Artificial neural network modeling of cut depth in rock cutting by abrasive waterjet


Karakurt İ., Aydın G., Kaya S., Hamzacebi C.

15th International Multidisciplinary Scientific Geoconference and EXPO, SGEM 2015, Albena, Bulgaristan, 18 - 24 Haziran 2015, cilt.3, ss.89-96 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası: 3
  • Basıldığı Şehir: Albena
  • Basıldığı Ülke: Bulgaristan
  • Sayfa Sayıları: ss.89-96
  • Anahtar Kelimeler: Abrasive waterjet, Rock cutting, Modeling, Artificial neural networks, PREDICTION, AWJ
  • Karadeniz Teknik Üniversitesi Adresli: Evet

Özet

ABSTRACT

© SGEM2015.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.