Dual-Domain Conditional Generative Adversarial Networks for Predicting the Contact Force Curve of Pantograph–Catenary System in High-Speed Railway

Abstract

In electric railways, the current collection quality of pantograph–catenary systems (PCSs) is typically evaluated through numerical simulations using the finite element method, which is computationally expensive and time-consuming. To address this challenge, we propose a surrogate modeling approach that trains a conditional generative model to approximate the output of the reference numerical model. Specifically, we introduce dual-domain conditional generative adversarial networks (DD-CGAN) to generate contact force (CF) curves for various PCS parameter configurations. The generator network takes system parameters as input and produces the corresponding CF curve, while the discriminator network distinguishes between real and predicted curves in both the time and frequency domains, ensuring greater consistency. Furthermore, the feature fusion module is proposed to extract and integrate time- and frequency-domain features by using a multiscale channel attention (MSCA) mechanism. Extensive experimental results demonstrate the effectiveness and advantages of DD-CGAN for surrogate modeling of pantograph–catenary interactions. The CF curves generated by our method exhibit high consistency with simulation results from high-fidelity numerical models with a mean absolute error (MAE) of 0.9815, which is six times more accurate than state-of-the-art methods. Most importantly, our method achieves a speedup of nearly $1000\times $ compared to traditional numerical simulations, highlighting its potential for practical use in designing and optimizing catenary structural parameters.