Document Type

Conference Proceeding

Conference

10th International Conference on Concrete Pavements

Publication Date

2012

Research Focus Area

Construction Engineering and Management, Transportation Engineering

City

Quebec City, Quebec, Canada

Abstract

The backcalculation of pavement layer moduli from Falling Weight Deflectometer (FWD) measured surface deflections is a challenging task. It can also be formulated as a global optimization problem with the objective of finding the optimal pavement layer moduli values that minimize the error between measured and computed surface deflections. Over the years, several backcalculation methodologies have been developed including the use of soft computing techniques such as Neural Networks (NNs), Genetic Algorithms (GAs), etc. In this paper, Differential Evolution (DE), a stochastic parallel direct search evolution strategy optimization method is integrated with rapid surrogate mapping of Finite Element (FE) solutions through Neural Networks (NNs) in developing an automated rigid pavement backcalculation toolbox.

Comments

This paper is from 10th International Conference on Concrete Pavements (2012), Quebec City, Quebec, Canada, July 8-12. p.1021-1035. Posted with permission.

Copyright Owner

International Society for Concrete Pavements

Language

en

Share

Article Location

 
COinS