Simulation based expert system to predict the deep drawing behaviour of tailor welded blanks

摘要: The forming behaviour of tailor welded blanks (TWB) is influenced by sheet thickness ratio, strength ratio and weld conditions in a synergistic fashion. In most the cases, these parameters deteriorate TWB. It necessary to predict suitable TWB for achieving better stamped product made blanks. This work primarily aims at developing an expert system based on artificial neural network (ANN) model deep drawing TWBs steel grade base materials. important characteristics namely maximum draw depth line profile are predicted within wide range varied blank conditions. square cup test simulated elastic-plastic finite element code, PAM STAMP 2G®, generating required output data ANN training validation. predictions from encouraging with acceptable prediction errors.