magistrsko delo
Klemen Kovič (Author), Miran Brezočnik (Mentor), Polona Tominc (Mentor)

Abstract

V magistrski nalogi predstavimo metode strojnega učenja in njihovo rabo za modeliranje treh različnih tehnoloških procesov: trdega struženja, visokohitrostnega struženja in rezkanja. Podatke smo pridobili iz znanstvenih člankov, objavljenih v mednarodnih revijah. Za modeliranje tehnoloških procesov smo uporabili multiplo linearno regresijo, naključne gozdove, stohastično gradientno pospeševanje in metodo cubist. Na koncu predstavimo prediktivne sposobnosti posameznih metod in primerjamo rezultate. Napovedi omenjenih štirih metod tudi primerjamo z rezultati, ki so jih poročali avtorji člankov, in identificiramo najuspešnejšo metodo strojnega učenja za vsak proces. Za zaključek še teoretično raziščemo vpliv strojnega učenja na industrijo in poslovanje podjetij.

Keywords

tehnološki procesi;struženje;rezkanje;visokohitrostne obdelave;modeliranje;strojno učenje;optimizacija poslovnih procesov;magistrske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UM FS - Faculty of Mechanical Engineering
Publisher: [K. Kovič]
UDC: 004.85:621.9(043.2)
COBISS: 27598339 Link will open in a new window
Views: 601
Downloads: 61
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Application of machine learning in modelling of technological processes
Secondary abstract: In the master's thesis we present the machine learning methods and their use for modelling of three different technological processes: hard turning, high speed turning and milling. Data was obtained from scientific articles published in international journals. Multiple linear regression, random forests, stochastic gradient boosting and the cubist method were used to model the technological processes. Finally, we present the predictive capabilities of each method and compare the results. We also compare the predictions of these four methods with the results reported by the authors of the articles and identify the most successful machine learning method for each process. To conclude, we explore the impact of machine learning on industry and business operations.
Secondary keywords: technological processes;turning;milling;high speed machining;modelling;machine learning;business process optimization;
Type (COBISS): Master's thesis/paper
Thesis comment: Univ. v Mariboru, Fak. za strojništvo, Gospodarsko inženirstvo
Pages: XII, 69 str.
ID: 11722743