基于局部模型网络的锂电池SOC估计方法  

State of charge estimation of lithium-ion batteries using local model network

作　　者：张振强 马思乐[1] 姜向远[1] 陈纪旸 马晓静[1] Zhang Zhenqiang;Ma Sile;Jiang Xiangyuan;Chen Jiyang;Ma Xiaojing(Institute of Marine Science and Technology,Shandong University,Qingdao 266237,China;Shandong Zhengzhong Information Technology Co.,Ltd.,Jinan 250014,China)

机构地区：[1]山东大学海洋研究院,青岛266237 [2]山东正中信息技术股份有限公司,济南250014

出　　处：《仪器仪表学报》2023年第7期161-171,共11页Chinese Journal of Scientific Instrument

基　　金：山东省重点研发计划(2021CXGC011304)项目资助。

摘　　要：锂电池的荷电状态(SOC)是电池管理最重要的参数,准确的SOC估计对保证电池运作的安全性至关重要。传统基于数据驱动的SOC估计法,如神经网络,在可解释性、参数整定方面表现不足。本文提出一种基于局部模型网络和天牛须搜索优化组合的SOC估计法。首先,借助局部模型网络描述复杂非线性系统的能力和其作为灰箱模型的可解释性,将模型的工况空间分解为多个可以用简单模型表示的局部子区间,再用调度函数组合为最终的模型。其次,在网络的训练过程中,采用天牛须搜索优化算法确定分裂空间上的最佳分裂方位,很好的兼顾了模型辨识的精度和运算复杂度。最后,在锂电池动态特性数据集上与已有文献中的SOC估计法进行了对比试验,本文所提出的方法在简单工况的训练集上的RMSE误差小于0.4%,在复杂工况的测试集上的RMSE误差小于0.9%,在不同温度上的表现也相对平稳,总体展现出较高的辨识精度及泛化能力。这一特点在实测的数据集上也得到了进一步验证。State of charge(SOC)is the key parameter of the lithium-ion battery management system,which needs to be estimated accurately to ensure the battery′s safe operation.The traditionally used data-driven SOC estimation methods(e.g.,neuro-network)have limitations on interpretability and parameter tuning.This article proposes a novel method by combining the local model network(LMN)and the beetle antenna search(BAS)algorithm.Firstly,LMN,known as a grey-box model that can model complex non-linear systems with some extent of interpretability,is employed to partition the working condition space into some sub-regions that can be represented by simple models.Then,they are combined by validation function.Secondly,during the training of LMN,BAS optimization is utilized to find the optimal splitting location and orientation globally,which reaches a good trade-off between the model identification accuracy and the computation complexity.Finally,the proposed SOC estimation method is compared with two existing methods on a lithium-ion battery dynamic characteristic dataset.The RMSE is less than 0.4%on the training set under simple test driving cycle,and less than 0.9%on the testing set under complex test driving cycles.The performance on different temperatures is relatively stable too.Therefore,it shows an excellent identification accuracy and generalization capability of the method.The advantage of the proposed method is verified on real measured dataset too.

关 键 词：锂电池 SOC估计 局部模型网络 天牛须搜索优化 

分 类 号：TH89[机械工程—仪器科学与技术]