Utilization of support vector machine for prediction of fracture parameters of concrete

This article employs Support Vector Machine (SVM) for determination of fracture parameters critical stress intensity factor (<TEX>KˢIc</TEX>) and the critical crack tip opening displacement (<TEX>CTODc</TEX>) of concrete. SVM that is firmly based on the theory of statistical learning theory, uses regression technique by introducing <TEX>ε</TEX>-insensitive loss function has been adopted. The results are compared with a widely used Artificial Neural Network (ANN) model. Equations have been also developed for prediction of <TEX>KˢIc</TEX> and <TEX>CTODc</TEX>. A sensitivity analysis has been also performed to investigate the importance of the input parameters. The results of this study show that the developed SVM is a robust model for determination of <TEX>KˢIc</TEX> and <TEX>CTODc</TEX> of concrete.