| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Uporaba strojnega učenja za identifikacijo glavnih parametrov bentonitne peščene mešanice za zmanjšanje izmeta ulitkov: razvoj modela znanja za klasifikacijo izmeta : diplomsko delo
Authors:ID Breznikar, Žiga (Author)
ID Brezočnik, Miran (Mentor) More about this mentor... New window
ID Bojinović, Marko (Comentor)
Files:.pdf UN_Breznikar_Ziga_2024.pdf (2,70 MB)
MD5: A3267E99AB6D0E17305C9514DE1F08F7
 
Language:Slovenian
Work type:Bachelor thesis/paper
Typology:2.11 - Undergraduate Thesis
Organization:FS - Faculty of Mechanical Engineering
Abstract:V diplomskem delu najprej obravnavamo teoretične osnove gravitacijskega litja in strojnega učenja. Nato smo na podlagi podatkov iz Podjetja X razvili spletno aplikacijo za interaktiven prikaz izmeta ulitkov in klasifikator za oceno njihove kakovosti. Za razvoj modela znanja klasifikacije smo uporabili SQL Server Management Studio in Visual Studio Code ter programska jezika MS SQL (Microsoft Structured Query Language) in Python. Izhodiščne podatke smo preuredili in analizirali z uporabo metod podatkovne znanosti in statističnih metod. Podatke o izmetu je bilo treba vizualno prikazati in ustvariti model znanja, naučen na razpoložljivih podatkih, ki lahko napove, če bo prišlo do izmeta. Delo se deli na dva segmenta. Prvi segment zajema opis postopka izdelave in prikaz spletne aplikacije. Drugi segment zajema opis priprave podatkov za namene klasifikatorja, predprocesiranje, optimizacijo in analizo klasifikatorja. Na koncu dela podajamo tudi napotke za nadaljnje delo in izboljšave.
Keywords:gravitacijsko litje, strojno učenje, izmet, klasifikator, podatkovna znanost
Place of publishing:Maribor
Place of performance:Maribor
Publisher:[Ž. Breznikar]
Year of publishing:2024
Number of pages:1 spletni vir (1 datoteka PDF (XI, 60 f., [3] f. pril.))
PID:20.500.12556/DKUM-90462 New window
UDC:621.7+621.9(043.2)
COBISS.SI-ID:216614403 New window
Publication date in DKUM:09.10.2024
Views:177
Downloads:66
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FS
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:04.09.2024

Secondary language

Language:English
Title:Application of machine learning for identifying key parameters of bentonite sand mixture to reduce casting defects: development of knowledge model for defect classification
Abstract:In this thesis, we first discuss the theoretical foundations of gravity casting and machine learning. Then, based on data from Company X, we developed a web application for the interactive display of casting defects and a classifier to assess their quality. To develop the classification knowledge model, we used SQL Server Management Studio and Visual Studio Code, along with the programming languages MS SQL (Microsoft Structured Query Language) and Python. The initial data was reorganized and analyzed using data science and statistical methods. The defect data needed to be visually represented, and a knowledge model was created, trained on the available data, that could predict whether a defect would occur. The work is divided into two segments. The first segment covers the process of creating and displaying the web application. The second segment covers the preparation of data for the classifier, preprocessing, optimization, and analysis of the classifier. The conclusion of the thesis provides guidelines for further work and improvements.
Keywords:gravity casting, machine learning, defect, classifier, data science


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica