Modeling, optimization and classification of weld quality in tungsten inert gas welding

In this paper, a neural network is used to construct the relationships betw een welding process parameters and weld pool geometry in tungsten inert gas (TIG) welding. An optimization algorithm called simulated annealing (SA) i s then applied to the network for searching the process parameters with an optimal weld pool geometry. Finally, the quality of aluminum welds based on the weld pool geometry is classified and verified by a fuzzy clustering te chnique. Experimental results are presented to explain the proposed approac h. (C) 1999 Elsevier Science Ltd. All rights reserved.