A Machine Learning Approach for Predicting Dynamic Characteristics of Granular Mixtures

This study presents application of artificial intelligence technique in predicting dynamic properties of gravel-tire chips mixtures (GTCM). Two Artificial Intelligence (AI) techniques, Support Vector Machine (SVM) and Artificial Neural Networks (ANN) were employed for modeling shear modulus and damping ratio of TDGM. Test results have shown that shear modulus and damping ratio of the granular mixtures are remarkably influenced by gravel fraction in GTCM. Furthermore, shear modulus was found to increase with the mean effective confining pressure and gravel fraction in the mixture. It was found that a feed-forward multilayer perceptron model with back-propagation training algorithm have better performance in predicting complex dynamic characteristics of granular mixture than SVM one.