An Artificial Intelligence Approach for Modeling Shear Modulus and Damping Ratio of Tire Derived Geomaterials

Scrap Tire Derived Materials (STDM) mixed with soil are often being used as geomaterials in civil engineering projects for reducing dynamic loads acting on geo-structures and soil liquefaction remediation purposes. On the other hand, any soil dynamic analysis involving STDM needs an estimation of dynamic characteristics of these materials. Predicting dynamic properties of STDM-soil mixture is a complicated task because there are large numbers of factors affecting dynamic properties of mixture, which might have complex relationships with each other within the soil-STDM system. There have been several attempts to evaluate and predict dynamic characteristics of STDM-soil mixtures using simple mathematical expressions. However, all those studies have been focused on case studies of some specific types of STDM and soil mixtures without considering various aspects of their dynamic behavior. 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 feedforward multilayer perceptron model with backpropagation training algorithm have better performance in predicting complex dynamic characteristics of granular mixture than SVM one.