Artificial neural networks for pitting potential prediction of resistance spot welding joints of AISI 304 austenitic stainless steel

The aim of this work is to predict the influence of welding process on pitting corrosion behaviour (PCB) of resistance spot welding (RSW) joints of AISI 304 austenitic stainless steel (ASS). PCB is estimated from the pitting potential (Epitt), which is predicted from three RSW parameters. The prediction is carried out by artificial neural networks (ANNs) because the phenomena that relate the heat generated in RSW process to the PCB are highly complex and nonlinear. The study of PCB of RSW joints of ASS by ANNs is a novel research field in which this work makes a significant contribution.