MODELING & OPTIMIZATION OF BEAD GEOMETRY IN GMAW USING GENETIC ALGORITHM & RESPONSE SURFACE METHODOLOGY

Abstract

Gas Metal Arc (GMA) welding is a manufacturing process, which is used to produce high quality joints and has to a capability to be utilized in automation systems to enhance productivity. Despite its widespread use in the various manufacturing industries, the full automation of the GMA welding has not yet been achieved partly because mathematical models for the process parameters for a given welding tasks are not fully understood and quantified. In the present work a response surface methodology and genetic algorithm approach have been suggested for determining the optimal welding conditions for the desired values. First, in the experimental region, by the application of response surface methodology mathematical models are developed between the welding input variables and bead geometry descriptors. In the second phase, to optimize multiple responses, desirability function approach has been used and to optimize the overall desirability function genetic algorithm is used. Application of the optimization method revealed a good result for finding optimal welding conditions in Gas Metal Arc Welding (GMAW) on mild steel plates of 6 mm thickness.