The article presents the results of a sensitivity analysis of artificial neural networks developed for a system which predicts the durability of forging tools used in the selected hot die forging process. The developed system makes it possible to calculate the geometric loss of the examined tool for the given values of its operating parameters (number of forgings, tool temperature at selected points, type of the applied protective layer, pressure and path of friction) and estimates the intensity of the occurrence of typical mechanisms of tool destruction, i.e. thermo-mechanical fatigue, mechanical wear, abrasive wear and plastic deformation. Nine neural networks operate in the developed system. Five of them determine the geometric loss of the material used for tools operating with protective layers, including a nitrided layer, a pad welded layer and three hybrid layers, i.e. AlCrTiSiN, Cr/CrN and Cr/AlCrTiN. Four networks make calculations determining the intensity of the occurrence of typical destructive mechanisms. The developed sensitivity analysis allows for each neural network to show which input parameters are most important and have the greatest impact on the explained variables. This is determined based on the network error analysis in the case of elimination of individual variables from the input data. The greater the network error calculated after rejecting an input variable relative to the error obtained for the network with all the input variables, the more sensitive the network to the lack of this variable. The best compliance was obtained for the first developed set of networks regarding the geometric loss of material, while the lowest compliance was obtained for the second developed set of networks regarding the applied protective layers, and in particular for plastic deformation and mechanical fatigue, probably due to the smallest size of these sets in the knowledge base. The obtained results of this analysis are important for the system operation, i.e. supporting the technologist’s decision in the selection of such process parameter values that will increase the die’s lifetime.

The paper presents a mathematical model of the pearlite - austenite transformation. The description of this process uses the diffusion mechanism which takes place between the plates of ferrite and cementite (pearlite) as well as austenite. The process of austenite growth was described by means of a system of differential equations solved with the use of the finite difference method. The developed model was implemented in the environment of Delphi 4. The proprietary program allows for the calculation of the rate and time of the transformation at an assumed temperature as well as to determine the TTT diagram for the assigned temperature range.

In this study, artificial neural networks were used to predict the plastic flow behaviour of S355 steel in the process of high-temperature deformation. The aim of the studies was to develop a model of changes in stress as a function of strain, strain rate and temperature, necessary to build an advanced numerical model of the soft-reduction process. The high-temperature characteristics of the tested steel were determined with a Gleeble 3800 thermo-mechanical simulator. Tests were carried out in the temperature range of 400–1450 °C for two strain rates, i.e. 0.05 and 1 s⁻¹. The test results were next used to develop and verify a rheological model based on artificial neural networks (ANNs). The conducted studies show that the selected models offer high accuracy in predicting the high-temperature flow behaviour of S355 steel and can be successfully used in numerical modelling of the soft-reduction process.

Stereological description of dispersed microstructure is not an easy task and remains the subject of continuous research. In its practical aspect, a correct stereological description of this type of structure is essential for the analysis of processes of coagulation and spheroidisation, or for studies of relationships between structure and properties. One of the most frequently used methods for an estimation of the density Nv and size distribution of particles is the Scheil - Schwartz - Saltykov method. In this article, the authors present selected methods for quantitative assessment of ductile iron microstructure, i.e. the Scheil - Schwartz - Saltykov method, which allows a quantitative description of three-dimensional sets of solids using measurements and counts performed on two-dimensional cross-sections of these sets (microsections) and quantitative description of three-dimensional sets of solids by X-ray computed microtomography, which is an interesting alternative for structural studies compared to traditional methods of microstructure imaging since, as a result, the analysis provides a three-dimensional imaging of microstructures examined.

Metallographic examinations and mechanical tests were carried out on the ductile iron with additions of Ni, Cu and Mo in as-cast state and after austempering. TTT and CCT diagrams were plotted. The heat treatment was performed in six different variants. Studies included qualitative assessment of the microstructure and testing of mechanical properties such as R_0,2, R_m, A, Z, HRC, KC. An analysis of the obtained results was also presented.