Optimizacija tehnoloških veličin globokega vleka z uporabo metode roja delcev

magistrsko delo

Katja Popovič (Author), Mirko Ficko (Mentor), Simon Klančnik (Co-mentor)

Abstract

Magistrsko delo obravnava optimizacijo tehnoloških parametrov globokega vleka pločevine, ki vplivajo na kakovost izdelkov. Razviti optimizacijski modeli, ki so predstavljeni v magistrski nalogi, temeljijo na rezultatih numeričnih simulacij. Predstavili smo razvoj regresijskih modelov in modelov na osnovi evolucijskega računanja, ki napovedujejo kakovost izdelka po preoblikovalnem postopku s pomočjo matematičnih metod in z genetskim programiranjem. Izdelane modele smo uporabili v algoritmu za optimizacijo z rojem delcev, s katero smo dobili nove vrednosti tehnoloških parametrov. Slednje smo nato uporabili v nadaljnjih numeričnih simulacijah globokega vleka ter rezultate kritično analizirali.

Keywords

pločevina;globoki vlek;računalniške simulacije;genetsko programiranje;optimizacija z rojem delcev;magistrske naloge;

Data

Language:	Slovenian
Year of publishing:	2017
Typology:	2.09 - Master's Thesis
Organization:	UM FS - Faculty of Mechanical Engineering
Publisher:	[K. Popovič]
UDC:	004.89:621.983(043.2)
COBISS:	21202966
Views:	893
Downloads:	173
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Optimization of the deep drawing parameters using the particle swarm optimization
Secondary abstract:	This master thesis presents optimization of deep drawing process parameters that affect metal during deep drawing process. The already developed optimization models in this master thesis are based on the results of numerical simulations. We presented the development of regression models and evolutionary models of surface quality of the sheet metal product, according to mathematical methods and with genetic programming. We used models in the particle swarm optimization, which gave us new values of technological parameters. The latter was then used in further numerical simulations of deep drawing process and the results were critically analyzed.
Secondary keywords:	sheet metal;deep drawing;computer simulation;artificial intelligence;genetic programming;particle swarm optimization;
URN:	URN:SI:UM:
Type (COBISS):	Master's thesis/paper
Thesis comment:	Univ. v Mariboru, Fak. za strojništvo, Računalniško inženirsko modeliranje
Pages:	XV, 87 f.
ID:	10864349