FIELD: materials science.
SUBSTANCE: invention relates to materials science and can be used in various fields of state-of-the-art electronics, alternative power engineering and machine building. Method of producing a wear-resistant nanocomposite coating with a specified value of microhardness on the surface of a polished glass-ceramic plate by ion-beam spraying involves providing required percentage of metal and ceramic phases in the obtained coating at a certain chemical composition of the said phases, herewith determined are values of microhardness for a metal and a ceramic coatings of different chemical compositions free from impurities of the ceramic or the metal phases, respectively, then produced is a coating with a specified chemical composition and the specified percentage of the above said phases with a certain pitch and with the percentage ratio of metal-to-ceramics phases varying in the coating from zero to maximum, then determined are values of the obtained coating microhardness at the preset ratio of the above said phases. Basing on the obtained data an artificial neural network is created and trained. Then a produced neural network model is tested by sequential exclusion from the statistical sampling used for its training, of the neural network model factors in the form of experimentally measured values including microhardness of the metal coating (Hm), microhardness of the ceramic coating (Hc) and concentration of the metal phase in the composite (Cc) with subsequent determination using the obtained neural network model of its output parameter in the form of the nanocomposite coating microhardness value (H) and comparing the obtained theoretical values with the initial experimental data. Then the said artificial neural network is entered with microhardness values for the metal and the ceramic phases without impurities and the percentage ratio of the said phases in the obtained coating and by means of the artificial neural network determined is the obtained nanocomposite metal-ceramic coating microhardness value at the entered ratio of the metal and the ceramic phases. In particular cases after comparing the obtained theoretical values of the nanocomposite coating microhardness (H) with the initial experimental data the produced neural network model is corrected.
EFFECT: provided is higher wear resistance at simultaneous reduction of the coating production cost and high stability of the determined parameters used for the coating application.
1 cl, 4 dwg
