Search

A numerical procedure for the prediction of the mechanical performances of squeeze cast ingots of an aluminium alloy is presented. A 2D finite element (FE) model was used to simulate the ingot cooling under squeezing. Extracting the ingot cooling rate across the aluminium alloy freezing range, it was possible to predict the average microhardness by using a material equation which takes into account the dependence of the mechanical properties on the cooling rate. The model was experimentally calibrated by means of laboratory tests. Some cylindrical ingots were direct squeeze cast at different mould temperatures and squeezing pressures. The ingots were characterised by surface analysis, optical microscopy, instrumented macro-indentation and Vickers microhardness. The agreement between the experimental average microhardness and the predicted one was optimal for each ingot.

In this paper, the application of a new technique based on artificial neural network is used for the characterisation of mechanical properties. Three applications are shown in this article: the room temperature superplastic behaviour in PbSn60 alloy, the compressive behaviour of Al foam with different starting powder composition (different pores amount) and the fatigue behaviour in rotating bending tests of Al 6082T6 (as-received and after the fluidised bed treatment). Three neural networks with back-propagation (BP) algorithm have been implemented. After validation, the artificial neural networks are able to predict the output values with considerable efficiency and accuracy.