Research on Intelligent Verification Technology of Bus Protection SCD File in Intelligent Substation Reconstruction and Expansion Project Based on Convolutional Neural Network

Abstract

Aiming at the problem of wrong modification of bus protection SCD file during the implementation of intelligent substation reconstruction and expansion project, an intelligent verification of bus protection SCD file of intelligent substation reconstruction and expansion project based on convolution neural network is proposed for the first time, which can verify the correctness of bus protection SCD file modification of 220kV intelligent station before and after reconstruction and expansion. This method first analyzes the interaction between bus protection and virtual terminals of different types of interval devices, and leads to the feasibility of using convolution neural network to check the correctness of SCD file modification of bus protection. Secondly, the principle and training process of convolution neural network are introduced in detail. Then it focuses on the realization of SCD file intelligent verification based on convolution neural network, and gives 9 kinds of neural network structure parameters trained under different types of intervals and different construction methods; finally, taking the main transformer extension SCD check neural network as an example, the trained network parameters are analyzed to verify the superiority and rationality of the neural network structure parameters and learning parameters given by this method. It has been verified that the correct rate of 9 kinds of neural networks can reach more than 95%.