The forming behavior of Tailor Welded Blanks (TWB) is influenced by thickness ratio, strength ratio, and weld conditions in a compounding fashion. It is necessary to predict suitable TWB conditions for achieving better stamped product made of welded blanks. This is quite difficult and resource intensive, requiring lot of simulations or experiments to be performed under varied base material and weld conditions. Sheet part designers will be greatly benefited if an ‘expert system’ is available that can deliver forming behavior of TWB for varied weld and blank conditions. This work primarily aims at developing an expert system based on Artificial Neural Network (ANN) model to predict the forming limit of welded blanks made of steel grade base materials. The forming limit strains (or FLC) of TWBs are predicted using Thickness Gradient based Necking Criterion (TGNC) by simulating limit dome height test in PAM STAMP 2G. The forming limit strains thus generated for wide range of TWB parameters are trained to construct ANN model/expert system. The predicted results from ANN are compared and validated with simulation results
(from TGNC) for two intermediate TWB conditions. Also the expert system predictions are validated with FLCs from Effective strain rate based (ESRC), Major strain rate based (MSRC), and Thickness strain rate based (TSRC). It is observed that the results obtained from expert system/ANN are encouraging with acceptable prediction errors. This expert system is part of the global expert system framework that is proposed earlier for designing TWB conditions that will deliver better TWB products.
