 10

图1

图2

图3

图4

图5

表1

图6

图7

图8

表2

参考文献 27

1	LU L G, HAN X B, LI J Q, et al. A review on the key issues for lithium-ion battery management in electric vehicles[J]. Journal of Power Sources, 2013, 226: 272-288.
2	RAHIMI-EICHI H, BARONTI F, CHOW M Y. Online adaptive parameter identification and state-of-charge coestimation for lithium-polymer battery cells[J]. IEEE Transactions on Industrial Electronics, 2014, 61(4): 2053-2061.
3	缪平, 姚祯, LEMMON John, 等. 电池储能技术研究进展及展望[J]. 储能科学与技术, 2020, 9(3):670-678.
	MIAO P, YAO Z, LEMMON J, et al. Current situations and prospects of energy storage batteries[J]. Energy Storage Science and Technology, 2020, 9(3):670-678.
4	张志超, 郑莉莉, 杜光超, 等. 锂离子电池充放电过程中产热特性研究综述[J]. 储能科学与技术, 2019, 8(S1): 31-37.
	ZHANG Z C, ZHENG L L, DU G C, et al. Review of research on heat generation characteristics during charging and discharging of lithium ion batteries[J]. Energy Storage Science and Technology, 2019, 8(S1): 31-37.
5	徐蒙, 张竹茜, 贾力, 等. 圆柱形锂离子动力电池放电过程电化学与传热特性研究[J]. 中国电机工程学报, 2013, 33(32): 54-61, 5.
	XU M, ZHANG Z Q, JIA L, et al. Study on electrochemical and heat transfer characteristics of cylindrical lithium-ion power battery during discharge cycle[J]. Proceedings of the CSEE, 2013, 33(32): 54-61, 5.
6	LI J, CHENG Y, AI L H, et al. 3D simulation on the internal distributed properties of lithium-ion battery with planar tabbed configuration[J]. Journal of Power Sources, 2015, 293: 993-1005.
7	LIN X F, PEREZ H E, MOHAN S, et al. A lumped-parameter electro-thermal model for cylindrical batteries[J]. Journal of Power Sources, 2014, 257: 1-11.
8	陈实, 方凯正, 穆道斌, 等. 神经网络模型在锂离子电池表面温度预测中的应用研究[J]. 北京理工大学学报, 2013, 33(4): 421-424.
	CHEN S, FANG K Z, MU D B, et al. Application of neural network model to predicting surface temperature of lithium-ion battery[J]. Transactions of Beijing Institute of Technology, 2013, 33(4): 421-424.
9	宋明超, 李国春, 王丽梅, 等. 基于电化学阻抗谱的锂离子电池内部温度估算研究[J]. 农业装备与车辆工程, 2020, 58(5): 56-61.
	SONG M C, LI G C, WANG L M, et al. Estimation of internal temperature of lithium-ion battery based on electrochemical impedance spectroscopy[J]. Agricultural Equipment & Vehicle Engineering, 2020, 58(5): 56-61.
10	PARK H M, CHO D H. The use of the Karhunen-Loève decomposition for the modeling of distributed parameter systems[J]. Chemical Engineering Science, 1996, 51(1): 81-98.
11	CHRISTOFIDES P D, CHOW J. Nonlinear and robust control of PDE systems: Methods and applications to transport-reaction processes[J]. Applied Mechanics Reviews, 2002, 55(2): B29-B30.
12	QI C K, LI H X, ZHANG X X, et al. Time/Space-separation-based SVM modeling for nonlinear distributed parameter processes[J]. Industrial & Engineering Chemistry Research, 2011, 50(1): 332-341.
13	LU X J, ZOU W, HUANG M H. An adaptive modeling method for time-varying distributed parameter processes with curing process applications[J]. Nonlinear Dynamics, 2015, 82(1/2): 865-876.
14	LIU Z, LI H X. Extreme learning machine based spatiotemporal modeling of lithium-ion battery thermal dynamics[J]. Journal of Power Sources, 2015, 277: 228-238.
15	WANG M L, LI H X. Real-time estimation of temperature distribution for cylindrical lithium-ion batteries under boundary cooling[J]. IEEE Transactions on Industrial Electronics, 2017, 64(3): 2316-2324.
16	BALACHANDAR S. Turbulence, coherent structures, dynamical systems and symmetry[J]. AIAA Journal, 1998, 36(3): 496.
17	ROWEIS S T, SAUL L K. Nonlinear dimensionality reduction by locally linear embedding[J]. Science, 2000, 290(5500): 2323-2326.
18	PRABHAKAR S K, RAJAGURU H. Expectation maximization based PCA and hessian LLE with suitable post classifiers for epilepsy classification from EEG signals[C]//Proceedings of the Eighth International Conference on Soft Computing and Pattern Recognition (SoCPaR 2016), 2018: 364-374.
19	BELKIN M, NIYOGI P. Laplacian eigenmaps and spectral techniques for embedding and clustering[M/OL]//Advances in Neural Information Processing Systems 14. The MIT Press, 2002: https://doi.org/10.7551/mitpress/1120.003.0080 .
20	KIM U S, SHIN C B, KIM C S. Modeling for the scale-up of a lithium-ion polymer battery[J]. Journal of Power Sources, 2009, 189(1): 841-846.
21	WU B, YUFIT V, MARINESCU M, et al. Coupled thermal-electrochemical modelling of uneven heat generation in lithium-ion battery packs[J]. Journal of Power Sources, 2013, 243: 544-554.
22	BELKIN M, NIYOGI P. Laplacian eigenmaps for dimensionality reduction and data representation[J]. Neural Computation, 2003, 15(6): 1373-1396.
23	王秀峰, 卢桂章. 系统建模与辨识[M]. 北京: 电子工业出版社, 2004.
	WANG X F, LU G Z. System modeling and identificatio [M]. Beijing: Publishing House of Electronics Industry, 2004.
24	HUANG G B, ZHU Q Y, SIEW C K. Extreme learning machine: Theory and applications[J]. Neurocomputing, 2006, 70(1/2/3): 489-501.
25	HUANG G B, WANG D H, LAN Y. Extreme learning machines: A survey[J]. International Journal of Machine Learning and Cybernetics, 2011, 2(2): 107-122.
26	LU X J, ZHOU C, HUANG M H, et al. Regularized online sequential extreme learning machine with adaptive regulation factor for time-varying nonlinear system[J]. Neurocomputing, 2016, 174: 617-626.
27	HUANG G B, ZHOU H M, DING X J, et al. Extreme learning machine for regression and multiclass classification[J]. IEEE Transactions on Systems, Man, and Cybernetics Part B(Cybernetics), 2012, 42(2): 513-529.

激活函数	RMSE	时间/s
Sigmoid	0.0017	0.021
tanh	0.0019	0.026
ReLU	0.0079	0.011

方法	训练阶段		测试阶段
方法	时间/s	RMSE	时间/s	RMSE
KL-ELM	4.59	0.0051	0.018	0.9182
LLE-ELM	7.95	0.0018	0.035	0.5606

基于LE -ELM的锂电池热过程时空建模方法

LE-ELM-based spatiotemporal modeling method of lithium battery thermal process

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 27

相关文章 1

编辑推荐

Metrics

本文评价