锂离子动力电池荷电状态联合估计  

Joint Estimation of State-of-Charge for Lithium-ion Power Battery

作　　者：杨云龙 徐自强 吴孟强 张大庆 李元勋[3] YANG Yun-long;XU Zi-qiang;WU Meng-qiang;ZHANG Da-qing;LI Yuan-xun(School of Materials and Energy,University of Electronic Science and Technology of China,Chengdu 611731,China;Chengdu Automobile Industry Academy,Chengdu 610101,China;State Key Laboratory of Electronic Thin Films and Integrated Devices,University of Electronic Science and Technology of China,Chengdu 610054,China)

机构地区：[1]电子科技大学材料与能源学院,成都611731 [2]成都汽车产业研究院,成都610101 [3]电子科技大学电子薄膜与集成器件国家重点实验室,成都610054

出　　处：《科学技术与工程》2018年第22期60-65,共6页Science Technology and Engineering

基　　金：国家自然科学基金(61301052;61471086);四川省科技计划重点研发项目(2017GZ0102;2017GZ0106;2017GZ0143;2017GZ0200);成都市电动乘用车产业集群协同创新项目(2017-XT00-00002-GX);中央高校基本科研业务费(ZYGX2015J095;ZYGX2016J035)资助

摘　　要：为了进一步提高锂离子动力电池荷电状态(SOC)的估计精度问题,在分析了电池电压、温度、电流和放电电量对电池SOC值的影响后,提出了一种新颖的混沌萤火虫算法(chaos firefly algorithm,CAF)和小波神经网络(WNN)相结合的锂离子动力电池SOC联合估计方法,该方法首次利用于电池SOC值估计中,通过新颖的混沌萤火虫算法优化小波神经网络,加入动量项优化网络的权值和调整修正参数,提高了网络的学习效率和SOC估计精度。克服神经网络进化缓慢并且容易陷入局部最小的缺陷,通过仿真和电池实际工况下实验,结果表明与WNN算法相比,所提出的方法具有更高的预测精度,均方根误差小于2%,验证了这一算法的可行性和有效性。In order to further improve the prediction accuracy of the state-of-charge(SOC)of the lithium battery,based on the analysis of the influence of battery voltage.temperature,current and discharge power of the battery SOC value,a novel chaotic firefly algorithm(CAF)and wavelet neural network(WNN)combined with lithium ion battery SOC estimation method was proposed,this method was first used in battery SOC in the estimation,through optimizing wavelet neural network chaotic firefly algorithm is novel,adding momentum to optimize the weight and adjust parameters,the learning efficiency and prediction accuracy were improved.To overcome the evolutionary neural network evolution slow and easy to fall into local minimum,the actual condition of the simulation and experimental results show that compared with WNN the proposed algorithm has higher prediction accuracy,the RMSE error is less than 2%,which verifies the feasibility and effectiveness of the algorithm.

关 键 词：荷电状态 萤火虫算法 小波神经网络 仿真 

分 类 号：TM912[电气工程—电力电子与电力传动]