Title: Pareto optimisation of certain quality characteristics in laser cutting by ANN-GA approach

Authors: Miloš Madić; Miroslav Radovanović; Dušan Petković

Addresses: Faculty of Mechanical Engineering in Niš, University of Niš, A. Medvedeva 14, Niš, Serbia ' Faculty of Mechanical Engineering in Niš, University of Niš, A. Medvedeva 14, Niš, Serbia ' Faculty of Mechanical Engineering in Niš, University of Niš, A. Medvedeva 14, Niš, Serbia

Abstract: Determining the optimal laser cutting conditions for simultaneous improvement of multiple cut quality characteristics is of great importance. The aim of the present research is to simultaneously optimise three cut quality characteristics such as surface roughness, kerf taper angle and burr height in CO₂ laser cutting of stainless steel. The laser cutting experiment was conducted based on Taguchi's experimental design using L₂₇ experimental plan by varying four parameters such as laser power, cutting speed, assist gas pressure and focus position at three levels. Using the obtained experimental results three mathematical models for the prediction of cut quality characteristics were developed using artificial neural networks (ANNs). The developed response models for cut quality characteristics were taken as objective functions for the multi-objective optimisation based on the genetic algorithm. The obtained optimal solution sets were used to generate 2-D and 3-D Pareto fronts. The overall improvement of about 16% was registered in multiple cut quality characteristics.

Keywords: Pareto optimisation; CO₂ laser cutting; stainless steel; artificial neural networks; ANNs; genetic algorithm.

DOI: 10.1504/IJAIP.2017.084988

International Journal of Advanced Intelligence Paradigms, 2017 Vol.9 No.4, pp.370 - 384

Received: 10 Apr 2015
Accepted: 07 Jun 2015
Published online: 10 Jul 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article