一种钠离子电池的健康状态估计方法

doi:10.3969/j.issn.2097-0706.2024.07.009

综合智慧能源 ›› 2024, Vol. 46 ›› Issue (7): 74-80.doi: 10.3969/j.issn.2097-0706.2024.07.009

一种钠离子电池的健康状态估计方法

孙文杰^1a(), 杨之乐¹^,²^,^*(), 郭媛君¹^,²(), 姚文娇^1b(), 许欢^1b(), 周博文³^,⁴()

1.中国科学院深圳先进技术研究院 a.集成技术研究所；b.碳中和技术研究所，广东深圳 518055
2.广东省碳中和研究院（韶关），广东韶关 511100
3.东北大学信息科学与工程学院，沈阳 110819
4.辽宁省综合能源优化与安全运行重点实验室，沈阳110819

收稿日期:2023-08-29 修回日期:2024-01-25 出版日期:2024-07-25
通讯作者: * 杨之乐（1987），男，副研究员，博士生导师，博士，从事AI优化、仿生算法和深度学习方面的研究，zl.yang@siat.ac.cn。
作者简介:孙文杰（2000），男，硕士生，从事基于数据驱动的电池状态估计方面的研究，wj.sun@siat.ac.cn；
郭媛君（1987），女，硕士生导师，博士，从事新能源电力系统中的数据驱动建模和人工智能技术应用方面的研究，yj.guo@siat.ac.cn；
姚文娇（1987），女，硕士生导师，博士，从事锂离子电池、钠离子电池和钾离子电池的阴极材料的开发和优化工作，wj.yao@siat.ac.cn；
许欢（1998），女，硕士生，从事钠离子电池阴极材料的开发和测试工作，huan.xu@siat.ac.cn；
周博文（1987），男，副教授，硕士生导师，博士，从事电力系统运行、稳定与控制，电动汽车与电网互动，储能，需求响应，虚拟储能，可再生能源，能源互联网，人工智能与电力系统等方面的研究，zhoubowen@ise.neu.edu.cn。
基金资助:
国家自然科学基金项目(52077213);国家自然科学基金项目(62003332);深圳市优秀创新人才基金项目(RCYX20221008093036022);南岭团队项目(220212207220502)

An estimation method for state of health of sodium-ion batteries

SUN Wenjie^1a(), YANG Zhile¹^,²^,^*(), GUO Yuanjun¹^,²(), YAO Wenjiao^1b(), XU Huan^1b(), ZHOU Bowen³^,⁴()

1. a. Institute of Integration Technical Research；b. Institute of Carbon Neutrality，Shenzhen Institute of Advanced Technology，Chinese Academy of Sciences， Shenzhen 518055，China
2. Guangdong Institute of Carbon Neutrality（Shaoguan），Shaoguan 511100，China
3. College of Information Science and Engineering，Northeastern University，Shenyang 110819，China
4. Key Laboratory of Integrated Energy Optimizationand Secure Operation of Liaoning Province，Northeastern University，Shenyang 110819，China

Received:2023-08-29 Revised:2024-01-25 Published:2024-07-25
Supported by:
National Science Foundation of China(52077213);National Science Foundation of China(62003332);Project of Shenzhen Excellent Innovative Talents(RCYX20221008093036022);"Nanling Team Project" of Shaoguan City(220212207220502)

摘要/Abstract

摘要：

钠离子电池因其经济性和材料来源丰富而成为有巨大潜力的储能设备。准确评估电池健康状态对于确保其高效、安全运行至关重要。结合循环神经网络和扩展卡尔曼滤波技术，提出一种新颖的健康状态估计框架。利用循环神经网络对时间序列数据的处理能力为健康状态估计提供强大的支持，而扩展卡尔曼滤波则用于确保状态估计的鲁棒性。通过对3个钠离子电池的试验验证，该方法显示了出色的估计效果，其中估计值与实际值的平均绝对误差约为1.79%，均方根误差约为1.38%，模型拟合度高达96.28%。此研究不仅提供了一种钠离子电池健康状态的高效估计方法，还为实际应用中的电池管理和维护提供了宝贵的参考。

关键词: 钠离子电池, 健康状态估计, 循环神经网络, 扩展卡尔曼滤波, 电池管理系统

Abstract:

Sodium ion batteries are promising energy storage devices due to their economy and abundant material sources.An accurate assessment on a battery's state of health（SOH） is essential to ensure its efficient and safe operation. Integrating the techniques of Recurrent Neural Networks（RNN） and Extended Kalman Filtering（EKF），a novel framework for SOH estimation is proposed.The RNN， with its capability to process time series data，offers a sound support for the SOH estimation，while the EKF ensures the robustness of state estimation. Through experimental validation on three sodium-ion batteries，the proposed method demonstrates outstanding estimating performances，with an average absolute error of less than 1.79%，a root mean square error of less than 1.38%，and a model fitting up to 96.28%. This research not only provides an efficient approach for the SOH estimation of sodium-ion batteries，but also offers valuable insights for battery management and maintenance in practical applications.

Key words: sodium-ion battery, state of health, recurrent neural network, extended Kalman filtering, battery management system

中图分类号:

TK01:TM912.1

孙文杰, 杨之乐, 郭媛君, 姚文娇, 许欢, 周博文. 一种钠离子电池的健康状态估计方法[J]. 综合智慧能源, 2024, 46(7): 74-80.

SUN Wenjie, YANG Zhile, GUO Yuanjun, YAO Wenjiao, XU Huan, ZHOU Bowen. An estimation method for state of health of sodium-ion batteries[J]. Integrated Intelligent Energy, 2024, 46(7): 74-80.

图/表 11

图1

图2

图3

图4

图5

表1

图6

表2

图7

表3

图8

参考文献 25

[1]	DEWAR D, GLUSHENKOV A M. Optimisation of sodium-based energy storage cells using pre-sodiation:A perspective on the emerging field[J]. Energy & Environmental Science, 2021, 14(3):1380-1401.
[2]	LIU M, ZHANG J F, SUN Z, et al. Dual mechanism for sodium based energy storage[J]. Small, 2023, 19(15):2206922.
[3]	LI H S, ZHANG X, ZHAO Z C, et al. Flexible sodium-ion based energy storage devices:Recent progress and challenges[J]. Energy Storage Materials, 2020, 26:83-104.
[4]	XU Z, WANG J. Toward emerging sodium-based energy storage technologies:From performance to sustainability[J]. Advanced Energy Materials, 2022, 12(29):2201692.
[5]	VAALMA C, BUCHHOLZ D, WEIL M, et al. A cost and resource analysis of sodium-ion batteries[J]. Nature Reviews Materials, 2018, 3(4):1-11.
[6]	ABRAHAM K M. How comparable are sodium-ion batteries to lithium-ion counterparts?[J]. ACS Energy Letters, 2020, 5(11):3544-3547.
[7]	FANG Y J, XIAO L F, CHEN Z X, et al. Recent advances in sodium-ion battery materials[J]. Electrochemical Energy Reviews, 2018, 1:294-323.
[8]	王青贵, 朱鑫, 王天华, 等. 钠离子电池发展现状[J]. 时代汽车, 2023(12):129-131.
	WANG Qinggui, ZHU Xin, WANG Tianhua, et al. Development status of sodium-ion batteries[J]. Modern Car, 2023(12):129-131.
[9]	XIANG H X, WANG Y J, LI K Q, et al. A comprehensive study on state-of-charge and state-of-health estimation of sodiumion batteries[J]. Journal of Energy Storage, 2023(72):108314.
[10]	FENG Y F, SHEN J N, CHE H Y, et al. State of health prediction for sodium-ion batteries[J]. Energy Storage Science and Technology, 2021, 10(4):1407-1415. doi: 10.19799/j.cnki.2095-4239.2021.0036
[11]	刘良俊, 高一钊, 朱景哲, 等. 数据驱动的锂离子电池健康状态估计[J]. 电池, 2022, 52(2):157-161.
	LIU Liangjun, GAO Yizhao, ZHU Jingzhe, et al. Data-driven SOH estimation of Li-ion battery[J]. Battery, 2022, 52(2):157-161.
[12]	沈佳妮, 贺益君, 马紫峰. 基于模型的锂离子电池SOC及SOH估计方法研究进展[J]. 化工学报, 2018, 69(1):309-316. doi: 10.11949/j.issn.0438-1157.20171097
	SHEN Jiani, HE Yijun, MA Zifeng. Progress of model based SOC and SOH estimation methods for lithium-ion battery[J]. CIESC Journal, 2018, 69(1):309-316.
[13]	张金龙, 佟微, 孙叶宁, 等. 锂电池健康状态估算方法综述[J]. 电源学报, 2017, 15(2):128-134. doi: 10.13234/j.issn.2095-2805.2017.2.128
	ZHANG Jinlong, TONG Wei, SUN Yening, et al. Summarize of lithium battery status of health estimation method[J]. Journal of Power Supply, 2017, 15(2):128-134. doi: 10.13234/j.issn.2095-2805.2017.2.128
[14]	SUN H L, SUN J R, ZHAO K, et al. Data-driven ICA-Bi-LSTM-combined lithium battery SOH estimation[J]. Mathematical Problems in Engineering, 2022, 2022:9645892.
[15]	周航, 程泽, 弓清瑞, 等. 基于TCN编码的锂离子电池SOH估计方法[J]. 湖南大学学报(自然科学版), 2023, 50(4):185-192.
	ZHOU Hang, CHENG Ze, GONG Qingrui, et al. SOH estimation method of lithium-ion battery based on TCN encoding[J]. Journal of Hunan University (Natural Sciences), 2023, 50(4):185-192.
[16]	张岸, 杨春德. 基于GAN-CNN-LSTM的锂电池SOH估计[J]. 电源技术, 2021, 45(7):902-906.
	ZHANG An, YANG Chunde. SOH estimation of lithium batteries based on GAN-CNN-LSTM[J]. Chinese Journal of Power Sources, 2021, 45(7):902-906.
[17]	田野, 闵锦涛. 基于PSO-XGBoost算法的多衰退特征锂离子电池SOH估计[J]. 电工材料, 2023(1):23-27.
	TIAN Ye, MIN Jintao. SOH prediction of lithium-ion battery with multiple degradation characteristics based on PSO-XGBoost algorithm[J]. Electrical Engineering Materials, 2023(1):23-27.
[18]	张吉昂, 王萍, 程泽. 基于ICA和Box-Cox变换的锂离子电池SOH估计方法[J]. 电力系统及其自动化学报, 2022, 34(2):9-15.
	ZHANG Ji'ang, WANG Ping, CHENG Ze. SOH estimation method for Li-ion battery based on ICA and Box-Cox transform[J]. Proceedings of the CSU-EPSA, 2022, 34(2):9-15.
[19]	许自强. 基于内阻观测的锂离子电池SOH估计研究[D]. 天津: 河北工业大学, 2019.
	XU Ziqiang. SOH estimation of lithium-ion battery based on resistance observation[D]. Tianjin: Hebei University of Technology, 2019.
[20]	FENG Y F, SHEN J N, MA Z F, et al. Equivalent circuit modeling of sodium-ion batteries[J]. Journal of Energy Storage, 2021, 43:103233.
[21]	WEI M, BALAYA P, YE M, et al. Remaining useful life prediction for 18650 sodium-ion batteries based on incremental capacity analysis[J]. Energy, 2022, 261:125151.
[22]	曹广华, 赵中林, 许昀昊. 基于GRU的锂电池组健康状态预测研究[J]. 吉林大学学报(信息科学版), 2022, 40(2):181-187.
	CAO Guanghua, ZHAO Zhonglin, XU Yunhao. Research on health state prediction of lithium battery pack based on GRU[J]. Journal of Jilin University (Information Science Edition), 2022, 40(2):181-187.
[23]	刘伟霞, 田勋, 肖家勇, 等. 基于混合模型及LSTM的锂电池SOH与剩余寿命预测[J]. 储能科学与技术, 2021, 10(2):689-694. doi: 10.19799/j.cnki.2095-4239.2020.0382
	LIU Weixia, TIAN Xun, XIAO Jiayong, et al. Estimation of SOH and remaining life of lithium batteries based on a combination model and long short-term memory[J]. Energy Storage Science and Technology, 2021, 10(2):689-694. doi: 10.19799/j.cnki.2095-4239.2020.0382
[24]	王凡, 史永胜, 刘博亲, 等. 基于注意力改进BiGRU的锂离子电池健康状态估计[J]. 储能科学与技术, 2021, 10(6):2326-2333. doi: 10.19799/j.cnki.2095-4239.2021.0099
	WANG Fan, SHI Yongsheng, LIU Boqin, et al. Health state estimation of lithium-ion batteries based on attention augmented BiGRU[J]. Energy Storage Science and Technology, 2021, 10(6):2326-2333. doi: 10.19799/j.cnki.2095-4239.2021.0099
[25]	李家晨, 朱成杰. 基于BiLSTM神经网络的锂电池SOH快速估计研究[J]. 无线互联科技, 2022, 19(20):146-148.
	LI Jiachen, ZHU Chengjie. Research on rapid SOH estimation of lithium battery based on BiLSTM neural network[J]. Wireless Interconnection Technology, 2022, 19(20):146-148.

算法	R_MSE/%	M_AE/%	R²/%
GRU	30.405 9	26.341 4	0.000 0
LSTM	40.642 3	36.049 5	0.000 0
BiGRU	26.882 4	23.105 7	0.000 0
BiLSTM	26.978 2	24.262 9	0.000 0
RNN	2.625 4	2.292 0	87.469 8
RNN-EKF	1.797 6	1.386 6	94.126 1

算法	R_MSE/%	M_AE/%	R²/%
GRU	5.881 5	5.222 3	38.064 5
LSTM	16.661 4	15.244 1	0.000 0
BiGRU	5.457 5	4.874 2	46.671 8
BiLSTM	11.026 4	10.294 2	0.000 0
RNN	1.406 0	1.159 0	96.460 5
RNN-EKF	1.313 4	1.074 6	96.911 3

算法	R_MSE/%	M_AE/%	R²/%
GRU	9.434 1	15.331 6	0.000 0
LSTM	31.435 5	26.751 1	0.000 0
BiGRU	28.925 8	23.972 0	0.000 0
BiLSTM	37.751 9	33.864 2	0.000 0
RNN	2.555 4	2.149 1	77.338 4
RNN-EKF	0.802 1	0.702 1	97.767 2

一种钠离子电池的健康状态估计方法

An estimation method for state of health of sodium-ion batteries

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 25

相关文章 3

编辑推荐

Metrics

本文评价

[1]	付豪, 邹花蕾, 张腾飞. 基于长短期记忆循环神经网络的变电站监控系统智能故障推理方法[J]. 综合智慧能源, 2022, 44(12): 11-17.
[2]	位帅洁, 李帅辉, 赵志鹏, 李丹. 花状二硫化锡的储钠性能研究[J]. 华电技术, 2021, 43(7): 37-41.
[3]	吕政权, 李朝阳, 王海峰, 陈怡君, 彭道刚. 基于GRU-CNN的综合能源网络安全攻击检测方法[J]. 华电技术, 2021, 43(2): 9-14.