Original scientific paper In this paper, multi-objective optimization of the cut quality characteristics in CO2 laser cutting of AISI 304 stainless steel was discussed. Three mathematical models for the prediction of cut quality characteristics such as surface roughness, kerf width and heat affected zone were developed using the artificial neural networks (ANNs). The laser cutting experiment was planned and conducted according to the Taguchi's L27 orthogonal array and the experimental data were used to train single hidden layer ANNs using the Levenberg-Marquardt algorithm. The ANN mathematical models were developed considering laser power, cutting speed, assist gas pressure, and focus position as the input parameters. Multi-objective optimization problem was formulated using the weighting sum method in which the weighting factors that are used to combine cut quality characteristics into the single objective function were determined using the analytic hierarchy process method.
Keywords: analytic hierarchy process; artificial neural networks; CO2 laser cutting; cut quality characteristics; genetic algorithm; multi-objective optimization
Višekriterijska optimizacija karakteristika kvalitete reza kod CO2 laserskog rezanja nehrđajućeg čelikaIzvorni znanstveni članak U ovom je radu predstavljena metodologija višekriterijske optimizacije karakteristika kvalitete reza kod CO2 laserskog rezanja AISI 304 nehrđajućeg čelika (korozijski postojanog čelika). Za predviđanje karakteristika kvalitete reza kao što su hrapavost površine reza, širina reza i zona utjecaja topline, kreirani su matematički modeli pomoću umjetnih neuronskih mreža. Eksperiment laserskog rezanja je planiran i izveden prema Taguchijevom L27 ortogonalnom nizu, a eksperimentalni podaci su korišteni za treniranje umjetnih neuronskih mreža pomoću Levenberg-Marquardtovog algoritma. Matematički modeli umjetnih neuronskih mreža su kreirani uzimajući u obzir snagu lasera, brzinu rezanja, tlak pomoćnog plina i položaj fokusa kao ulazne parametre. Problem