State Diagnosis of Transmission Line Faults and Defects Based on Graph Convolutional Neural Network
In order to solve the problems of frequent transmission line faults,high false alarm rate of alarm system,and depend-ence on operation and maintenance personnel analysis,this paper proposes a fault defect diagnosis method of transmission line based on graph convolutional neural network.According to the evaluation of the historical transmission line defect data,the transmission line defect state is obtained,and the k-means algorithm is used for data discretization to extract the transmission line defect features and construct feature vectors.The Mahalanobis distance is used to represent the similarity between each vector and construct the graph structure.The graph convolutional neural network is used to realize the classification of trans-mission line faults and defects,and accurately identify the state of transmission lines faults and defects.The experiment results show that the proposed method makes more accurate diagnosis results and has the best comprehensive diagnosis effect.
万方数据
维普
