artificial intelligence method for predicting mechanical properties of sand/glass reinforced polymer: a new model

In this paper, the aim is to propose a new model to obtain the mechanical properties of sand/glass polymeric concrete including modulus of elasticity and the ultimate tensile stress. the neural network soft computation, support vector machine (svm), and active learning method (alm) that is a fuzzy regression model are all used to construct a simple and reliable model based on experimental datasets. the experimental data are obtained via the tensile and bending tests of sand/glass reinforced polymer with different weight percentages of sand and chopped glass fibers. the extracted results are then used for training and testing of the neural network models. two different types of neural networks including feed-forward neural network (ffnn) and radial basis neural network (rbnn) are employed for connecting the properties of the sand/glass reinforced polymer to the properties of the resin and weight percentages of sand and glass fibers. besides the neural network models, the svm and alm models are applied to the problem. the models are compared with each other with respect to the statistical indices for both train and test datasets. finally, to obtain the properties of the sand/glass reinforced polymer, the most accurate model is presented as an ffnn model.