Fault diagnostic method for PV array based on improved wavelet neural network algorithm

As the key equipment in photovoltaic system, the operating reliability of PV array influences on the security and stability of photovoltaic system deeply. To diagnose the fault of PV array effectively, the paper proposes an improved wavelet neural network algorithm for fault diagnosis of PV array, in which uses Gaussian function as activation function and adds additional momentum method and adaptive learning rate method to the training algorithm. The proposed algorithm is applied to fault diagnosis of the actual PV array, the experimental results demonstrate the effectiveness of the algorithm.