基于GA-BP神经网络的锂离子电池SOH的估算方法研究  

Study on SOH Estimation Method of Li-ion Battery Based on GA-BP Neural Network

作　　者：陈小兵 赵宝平[2] Chen Xiaobing;Zhao Baoping(Hunan Automotive Technician College,Shaoyang,Hunan 422000,China;Jinken Vocational and Technical College,Nanjing 211156,China)

机构地区：[1]湖南省汽车技师学院,湖南邵阳422000 [2]金肯职业技术学院,江苏南京211156

出　　处：《汽车电器》2025年第4期99-103,共5页Auto Electric Parts

摘　　要：锂离子电池的健康状态SOH估算对保障动力电池系统的可靠安全运行,提升新能源汽车的动力性、经济性和安全性具有重要意义。文章以电动汽车动力电池作为研究主体,运用增量容量分析(ICA)方法,提取能够表征电池健康状况的特征因子;进而基于GA-BP神经网络搭建电池SOH估计模型,借助遗传算法(GA)对误差逆传播(BP)神经网络予以优化,成功克服了BP神经网络收敛速度缓慢、全局搜索能力不足以及易陷入局部最小值等缺点。最终,利用NASA电池老化数据对该算法进行验证,结果表明,此算法能够契合动力电池SOH估算的实际需求。The estimation of the health status(SOH)of lithium-ion batteries is of great significance to ensure the reliable and safe operation of the power battery system and improve the power performance,economy and safety of new energy vehicles.This paper takes electric vehicle power battery as the main body of research,and uses incremental capacity analysis(ICA)to extract characteristic factors that can characterize battery health.Then,the battery SOH estimation model is built based on GA-BP neural network,and the error reverse propagation(BP)neural network is optimized by genetic algorithm(GA),which successfully overcomes the shortcomings of BP neural network such as slow convergence speed,insufficient global search ability and easy to fall into local minimum.Finally,NASA battery aging data is used to verify the algorithm,and the results show that the algorithm can meet the actual demand of power battery SOH estimation.

关 键 词：GA-BP神经网络 锂离子电池 SOH 估算方法 研究 

分 类 号：U463.633[机械工程—车辆工程]