Analytical Evaluation of Load Movement on Flexible Pavement and Selection of Optimum Neural Network Algorithm

Nowadays, Finite Element Method (FEM) is used to predict pavement responses, which presents accurate results, considering all determinative parameters, including dynamic loading, crack, non-linear elastic and viscoelastic behaviours, damping and etc. On the other hand, due to the type of loads and the material properties, pavement analysis requires a lot of time. This paper describes the use of Artificial Neural Networks (ANNs) as pavement structural analysis tools for the rapid and accurate prediction of longitudinal strains at the bottom of asphalt layer of flexible pavements subjected to moving loads. A back propagation neural network of three layers is employed. Results indicate that ANN predicts the pavement strain with high accuracy. It is also demonstrated that ANN is an excellent method that can reduce time consumed and can be used as an important tool in evaluating the pavement responses.


  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01632821
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Apr 28 2017 10:39AM