Using conventional gas tungsten arc welding (C-GTAW) process includes some demerits, shallow penetration has been considered as the most important ones. Recently, in order to cope with the mentioned disadvantage (low penetration), using a paste like coating of activating flux during welding process known as activated GTAW (AGTAW) has been proposed. In this paper, effect of A-GTAW process input adjusting parameters including welding speed (S), welding current (C) and percentage of activating fluxes (TiO2 and SiO2) combination (F) on weld bead width (WBW), depth of penetration (DOP), and consequently aspect ratio (ASR) (the most important quality characteristics) in welding of AISI316L parts have been studied. Box-behnken design (BBD) of experiments has been used to prepare the required experimental matrix for modeling and optimization objectives. Back propagation neural network (BPNN), architecture (hidden layers number and their corresponding neurons/nodes) of which has been determined using heuristic algorithm employed to model the process outputs, the most fitted ones have been optimized using simulated annealing (SA), and particle swarm optimization (PSO) algorithms in order to obtain the desired aspect ratio, maximum depth of penetration, and minimum weld bead width. Finally, confirmation experimental tests have been carried out to evaluate the performance of the proposed method. Due to the obtained results, the suggested method for modeling and optimization of A-GTAW process is quite efficient (with less than 4% error).

Keywords