Fault Diagnosis of Power Grid Based on Convolutional Neural Network

Abstract

Due to the operation of regional networking, the scale of the power grid is becoming larger and larger, and a fault in the power grid needs to be located in the fault area timely and accurately. The models and structures of BP neural network and convolution neural network are analyzed. The training and test samples are constructed for a power grid model, and the BP neural network and convolution neural network are used for simulation verification respectively. The simulation results show that the convolutional neural network based grid fault diagnosis method has higher accuracy and fault tolerance.