Igor Duplančić

Parametric and non-parametric modelling of earing and hardness of deep drawn cups

Abstract This study compares different approaches in modelling the earing phenomenon and hardness of cups in deep drawing process. The blank holder force (BHF), annealing temperature and annealing time of blanks before deep drawing process have been chosen as the three influential parameters on the earing and hardness. To obtain mathematical models for the earing and hardness of the deep drawn cups, the methodology of artificial neural networks have been used. Bayesian network, radial basis function network, Gaussian processes and multilayer perceptron are four different ANN approaches that have been used for the modelling. The research has been conducted on a cold rolled Al–Fe–Si (AA8011A) aluminium sheet. After obtaining the mathematical models describing the influence of BHF and annealing on hardness and earing, a comparison of the proposed models has been performed. A search for the optimal parameters of deep drawing process has been carried out.

Possibility of grain size prediction in AA5754 aluminium ingots using neural networks

Abstract The approach to the grain size prediction in AA5754 Al alloy ingots based on artificial neural networks (ANN) has been used in the present study. The ANN has been trained on data that was measured in the real industrial conditions during the process of direct chill Al ingots casting. A very complex relation between the numerous casting parameters and the microstructure of the ingots justifies the application of neural networks, which are known for mapping complex and non-linear systems. A feed forward ANN model with the resilient back-propagation learning algorithm and weight decay regularisation has been developed to relate the grain size to casting rate, meniscus level, casting temperature, water flow for the metal mould cooling and speed of wire for master alloy addition. The results obtained from the ANN are found to be consistent with the theoretical researches and experience from the foundry.