COMPUTER AIDED DETERMINATION OF DRILLING PARAMETERS TO OBTAIN TARGETED SURFACE ROUGHNESS

TOPAL E. S., Arafat M., ÜNLÜ Ş. M.

JOURNAL OF THE BALKAN TRIBOLOGICAL ASSOCIATION, cilt.22, sa.2, ss.1544-1551, 2016 (SCI-Expanded) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 22 Sayı: 2
  • Basım Tarihi: 2016
  • Dergi Adı: JOURNAL OF THE BALKAN TRIBOLOGICAL ASSOCIATION
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.1544-1551
  • Anahtar Kelimeler: drilling, surface roughness, Artificial Neural Network
  • Akdeniz Üniversitesi Adresli: Evet

Özet

The aim of this study was to obtain targeted surface roughness values in drilling by determining drilling parameters using Artificial Neural Networks (ANN). In realizing this, two Artificial Neural Network (ANN) models were developed for the drilling process. The first model is employed for predicting the surface roughness of holes, depending on the drilling parameters (spindle speed and feed rate). The second model is involved with the experimental data and used to determine the drilling parameters to obtain targeted surface roughness. The drilling experiments were performed by changing the spindle speed and feed rate, while the other parameters were kept constant. While the surface roughness of drilled holes was predicted successfully by the first ANN Model, the optimaldrilling parameters to obtain targeted surface roughness were determined by the second model. By this approach, enhanced surface roughness (Ra) values reaching up to the 0.17 lam were obtained during the drilling of AISI 2080 steel.