The reliable determination of the geomechanical parameters of rocks such as unconfined compressive strength (UCS) and elastic modulus (E) using laboratory methods is difficult and time-consuming. In this regard, the development of predictive models for the estimation of these properties seems to be essential in rock engineering projects. The main purpose of this work is to construct an ANFIS approach to estimate the UCS and E of sandstones. For this purpose, a database of laboratory tests conducted on 130 sandstone samples was prepared. The data included porosity, P-wave velocity, dry density, slake durability index, and water absorption as input variables and UCS and E as the output variables. The performance of the proposed ANFIS model is evaluated based on the criteria including coefficient of determination (R2), root mean squared error (RMSE), and variance account for (VAF). The prepared ANFIS model showed a good performance in predicting UCS with R2, RMSE, and VAF values of 0.910, 0.070, and 97.00%, respectively. Likewise, the ANFIS model prepared for predicting the E showed a high performance, with its R2, RMSE, and VAF being 0.866, 0.086, and 89.00 %, respectively.
Abdi, Yasin and Taheri-Garavand, Amin
"Application of the ANFIS Approach for Estimating the Mechanical Properties of Sandstones,"
Emirates Journal for Engineering Research: Vol. 25:
4, Article 1.
Available at: https://scholarworks.uaeu.ac.ae/ejer/vol25/iss4/1