engleski

DETERMINING OF STEEL CARBURIZING PARAMETERS USING NEURAL NETWORKS

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.

carburizing; carbomaag; neural networks

nije evidentirano