Prediction of abrasiveness index of some Indian rocks using soft computing methods

The present paper mainly describes the prediction methodology to determine the Cerchar Abrasiveness Index and Penetration Rate related to rock excavation using simple geomechanical parameters as predictors. As abrasiveness of rocks is influenced by many geomechanical parameters, an attempt is made to use these parameters for its prediction using Multivariate Regression Analysis and Artificial Neural Networking. Abrasiveness Index as well as Penetration Rate are very vital in deciding the economics of the excavations as they directly govern the wear and tear of drill bit. It was observed that ANN shows a better prediction capability than MVRA using UCS, Point load index, P wave velocity and Young's modulus as predictors.