PREDICTION OF SURFACE ROUGHNESS USING REGRESSION AND ANN MODELS IN CO2 LASER CUTTING OF MILD STEEL
1. dr Miloš Madić, Serbia
2. prof Miroslav Radovanović, Univerzitet u Nišu, Mašinski fakultet, Serbia
3. MSc Dušan Petković, Univerzitet u Nišu, Mašinski fakultet, Serbia
4. prof Predrag Janković, Univerzitet u Nišu, Mašinski fakultet, Serbia
5. prof Miloš Milošević, Univerzitet u Nišu, Mašinski fakultet, Serbia
In this paper, linear and quadratic regression models and artificial neural network model were developed to predict surface roughness for different values of cutting speed, laser power and assist gas pressure in CO2 laser cutting of mild steel. For the purpose of laser cutting experimentation Taguchi’s L25 orthogonal array was used arranging three factors at five levels. Surface roughness predicted values by both models were compared with the experimental values. The artificial neural network model was found to be capable of better predictions.
Ključne reči : CO2 laser cutting regression analysis artificial neural networks modeling
Tematska oblast:
Production and Computer-Aided Technologies
Datum:
06.05.2015.
