* Corresponding author. Tel: +381 18500687 Fax: +381 18 588244
E-mail: madic@masfak.ni.ac.rs (M. Madić)
© 2014 Growing Science Ltd. All rights reserved.
doi: 10.5267/j.ijiec.2014.9.003
International Journal of Industrial Engineering Computations 6 (2015) 33–42
Contents lists available at GrowingScience
International Journal of Industrial Engineering Computations
homepage: www.GrowingScience.com/ijiec
ANN modeling of kerf taper angle in CO
2
laser cutting and optimization of cutting
parameters using Monte Carlo method
Miloš Madić
a*
, Miroslav Radovanović
a
and Marin Gostimirović
b
a
Faculty of Mechanical Engineering, University of Niš, A. Medvedeva 14, Niš, Serbia
b
Faculty of Technical Science, University of Novi Sad, Trg Dositeja Obradovića 6, Serbia
C H R O N I C L E A B S T R A C T
Article history:
Received June 6 2014
Received in Revised Format
September 9 2014
Accepted September 15 2014
Available online
September 22 2014
In this paper, an attempt has been made to develop a mathematical model in order to study the
relationship between laser cutting parameters such as laser power, cutting speed, assist gas
pressure and focus position, and kerf taper angle obtained in CO
2
laser cutting of AISI 304
stainless steel. To this aim, a single hidden layer artificial neural network (ANN) trained with
gradient descent with momentum algorithm was used. To obtain an experimental database for the
ANN training, laser cutting experiment was planned as per Taguchi’s L
27
orthogonal array with
three levels for each of the cutting parameters. Statistically assessed as adequate, ANN model
was then used to investigate the effect of the laser cutting parameters on the kerf taper angle by
generating 2D and 3D plots. It was observed that the kerf taper angle was highly sensitive to the
selected laser cutting parameters, as well as their interactions. In addition to modeling, by
applying the Monte Carlo method on the developed kerf taper angle ANN model, the near
optimal laser cutting parameter settings, which minimize kerf taper angle, were determined.
© 2015 Growing Science Ltd. All rights reserved
Keywords:
CO
2
laser cutting
Kerf taper
Modeling
Optimization
Artificial neural network
Monte Carlo method
1. Introduction
Laser cutting is a thermal energy based advanced machining process which has many applications in
industry where a variety of components in large numbers are required to be machined with high quality
and close tolerance at low costs. The wide spectrum of industrial application of the laser cutting is due
to its convenience of operation, high precision, small heat-affected zone (HAZ), minimum deformity,
low cost, high product quality, high cutting speed, low level of noise, flexibility, ease of automation,
etc. (Madić & Radovanović, 2013).
Due to many advantages that offer, laser cutting technology is area of continuous research and
development. A number of analytic, numerical and experimental modeling studies have been carried
out in order to analyze the laser cutting process, and some of the findings and possibilities of this
cutting technology are summarized in a comprehensive review paper (Dubey & Yadava, 2008).