Naslov
DETERMINING OF STEEL CARBURIZING PARAMETERS USING NEURAL NETWORKS

Autori
Dragutin Lisjak, Božidar Matijević

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
INTEGRATION OF HEAT TREATMENT AND SURFACE ENGINEERING IN THE MANUFACTURE OF ENGINEERING COMPONENTS / Božidar Liščić - Zagreb : Hrvatsko društvo za toplinsku obradu i inženjerstvo površina, 2001, 407-413

Skup
8th SEMINAR OF THE INTERNATIONAL FEDERATION FOR HEAT TREATMENT AND SURFACE ENGINERRING – IFHTSE 2001

Mjesto i datum
Dubrovnik, Hrvatska, 12.09.2001. - 14.09.2001

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
carburizing; carbomaag; neural networks

Sažetak
The paper discusses application of neural networks for calculating the laws of complex processes, among which are carbon diffusion processes in steel carburizing. For determining of technological carburizing parameters, which results in required course of carbon curves in the carburized layer, empirical and mathematical model for Carbomaag carburizing process are presented, which are proven in practice. The results of empirical carburizing model were used as a neural network training set and compared with the results of computer simulation of mathematical model. Comparison of results of carburizing provided by neural network with empirical and mathematical model shows good correspondence. It is considered that more experiments and using newer sets of experimental data in training of neural network would provide better solutions i.e. deficiencies of empirical and theoretical models would be avoided.

Izvorni jezik
Engleski

Znanstvena područja
Strojarstvo

POVEZANOST RADA