Developing a Hybrid ANN-Jaya Procedure for Backcalculation of Flexible Pavements Moduli

Abstract

This research aim is to develop a procedure for backcalculation of flexible pavements moduli based on the hybridization of the Artificial Neural Network (ANN) and the Jaya optimization algorithm. The ANN was applied to predict the pavement deflection basin, and the Jaya was employed for moduli backcalculation. The comparison of hybrid ANN-Jaya procedure with some backcalculation software indicates the high ability of the developed method to perform backcalculation of flexible pavements moduli. The comparison of the computational speed and accuracy of hybrid ANN-Jaya with ANN-PSO and ANN-GA indicates the superior performance of ANN-Jaya compared to other methods.

Keywords

• artificial neural network (ann)
• backcalculation
• falling weight deflectometer (fwd)
• flexible pavements
• jaya optimization algorithm