Naslov
Hardness of Ductile Cast Iron Estimated by Artificial Neural Networks

Autori
Žmak, Irena ; Filetin, Tomislav ; Hren, Smiljan

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

Izvornik
Annals of DAAAM for 2009 & Proceedings of the 20th International DAAAM Symposium / Katalinić, Branko - Beč : DAAAM International Vienna, 2009, 1401-1402

ISBN
978-3-901509-70-4

Skup
20th International DAAAM Symposium "Intelligent Manufacturing and Automation: Focus on Theory, Practice and Education"

Mjesto i datum
Beč, Austrija, 25.11.2009. - 28.11.2009

Vrsta sudjelovanja
Poster

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
ductile cast iron; hardness; artificial neural networks; modelling

Sažetak
The paper gives the results of application of artificial neural networks in determining hardness of ductile cast iron. Data for 147 melts were collected in a Croatian foundry. The error back-propagation algorithm was used to train the multilayer feed-forward network. The optimal size of the hidden neuron layer was selected by analysing error parameters in the testing data set. There were 8 input parameters: liquidus temperature, lowest eutectic temperature, the recalescence, solidus, graphite factor 1, graphite factor 2, cooling rate at solidus, and eutectoid temperature. A statistical analysis of errors in estimating hardness of ductile cast iron was made.

Izvorni jezik
Engleski

Znanstvena područja
Strojarstvo, Temeljne tehničke znanosti

POVEZANOST RADA