基于递归小脑模型神经网络和卡尔曼滤波器的锂电池荷电状态预测

doi:10.3969/j.issn.2097-0706.2024.07.010

综合智慧能源 ›› 2024, Vol. 46 ›› Issue (7): 81-86.doi: 10.3969/j.issn.2097-0706.2024.07.010

• 储能技术 • 上一篇

基于递归小脑模型神经网络和卡尔曼滤波器的锂电池荷电状态预测

徐智帆¹(), 李华森²(), 李文院³(), 余凯⁴()

1.国网厦门供电公司，福建厦门 361001
2.国网漳州供电公司，福建漳州 363020
3.国网福建物资公司，福州 350001
4.国网福建建设公司，福州 350001

收稿日期:2023-04-18 修回日期:2023-07-05 出版日期:2024-07-25
作者简介:徐智帆（1995），男，助理工程师，硕士，从事变电检修试验和人工智能在新能源系统应用方面的工作，zhifan_xu@foxmail.com；
李华森（1996），男，助理工程师，硕士，从事人工智能在新能源系统应用方面的工作，1135737873@qq.com；
李文院（1996），男，助理工程师，硕士，从事智能物资管理和基于人工智能的故障诊断方面的工作，593929284@qq.com；
余凯（1997），男，助理工程师，硕士，从事电力电子故障诊断方面的工作，460960646@qq.com。

State of charge prediction for lithium-ion batteries based on KF-RCMNN

XU Zhifan¹(), LI Huasen²(), LI Wenyuan³(), YU Kai⁴()

1. State Grid Xiamen Electric Power Supply Company，Xiamen 361001，China
2. State Grid Zhangzhou Electric Power Supply Company，Zhangzhou 363020，China
3. State Grid Fujian Procurement Company Limited，Fuzhou 350001，China
4. State Grid Fujian Construction Company，Fuzhou 350001，China

Received:2023-04-18 Revised:2023-07-05 Published:2024-07-25

摘要/Abstract

摘要：

由于储能系统被广泛应用到新能源汽车、分布式发电等领域，其在运行过程中的可靠性是研究的重点之一。荷电状态（SOC）是反映电池续航能力的关键参数。为保证储能系统的正常运行，提出了一种锂电池SOC估计的方法，将递归小脑模型神经网络（RCMNN）和卡尔曼滤波器（KF）都用于荷电状态估计。为了强化RCMNN的捕获动态特征的能力，在联想记忆层和权值记忆层均加入了递归单元。将采集的电压、电流和温度作为模型的输入，用于模拟储能系统的不同充、放电情况。考虑到实际工况下电池放电的复杂性，在不同的放电条件和不同SOC初值的情况下将SOC的实际值与预测值进行对比。试验结果表明，该预测方法在不同条件下都具有较高的精度和鲁棒性。

关键词: 荷电状态, 锂电池, 储能系统, 递归小脑模型神经网络, 卡尔曼滤波器

Abstract:

Since energy storage systems（ESSs） are widely used in electric vehicles，distributed power generation and other fields，the reliability of batteries has become an issue of concern for researchers. The state of charge（SOC）is a crucial parameter reflecting the battery endurance. This study proposes a new method for lithium-ion battery SOC estimation to keep the stable working of an ESS. Recurrent cerebellar model neural network（RCMNN）and Kalman filter（KF）are both applied in the estimation method. Integrating recurrent units in associative memory space and weight memory space can improve the RCMNN in dynamic feature capture. The RCMNN and KF with inputs of voltage，current and temperature can simulate the charging and discharging of the ESS. Considering the complexity of discharging process of the battery， the measured and simulated values of the SOC under different charging and discharging conditions with varied SOC initial values are compared. The results show that the proposed method has decent accuracy and robustness under different conditions.

Key words: state of charge, lithium-ion battery, energy storage system, recurrent cerebellar model neural network, Kalman filter

中图分类号:

TM91:TK01

徐智帆, 李华森, 李文院, 余凯. 基于递归小脑模型神经网络和卡尔曼滤波器的锂电池荷电状态预测[J]. 综合智慧能源, 2024, 46(7): 81-86.

XU Zhifan, LI Huasen, LI Wenyuan, YU Kai. State of charge prediction for lithium-ion batteries based on KF-RCMNN[J]. Integrated Intelligent Energy, 2024, 46(7): 81-86.

图/表 7

图1

图2

图3

图4

图5

表1

图6

参考文献 22

[1]	徐智帆. 超级电容在微电网中的应用及健康状态分析综述[J]. 电气开关, 2022, 60(6):1-5,97.
	XU Zhifan. A review of the application and state of health for supercapacitor in microgrid[J]. Electric Switchgear, 2022, 60(6): 1-5,97.
[2]	LIN Q B, LI H S, CHAI Q Q, et al. Simultaneous and rapid estimation of state of health and state of charge for lithium-ion battery based on response characteristics of load surges[J]. Journal of Energy Storage, 2022, 55: 105495.
[3]	LENG F, TAN C M, YAZAMI R, et al. A practical framework of electrical based online state-of-charge estimation of lithium ion batteries[J]. Journal of Power Sources, 2014, 255: 423-430.
[4]	XIONG R, CAO J Y, YU Q Q, et al. Critical review on the battery state of charge estimation methods for electric vehicles[J]. IEEE Access, 2017, 6: 1832-1843.
[5]	ZHANG L, HU X S, WANG Z P, et al. Fractional-order modeling and state-of-charge estimation for ultracapacitors[J]. Journal of Power Sources, 2016, 314: 28-34.
[6]	KUNG C C, LIU S H. The state of charge estimation of lithium-ion battery based on temperature-compensated method with adaptive extended Kalman filter[C]// 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC). IEEE, 2018: 4144-4149.
[7]	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.
[8]	李超然, 肖飞, 樊亚翔. 基于循环神经网络的锂电池SOC估算方法[J]. 海军工程大学学报, 2019, 31(6):107-112.
	LI Chaoran, XIAO Fei, FAN Yaxiang. Approach to lithium battery SOC estimation based on recurrent neural network[J]. Journal of Naval University of Engineering, 2019, 31(6): 107-112.
[9]	LAI X, ZHENG Y J, SUN T. A comparative study of different equivalent circuit models for estimating state-of-charge of lithium-ion batteries[J]. Electrochimica Acta, 2018, 259: 566-577.
[10]	ZHANG Z Y, JIANG L, ZHANG L Z, et al. State-of-charge estimation of lithium-ion battery pack by using an adaptive extended Kalman filter for electric vehicles[J]. Journal of Energy Storage, 2021, 37: 102457.
[11]	WANG Y J, CHEN Z H. A framework for state-of-charge and remaining discharge time prediction using unscented particle filter[J]. Applied Energy, 2020, 260: 114324.
[12]	BURGOS C, SAEZ D, ORCHARD M E, et al. Fuzzy modelling for the state-of-charge estimation of lead-acid batteries[J]. Journal of Power Sources, 2015, 274:355-366.
[13]	CHAOUI H, IBE-EKEOCHA C C. State of charge and state of health estimation for lithium batteries using recurrent neural networks[J]. IEEE Transactions on vehicular technology, 2017, 66(10): 8773-8783.
[14]	LI C R, XIAO F, FAN Y X. An approach to state of charge estimation of lithium-ion batteries based on recurrent neural networks with gated recurrent unit[J]. Energies, 2019, 12(9):1592.
[15]	LIN Q, CHEN S, LIN C M. An optimization method for the initial parameters selection of fuzzy cerebellar model neural networks in parametric fault diagnosis[J]. International Journal of Fuzzy Systems, 2020, 22(7): 2071-2082.
[16]	LIN C M, HOU Y L, CHEN T Y, et al. Breast nodules computer-aided diagnostic system design using fuzzy cerebellar model neural networks[J]. IEEE Transactions on Fuzzy Systems, 2014, 22(3): 693-699.
[17]	GUAN J S, HONG S J, KANG S B, et al. Robust adaptive recurrent cerebellar model neural network for non-linear system based on GPSO[J]. Frontiers in Neuroscience, 2019, 13: 390.
[18]	HUYNH T T, LE T L, LIN C M. A TOPSIS multicriteria decision method-based intelligent recurrent wavelet CMAC control system design for MIMO uncertain nonlinear systems[J]. Neural Computing and Applications, 2020, 32: 4025-4043.
[19]	ZHAO J, LIN C M. Wavelet-TSK-Type fuzzy cerebellar model neural network for uncertain nonlinear systems[J]. IEEE Transactions on Fuzzy Systems, 2019, 27(3):549-558.
[20]	LIN Q B, XU Z F, LIN C M. State of health estimation and remaining useful life prediction for lithium-ion batteries using FBELNN and RCMNN[J]. Journal of Intelligent and Fuzzy System, 2021, 40(6): 10919-10933.
[21]	XU W, XU J L, LANG J F, et al. A multi-timescale estimator for lithium-ion battery state of charge and state of energy estimation using dual H infinity filter[J]. 2019, IEEE Access, 7: 181229-181241.
[22]	TIAN Y, LAI R C, LI X Y, et al. A combined method for state-of-charge estimation for lithium-ion batteries using a long short-term memory network and an adaptive cubature Kalman filter[J]. Applied Energy, 2020, 265: 114789.

放电条件	RCMNN-KF		FNN-KF
放电条件	RMSE	ME	RMSE	ME
脉冲放电	0.237 6	0.493 0	0.967 6	1.404 3
阶梯放电1	0.508 7	0.861 0	0.945 3	2.401 4
阶梯放电2	0.369 1	0.855 2	0.395 2	0.745 0

基于递归小脑模型神经网络和卡尔曼滤波器的锂电池荷电状态预测

State of charge prediction for lithium-ion batteries based on KF-RCMNN

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 22

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张勋祥, 吴杰康, 孙烨桦, 彭其坚. 平抑海上风电波动的混合储能系统容量优化配置[J]. 综合智慧能源, 2024, 46(6): 54-65.
[2]	苑曙光, 张瑜婷, 王峰, 苑广震. 蒙西地区规模化储能商业运行模式及风险分析[J]. 综合智慧能源, 2024, 46(3): 63-71.
[3]	孙娜, 董海鹰, 陈薇, 马虎林. 新型电力系统场景下网侧规模化储能二次调频控制策略[J]. 综合智慧能源, 2024, 46(2): 59-67.
[4]	乔力晖, 李明澈, 张睿, 方宗杰. 直流微网蓄电池-SMES混合储能系统容量配置方法[J]. 综合智慧能源, 2023, 45(9): 59-64.
[5]	马彦宏, 吕清泉, 张珍珍, 赵龙, 周强, 高鹏飞. 考虑储能系统SOC的双卡尔曼滤波风电功率波动平抑策略[J]. 综合智慧能源, 2023, 45(2): 61-68.
[6]	徐天韵, 陈涛, 高赐威. 电力市场背景下的近用户侧储能站容量优化配置研究[J]. 综合智慧能源, 2023, 45(2): 77-84.
[7]	吴雪琼, 夏栋. 新型主动配电网智能规划与决策技术研究综述[J]. 综合智慧能源, 2023, 45(11): 20-26.
[8]	胡祖源, 靳现林, 谭雅之, 樊静宜. 基于改进粒子群算法的分布式光伏及储能系统优化配置[J]. 综合智慧能源, 2023, 45(1): 49-57.
[9]	冶兆年, 赵长禄, 王永真, 韩恺, 刘超凡, 韩俊涛. 基于纳什议价的共享储能能源互联网络双目标优化[J]. 综合智慧能源, 2022, 44(7): 40-48.
[10]	杜欣烨, 王建喜, 孙永辉, 何逸, 吴鹏鹏, 周伟. 计及海水淡化制氢的微电网混合储能优化规划[J]. 综合智慧能源, 2022, 44(5): 49-55.
[11]	刘静, 史梦鸽, 胡永锋. 含电池储能系统的智能楼宇多阶段能量管理策略[J]. 综合智慧能源, 2022, 44(3): 29-37.
[12]	管馨, 陈涛, 高赐威. 适应风电参与电力市场的需求侧储能负荷运行优化研究[J]. 综合智慧能源, 2022, 44(2): 35-41.
[13]	周成伟, 李鹏, 俞斌, 俞天杨, 孟伟. 风光储微电网储能系统容量优化配置[J]. 综合智慧能源, 2022, 44(12): 56-61.
[14]	张兴科, 魏朝阳, 王康平, 田浩, 缪鹏飞, 周霞, 魏聪. 面向高比例光伏并网的火电爬坡压力缓解策略[J]. 综合智慧能源, 2022, 44(1): 1-8.
[15]	李勇琦, 雷旗开, 王浩, 华思聪. 基于BP神经网络的梯次利用电池健康状态诊断[J]. 华电技术, 2021, 43(7): 42-46.