DBPapers
DOI: 10.5593/SGEM2015/B13/S3.012

ARTIFICIAL NEURAL NETWORK MODELING OF CUT DEPTH IN ROCK CUTTING BY ABRASIVE WATERJET

I. Karakurt, S. Kaya, G. Aydin, C. Hamzacebi
Friday 7 August 2015 by Libadmin2015

References: 15th International Multidisciplinary Scientific GeoConference SGEM 2015, www.sgem.org, SGEM2015 Conference Proceedings, ISBN 978-619-7105-33-9 / ISSN 1314-2704, June 18-24, 2015, Book1 Vol. 3, 89-96 pp

ABSTRACT
In this study, rock cutting performance of abrasive waterjet (AWJ) was investigated and modeled using artificial neural networks (ANNs). A pre-dimensioned granitic rock was sampled and subjected to cut by an AWJ. Cut depth (CD) was assessed as the cutting performance of the AWJ. Three operating variables including traverse speed, abrasive mass flow rate and waterjet pressure were studied for obtaining different results for the CD and the CD modeled by considering these operating variables. The developed model was then tested using a test data set which was not utilized during construction of model. Additionally, performance of model was measured for showing the accuracy levels in prediction of CD. The results revealed that ANN modeling approach is capable of giving adequate prediction for CD with an acceptable accuracy level.

Keywords: Abrasive waterjet, Rock cutting, Modeling, Artificial neural networks