Scientia Iranica

Scientia Iranica

Simultaneous Optimization of Joint Edge Geometry and Process Parameters in Gas Metal Arc Welding Using Integrated ANN - PSO Approach

Authors
M. Azadi Moghaddam
R. Golmezerji
F. Kolahan
Ferdowsi University of Mashhad, Department of Mechanical Engineering, Mashhad, Iran
10.24200/sci.2017.4031
Abstract
Gas metal arc welding (GMAW) can be considered the most extensively used process in automated welding due to its high productivity. However, to simultaneously achieve several conflicting objectives such as reducing production time, increasing product quality, full penetration, proper joint edge geometry and optimal selection of process parameters a multi criteria optimization procedure must be used. The aim of this research is to develop a multi criteria modeling and optimization procedure for GMAW process. To simultaneously predict weld bead geometry (WBG) characteristics and heat affected zone (HAZ), a back propagation neural network (BPNN) has been proposed. The experimentally derived data sets are used in training and testing of the network. Results demonstrated that the finely tuned BPNN model can closely simulate actual GMAW process with less than 1% error. Next, to simultaneously optimize process characteristics the BPNN model is inserted into a particle swarm optimization (PSO) algorithm. The proposed technique determines a set of parameters values and the work piece groove angle in such a way that a pre specified WBG is achieved while the HAZ of the weld joint is minimized. Optimal results were verified through additional experiments.
Keywords
Gas Metal Arc Welding (GMAW)
 Joint Edge Geometry
Heat Affected Zone (HAZ)
  Multi-Criteria Optimization
artificial neural network (ANN)
Particle swarm optimization (PSO) algorithm
Scientia Iranica
Volume 24, Issue 1 - Serial Number 1
Transactions on Mechanical Engineering (B)
February 2017
Pages 260-273

  • Receive Date 24 July 2016
  • Accept Date 27 July 2017