a new method for predicting indirect tensile strength of sandstone rock samples

The tensile strength (σt) of a rock plays an important role in the reliable construction ofseveral civil structures such as dam foundations and types of tunnels and excavations.determination of σt in the laboratory can be expensive, difficult, and time-consuming forcertain projects. due to the difficulties associated with the experimental procedure, it isusually preferred that the σt is evaluated in an indirect way. for these reasons, in thiswork, the adaptive network-based fuzzy inference system (anfis) is used to build aprediction model for the indirect prediction of σt of sandstone rock samples from theirphysical properties. two anfis models are implemented, i.e. anfis-subtractiveclustering method (scm) and anfis-fuzzy c-means clustering method (fcm). theanfis models are applied to the data available in the open source literature. in thesemodels, the porosity, specific gravity, dry unit weight, and saturated unit weight areutilized as the input parameters, while the measured σt is the output parameter. theperformance of the proposed predictive models is examined according to two performanceindices, i.e. mean square error (mse) and coefficient of determination (r2). the resultsobtained from this work indicate that anfis-scm is a reliable method to predict σt witha high degree of accuracy.