An Evaluation Approach for Prediction of Process Parameters with Genetic Algorithm

Abstract:

Gas Metal Arc (GMA) welding process has widely been employed due to the wide range of applications, cheap consumables and easy handling. A suitable mathematical model to achieve a high level of welding performance and quality should be required to study the characteristics for the effects of process parameters on the bead geometry in the GMA welding process. The objective of this paper is to present development of three empirical models (linear, curvilinear and intelligent model) based on full factorial design with two replications to estimate process parameters on top-bead width in robotic GMA welding process. Regression analysis was employed for optimization of the coefficients of linear and curvilinear models, but Genetic Algorithm (GA) was utilized to estimate the coefficients of intelligent model. ANOVA analysis using experimental data were carried out representation of main and interaction effects between process parameters on top-bead width. Resulting solutions and graphical representation showed that the developed intelligent model can be used for prediction on top-bead width in robotic GMA welding process

• Periodical: Materials Science Forum (Volumes 580-582)
• Pages: 375-378
• DOI: https://doi.org/10.4028/www.scientific.net/MSF.580-582.375
• Online since: June 2008
• Authors: D.T. Thao, Ill Soo Kim
• Keywords: Genetic Algorithm (GA), GMA Welding, Multiple Regression, Process Parameter, Robotic Arc Welding

References

This article has no references.