Using Genetic Algorithms to Improve Airport Pavement Structural Condition Assessment: Code Development and Case Study

In this paper, we propose a new method of optimization based on genetic algorithms using the MATLAB toolbox “Global Optimization”. The algorithm finds layers moduli flexible pavement through measurement surface deflections under assigned load conditions. First, for forward calculation is validated, then back-calculation proposed, and results are compared, in case airport pavements, with other software different techniques. goodness procedure way managing operator demonstrated by means positive feedback obtained from comparison ELMOD BackGenetic3D. Moreover, findings analysis prove that, such an GA, best solution always reached low number generations, generally less than 10, allowing reduction time choosing population big enough to select good probability, initial population, solutions close real ones. code made available that reader can easily apply it pavements fully bonded (both roads airports). particular, interested readers modify parameters (population number, stop criteria, probability mutation, cross-over, reproduction) type fitness function minimize, together geometric characteristics (number thickness range module variation). possibility change allows exploring scenarios order find terms values. It also possible intervene algorithm’s stopping criteria.