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

摘要

In this paper, a neural network is used to construct the relationships between welding process parameters and weld pool geometry in tungsten inert gas (TIG) welding. An optimization algorithm called simulated annealing (SA) is then applied to thenetwork 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 technique. Experimental results are presented toexplain the proposed approach.