Prediction of Tensile Behavior of DP 590 Steel Tailor Welded Blanks by ANN

Abstract

The forming behavior of Tailor Welded Blanks (TWB) are greatly influenced by blank conditions like thickness ratio, strength ratio, weld conditions like weld orientation, weld location, and weld properties. 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) to predict the tensile behavior of TWBs made of DP 590 Steel grade base material. ANN models are developed based on full factorial and L27 orthogonal array design of experiments method and the results are compared. Through out the work, PAM STAMP 2G® finite element (FE) code is used to simulate the tensile behavior. The strain hardening exponent ‘n’ and strength co-efficient ‘K’ are predicted and used to train the ANNs. The results obtained from expert system/ANN models are validated by comparing them with the results obtained from FE simulations for chosen intermediate levels. The results are encouraging with acceptable prediction errors.