Učinkovitost algoritmov umetne inteligence pri mikroplaniranju proizvodnje

diplomsko delo

Vukašin Radisavljević (Author), Matjaž Roblek (Mentor), Alenka Brezavšček (Co-mentor)

Abstract

Diplomsko delo se osredotoča na analizo podatkov v kontekstu uporabe umetne inteligence pri mikroplaniranju proizvodnje. Na podlagi analize pridobljenih podatkov smo identificirali zakonitosti in trende, ki se nanašajo na učinkovitost sistema za napredno planiranje in razporejanje proizvodnje z umetno inteligenco Qlector LEAP. Opažamo korelacije med relativno napako planiranja s Qlector LEAP-om in številom poskusov planiranja, pri čemer opažamo določene trende za določene izdelke. Primerjamo učinek planiranja Qlector LEAP-a tudi z učinkom planiranja po normativih. Razprava se osredotoča tudi na tehnološke, kadrovske in organizacijske dejavnike ter priporoča organizacijske ukrepe za izboljšanje učinkovitosti planiranja z LEAP-om. Kljub izzivom pri dokazovanju hipotez je razprava pokazala možnosti za nadaljnje raziskave, ki vključujejo kvantifikacijo zanesljivosti planiranja z LEAP-om in preučevanje drugih modulov Qlector LEAP-a. Skupaj s postavljenimi organizacijskimi ukrepi diplomsko delo zagotavlja osnovo za nadaljnje raziskave na tem področju.

Keywords

umetna inteligenca;strojno učenje;mikroplaniranje proizvodnje;sistem za napredno planiranje in razporejanje proizvodnje;merjenje učinka;

Data

Language:	Slovenian
Year of publishing:	2024
Typology:	2.11 - Undergraduate Thesis
Organization:	UM FOV - Faculty of Organizational Sciences
Publisher:	[V. Radisavljević]
UDC:	004.8
COBISS:	198758915
Views:	37
Downloads:	1
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Performance of ai algorithms in production scheduling
Secondary abstract:	The thesis focuses on data analysis in the context of artificial intelligence usage in production scheduling. Based on the analysis of the acquired data, we identified patterns and trends related to the effectiveness of the APS system with artificial intelligence (Qlector LEAP). We observe correlations between the relative planning error with Qlector LEAP and the number of planning attempts, where we notice certain trends for specific products. Additionally, we compare the planning efficiency of Qlector LEAP with the efficiency of planning based on normative times. The discussion also emphasizes technological, personnel, and organizational factors, recommending organizational measures to improve planning efficiency with LEAP. Despite challenges in proving hypotheses, the discussion has shown possibilities for further research, including quantifying the reliability of planning with LEAP and examining other Qlector LEAP modules. Together with the proposed organizational measures, the thesis provides a solid foundation for further research in this field.
Secondary keywords:	Umetna inteligenca;Univerzitetna in visokošolska dela;
Type (COBISS):	Bachelor thesis/paper
Thesis comment:	Univ. v Mariboru, Fak. za organizacijske vede
Pages:	V, 57 f.
ID:	23677931