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 meth-od,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 prob-lem 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
Key words
substation DC power supply/battery state of charge(SOC)/BP neural network/sparrow search algorithm
维普
万方数据