신경망을 이용한 냉간 단조품의 기하학적 형상 및 연성파괴 예측

The Prediction of Geometrical Coniguration and Ductile Fracture using the Artificial Neural Network for a Cold Forged Product

This paper suggests the scheme to simultaneously accomplish prediction of fracture initation and geometrical configuration of deformation in metal forming processes using the artificial neural network. A three-layer neural network is used and a back propagation algorithm is adapted to train the network. The Cockcroft-Latham criterion is used to estimate whether fracture occurs during the deformation process. The geometrical configuration and the value of ductile fracture are measured by finite element method. The prediction of network and numerical results of simple upsetting are compared. The proposed scheme has successfully predicted the geometrical configuration and fracture initiation.