基于KA Informer的电动汽车动力电池荷电状态和健康状态估算

doi:10.19595/j.cnki.1000-6753.tces.241502

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (4090 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Accurate estimation of the state of charge (SOC) and state of health (SOH) during electric vehicle power batteries’ charging and discharging phases is crucial for electric vehicle users to plan their trips rationally and to charge the battery. However, traditional methods ignore data anomalies and missingness, multidimensionality, and time dependence, resulting in low operational efficiency, poor real-time performance, and low accuracy. This paper proposes the KA Informer model for estimating the SOC and SOH. Learning the characteristics of voltage, temperature, and current data obtained from sensors can accurately obtain electric vehicle power batteries’ SOC and SOH changes.
Firstly, based on the Kolmogorov-Arnold theory, the internal weights of the Stacked Denoising Autoencoder are optimized as an activation function B-spline. Furthermore, during the initial model training phase of the Kolmogorov-Arnold stacked denoising autoencoder (KASDAE), the grid expansion technique is used to enhance the B-spline curve. Thus, the KASDAE model can clean the voltage, current, and temperature data captured from the sensors. Secondly, Fourier-mixed window attention is proposed to improve the Informer model, enhancing the model's ability to local and global information capture in long sequences. Finally, the cleaned data is fed into the Fourier-mixed window attention informer (FMWA Informer) network model. The KA Informer model contains two parts, KASDAE and FMWA Informer, which address the above issues and significantly improve the accuracy in estimating SOC and SOH.
The experimental results on the University of Maryland PL sample battery dataset, the Oxford University battery dataset, and the Nature dataset of Beijing Institute of Technology indicate that at temperatures of -40℃, -5℃, 20℃, 40℃, 45℃, and 50℃, the KA Informer model estimates SOC with mean absolute error and root mean square error of 0.24% and 0.37%, as well as SOH with 0.5% and 0.62%, respectively. The KA Informer model consumes much fewer computational resources than the traditional Informer, Transformer, LSTM, GRU, and ELM models, with faster computation speeds and lower time and space complexity. Finally, ablation experiment results show that the proposed KASDAE model cleans anomalous, vacant, and noisy data, and the proposed Fourier Mixed Window Attention Mechanism improves the Informer model. Both parts can effectively improve the accuracy of the SOC and SOH estimation.
The following conclusions can be drawn. (1) The KA Informer in the proposed model reduces the consumption of computational resources and solves the problems of slow computational efficiency and estimation accuracy. Therefore, it is suitable for estimating electric vehicle power batteries’ charging state and health status. (2) The proposed model only requires collecting voltage, current, and temperature data from sensors, which is more practical than the traditional battery model, model-based filtering method, and model-based observer approach. (3) The improved Informer model achieves the simultaneous estimation of SOC and SOH, enhancing the battery’s management ability.

Key words： Electric vehicle power battery Kolmogorov-Arnold theory stacked denoising autoencoder enhanced Informer

Received: 26 August 2024

PACS:	U469.72
	TP183

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Peng Ziran
	Wang Shunhao
	Xiao Shenping
	Xiao Lijun

Cite this article:

Peng Ziran,Wang Shunhao,Xiao Shenping等. State of Charge and State of Health Estimation of Electric Vehicle Power Battery Based on KA Informer Model[J]. Transactions of China Electrotechnical Society, 2025, 40(19): 6378-6394.

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.241502 OR https://dgjsxb.ces-transaction.com/EN/Y2025/V40/I19/6378

[1] 高德欣, 郑晓雨, 王义, 等. 电动汽车充电状态监测与多级安全预报警方法[J]. 电工技术学报, 2022, 37(9): 2252-2262.
Gao Dexin, Zheng Xiaoyu, Wang Yi, et al.A state monitoring and multi-level safety pre-warning method for electric vehicle charging process[J]. Transactions of China Electrotechnical Society, 2022, 37(9): 2252-2262.
[2] 杨续来, 袁帅帅, 杨文静, 等. 锂离子动力电池能量密度特性研究进展[J]. 机械工程学报, 2023, 59(6): 239-254.
Yang Xulai, Yuan Shuaishuai, Yang Wenjing, et al.Research progress on energy density of Li-ion batteries for EVs[J]. Journal of Mechanical Engineering, 2023, 59(6): 239-254.
[3] 杨梦洁, 杨爱军, 叶奕君, 等. 基于气体分析的锂离子电池热失控早期预警研究进展[J]. 电工技术学报, 2023, 38(17): 4507-4538.
Yang Mengjie, Yang Aijun, Ye Yijun, et al.Research progress on early warning of thermal runaway of Li-ion batteries based on gas analysis[J]. Transactions of China Electrotechnical Society, 2023, 38(17): 4507-4538.
[4] 张青松, 赵启臣. 过充循环对锂离子电池老化及安全性影响[J]. 高电压技术, 2020, 46(10): 3390-3397.
Zhang Qingsong, Zhao Qichen.Effects of overcharge cycling on the aging and safety of lithium ion batteries[J]. High Voltage Engineering, 2020, 46(10): 3390-3397.
[5] 孙丙香, 李凯鑫, 荆龙, 等. 锂离子电池不同工况下充电效果对比及用户充电方法选择研究[J]. 电工技术学报, 2023, 38(20): 5634-5644.
Sun Bingxiang, Li Kaixin, Jin Long, et al.Comparison of charging effect of lithium-ion battery under different working strategies and study on user charging method selection[J]. Transactions of China Electrotechnical Society, 2023, 38(20): 5634-5644.
[6] Kumar R R, Bharatiraja C, Udhayakumar K, et al.Advances in batteries, battery modeling, battery management system, battery thermal management, SOC, SOH, and charge/discharge characteristics in EV applications[J]. IEEE Access, 2023, 11: 105761-105809.
[7] 黄凯, 孙恺, 郭永芳, 等. 基于观测方程重构滤波算法的锂离子电池荷电状态估计[J]. 电工技术学报, 2024, 39(7): 2214-2224.
Huang Kai, Sun Kai, Guo Yongfang, et al.State of charge estimation of lithium-ion battery based on observation equation reconstruction filtering algorithm[J]. Transactions of China Electrotechnical Society, 2024, 39(7): 2214-2224.
[8] 张效伟, 衣振晓, 王凯. 基于改进自适应蜜獾优化算法优化时间卷积网络的车载锂离子电池健康状态估计[J/OL]. 发电技术, 2024: 1-13. (2024-07-22). https://kns.cnki.net/kcms/detail/detail.aspx?dbcode=CJFD&dbname=CJFD&filename=SLJX20240719001.
Zhang Xiaowei, Yi Zhenxiao, Wang Kai. Health state estimation of lithium-ion batteries for electric vehicles based on improved honey badger optimization algo-rithm optimizing temporal convolutional network[J/OL]. Power Generation Technology, 2024: 1-13. (2024-07-22). https://kns.cnki.net/kcms/detail/detail.aspx?dbcode=CJFD&dbname=CJFD&filename=SLJX20240719001.
[9] Huang Zexin, Best M, Knowles J, et al.Adaptive piecewise equivalent circuit model with SOC/SOH estimation based on extended Kalman filter[J]. IEEE Transactions on Energy Conversion, 2023, 38(2): 959-970.
[10] 贠祥, 张鑫, 王超, 等. 基于联合参数辨识的粒子群优化扩展粒子滤波的锂电池荷电状态估计[J]. 电工技术学报, 2024, 39(2): 595-606.
Yun Xiang, Zhang Xin, Wang Chao, et al.State of charge estimation of Li-ion battery using particle swarm optimization extended Kalman particle filter based on joint parameter identification[J]. Transa-ctions of China Electrotechnical Society, 2024, 39(2): 595-606.
[11] 李卓昊, 石琼林, 王康丽, 等. 锂离子电池健康状态估计方法研究现状与展望[J]. 电力系统自动化, 2024, 48(20): 109-129.
Li Zhuohao, Shi Qionglin, Wang Kangli, et al.Research status and prospects of state of health estimation methods for lithium-ion batteries[J]. Auto-mation of Electric Power Systems, 2024, 48(20): 109-129.
[12] 刘萍, 李泽文, 蔡雨思, 等. 基于等效电路模型和数据驱动模型融合的SOC和SOH联合估计方法[J]. 电工技术学报, 2024, 39(10): 3232-3243.
Liu Ping, Li Zewen, Cai Yusi, et al.Joint estimation method of SOC and SOH based on fusion of equivalent circuit model and data-driven model[J]. Transactions of China Electrotechnical Society, 2024, 39(10): 3232-3243.
[13] 刘旖琦, 雷万钧, 刘茜, 等. 基于双自适应扩展粒子滤波器的锂离子电池状态联合估计[J]. 电工技术学报, 2024, 39(2): 607-616.
Liu Yiqi, Lei Wanjun, Liu Qian, et al.Joint state estimation of lithium-ion battery based on dual adaptive extended particle filter[J]. Transactions of China Electrotechnical Society, 2024, 39(2): 607-616.
[14] 钱伟, 王浩宇, 郭向伟, 等. 联合改进滑模观测器的自适应卡尔曼滤波荷电状态估计[J]. 电工技术学报, 2025, 40(6): 1984-1994.
Qian Wei, Wang Haoyu, Guo Xiangwei, et al. State of charge estimation using adaptive kalman filter with improved sliding mode observer[J]. Transactions of China Electrotechnical Society, 2025, 40(6): 1984-1994. https://doi.org/10.19595/j.cnki.1000-6753.tces.240373.
[15] 蔡涛, 张钊诚, 袁奥特, 等. 锂离子电池储能安全管理中的机器学习方法综述[J]. 电力系统保护与控制, 2022, 50(24): 178-187.
Cai Tao, Zhang Zhaocheng, Yuan Aote, et al.Review of machine learning for safety management of Li-ion battery energy storage[J]. Power System Protection and Control, 2022, 50(24): 178-187.
[16] 高昊天, 陈云霞. 基于机器学习的锂离子电池健康状态分类与预测[J]. 北京航空航天大学学报, 2023, 49(12): 3467-3475.
Gao Haotian, Chen Yunxia.A machine learning based method for lithium-ion battery state of health classification and prediction[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49(12): 3467-3475.
[17] 丁伟, 邹复民, 刘吉顺, 等. 基于CNN-BiLSTM-Attention的电动装载机电池荷电状态预测[J/OL]. 电源学报, 2024: 1-12. (2024-04-26). https://kns.cnki.net/kcms/detail/12.1420.TM.20240426.1024.024.html.
Ding Wei, Zou Fumin, Liu Jishun, et al. Prediction of battery charge state of electric loader based on CNN-BiLSTM-Attention[J/OL]. Journal of Power Supply, 2024: 1-12. (2024-04-26). https://kns.cnki.net/kcms/detail/12.1420.TM.20240426.1024.024.html.
[18] 毛玲, 温佳林, 赵晋斌, 等. 基于集成ELM的锂离子电池充电截止电压下的SOC和SOH联合估计[J]. 电力系统保护与控制, 2023, 51(11): 86-95.
Mao Ling, Wen Jialin, Zhao Jinbin, et al.Joint estimation of SOC and SOH at lithium-ion battery charging cut-off voltage based on an ensemble extreme learning machine[J]. Power System Pro-tection and Control, 2023, 51(11): 86-95.
[19] 王桥, 魏孟, 叶敏, 等. 基于GWO-LSTM与LSSVM的锂离子电池荷电状态与容量联合估计[J]. 汽车安全与节能学报, 2022, 13(3): 571-579.
Wang Qiao, Wei Meng, Ye Min, et al.Co-estimation of state of charge and capacity of lithium-ion battery based on GWO optimized LSTM and LSSVM[J]. Automotive Safety and Energy,2022, 13(3): 571-579.
[20] 李超然, 肖飞, 樊亚翔, 等. 基于深度学习的锂离子电池SOC和SOH联合估算[J]. 中国电机工程学报, 2021, 41(2): 681-692.
Li Chaoran, Xiao Fei, Fan Yaxiang, et al.Joint estimation of the state of charge and the state of health based on deep learning for lithium-ion batteries[J]. Proceedings of the CSEE, 2021, 41(2): 681-692.
[21] Vaswani A, Shazeer N, Parmar N, et al.Attention is all you need[J]. Advances in Neural Information Processing Systems, 2017, 30: 6000-6010.
[22] 耿鑫月, 郑建飞, 胡昌华, 等. 多因素影响下双时间尺度退化设备剩余寿命预测[J]. 哈尔滨工程大学学报, 2025, 46(9): 1745-1753.
Geng Xinyue, Zheng Jianfei, Hu Changhua, et al.Remaining useful life prediction of dual time scales degraded devices under multi-factors influence[J]. Journal of Harbin Engineering University, 2025, 46(9): 1745-1753.
[23] Bao Zhengyi, Nie Jiahao, Lin Huipin, et al.TTSNet: state-of-charge estimation of Li-ion battery in electrical vehicles with temporal transformer-based sequence network[J]. IEEE Transactions on Vehicular Technology, 2024, 73(6): 7838-7851.
[24] Gao Mingyu, Shen Handan, Bao Zhengyi, et al.A correlation-augmented informer-based method for state-of-health estimation of Li-ion batteries[J]. IEEE Sensors Journal, 2024, 24(3): 3342-3353.
[25] 张博玮, 郑建飞, 胡昌华, 等. 基于流模型的缺失数据生成方法在剩余寿命预测中的应用[J]. 自动化学报, 2023, 49(1): 185-196.
Zhang Bowei, Zheng Jianfei, Hu Changhua, et al.Missing data generation method based on flow model and its application in remaining life prediction[J]. Acta Automatica Sinica, 2023, 49(1): 185-196.
[26] 欧阳天成, 徐裴行, 叶今禄, 等. 数据采集异常下的车用动力电池状态监测与故障诊断[J]. 中国电机工程学报, 2023, 43(15): 6040-6049.
Ouyang Tiancheng, Xu Peixing, Ye Jinlu, et al.Condition monitoring and fault diagnosis of vehicle power battery under abnormal data acquisition[J]. Proceedings of the CSEE, 2023, 43(15): 6040-6049.
[27] 秦潘昊, 陈威宇, 胡秦然, 等. 新型电力系统设备状态监测与故障诊断传感芯片关键技术与展望[J]. 电力系统自动化, 2024, 48(6): 83-95.
Qin Panhao, Chen Weiyu, Hu Qinran, et al.Essential technologies and prospects for device condition monitoring and diagnosis sensor chips in new power system[J]. Automation of Electric Power Systems, 2024, 48(6): 83-95.
[28] 尹杰, 刘博, 孙国兵, 等. 基于迁移学习和DAE-LSTM的锂离子电池剩余寿命预测[J]. 电工技术学报, 2024, 39(1): 289-302.
Yin Jie, Liu Bo, Sun Guobing, et al.Transfer learning DAE-LSTM for remaining useful life prediction of Li-ion batteries[J]. Transactions of China Electro-technical Society, 2024, 39(1): 289-302.
[29] 计蓉, 侯慧娟, 盛戈皞, 等. 基于粒子群优化堆叠降噪自编码器的电力设备状态数据质量提升[J]. 上海交通大学学报, 2025, 59(6): 780-788.
Ji Rong, Hou Huijuan, Sheng Gegao, et al.Data quality improvement method for power equipment condition based on stacked denoising autoencoders improved by particle swarm optimization[J]. Journal of Shanghai Jiaotong University, 2025, 59(6): 780-788.
[30] Zhou Haoyi, Zhang Shanghang, Peng Jieqi, et al.Informer: beyond efficient transformer for long sequence time-series forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence, Beijing, China, 2021: 11106-11115.