The performance of sandwich beams in high-speed railway systems experiences severe challenges because their dynamic stability and safety need material configuration tests under high dynamic loads. The research studies sandwich beam performance which consists of 2D functionally graded face sheets and honeycomb core structures when exposed to moving loads that mimic high-speed train operations. The higher-order shear deformation theory (HSDT) enables accurate modeling of transverse shear effects in thick and layered sandwich structures without the need for shear correction factors. The researchers used Hamilton's principle to create the governing equations of motion through a detailed process which included both moving load kinematics and material gradation in face sheets. The researchers applied the differential quadrature method (DQM) to discretize the coupled partial differential equations, which achieved high precision using a minimal number of grid points, while the Newmark method was used for time integration to maintain numerical stability and operational efficiency. Researchers conduct parametric studies to study how different factors impact dynamic stability limits and vibration behavior of sandwich beams which include load velocity and material gradation indices and honeycomb core characteristics and geometric parameters. The development of a hybrid machine learning system enables better verification of numerical results which enhances the generated confidence level. The machine learning models achieve training success through the DQM-Newmark solutions which function as both verification systems and quick assessment tools. Engineers can employ the combined theoretical-numerical-data-driven method as a robust framework to assess dynamic stability and safety for advanced sandwich beam structures in high-speed railway systems.
Mao et al. (Wed,) studied this question.