Title: Utilisation of artificial neural networks in analysing rigid pavements response under axle loads
Abstract: The analysis of stresses, strains and deflections in rigid pavement is an important step in the mechanistic pavement design of new pavements and rehabilitation design of existing pavements. However the closed form solutions have a limited usefulness due to their very simple loading cases and pavement structure. In order to consider actual loading cases and realistic pavement structures a finite element analysis is needed. To perform finite element analysis special expertise, suitable software and a great amount of time is needed. In this research, the outputs of finite elements for multiple axle loads, pavement configurations and material properties was used to train an artificial neural network to predict stresses and deflection in rigid pavement with great accuracy. The fully trained network can be used to predict unseen data with a mean squared error of 0.002. More research can be done in the future in order to make the use of artificial neural network more attractive to practitioners.
Publication Year: 2012
Publication Date: 2012-08-01
Language: en
Type: article
Access and Citation
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot