Naslov
ROLLING FORCE PREDICTION FOR ALUMINIUM STRIP HOT ROLLING PROCESS BY MEANS OF FUNCTIONAL DATA ANALYSES

Autori
Lela, Branimir ; Duplančić, Igor ; Šupe, Miroslav

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

Izvornik
CONFERENCE PROCEEDINGS of the 7th World Congress Aluminium Two Thousand / Walter Dalla Barba - Modena : Interall, 2011

Skup
7th World Congress Aluminium Two Thousand

Mjesto i datum
Bologna, Italija, 17.05.2011. - 21.05.2011

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Functional data analysis; Aluminium hot rolling; Rolling force; Mathematical modelling

Sažetak
Methodology of functional data analysis (FDA) has been used in the present study with the purpose of rolling force prediction in the hot rolling process of aluminium strips. A new linear regression mathematical model has been proposed for the prediction of the rolling force. Regression coefficients of the model are in the form of time dependent functions that have been determined through the use of FDA methodology. The mathematical model has been developed using data for technological rolling parameters that were measured and recorded on the rolling stand during the real hot rolling process of strips made of aluminium alloy AA1050. Simulation of the mathematical model shows that its predictions are in good accordance with the measured data on the rolling force.

Izvorni jezik
Engleski

Znanstvena područja
Strojarstvo

POVEZANOST RADA