MODELING OF CO2 LASER CUTTING PARAMETERS FOR STAINLESS STEEL 316 USING ARTIFICIAL NEURAL NETWORK TECHNIQUE

Document Type : Original Article

Authors

1 Assistant Lecturer, Modern Academy for Engineering and Tech., Cairo, Egypt.

2 Dean of Higher Institute for Engineering and Modern Technology Marg, Egypt.

3 Professor, Design and Prod. Engineering Department, Faculty of Engineering, Ain Shams University, Cairo, Egypt.

Abstract

ABSTRACT
Artificial neural networks (ANNs) became one of the most important artificial
intelligent tools that have found extensive application in solving many complicated
real-world problems. This research presents a new predictive model of CO2 laser
cutting of stainless steel 316 using ANN. The aim of this research is to develop an
(ANN) model capable to predict the laser cutting process output parameters for
certain input variables. The laser beam was used to cut 2mm thickness of stainless
steel 316 sheet. The input parameters for the neural network are: laser power (P),
traverse speed (v), assisted gas pressure(p) and focal plane position (F). The outputs
of the neural network model are three most important performance parameters
namely: upper kerf width (UKW), lower kerf width (LKW), and the average surface
roughness (Ra). The model is based on multilayer feed-forward neural network. The
experimentally acquired data is used to train, validate and test the neural network's
performance, and special graphs were drawn for this purpose. Finally, this research
work would provide a new model based on ANN technique to predict the cutting-edge
quality parameters.

Keywords