FENet: A Physics‐Informed Dynamics Prediction Model of Pantograph‐Catenary Systems in Electric Railway

ABSTRACT In electric railways, the interaction performance between the pantograph and catenary is crucial for maintaining a stable current supply. Establishing high‐fidelity numerical models using the finite element method is generally desirable, yet it involves considerable computational complexity and time demands. In this paper, we propose a novel dynamic prediction model that integrates physical information and data‐driven approaches to solve the pantograph‐catenary interaction, called FENet. Specifically, there are two significant aspects: (1) A deep learning framework is developed for efficient simulation. The network utilises the temporal convolutional network to extract short‐term local features. Simultaneously, the attention‐based long short‐term memory is leveraged to capture the long‐term dependencies in the interaction sequence. FENet establishes the dynamic relationship between the system state and excitation variables, achieving fast and accurate simulation. (2) We integrate multiple physics‐informed loss terms to handle implicit constraints within motion equations, which leverages physical principles to guide the learning process. Additionally, a dynamic weighting mechanism adaptively balances the contributions of various terms in the physics‐based loss function. Experimental results reveal that FENet exhibits effectiveness and robustness against different external excitations and achieves long‐term dynamic response prediction with negligible computational effort. Moreover, it shows promising potential for real‐time simulation and feedback in pantograph hardware‐in‐the‐loop test rigs.