A comparative study to estimate the mode I fracture toughness of rocks using several soft computing techniques

Fracture toughness is an important phenomenon to reveal the actual strength of fractured rock materials. It is, therefore, crucial use fracture models principally for simulating performance medium. In this study, mode-I (KIC) was investigated using several soft computing techniques. For purpose, extensive literature survey carried out obtain a comprehensive database that includes simple and widely used mechanical parameters such as uniaxial compressive (UCS) Brazilian tensile (BTS). Several techniques artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), gene expression programming (GEP), multivariate regression spline (MARS) were attempted availability these methods estimate KIC. Among techniques, it determined ANN presents best prediction capability. The correlation determination value (R2) proposed model 0.90, showing its relative success. manner, present study can be declared case indicating applicability evaluation However, number samples different types should increased improve established predictive in future studies.