Comparative analysis of BP neural network model prediction of asphalt aging index of hot in-place local recycling asphalt pavement

In order to use in the regeneration of asphalt pavement regeneration scientific monitoring of the asphalt pavement decay index and the next period of regeneration of aging asphalt. Based on Shenyang to Dalian and Tieling to Fuxin expressway, this paper uses the BP neural network time series model and support vector machine model as two typical forecasting methods to predict and analyze the decay of asphalt aging index in geothermal regeneration asphalt pavement, and solve it with the help of MATLAB software. The prediction results show that the support vector machine model has the higher prediction accuracy in the case of limited data. On the basis of this, Summed up the optimal maintenance time combined with the local regeneration maintenance standard in Liaoning.