Naslov
Neural Networks Application in Prediction of Strip Profile in Rolling Processes

Autori
Tomašić, Ivan

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

Izvornik
Proceedings of the joint conferences CTS+CIS, MIPRO, 2004. / Budin, Leo ; Ribarić, Slobodan - Rijeka : Hrvatska udruga za informacijsku i komunikacijsku tehnologiju, elektroniku i mikroelektroniku - MIPRO, 2004, 135-139

ISBN
953-233-003-8

Skup
MIPRO 2004 International Convention

Mjesto i datum
Opatija, Hrvatska, 24.05.2004. - 28.05.2004

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Neural networks; Rollling process

Sažetak
One of the most important technological requirements of rolling process is strip profile. Although, most of the modern rolling plants are equipped with sophisticated automation software that has to ensure final strip profile, often that profile is not satisfactory. That’s why there is a need for prediction of final strip profile. In this work, application of neural networks for such purpose is discussed. Neural networks can learn, automatically, complex relationship among data. This feature makes it very useful in modeling process for which mathematical modeling is difficult or impossible. After explaining the idea of using neural networks for this purpose main features of rolling process will be shortly explained, particularly hot rolling of aluminum. After that profile will be defined with all parameters that have influence on it. Than, learning of neural network and results obtained from simulation will be presented. At the end results obtained from simulation will be discussed. Those results will show that neural network application is very useful for prediction of strip profile.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo, Strojarstvo

POVEZANOST RADA