基于加权UMAP和改进BLS的锂电池温度预测

doi:10.19799/j.cnki.2095-4239.2024.0549

摘要/Abstract

摘要：

锂电池热过程的温度预测对锂电池的寿命管理和使用安全有着重要意义。一般电池管理系统热管理依赖准确的热过程模型。然而锂电池热过程的机理复杂，属于强非线性分布参数系统，具有参数时空耦合、时变、强非线性的特点，常规方法难以实现其热过程的精确建模。针对上述问题，提出了一种基于加权UMAP和改进BLS的三段式锂电池热过程建模方式。首先通过引入加权改进的均匀流形逼近与投影(weighted uniform manifold approximation and projection，WUMAP)降维算法解决非线性降维难题的同时保留了数据的全局与局部信息。然后利用一段宽度学习系统(broad learning system，BLS)模型对降维得到的时序数据预测。最后再通过一段粒子群算法优化的混合核宽度学习系统(particle swarm optimization-mixed kernel broad learning system，PSO-MKBLS)模型对时空域温度数据重构。为验证模型有效性，使用平板式32 Ah的Li(Ni_0.5Co_0.2Mn_0.3)O₂三元软包锂电池的热过程建模试验。实验结果表明：最终模型与改进前相比，R²提高0.0546，MAE和RMSE分别降低0.0082和0.0092；同时与多个对比模型相比，相对误差ARE较低(在0.035以内)，并且各误差指标也更好，证明模型具有良好的预测精度。

关键词: 分布参数系统, 锂电池温度预测, 加权均匀流形逼近与投影, 混合核宽度学习系统

Abstract:

Predicting the temperature of the thermal process in lithium batteries has significant implications for the lifespan management and safety of these batteries. Thermal management in battery management systems typically depends on accurate thermal process models. However, the thermal process in lithium batteries is complex, constituting a strongly nonlinear distributed parameter system with the characteristics of parameter spatiotemporal coupling, time variation, and strong nonlinearity. Conventional methods struggle to accurately model this thermal process.To address these issues, this study proposes a three-stage lithium battery thermal process modeling method based on weighted uniform manifold approximation and projection (WUMAP) and an improved broad learning system (BLS). First, a WUMAP dimensionality reduction algorithm was introduced to solve the nonlinear dimensionality reduction problem while preserving global and local data information. Then, a BLS model was introduced to predict the temporal data obtained from the dimensionality reduction. Finally, a mixed multikernel BLS (MKBLS) model optimized by particle swarm optimization was used to reconstruct the spatiotemporal temperature data.To validate the effectiveness of the model, modeling experiments were conducted on the thermal process of a flat plate 32 Ah Li(Ni_0.5Co_0.2Mn_0.3)O₂ ternary lithium battery. The experimental results show that the final model, compared to its previous version, increased R² by 0.0546 and decreased MAE and RMSE by 0.0082 and 0.0092, respectively. When compared with several other models, the final model demonstrated a lower relative error (ARE) of less than 0.035 and better performance on all error indicators, confirming its high prediction accuracy.

Key words: distributed parameter system, temperature prediction, weighted uniform manifold approximation and projection (WUMAP), mixed kernel broad learning system (MKBLS)

中图分类号:

TM 912.9

黎耀康, 杨海东, 徐康康, 蓝昭宇, 章润楠. 基于加权UMAP和改进BLS的锂电池温度预测[J]. 储能科学与技术, 2024, 13(9): 3006-3015.

Yaokang LI, Haidong YANG, Kangkang XU, Zhaoyu LAN, Runnan ZHANG. Temperature prediction of lithium batteries based on weighted UMAP and improved BLS[J]. Energy Storage Science and Technology, 2024, 13(9): 3006-3015.

图/表 10

图1

图2

图3

图4

图5

表1

图6

图7

图8

图9

参考文献 21

1	LU X J, ZOU W, HUANG M H. A novel spatiotemporal LS-SVM method for complex distributed parameter systems with applications to curing thermal process[J]. IEEE Transactions on Industrial Informatics, 2016, 12(3): 1156-1165. DOI: 10.1109/TII.2016.2557805.
2	XU K K, YANG H D, ZHU C J, et al. Deep extreme learning machines based two-phase spatiotemporal modeling for distributed parameter systems[J]. IEEE Transactions on Industrial Informatics, 2023, 19(3): 2919-2929. DOI: 10.1109/TII.2022.3165870.
3	WANG Y L, CHEN X J, LI C L, et al. Temperature prediction of lithium-ion battery based on artificial neural network model[J]. Applied Thermal Engineering, 2023, 228: 120482. DOI: 10.1016/j.applthermaleng.2023.120482.
4	杨小钰, 马文斌, 谢松. 高温环境轻微过放电对锂电池老化行为的影响[J/OL]. 北京航空航天大学学报. [2024-05-21]. https://doi.org/10.13700/j.bh.1001-5965.2023.0634.
	YANG X Y, MA W B, XIE S. Influence of slight over-discharge on the aging behavior of lithium-ion batteries under high temperature environment[J/OL]. Journal of Beijing University of Aeronautics and Astronautics. [2024-05-21]. https://doi.org/10.13700/j.bh.1001-5965.2023.0634.
5	陈现涛, 李雨泽, 邹晓龙, 等. 不同热处理次数对软包锂离子电池热安全性影响[J]. 科学技术与工程, 2022, 22(4): 1719-1724. DOI: 10.3969/j.issn.1671-1815.2022.04.055.
	CHEN X T, LI Y Z, ZOU X L, et al. Effect of different times of heat treatment on thermal safety of soft pack lithium-ion battery[J]. Science Technology and Engineering, 2022, 22(4): 1719-1724. DOI: 10.3969/j.issn.1671-1815.2022.04.055.
6	JIANG M, WU J G, ZHANG W A, et al. Empirical Gramian-based spatial basis functions for model reduction of nonlinear distributed parameter systems[J]. Mathematical and Computer Modelling of Dynamical Systems, 2018, 24(3): 258-274. DOI: 10.1080/13873954.2018.1446448.
7	FAN Y J, XU K K, WU H, et al. Spatiotemporal modeling for nonlinear distributed thermal processes based on KL decomposition, MLP and LSTM network[J]. IEEE Access, 2020, 8: 25111-25121. DOI: 10.1109/ACCESS.2020.2970836.
8	XU K K, LI H X, YANG H D. Local-properties-embedding-based nonlinear spatiotemporal modeling for lithium-ion battery thermal process[J]. IEEE Transactions on Industrial Electronics, 2018, 65(12): 9767-9776. DOI: 10.1109/TIE.2018.2818645.
9	XU K K, LI H X, LIU Z. ISOMAP-based spatiotemporal modeling for lithium-ion battery thermal process[J]. IEEE Transactions on Industrial Informatics, 2018, 14(2): 569-577. DOI: 10.1109/TII.2017.2743260.
10	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. DOI: 10.1016/j.jpowsour. 2014.12.013.
11	金熹. 分布参数系统时空建模方法研究及其应用[D]. 广州: 广东工业大学, 2023.
	JIN X. Research and application of spatio-temporal modeling method for distributed parameter system[D]. Guangzhou: Guangdong University of Technology, 2023.
12	ANOWAR F, SADAOUI S, SELIM B. Conceptual and empirical comparison of dimensionality reduction algorithms (PCA, KPCA, LDA, MDS, SVD, LLE, ISOMAP, LE, ICA, t-SNE)[J]. Computer Science Review, 2021, 40: 100378. DOI: 10.1016/J.COSREV. 2021.100378.
13	朱成就. 面向工业热过程的智能时空建模方法研究[D]. 广州: 广东工业大学, 2023.
	ZHU C J. Research on intelligent spatio-temporal modeling method for industrial thermal process[D]. Guangzhou: Guangdong University of Technology, 2023.
14	CHEN W X, YANG K X, YU Z W, et al. Double-kernel based class-specific broad learning system for multiclass imbalance learning[J]. Knowledge-Based Systems, 2022, 253: 109535. DOI: 10.1016/j.knosys.2022.109535.
15	LYU L, WANG W H, ZHANG Z Y, et al. A novel intrusion detection system based on an optimal hybrid kernel extreme learning machine[J]. Knowledge-Based Systems, 2020, 195: 105648. DOI: 10.1016/j.knosys.2020.105648.
16	MCINNES L, HEALY J, MELVILLE J. UMAP: Uniform manifold approximation and projection for dimension reduction[EB/OL]. 2018: 1802. 03426. [2024-02-05]. https://arxiv.org/abs/1802. 03426v3
17	GHOJOGH B, GHODSI A, KARRAY F, et al. Uniform manifold approximation and projection (UMAP) and its variants: Tutorial and survey[EB/OL]. 2021: 2109.02508. [2024-02-05]. https://arxiv.org/abs/2109.02508v1
18	夏丽莎, 方华京. 改进的加权t-SNE算法及在故障诊断中的应用[J]. 计算机应用研究, 2020, 37(7): 2078-2081. DOI: 10.19734/j.issn.1001-3695.2018.12.0952.
	XIA L S, FANG H J. Improved weighted t-SNE algorithm and application in fault diagnosis[J]. Application Research of Computers, 2020, 37(7): 2078-2081. DOI: 10.19734/j.issn.1001-3695.2018.12.0952.
19	CHEN C L P, LIU Z L. Broad learning system: An effective and efficient incremental learning system without the need for deep architecture[J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(1): 10-24. DOI: 10.1109/TNNLS. 2017.2716952.
20	周汉胜, 李泽瑞, 周金华. 基于单类分类方法的道路高排放源识别算法[J]. 传感器与微系统, 2023, 42(1): 140-143, 148. DOI: 10.13873/J.1000-9787(2023)01-0140-04.
	ZHOU H S, LI Z R, ZHOU J H. Algorithm of on-road high-emitters identification based on one-class classification method[J]. Transducer and Microsystem Technologies, 2023, 42(1): 140-143, 148. DOI: 10.13873/J.1000-9787(2023)01-0140-04.
21	吕洲, 何波, 黄镇泽, 等. 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. DOI: 10.19799/j.cnki.2095-4239.2022.0030.
	LYU Z, HE B, HUANG Z Z, et al. LE-ELM-based spatiotemporal modeling method of lithium battery thermal process[J]. Energy Storage Science and Technology, 2022, 11(10): 3200-3208. DOI: 10.19799/j.cnki.2095-4239.2022.0030.

预测模型	R²	MAE	RMSE	MSE
WUMAP-BLS-MKBLS	0.9731	0.0081	0.0129	0.000166
WUMAP-BLS-K_RBFBLS	0.9705	0.0085	0.0134	0.000180
WUMAP-BLS-K_ployBLS	0.9632	0.0097	0.0149	0.000222
LLE-ELM	0.9619	0.0104	0.0144	0.000210
KL-ELM	0.9396	0.0148	0.0187	0.000350
WUMAP-BLS-BLS	0.9355	0.0142	0.0193	0.000372
UMAP-BLS-BLS	0.9185	0.0163	0.0221	0.000488
t-SNE-BLS-BLS	0.8640	0.0226	0.0295	0.000870