论文部分内容阅读
光伏阵列由数量庞大的光伏组件构成,使得在发生故障时难以精确定位故障位置.针对这一难题,该文提出一种基于改进BP神经网络的光伏阵列多传感器故障检测定位方法,该方法将传感器分成若干个检测单元,在检测故障时,先将故障定位到检测单元;然后利用改进BP神经网络对检测单元内部的故障特征值与故障位置间的映射关系进行学习,从而实现光伏阵列故障点的检测与定位;最后提出一种新的非硬性故障判据.经过Matlab仿真测试,论证该方法的有效性及优异性.“,”The PV array consists of a large number of photovoltaic cell components,making it difficult to pinpoint the fault location in the event of a fault.Aiming at this problem,this paper presents a multi-sensor fault detection and positioning method based on improved BP neural network.The sensors is divided into several detection units.When the fault is detected,the fault is first positioned to the detection unit.Then,The neural network is used to study the mapping relations between the fault feature value and the fault location in the detection unit,so as to realize the selfdiscrimination of the fault location of the PV array.This fault detection and location method can improve the efficiency of large-scale PV array fault detection and positioning.Finally,a new unforced fault criterion is proposed.The validity and superiority of this method are proved by Matlab simulation test.