Contact Force Surrogate Model and Its Application in Pantograph-Catenary Parameter Optimization

The significant increase in the speed of high-speed trains has made the optimization of pantograph-catenary parameters aimed at improving current collection quality become one of the key issues that urgently need to be addressed. In this paper, a method and solutions are proposed for optimizing multiple pantograph-catenary parameters, taking into account the speed levels and engineering feasibility, for pantograph-catenary systems that contain dozens of parameters and exhibit strong nonlinear coupling characteristics. Firstly, a surrogate model capable of accurately predicting the standard deviation of contact force based on speed and 14 pantograph-catenary parameters was constructed by using the pantograph-catenary finite element model and feedforward neural network. Secondly, sensitivity analysis and rating of the pantograph-catenary parameters under different speeds were conducted using the variance-based method and the surrogate model. Finally, by combining the sensitivity analysis results and the Selective Crow Search Algorithm, joint optimization of 10 combinations of the pantograph-catenary parameters across the entire speed range was performed, providing efficient pantograph-catenary parameter optimization solutions for various engineering conditions.