Power transmission line icing prediction method and system based on multi-source satellite remote sensing

Abstract

The invention discloses a power transmission line icing prediction method and system based on multi-source satellite remote sensing, and belongs to the technical field of power transmission line icing prediction. The method comprises the steps: obtaining a historical data set; normalizing the indexes of the remote sensing data; based on a random forest method, obtaining a misclassification rate of the index; screening main indexes according to the misclassification rate; screening a historical data set according to the main indexes to obtain a training set; based on a multi-core relevance vector machine method, using the training set to train, and obtaining an icing prediction model of the power transmission line; and predicting the remote sensing data according to the icing prediction model to obtain the icing thickness. Based on a random forest-multi-core relevance vector machine method, multi-source satellite remote sensing data and actual icing data are used for training, an icing prediction model is constructed, and the icing prediction model is used for predicting the icing thickness according to the remote sensing data; and a plurality of kernel functions are combined to construct an icing prediction model so as to enhance the prediction effect of the model.

Description

technical field [0001] The invention relates to the technical field of transmission line icing prediction, in particular to a method and system for transmission line icing prediction based on multi-source satellite remote sensing. Background technique [0002] Icing on transmission lines often causes power accidents and seriously affects the normal operation of the power system. The icing of transmission lines can lead to flashover and tripping of transmission and transformation equipment, and can cause overhead transmission lines to be disconnected, towers to collapse, and even large-scale power grids to be paralyzed. [0003] In response to many problems caused by icing of transmission lines, since the 1950s, domestic and foreign technical forces have been invested in the observation and research of icing on transmission lines, and the mechanism, formation conditions and prediction methods of icing on transmission lines have been explored. At present, the existing icing p...

AI Technical Summary

Problems solved by technology

Some important parameters of physical theoretical models are difficult to measure in conventional meteorological observations, and there are many limitations in practical applications

Statistical models are difficult to implement through statistical prediction methods because the indicators that affect icing are very complex.

The intelligent model is currently the best type of model in the icing prediction work, but in the actual application work, due to the lack of data sources and the limitation of measurement technology, the existing models have disadvantages such as low prediction accuracy

Images