Application of a neural network to predict thickness strains and finite element simulation of hydro-mechanical deep drawing

Abstract

In this paper an artificial neural network (ANN) is used to predict the thickness along a cup wall in hydromechanical deep drawing. This model uses a feed-forward backprorogation neural network. After using the experimental results to train and test the network, the model was applied to new data for the prediction of thickness strains in hydro-mechanical deep drawing. The results are promising. In the present work, we also attempt to perform a finite element simulation of the process for the two dimensional axi-symmetric case using explicit finite element code LS-DYNA 2D. Counter pressure on the blank is applied by specifying the pressure boundary conditions. A comparison was made between simulated, experimental and ANN results of hydro-mechanical deep drawing using low carbon extra deep drawing grade steel sheets of 0.96 mm thickness. It was also found that by hydro-mechanical deep drawing, a higher drawability and a more uniform thickness distribution were obtained when compared to conventional deep drawing.

Investigation of Sheet Thickness and Punch Force in Die Surface Angled Hydro-mechanical Deep Drawing Method

“…The reason for this is that when the pressure is excessive, it will cause more swelling on the sheet metal material, and the sheet metal material will tear. If the chamber pressure is low, the pressure will not have an effect on the deep drawing process [6,33]. The cases where thinning occurs are situations where there is insufficient or excessive pressure.…”

Design of Drawing Compound Die for Side Hole Part

“…However all the three methods are not able tosatisfy the high precision and low cost and high efficiency requirements in modern production. The part example is used to demonstrate a concept that compounds the 4 procedures of blanking, drawing, punching and trimming in the same forming-position and those questions which can not meet modern production requirements had been solved [4,5,6].…”

Development of ANN model and study the effect of temperature on strain ratio and sensitivity index of EDD steel

“…Since it is important to know the thickness strains in the drawn cup to ensure the quality of cups, a Neural Network model has been developed to predict the thickness strains in hydromechanical deep drawing. Singh et al [12] also used ANN network to predict the thickness variation in the drawn cup.…”