The prediction of transmission line icing thickness based on MEABP

Abstract

In order to prevent the occurrence of ice accidents on transmission lines and reduce their serious impact on grid safety, a prediction model of ice thickness of transmission lines based on MEABP model is proposed. According to the characteristics of multi-dimensional and high degree of freedom of measured micro-meteorological-ice-covered data, the tensile force, wind speed, wind direction, temperature, humidity and pressure of the transmission line with high correlation with ice coating are selected by analyzing and extracting the previous statistical model. The light intensity is used as the input amount and the ice thickness is used as the output. Comparing the predicted values of the model with the measured data, the results show that the mean square error of the model is only 0.0735, and the time used is greatly shortened compared with the basic BP algorithm, which is better adapted to the timeliness and accuracy required by a monitoring system. specialty. In areas prone to glacial disasters, the application of this prediction model can reduce the losses caused by ice hazards to some extent.