Method and system for predicting icing galloping of power transmission line

The invention provides a power transmission line icing galloping prediction method and system. The method comprises the steps of obtaining galloping monitoring data of a power transmission line; based on the galloping monitoring data of the power transmission line, utilizing a pre-trained deep learning galloping prediction model to obtain a prediction result of icing galloping of the power transmission line; wherein the deep learning galloping prediction model is obtained by training a stacked auto-encoder by taking historical galloping monitoring data as input data of training data and taking an icing galloping index value corresponding to the historical galloping monitoring data as output data of the training data; the stacked auto-encoder comprises an input layer, at least two continuous hidden layers and a Softmax output layer; according to the invention, the deep learning galloping prediction model constructed by the stacked auto-encoder based on the multilayer network structure can carry out efficient a