MLP neural networks for compressive strength assessment of AFRP-confined concrete

Several researchers are interested in the prediction of the compressive strength of fiber reinforced polymers confined concrete. For this purpose, many linear and nonlinear regression equations were elaborated. Alternatively, other models have been developed using artificial intelligence techniques such as neural networks. The aim of this paper is the development of a model to predict the compressive strength of concrete confined by polymers reinforced with aramid fibers using a multilayer perceptron neural network technique. However, a database of 212 experimental results obtained from the literature was used. The performance of the developed model was demonstrated by comparing the simulation results with those obtained by other theoretical models. In addition, a parametric study was conducted to verify the ability of the model to represent the effect of various parameters that control the compressive strength.