Cavities have been widely observed during the superplastic deformation of metals and alloys, the superplasticity of metals and alloys generally being sensitive to cavity formation. However, the shape of the cavities is irregular during superplastic deformation, thus quantitative analysis of the shape of the cavities is one of the keys to the studying of the superplastic deformation mechanism. In this paper, the quantitative effects of process parameters on the fractal dimension, Df, of the shape of cavities during the superplastic deformation of duralumin LYI2CZ (approximately corresponding to ASTM 2024) with and without the application of an external electric field is studied. The experimental results show that: (i) the fractal dimension of the shape of cavities varies with the change of process parameters (deformation temperature, T, true strain, ε, initial strain rate, ε0), both with and without the application of an external electric field; (ii) the fractal dimension of the shape of cavities also varies with the intensity of the electric field, E, under otherwise identical conditions. The results in this paper show that the improvement of superplasticity with the application of an external electric field is related to a lower value of the fractal dimension in the quasi-stable flow stage of superplastic deformation.

investigated. The electroplastic effect of 15 vol% SiCp/LY12 Al composite and the influence of deformation process parameters on the superplasticity have also been studied. The experimental results show that: (i) the optimum intensity of the electric field improves the superplasticity of 15 vol% SiCp/LY12 AI composite, i.e. the strain-rate sensitivity index (m) is increased by 13% and the elongation (δ) is 420%, being increased by 20%; (ii) the optimum intensity of the electric field decreases the flow stress by 16% during the superplastic deformation of 15 vol% SiCp/LY12 Al composite; (iii) the optimum intensity of the electric field makes the grain size finer during the superplastic deformation of 15 vol% SiCp/LYI2 Al composite, which provides the microstructural conditions for the improvement of superplasticity, but the electric field has only a slight influence on the microstructure before superplastic deformation.

In this paper, an adaptive model of grain size, has been established with the help of the fuzzy neural networks (FNNs), based on experimental results for Ti-6Al-4V titanium alloy with homogeneous deformation under various process technological parameters. The data of Teacher's samples has been obtained from the experimental results. By the comparison of the calculated results with the experimental data of the Teacher's samples and the testing samples, it has been verified that the model proposed in this paper can be applied to compute the grain size evolution during the deformation of Ti-6Al-4V titanium alloy.

Microstructural evolution and the mechanical properties of the semisolid Al-4Cu-Mg alloy were investigated, and a grain coarsening equation of this semisolid alloy in the semisolid state was provided based on Ostwald ripening theory. The experimental results showed that the process parameters, including height reduction, isothermal temperature and holding time, affect grain size, fractal dimension and distribution of grain size to some extent. The grain size decreases with an increase of the height reduction, a decrease of the isothermal temperature and/or the holding time. The spheroidization of grains is promoted with an increase of height reduction, isothermal temperature or holding time. The grain size has a Gaussian distribution under different experimental conditions. There will be a more uniform distribution of grain size at high height reduction, low isothermal temperature and short holding time. The pretreatment of samples with cold or hot deformation before isothermal heat treatment is necessary. Good ultimate strength and yield strength could be obtained by the conditions of suitable height reduction, low isothermal temperature and short holding time. Finally, a kinetic equation of grain coarsening was put forward, which could be applied to the semisolid Al-4Cu-Mg alloy system over a high volume fraction of separated grains range from 0.75 to 0.90.

In this paper, an adaptive fuzzy-neural network model has been established to model the microstructure evolution and constitutive relation of 15 vol% SiCp/LY12 aluminum composite during superplastic deformation. This network integrates the learning power of neural networks with fuzzy inference systems. During the training process of the network, the back-propagation learning algorithm is applied to optimally adjust the weight coefficients of the neural network and the parameters of the fuzzy membership functions. Then, the trained network is used to predict the microstructure evolution and constitutive relation of 15 vol% SiCp/LY12 aluminum composite during superplastic deformation. The predicted results agree very well with the experimental data of the test samples. On the basis of the good prediction ability of the proposed fuzzy-neural network, the constitutive relation and microstructure of 15 vol% SiCp/LY12 aluminum composite under various superplastic deformation conditions have also been calculated and analyzed.