Porous asphalt concrete heat conductivity coefficient calculation method based on neural network model

The invention discloses a method for calculating the heat conductivity coefficient of porous asphalt concrete based on a neural network model. The method comprises the following steps: measuring the heat conductivity coefficient of a material by adopting a steady-state method; generating a three-dimensional aggregate template; establishing a mesoscopic model of the three-dimensional heterogeneous porous asphalt concrete; performing heat conduction analysis based on a finite element method; creating a neural network data set; training a neural network model; calculating the macroscopic heat conductivity coefficient of the porous asphalt concrete; by constructing the three-dimensional heterogeneous porous asphalt concrete digital matrix model, the porous and heterogeneous microstructure characteristics of the asphalt concrete can be accurately described, and a foundation is laid for heat-conducting property calculation; by combining finite element numerical analysis with the neural network model, the macroscopi