基于SSA-BP神经网络的蓄电池SOC估计  

Battery SOC Estimation Based on SSA-BP Neural Network

作　　者：李剑卿 叶伟 汪刘峰 宋海波 叶攀 LI Jianqing;YE Wei;WANG Liufeng;SONG Haibo;YE Pan(Anhui Jiyuan Electric Power System Tech Co.,Ltd.,Hefei 230088,China)

机构地区：[1]安徽南瑞继远电网技术有限公司,安徽合肥230088

出　　处：《微型电脑应用》2024年第6期79-82,共4页Microcomputer Applications

基　　金：南瑞集团有限公司(SGNR0000KJJS2106316)。

摘　　要：蓄电池作为变电站直流电源的最后一道保护屏障,一个精确的蓄电池荷电状态(SOC)估计值极为重要。为选择一个精确,易实现的SOC估计方法,采用麻雀搜索算法优化的BP神经网络作为SOC估计模型。该方法具有BP神经网络高适应性、非线性映射能力等优点,同时解决了BP神经网络容易陷入局部最优解的问题。通过数据仿真验证,SSA-BP神经网络能够更加精确地进行蓄电池SOC值估计,具有更小的误差和更快的迭代速度。As the battery is the last protective barrier of the DC power supply in the substation,an accurate battery state of charge(SOC)estimation is extremely important.In order to choose an accurate and easy-to-implement SOC estimation method,the BP neural network optimized by the sparrow search algorithm is used as the SOC estimation model.This method has the advantages of high adaptability and nonlinear mapping ability of BP neural network,and at the same time solves the problem that BP neural network is easy to fall into local optimal solution.Through data simulation verification,the SSA-BP neural network can more accurately estimate the battery SOC value,with smaller errors and faster iteration speed.

关 键 词：变电站直流电源 蓄电池SOC BP神经网络 麻雀搜索算法 

分 类 号：TM912[电气工程—电力电子与电力传动]