A polynomial model for concrete compressive strength prediction using GMDH-type neural networks and genetic algorithm

Compressive strength of concrete is experimentally determined at different ages such as 7, 28 and 42- day old as an witness specimen for final judgment. In this paper, compressive strength of 42-day is modeled and predicted using GMDH-type neural networks base on some experimental data. The aim of such modelling is to show how compressive strength of 42-day change with the variation of Compressive strength of 7 and 28 days old. In this way, a new encoding scheme is presented to genetically design generalized GMDH-type neural networks in which the connectivity configuration in such networks is not limited to adjacent layers. Such generalization of network's topology provides optimal networks in terms of hidden layers and/or number of neurons so that a simple polynomial expression to model and predict the compressive strength of 42-day old concrete consequently.