Abstract:

To investigate the temperature pattern of the steel box girder of high-speed railway large-span cable-stayed bridges. Based on the measured temperature data of Yuxi River Bridge on the Shangqiu-Hefei-Hangzhou High-Speed Railway and database information, a study was conducted on the influence patterns of various meteorological factors on the temperature of the steel box girder and the temporal and spatial distribution of the temperature field using machine learning methods. By establishing machine learning models that map various meteorological factors to the uniform temperature of the steel box girder, the superiority, inferiority, and applicability of each model were analyzed, and the importance ranking of meteorological factors affecting the uniform temperature of the steel box girder was obtained. A comprehensive study on the vertical distribution pattern of the temperature of the steel box girder was conducted using machine learning methods and exponential fitting. The results show that the importance ranking of meteorological factors affecting the uniform temperature of the steel box girder from high to low is: air temperature, cumulative radiation, air pressure, humidity, radiation intensity, wind direction, horizontal visibility, wind speed, and precipitation, with the temperature importance far exceeding other meteorological factors. Among them, the atmospheric temperature 2 to 3 hours ago has the greatest impact on the uniform temperature of the steel box girder, reflecting a lag of 2 to 3 hours in the impact of atmospheric temperature changes on the uniform temperature of the steel box girder. Neural networks, random forests, and XGBoost models can all accurately predict the uniform temperature of the steel box girder, with the neural network model performing better overall. The sensitivity of the negative temperature difference of the steel box girder to meteorological factors is relatively low, and it is more related to the heat transfer mode of its own structure. The exponential function can fit the distribution of the maximum positive temperature difference of the steel box girder vertically with higher accuracy, and the parameters can be determined through machine learning methods, with different parameters having practical physical meanings. The results provide reference for the prediction and distribution pattern of temperature in the steel box girder of high-speed railway large-span cable-stayed bridges.

Key words: high-speed railway, steel box girder, temperature mode, meteorological factors, machine learning