Research on the Reconstruction of Galloping Curve of Transmission Line Based on BP Neural Network

Galloping disasters have extremely bad effects on the operation of transmission lines, and the realization of galloping prediction is extremely necessary. The study takes the galloping sample data of the power system in Henan Province as an example to analyze the temporal and spatial distribution characteristics of meteorological data, meanwhile selects the BP neural network algorithm to complete the prediction of icing galloping on transmission lines. In line dancing prediction, the false alarm rate and false alarm rate of BP neural network algorithm are within a reasonable range. Compared with the other three prediction methods, the BP neural network algorithm has good performance in both the training set and the test set of transmission line icing galloping prediction The line galloping prediction results of the training set and the test set show that the BP neural network algorithm has ideal performance, and prediction accuracy rate increases by about 5-20%. The constructed transmission line ice galloping prediction model can give early warning of severe weather in time, ensuring the stability and safety of the power network. The research results can effectively control the hazards caused by grid galloping, improve the reliability level of transmission lines, and ensure the safety of the transmission system during peak winter.