Visual analytics and prediction system based on deep belief networks for icing monitoring data of overhead power transmission lines

Abstract

In this paper, a system is proposed for visualizing and analyzing icing monitoring data of power transmission lines. The distributions of temperature and humidity are visualized by two-dimensional maps with customizable map layers. The multi-dimensional monitoring data are visualized as parallel coordinates. Moreover, a prediction algorithm that is based on a hybrid deep belief network is integrated into the system for predicting the icing thickness. If the icing thickness of a certain location exceeds the threshold value, the historical meteorological data of the location can be visualized as line graphs, which helps to choose the appropriate de-icing measures. According to the experimental results, our system is capable of reflecting the statistical features of icing monitoring data with high accuracy of icing thickness prediction.