Metal Inert Gas (MIG) Welding Process Optimization using Teaching-Learning Based Optimization (TLBO) Algorithm

Abstract

Welding parameters play a great significant role in determining the weld joint quality in terms of weld-bead geometry. To obtain a good quality weld, it is necessary to select the proper welding parameters. This study focuses on the optimization parameters for Metal Inert Gas (MIG) welding on AISI 1018 mild steel by Teaching-Learning Based Optimization (TLBO) algorithm. The input parameters considered are welding current, workpiece thickness, voltage and wire feed rate. Taguchi's L27 orthogonal array have been used for design of experiment (DoE) and the mathematical models have been developed for output response using MINITAB16. Results show that welding current and voltage are statistical significance on overall MIG welding performance. © 2017 Elsevier Ltd.