| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Akustično zaznavanje poškodb ležajev motorjev z uporabo umetne inteligence na PSoC 6 AI : magistrsko delo
Authors:ID Dragšič, Gal (Author)
ID Uran, Suzana (Mentor) More about this mentor... New window
ID Karner, Timi (Mentor) More about this mentor... New window
ID Bratina, Božidar (Comentor)
Files:.pdf UN_Dragsic_Gal_2026.pdf (4,37 MB)
MD5: 0F9B6E376831C5A531448C450B3D62E8
 
Language:Slovenian
Work type:Bachelor thesis/paper
Typology:2.11 - Undergraduate Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:Diplomsko delo obravnava akustično diagnostiko za zaznavanje poškodb ležajev motorjev z uporabo razvojne ploščice PSoC 6 AI, digitalnega MEMS mikrofona in konvolucijske nevronske mreže, naučene v okolju DEEPCRAFT™ Studio. Teoretični del predstavi mehanizme poškodb kotalnih ležajev, akustično diagnostiko, Fourierjevo transformacijo in nevronske mreže. V praktičnem delu so bile izvedene meritve na poškodovanem in nepoškodovanem testnem ventilatorju ebm-papst, na podlagi katerih so bili razviti in medsebojno primerjani trije modeli z različno obliko vhodnih podatkov. Izbran najboljši model doseže testno vrednost F1 89,56 % z le 3704 učnimi parametri, kar potrjuje izvedljivost pristopa na vgrajenih sistemih.
Keywords:akustična diagnostika, ležaji, konvolucijske nevronske mreže, PSoC 6 AI, vgrajeni sistemi
Place of publishing:Maribor
Place of performance:Maribor
Publisher:[G. Dragšič]
Year of publishing:2026
Number of pages:1 spletni vir (1 datoteka PDF (IX, 70 str.))
PID:20.500.12556/DKUM-98743 New window
UDC:004.891.3:534.6(043.2)
COBISS.SI-ID:290253827 New window
Publication date in DKUM:18.08.2026
Views:358
Downloads:24
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
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:04.07.2026

Secondary language

Language:English
Title:Acoustic detection of motor bearing faults using artificial intelligence on PSoC 6 AI
Abstract:This diploma presents acoustic diagnostics for detecting motor bearing damage using the PSoC 6 AI development board, a digital MEMS microphone, and a convolutional neural network trained in DEEPCRAFT™ Studio. The theoretical part covers rolling bearing damage mechanisms, acoustic diagnostics, the Fourier transform, and neural networks. In the practical part, measurements on damaged and undamaged ebm-papst test fans were used to develop and compare three models with different input data forms. The best-performing model achieves a test F1 score of 89,56% with only 3704 trainable parameters, confirming the approach's feasibility on embedded systems.
Keywords:acoustic diagnostics, bearings, convolutional neural networks, PSoC 6 AI, embedded systems


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