基于粒子群优化小波神经网络的光伏阵列故障检测

Fault detection of photovoltaic array based on particle swarm optimization wavelet neural network

光伏阵列通常安放在室外,环境恶劣,因此容易出现故障,为了准确检测光伏阵列的故障,提出了基于粒子群优化小波神经网络(particle swarm optimization wavelet neural network,PSOWNN)的光伏阵列故障检测方法。分析了光伏阵列的输出特性,确定了故障检测模型的输入特征参数。结合Matlab仿真模型获取光伏阵列正常状态与故障状态时的特征参数数据,并建立基于PSOWNN的光伏阵列故障检测模型。将PSOWNN的检测结果与BP(back propagation)神经网络和小波神经网络的检测结果进行对比,结果表明基于PSOWNN的故障检测方法不仅可以有效检测光伏阵列的故障类型,而且能够提高故障检测的准确率。

Photovoltaic arrays are usually placed in harsh outdoor environments, so they are prone to failure. In order to accurately detect the faults of photovoltaic arrays, a particle swarm optimization wavelet neural network(PSOWNN) based photovoltaic array fault detection method is proposed. The output characteristic of the photovoltaic array is analyzed, and the input characteristic parameters of the fault detection model are determined. The characteristic parameter datum of the photovoltaic array in the normal state and the fault state are obtain from the Matlab simulation model, and the photovoltaic array fault detection model based on PSOWNN is established. The detection results of PSOWNN are compared with those of back propagation neural network and wavelet neural network. The simulation results show that the PSOWNN fault detection method can not only effectively detect the fault type but also improve the accuracy rate of photovoltaic array detection.