Pregled bibliografske jedinice broj: 381617
Mechanical Properties of Ductile Cast Iron Determined by Neural Networks
Mechanical Properties of Ductile Cast Iron Determined by Neural Networks // The proceedings of the Third International Conference on Modeling, Simulation and Applied Optimization 2009 / Kucuk, I. ; El-Tarhuni, M. ; Sadek, I. ; Abdulla, J. ; Anabtawi, M. ; Al Jarrah, M. (ur.).
Sharjah: American University of Sharjah, 2009. str. 1-5 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 381617 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Mechanical Properties of Ductile Cast Iron Determined by Neural Networks
Autori
Žmak, Irena ; Filetin, Tomislav
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
The proceedings of the Third International Conference on Modeling, Simulation and Applied Optimization 2009
/ Kucuk, I. ; El-Tarhuni, M. ; Sadek, I. ; Abdulla, J. ; Anabtawi, M. ; Al Jarrah, M. - Sharjah : American University of Sharjah, 2009, 1-5
ISBN
978-9948-427-12-4
Skup
The Third International Conference on Modeling, Simulation and Applied Optimization
Mjesto i datum
Sharjah, Ujedinjeni Arapski Emirati, 20.01.2009. - 22.01.2009
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Determination; Ductile Cast Iron; Mechanical Properties; Neural Networks; Prediction
Sažetak
This paper presents the results of application of artificial neural networks in determination of mechanical properties of ductile cast iron. All data were collected in a Croatian foundry for 147 melts. Error back-propagation training algorithm was applied to train the multilayer networks. The optimal size of the hidden neuron layer was determined through the analysis of error parameters. The optimal slope of the tangent sigmoid activation function was investigated. Neural networks were modeled to predict each mechanical property, namely: tensile strength, yield strength, elongation, and hardness. Input parameters were 13 weight contents of chemical elements in the melt. A comprehensive analysis of errors in predicting mechanical properties of ductile cast iron was made.
Izvorni jezik
Engleski
Znanstvena područja
Strojarstvo
POVEZANOST RADA
Projekti:
120-1201780-1779 - Modeliranje svojstava materijala i parametara procesa (Filetin, Tomislav, MZOS ) ( CroRIS)
Ustanove:
Fakultet strojarstva i brodogradnje, Zagreb