Evaluation of shear strength parameters of granulated waste rubber using artificial neural networks and group method of data handling

Utilizing rubber shreds in the civil engineering industry, such as geotechnical structures, can accelerate the generated waste tire recycling process in an economic and environmentally-friendly manner. However, understanding the strength parameters of rubber grains is required for engineering designs and can be acquired through experimental tests. In this study, small and large direct shear tests were implemented to specify shear strength parameters of five groups of rubber grains, which are different in gradation and size. Moreover, Articial Neural Networks (ANN) were developed based on the test results, and optimized networks, which best captured the shear stress (T ) and vertical strain ("v) behavior of rubbers, were introduced. Additionally, a prediction model using the combinatorial algorithm in Group Method of Data Handling (GMDH) was proposed for the shear strength and vertical strain in the arrangement of closed-form equations. The performance and accuracy of the proposed models were checked using correlation coeffcient (R) between the experimental and predicted data, and the existing Mean Square Error (MSE) was evaluated. R-values of the modeled and "v were found to be equal to 0.9977 and 0.9994 for ANN and 0.9862 and 0.9942 for GMDH models, respectively. The GMDH proposed models were presented as comparatively simple explicit mathematical equations for further applications.