prikaz prve stranice dokumenta Procjena kvarova ležajeva primjenom strojnog učenja
  Download
PDF 2.17 MB
master's thesis
Procjena kvarova ležajeva primjenom strojnog učenja
Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2019. urn:nbn:hr:235:776526
Biluš, Luka
University of Zagreb
Faculty of Mechanical Engineering and Naval Architecture

Cite this document

Biluš, L. (2019). Procjena kvarova ležajeva primjenom strojnog učenja (Master's thesis). Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:235:776526

Biluš, Luka. "Procjena kvarova ležajeva primjenom strojnog učenja." Master's thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2019. https://urn.nsk.hr/urn:nbn:hr:235:776526

Biluš, Luka. "Procjena kvarova ležajeva primjenom strojnog učenja." Master's thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2019. https://urn.nsk.hr/urn:nbn:hr:235:776526

Biluš, L. (2019). 'Procjena kvarova ležajeva primjenom strojnog učenja', Master's thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, accessed 25 April 2024, https://urn.nsk.hr/urn:nbn:hr:235:776526

Biluš L. Procjena kvarova ležajeva primjenom strojnog učenja [Master's thesis]. Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture; 2019 [cited 2024 April 25] Available at: https://urn.nsk.hr/urn:nbn:hr:235:776526

L. Biluš, "Procjena kvarova ležajeva primjenom strojnog učenja", Master's thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, Zagreb, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:235:776526

Please login to the repository to save this object to your list.
Metadata
TitleProcjena kvarova ležajeva primjenom strojnog učenja
Title (english)Machine learning based bearing fault diagnosis
AuthorLuka Biluš
MentorDragutin Lisjak (mentor)
GranterUniversity of Zagreb
Faculty of Mechanical Engineering and Naval Architecture
Zagreb
Defense date and country2019-01-24, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Mechanical Engineering
Abstract
Održavanje tehničkih sustava u funkcionalnom stanju jedno je od najznačajnijih djelatnosti suvremenih poduzeća. Samim time razvoj održavanja također ima velik značaj, gdje se počinju primjenjivati inteligentni sustavi kojima je moguća rana dijagnostika kvarova unutar sustava održavanja. Primjena algoritama strojnog učenja unutar održavanja po stanju rezultira smanjenjem vremena zastoja, povećanjem kvalitete proizvoda i usluga, omogućavanjem predviđanja kvarova. Unutar ovog rada primijenjen je jedan od algoritama konvolucijskih neuronskih mreža koje spadaju pod strojno učenje. Algoritmom se provela analiza vibracijskih signala ležajeva sa različitim oštećenjima sa ciljem raspoznavanja tih oštećenja bez ikakvog ručnog izvlačenja značajki iz podataka. Vibracijski signali prolaze kroz višeslojnu konvolucijsku mrežu koja automatski uči značajke signala. Točnost klasifikacije ovog algoritma iznosi oko 97,58%.
Abstract (english)
The maintenance of technical systems in a functional state is one of the most important activities of modern companies. As a result of that, maintenance development also has great significance, where intelligent systems are beginning to be used to provide early diagnosis of failuers within the maintenance systems. The application of machine learning algorithms within the condition based maintenance results in reduction of downtime, increasing the quality of products and services and enables the prediction of failures. In this thesis, one of the algorithms of convolutional neural networks that are part of machine learning has been applied. The algorithm was used to conduct an analysis of vibration signals of bearings with various damages with the purpose of recognizing those damages without extracting any features from the data. Vibration signals pass through a multilayer convolutional network that automatically learns the signals features. The achived accuracy of the classification with the use of this algorithm is approximately 97,58%.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:235:776526
Study programmeTitle: Mechanical Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka strojarstva (magistar/magistra inženjer/inženjerka strojarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
RepositoryRepository of Faculty of Mechanical Engineering and Naval Architecture University of Zagreb
Created on2019-05-24 13:06:32

(©) Nacionalna i sveučilišna knjižnica u Zagrebu 2015. Sva prava pridržana. | Hrvatske bratske zajednice 4 p.p. 550, 10000 Zagreb, Hrvatska Tel. ++ 385 1 616-4040
OIB: 84838770814 | IBAN: HR66 2340 0091 1000 1008 1, Porezni broj (PDV identifikacijski broj) - VAT Number: HR84838770814
Prijava u repozitorij