Naslov
The Prediction of the As-Cast Ductile Iron Impact Toughness by Using Thermal Analysis and Artificial Neural Networks

Autori
Glavaš, Zoran ; Unkić, Faruk ; Lisjak, Dragutin

Izvornik
Livarski vestnik (0024-5135) 55 (2008), 2; 62-81

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
ductile iron ; impact toughness ; artificial neural networks ; thermal analysis

Sažetak
This paper presents the application of artificial neural network (ANN) in the foundry process. A two-layer feedforward neural network which is trained using backpropagation algorithm that updates weights and biases values according to gradient descent momentum and an adaptive learning rate (Backpropagation Neural Network- BPNN) have been established to predict the as- cast impact toughness of ductile iron (DI) using the thermal analysis (TA) parameters as inputs. The generalization property of the developed ANN is very good, which is confirmed by a very good accordance between the predicted and the targeted values of as-cast impact toughness on a new data set that was not included in the training data set.

Izvorni jezik
Engleski

Znanstvena područja
Metalurgija

Napomena
Rad je kao predavanje prezentiran na skupu 47th Internationa Foundry Conference, održanom od 12.-14.09.2007., Portorož, Slovenija ; objavljen bez recenzije u Zborniku (ISSN 1318-9123) ; Ljubljana, Livarsko strokovno posvetovanje, 2007 ; str. 56-58.

POVEZANOST RADA