Study on Dynamic Electrical Contact Failure of Pantograph-Catenary Under Fluctuating Load

The contact state between the pantograph system affects the service performance of the electric locomotive, and the relative stability coefficient and offline rate of the current are important parameters to measure the contact reliability of the pantograph system, and the contact reliability is affected by the working conditions. Based on the sliding electrical contact experimental machine, this paper carries out the grinding experiment under different conditions of fluctuating load, different current and different speed conditions, and obtains the change law of the relative stability coefficient of the current and the offline rate under different working conditions. The support vector machine is then used to establish a current relative stability coefficient prediction model and an offline rate prediction model, and the gray wolf algorithm is used to optimize the hyperparameter of the support vector machine, and the prediction model is combined with the current relative stability coefficient failure threshold and the offline rate failure threshold to establish a prediction model for the failure of the sliding electrical contact of the pantograph network, which provides a reference for the study of the failure of the pantograph network.