Tensile strength prediction of rubber blends using linear regression techniques

A wide range of mechanical properties of carbon-black reinforced rubber blends are usually studied to evaluate their performance according to the initial material composition. Different amount of each composition element generate rubber blends with different mechanical properties, subsequently model the relationship between composition and mechanical properties could contribute useful information and could also save manufacturer industries significant amounts of capital. This study models tensile strength property using linear regression techniques and low errors were obtained in comparison with the values obtained from real experiments. Linear regression and generalized linear regression techniques, simple and enhanced with Gradient Boosting techniques, were used to create linear models with RMSE errors of approximately 25.33% in tensile strength prediction.