Prediction of burr height formation in blanking processes using neural network

Abstract

Productivity and quality in sheet metal blanking processes part can be assessed by the burr height of the sheared edge after blanking. This paper combines predictive finite element approach with neural network modelling of the leading blanking parameters in order to predict the burr height of the parts for a variety of blanking conditions. Experiments on circular blanking operation has been performed to verify the validity of the proposed approach. The numerical results obtained by finite element computation including damage and fracture modelling and tool wear effects were utilized to train the developed simulation environment based on back propagation neural network modelling. A trained neural network system was used in predicting burr height of the blanked parts versus tool wear state and punch-die clearance. The comparative study between the results obtained by neural network computation and the experimental ones gives good results.