With the rapid expansion of high-speed railway networks, many suspension bridges are being constructed to span mountains and canyons. To ensure the safe and smooth running of high-speed trains, various stiffness indicators of suspension bridges are strictly limited. However, the research on these stiffness indicators is primarily based on numerical simulation, and there is still a lack of sufficient experimental verification. To address this issue, this study conducted a coupled vibration test of train-track-suspension bridge using real-time hybrid simulation. In this test, the train physical substructure is established and verified, and a deep learning agent model for the track-bridge numerical substructure is established. Considering different running speeds and track irregularities, a series of tests were carried out. By analyzing the acceleration of the train body, the relationship of running smoothness indicators between numerical simulation and test has been established. Further considering the influence of temperature load, the smoothness of high-speed train in the actual running process is analyzed. This study has identified the main factors affecting the running smoothness of high-speed trains on suspension bridges, providing strong technical support for the determination of stiffness indicators.
He et al. (Thu,) studied this question.