Predictive model of superplastic properties of aluminum bronze and of the superplastic extrusion test

The superplastic properties of aluminum bronze were studied by way of artificial neural network. The model was established using Levenberg–Marquardt algorithm. It was improved by studying superplastic tension test data of aluminum bronze such that the superplastic forming parameters were optimized. According to the parameters, the experiment of superplastic extrusion of a solid bearing was performed. It is shown that the model reflected well the relationship between superplastic properties of aluminum bronze and superplastic tension conditions. The relative error between the test values and the predicted values of the network is less than 8.5%, which meets perfectly the demands of superplastic deformation of aluminum bronze. Moreover, the superplastic forming of solid cage of aluminum bronze show that it is feasible to produce solid cage using superplastic extrusion process. This extrusion process has remarkable economic benefits as well.