Prediction model for icing growth characteristics of high-speed railway contact lines

Abstract

The sliding electrical contact is the only means by which high-speed trains obtain energy. When icing occurs on the contact lines, the impact vibrations of the pantograph-catenary system are further exacerbated, electrical arcing becomes more frequent, and abnormal wear is caused, seriously threatening the safety of the energy supply for high-speed railways. To address the unclear mechanisms, unpredictable patterns, and challenging characterization of contact lines icing, this paper proposes a dynamic simulation method for the first time. Furthermore, a surrogate model for predicting contact line icing is developed using deep learning algorithms. First, based on grid updating, flow field analysis, and icing calculations, key icing parameters are obtained to establish a numerical model of contact lines icing under time-varying meteorological parameters. Then, the effects of factors such as wind speed, temperature, and liquid water content on the dynamic evolution characteristics of contact line icing are analyzed. Finally, using the CNN-GRU algorithm, a prediction model for contact line icing is constructed to predict the icing mass and contours. This research clarifies the evolution patterns of contact lines icing, addresses challenges in monitoring and predicting icing states, and lays a theoretical foundation for high-speed railways' safe and stable operation under icing conditions.