The Effects of Rock Index Tests on Prediction of Tensile Strength of Granitic Samples: A Neuro-Fuzzy Intelligent System

Rock tensile strength (TS) is an essential parameter for designing structures in rock-based projects such as tunnels, dams, and foundations. During the preliminary phase of geotechnical projects, rock TS can be determined through laboratory works, i.e., Brazilian (BTS) test. However, this approach often restricted by laborious costly procedures. Hence, study attempts to estimate BTS values employing three non-destructive index tests. predictive models were developed using 127 granitic samples. Since simple regression analysis did not yield a meaningful result, development that integrate multiple input parameters considered improve prediction accuracy. The effects tests examined use linear (MLR) adaptive neuro-fuzzy inference system (ANFIS) approaches. Different strategies scenarios implemented during modelling MLR ANFIS approaches, where focus was consider most important these techniques. As according background behaviour (or neuro-fuzzy) model, predicted obtained intelligent methodology are closer actual compared which works based on statistical rules. For instance, terms error a-20 index, (0.84 1.20) (0.96 0.80) evaluation parts techniques, revealed model outperforms forecasting values. In addition, same results ranking systems authors. strong technique capacity it used other solving relevant problems.