Simulacijsko modeliranje procesa toplog valjanja aluminijskih traka

scientific master's theses

• Author: Ivan Tomašić
• Mentor: Leo Budin (mentor)
• Committee member: Mario Žagar (predsjednik povjerenstva)
• Committee member: Leo Budin (član povjerenstva)
• Committee member: Željko Hocenski (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; (Department of Electronics, Microelectronics, Computer and Intelligent Systems); Zagreb
• Defense date and country: 2005-01-19, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing
• Universal decimal classification (UDC): 621.3 - Electrical engineering ; 004 - Computer science and technology. Computing. Data processing

Abstract

Bitna tehnološka karakteristika toplo valjane trake je njen profil. Za ostvarivanje željenog profila valjaoničari se često služe matematičkim modelima valjačkog stroja koji nisu savršeni. Ovaj rad prezentira mogućnosti korištenja neuronskih mreža u svrhu modeliranja tog procesa.
Prezentirano je modeliranje sile valjanja i profila izvaljane trake neuronskom mrežom. Izlaz iz mreže koja modelira silu je iskorišten kao ulaz u neuro-matematičkom modelu za izračun profila valjane trake.
Simulacijski rezultati koje daje neuronska mreža za predikciju profila izvaljane trake su više nego zadovoljavajući, dok su rezultati koje daje neuronska mreža za predikciju sile izvrsni. Rezultati koje daje miješani neuro-matematički model nisu zadovoljavajući jer model nije dobar. To pokazuje koliko je teško matematički modelirati taj kompleksni proces i dodatno opravdava primjenu neuronskih mreža u modeliranju procesa toplog valjanja aluminijskih traka.

Abstract (english)

Important technological requirement of rolling process is strip profile. To ensure desired strip profile mathematical model of plant is often used. Mathematical models of this complex process are not perfect. In this work, application of neural networks for purpose of modeling rolling process is discussed.
Modeling of rolling force and strip profile has been presented in this work. Output from network that models force is used as an input to mixed neuro-mathematical model for strip profile calculation.
Simulation results from network that predicts profile are more than satisfactory. Results from neural network for force prediction are excellent. Simulation results from neuro-mathematical model are not satisfactory because model is not precise. That proves how difficult is to model this complex process and even more justifies neural network application in modeling process of hot rolling of aluminium.

• Keywords: Valjanje aluminija; modeliranje procesa valjanja; simuliranje procesa valjanja; sila valjanja; profil trake; neuronska mreža
• Keywords (english): Rolling of aluminium; rolling process modeling; rolling process simulating; rolling force; strip profile; neural network
• Language: croatian
• URN:NBN: urn:nbn:hr:168:402486
• Study programme: Title: Postgraduate master programe in computing; Study programme type: university; Study level: postgraduate; Academic / professional title: magistar inženjer računarstva (magistar inženjer računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-06-26 08:31:35