基于Informer神经网络的锂离子电池容量退化轨迹预测

doi:10.19799/j.cnki.2095-4239.2023.0812

摘要/Abstract

摘要：

通过对锂离子电池容量退化轨迹的精确预测可以大幅提升电池材料的研究效率。针对Transformer网络在锂电池容量退化轨迹预测这种长时间序列预测任务中存在的问题，本工作采用滑动窗口策略，构建了一种基于Informer网络的锂离子电池容量退化轨迹预测方法。首先，利用滑动窗口对数据集进行划分和再拼接，便于神经网络挖掘数据序列内部的相关性；然后，根据Informer网络的周期性时间特征捕捉能力设计适用于锂电池数据的全局时间戳；最后，使用前10%容量数据通过多步滚动预测方法实现模型输出，缓解预测中的误差累积问题，进而得到完整的预测轨迹。通过选取不同的误差评价指标和训练过程中的时间开销，在美国马里兰大学提供的锂电池数据集上验证了所建立模型的准确性和训练效率，并在美国航空航天局提供的电池数据集上验证了模型的泛用性。本工作模型的预测结果与多层感知机神经网络、循环神经网络及Transformer网络模型对比，退化轨迹与真实轨迹最为拟合，且训练时间开销小，预测结果的平均绝对误差和均方根误差控制在2.57%和3.5%，验证了所提预测方法的有效性。

关键词: 锂离子电池, 容量退化轨迹, 长时间序列预测, 滑动窗口策略, Informer网络

Abstract:

Accurate prediction of lithium-ion battery capacity degradation trajectories enhances the efficiency of battery materials research. Aiming to resolve the challenges associated with the Transformer network in the prediction of lithium-ion battery capacity degradation trajectory, this study adopts the sliding window strategy and constructs a lithium-ion battery capacity degradation trajectory prediction method based on Informer, a time series forecasting model. First, the sliding window is used to divide and re-splice the dataset; this facilitates the neural network to exploit the correlation within the dataset; subsequently, the global timestamp applicable to lithium-ion battery data is designed according to the periodic time series capturing ability of Informer; finally, the model output is realized through the multistep rolling prediction method by using the first 10% of the battery capacity data to alleviate the error accumulation in the prediction, subsequently obtaining the complete prediction trajectory. The accuracy and training efficiency of the established model are verified using the lithium-ion battery dataset provided by the University of Maryland. Different error evaluation and time overhead metrics are selected in the training process; additionally, the generalizability of the model is verified using the lithium-ion battery dataset provided by NASA. Comparing the prediction results of the model in this study with that of the multilayer perceptron neural network, recurrent neural network, and Transformer network model, the following is observed: the degraded trajectories obtained in this study are best fitted to the real trajectories; the training time overhead is small; and, the average absolute and root mean square errors of the prediction results are controlled at 2.57% and 3.5%, thus verifying the validity of the proposed prediction method.

Key words: lithium-ion battery, capacity degradation trajectory, long-term time series forcasting, sliding window strategy, Informer network

中图分类号:

TM 911

唐梓巍, 师玉璞, 张雨禅, 周奕博, 杜慧玲. 基于Informer神经网络的锂离子电池容量退化轨迹预测[J]. 储能科学与技术, 2024, 13(5): 1658-1666.

Ziwei TANG, Yupu SHI, Yuchan ZHANG, Yibo ZHOU, Huiling DU. Prediction of lithium-ion battery capacity degradation trajectory based on Informer[J]. Energy Storage Science and Technology, 2024, 13(5): 1658-1666.

图/表 8

图1

图2

图3

图4

表1

图5

图6

表2

参考文献 10

11	邢子轩, 张凡, 武明虎, 等. 基于WD-GRU的锂离子电池剩余寿命预测[J]. 电源技术, 2022, 46(8): 867-871.
	XING Z X, ZHANG F, WU M H, et al. Remaining life prediction of lithium ion batteries based on WD-GRU[J]. Chinese Journal of Power Sources, 2022, 46(8): 867-871.
12	陈欣, 李云伍, 梁新成, 等. 基于模态分解的Transformer-GRU联合电池健康状态估计[J]. 储能科学与技术, 2023, 12(9): 2927-2936.
	CHEN X, LI Y W, LIANG X C, et al. Battery health state estimation of combined Transformer-GRU based on modal decomposition[J]. Energy Storage Science and Technology, 2023, 12(9): 2927-2936.
13	CHEN D Q, HONG W C, ZHOU X Z. Transformer network for remaining useful life prediction of lithium-ion batteries[J]. IEEE Access, 2022, 10: 19621-19628.
14	ZENG A L, CHEN M X, ZHANG L, et al. Are transformers effective for time series forecasting? [EB/OL]. 2022: arXiv: 2205.13504. http://arxiv.org/abs/2205.13504
15	SHI S Q, GAO J, LIU Y, et al. Multi-scale computation methods: Their applications in lithium-ion battery research and development[J]. Chinese Physics B, 2016, 25(1): 018212.
16	ZHOU H Y, ZHANG S H, PENG J Q, et al. Informer: Beyond efficient transformer for long sequence time-series forecasting[J]. ArXiv e-Prints, 2020: arXiv: .
17	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[EB/OL]. 2017: arXiv: 1706.03762. http://arxiv.org/abs/1706.03762
18	余宇峰, 朱跃龙, 万定生, 等. 基于滑动窗口预测的水文时间序列异常检测[J]. 计算机应用, 2014, 34(8): 2217-2220, 2226.
	YU Y F, ZHU Y L, WAN D S, et al. Time series outlier detection based on sliding window prediction[J]. Journal of Computer Applications, 2014, 34(8): 2217-2220, 2226.
19	WILLIARD N, HE W, OSTERMAN M, et al. Comparative analysis of features for determining state of health in lithium-ion batteries[J]. International Journal of Prognostics and Health Management, 2020, 4(1): doi: 10.36001/IJPHM.2013.V4I1.1437.
20	SAHA B, GOEBEL K. Battery data set[R]. NASA Ames Prognostics Data Analysis, 2007.
1	LIU X Q, ZHU S L, LIANG Y Q, et al. 3D N-doped mesoporous carbon/SnO₂ with polypyrrole coating layer as high-performance anode material for Li-ion batteries[J]. Journal of Alloys and Compounds, 2022, 892: 162083.
2	刘巧云, 祁秀秀, 郝卫强. 锂电池用正极材料钴酸锂改性研究进展[J]. 电源技术, 2022, 46(12): 1357-1359.
	LIU Q Y, QI X X, HAO W Q. Research progress on modification of lithium cobalt oxide as cathode material for lithium battery[J]. Chinese Journal of Power Sources, 2022, 46(12): 1357-1359.
3	杨欢, 乔志军. 纳米SnO₂锂电负极材料的研究进展[J]. 云南化工, 2020, 47(3): 5-6.
	YANG H, QIAO Z J. Research progress of nano SnO₂ lithium battery anode materials[J]. Yunnan Chemical Technology, 2020, 47(3): 5-6.
4	张雨, 吕瑞华, 聂丽宇, 等. 浅谈基于BP神经网络对实验室锂电池循环性能预测研究[J]. 江西化工, 2020(3): 93-95.
	ZHANG Y, LYU R H, NIE L Y, et al. Study on prediction of lithium battery cycle performance based on BP neural network[J]. Jiangxi Chemical Industry, 2020(3): 93-95.
5	黄奂奇. 基于电化学热耦合模型的锂离子电池老化状态估计[D]. 哈尔滨: 哈尔滨工业大学, 2021.
	HUANG H Q. Aging state estimation of lithium ion battery based on electrochemical thermal coupling model[D].Harbin: Harbin Institute of Technology, 2021.
6	黄泽波. 基于电化学模型估算锂电池SOC的方法研究[J]. 电源世界, 2016(7): 25-27.
	HUANG Z B. Lithium battery SOC estimation method study based on electrochemical model[J]. The World of Power Supply, 2016(7): 25-27.
7	刘月峰, 赵光权, 彭喜元. 多核相关向量机优化模型的锂电池剩余寿命预测方法[J]. 电子学报, 2019, 47(6): 1285-1292.
	LIU Y F, ZHAO G Q, PENG X Y. A lithium-ion battery remaining using life prediction method based on multi-kernel relevance vector machine optimized model[J]. Acta Electronica Sinica, 2019, 47(6): 1285-1292.
8	王超, 范兴明, 张鑫, 等. 基于IRVM的锂电池荷电状态评估方法与仿真验证[J]. 电子技术应用, 2018, 44(12): 127-130, 134.
	WANG C, FAN X M, ZHANG X, et al. An evaluation method of Li-ion batteries state of charge based on IRVM and verified by simulation[J]. Application of Electronic Technique, 2018, 44(12): 127-130, 134.
9	吴章玉, 朱成杰, 王鸣雁. 基于RNN的锂电池健康预测[J]. 绿色科技, 2021, 23(18): 201-203.
	WU Z Y, ZHU C J, WANG M Y. Health prediction of lithium battery based on RNN[J]. Journal of Green Science and Technology, 2021, 23(18): 201-203.
10	GONG Y D, ZHANG X Y, GAO D Z, et al. State-of-health estimation of lithium-ion batteries based on improved long short-term memory algorithm[J]. Journal of Energy Storage, 2022, 53(9): 1-13.

模型	RE	MAE	RMSE	time cost/s
MLP	0.3636	0.1287	0.1462	55
RNN	0.1122	0.0811	0.0961	327
LSTM	0.0877	0.0708	0.0897	206
GRU	0.0526	0.0324	0.0456	187
Transformer	0.0553	0.0332	0.0440	558
Informer	0.0322	0.0257	0.0350	180

模型	RE	MAE	RMSE	time cost/s
MLP	0.2103	0.0596	0.0662	16
RNN	0.6748	0.2074	0.2654	25
LSTM	0.4455	0.0785	0.0899	54
GRU	0.6027	0.1	0.1129	26
Transformer	0.5477	0.0572	0.067	96
Informer	0.3468	0.0349	0.046	64

[1]	缪胤宝, 张文华, 刘伟昊, 王帅, 陈哲, 彭望, 曾杰. 富锂正极材料Li_1.2Ni_0.13Co_0.13Mn_0.54O₂ 的制备及性能[J]. 储能科学与技术, 2024, 13(5): 1427-1434.
[2]	廉高棨, 叶敏, 王桥, 李岩, 麻玉川, 孙乙丁, 杜鹏辉. 基于改进模型与优化自适应CKF的锂离子电池快速变温工况下的SOC估计[J]. 储能科学与技术, 2024, 13(5): 1667-1676.
[3]	吕兆财, 王玉西, 汪智涛, 孙晓辉, 李景康. 热辊压对锂离子电池正极极片性能的影响[J]. 储能科学与技术, 2024, 13(5): 1443-1450.
[4]	李润源, 郭傅傲, 赵钢超. 集装箱式锂离子电池储能系统消防安全早期预警方法[J]. 储能科学与技术, 2024, 13(5): 1595-1602.
[5]	何林, 刘江岩, 刘彬, 李夔宁, 代帅. 数据分布多样性对锂电池SOC预测的泛化影响[J]. 储能科学与技术, 2024, 13(5): 1677-1687.
[6]	韩亚露, 陈奕戈, 邸会芳, 林杰欢, 王振兵, 张扬, 苏方远, 陈成猛. 锂离子电池不同服役工况下失效研究进展[J]. 储能科学与技术, 2024, 13(4): 1338-1349.
[7]	袁悦博, 王贺武, 孔祥栋, 蒲明伟, 孙玉坤, 韩雪冰, 欧阳明高. 金属异物缺陷演化特性及其对产线 K 值的影响机制[J]. 储能科学与技术, 2024, 13(4): 1197-1204.
[8]	李革, 孔祥栋, 孙跃东, 陈飞, 袁悦博, 韩雪冰, 郑岳久. 基于产线大数据的锂离子电池一致性动态特性分选方法[J]. 储能科学与技术, 2024, 13(4): 1188-1196.
[9]	刘淳正, 来沛霈, 孙卓, 聂耳, 张哲娟. 构造凹陷的硅碳颗粒提高锂离子电池负极电化学性能[J]. 储能科学与技术, 2024, 13(4): 1302-1309.
[10]	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.
[11]	杨家沐, 陈育新, 练成, 徐至, 刘洪来. 电极浆料涂布模头流场分析与结构优化[J]. 储能科学与技术, 2024, 13(4): 1109-1117.
[12]	王玉婷, 李秋桐, 胡一鸣, 郭新. 锂离子电池内部信号监测技术概述[J]. 储能科学与技术, 2024, 13(4): 1253-1265.
[13]	申小雨, 尹丛勃. 基于卷积Fastformer的锂离子电池健康状态估计[J]. 储能科学与技术, 2024, 13(3): 990-999.
[14]	胡大林, 任潘利, 张昌明, 杨明阳, 卢周广. Al-Y-Zr原位共掺杂提高4.53 V钴酸锂正极材料的循环性能[J]. 储能科学与技术, 2024, 13(3): 742-748.
[15]	张稚国, 李华清, 王莉, 何向明. 锂离子电池塑料-金属复合集流体的特性及制备研究进展[J]. 储能科学与技术, 2024, 13(3): 749-758.