engleski

The Prediction of the As-cast Ductile Iron Impact Toughness by Using Artificial Neutral Network and Chemical Composition

This paper present the application of artificial neural network in the production process of ductile iron. A backpropagation neural network has been established to predict the as-cast ductile irons impact toughness by using chemical compositions as inputs. The generalization property of the developed artificial neural network is very good, which is confirmed by a very good accordance between the predicted and the targeted values of the ascast impact toughness on a new data set that was not included in the training data set.

ductile iron ; impact toughness ; artificial neural network

Puni terkst rada objavljen na CR-u, ISBN 978-953- 7040-14-7.