This study addresses a modeling and optimization procedure in tungsten inert gas (TIG) welding of AL5052 alloy. Experimental required data for modeling and optimization purposes gathered using central composite design (CCD). Welding current (I), frequency (F), welding speed (S) and gap (G) are the most important parameters in TIG welding process. The weld bead geometry (WBG) and heat affected zone (HAZ) considered as the most important quality measures of the welding process. Image processing technique is used to take accurate measurements of WBGs and HAZs. In order to determine the relationship between input and output parameters based on regression models, the response surface methodology (RSM) has been used. The significance of the process parameters on the quality characteristics of the process was also evaluated quantitatively using the analysis of variance (ANOVA) method. Next, simulated annealing (SA) algorithm has been used to optimize HAZ and WBG separately (single-objective optimization) and simultaneously (multi- objective optimization). The results based on the analysis of RSM has also been compared with the optimized results using SA algorithm. Verification tests demonstrate that the proposed RSM-SA approach is quite efficient in single and multi-criteria modeling and optimization of TIG welding process

Keywords