The article shows a new model of Continuous Cooling Transformation (CCT) diagrams of structural steels and engineering steels. The modelling used artificial neural networks and a set of experimental data prepared based on 550 CCT diagrams published in the literature. The model of CCT diagrams forms 17 artificial neural networks which solve classification and regression tasks. Neural model is implemented in a computer software that enables calculation of a CCT diagram based on chemical composition of steel and its austenitizing temperature.
The use of fly ash as a material for earth structures involves its proper compaction. Fly ash compaction tests have to be conducted on separately prepared virgin samples because spherical ash grains are crushed during compaction, so the laboratory compaction procedure is time-consuming and laborious. The aim of the study was to determine the neural models for prediction of fly ash compaction curve shapes. The attempt of applying the artificial neural networks type MLP was made. ANN inputs were new-created variables – principal components dependent on grain-size distribution (as D₁₀–D₉₀ and uniformity and curvature coefficients), compaction method, and fly ash specific density. The output vectors were presented by co-ordinates of generated compaction curve points. Each point (wᵢ, ρdi) was described by two independent ANNs. Using ANN-based modelling method, models which enable establishing the approximate compaction curve shape were obtained.
In the paper the use of the artificial neural network to the control of the work of heat treating equipment for the long axisymmetric steel elements with variable diameters is presented. It is assumed that the velocity of the heat source is modified in the process and is in real time updated according to the current diameter. The measurement of the diameter is performed at a constant distance from the heat source (∆z = 0). The main task of the model is control the assumed values of temperature at constant parameters of the heat source such as radius and power. Therefore the parameter of the process controlled by the artificial neural network is the velocity of the heat source. The input data of the network are the values of temperature and the radius of the heated element. The learning, testing and validation sets were determined by using the equation of steady heat transfer process with a convective term. To verify the possibilities of the presented algorithm, based on the solve of the unsteady heat conduction with finite element method, a numerical simulation is performed. The calculations confirm the effectiveness of use of the presented solution, in order to obtain for example the constant depth of the heat affected zone for the geometrically variable hardened axisymmetric objects.