SOC Estimation Method of New Energy Vehicle Battery Based on Genetic Algorithm
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
维普
万方数据
为解决目前新能源汽车电池荷电状态(State of Charge,SOC)估算方法存在的最大绝对误差偏大问题,文章提出一种基于遗传算法的优化方法.该方法通过构建物理电路模型来等效电池内部结构,并引入充放电分区机制补偿滞后状态,完成电流值修正.同时,离散化处理模型参数,并利用最小二乘法完成参数辨识.在神经网络(Back Propagation,BP)中,采用遗传算法估算并优化模型,以输出精确的SOC估算结果.实验结果显示,利用该方法估算的最大绝对误差稳定在0.0～0.2,显著提升了估算精度,满足预期的误差要求.
In order to solve the problem that the maximum absolute error of the current estimation methods of the State of Charge(SOC)of new energy vehicles is too large,this paper proposes an optimization method based on genetic algorithm.In this method,the internal structure of the battery is equivalent by constructing a physical circuit model,and the charging and discharging partition mechanism is introduced to compensate the lagging state,thus completing the current value correction.At the same time,the model parameters are discretized and the parameters are identified by least square method.In Back Propagation(BP),genetic algorithm is used to estimate and optimize the model to output accurate SOC estimation results.The experimental results show that the maximum absolute error estimated by this method is stable at 0.0～0.2,which significantly improves the estimation accuracy and meets the expected error requirements.
genetic algorithmnew energy vehiclesState of Charge(SOC)
维普
万方数据
