Data Mining Based Early Warning Method of Transmission Line Icing Galloping
In recent years,transmission line galloping accidents occur frequently,seriously threatening the safe operation of the power grid.In order to achieve the purpose of early warning and early prevention,and reduce the impact of transmission line galloping on the safe operation of the power grid,a transmission line galloping early warning method is proposed based on data mining.Firstly,the trans-mission line icing growth model is established,and the weight of each meteorological factor of conductor icing is analyzed by using BP neural network.Based on the meteorological numerical prediction results and topographic information,Bayes-Adaboost method is used to model the galloping probability of transmission lines and realize the galloping probability early warning of transmission lines.Finally,the validity of the model is verified according to the historical meteorological data of Henan power grid.