Naslov
Genetic algorithms and neural networks in optimization and control of aluminum extrusion process

Autori
Lozina, Željan ; Duplančić, Igor

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

Izvornik
Zbornik III savjetovanje hrvatskih metalurga / - , 1998

Skup
III Savjetovanje hrvatskih metalurga

Mjesto i datum
Šibenik, Hrvatska, 1998

Vrsta sudjelovanja
Poster

Vrsta recenzije
Domaća recenzija

Ključne riječi
genetic algorithm; neural network; optimization; aluminium; extrusion

Sažetak
In this paper an effort is made to introduce new approaches to optimization and control of aluminum extrusion process in order to establish an expert system capable to assist production and technology menagement. Neural network is trained on technology process track record to be able to describe complex dependances between influence parameters and product outgoing characteristics. A genetic algorithm based optimization of the technological process is proposed, where influence parameters are treated as heritage information and neural network is used as fitness function.

Izvorni jezik
Engleski

Znanstvena područja
Strojarstvo

POVEZANOST RADA