Prediction Of Environmental Vibration Caused By High-Speed Train Based On Random Forest

In recent years,with the rapid development of high-speed railway in China.The problem of environmental vibration caused by high-speed train is more and more prominent.Therefore,the research on the prediction of environmental vibration caused by high-speed train has very important theoretical significance and application value.In this paper,according to the transmission and reflection law of wave propagation theory at the contact surface of different media,the stiffness coefficient of simulated spring between soil and building structure is derived;considering the soil structure dynamic interaction,the three-dimensional finite element model of high-speed train track subgrade,subgrade site and contact surface building is established,and the vibration of soil and building caused by different factors is analyzed Based on the random forest algorithm,taking the influencing factors as the input and the vibration response as the output,the prediction model of environmental vibration caused by highspeed train is established,and the prediction model is optimized by the measured data to improve the accuracy of the prediction model.The main research results and conclusions of this paper are as follows:(1)In the finite element model,compared with the method of joint between soil and building,the method of elastic contact between soil and building can more truly reflect the dynamic interaction between soil and building.(2)The numerical results show that the train speed,the axle load,the distance between the track and the building,the density of the soil and the damping ratio of the soil have great influence on the environmental vibration response caused by the highspeed train.(3)The prediction model of environmental vibration caused by high-speed train based on random forest algorithm can effectively predict the vibration response of soil and buildings caused by high-speed train.(4)The accuracy of the prediction model can be improved by the depth optimization of the measured data.In this paper,the prediction model established by artificial intelligence algorithm can provide reference value for the prediction of environmental vibration caused by high-speed train.