<p>Disertacija obrađuje problematiku pronalaženja pouzdane tehnike analize signala mehaničkih vibracija s ciljem identifikacije analiziranih tipova oštećenja zupčastih parova. U disertaciji je predložen postupak redukcije dimenzionalnosti obeležja primenom metode analize glavnih komponenata. Istraživanje uspešno demonstrira primenu naprednih tehnika procesiranja signala vibracija i inteligentnih metoda u vibrodijagnostici zupčastih parova te omogućava osobama koje nisu specijalisti iz oblasti dijagnostike da procene stanje zupčastog para. Predložena su najuniverzalnija obeležja u vibrodijagnostici zupčastih parova baziranih na signalima vibracija prikupljenih na kućištu zupčastog prenosnika.</p> / <p>The dissertation deals with the issue of finding reliable signal analysis technique of mechanical vibrations to identify analyzed types of gear pair faults. The dissertation presents a method of reducing the dimensionality of features by using the method of principal components analysis. The study successfully demonstrates use of advanced signal processing techniques and artificial intelligent methods in diagnostics of gear pairs faults and allows engineers who are not specialists in the field to assess the condition of gear pair using vibration signals. The most universal features in diagnostics of gear pairs based on vibration signals collected on the gearbox housing are proposed.</p>
| Identifer | oai:union.ndltd.org:uns.ac.rs/oai:CRISUNS:(BISIS)101518 |
| Date | 23 September 2016 |
| Creators | Bajrić Rusmir |
| Contributors | Zuber Ninoslav, Vladić Jovan, Šostakov Rastislav, Cvetković Dragan, Jašarević Sabahudin |
| Publisher | Univerzitet u Novom Sadu, Fakultet tehničkih nauka u Novom Sadu, University of Novi Sad, Faculty of Technical Sciences at Novi Sad |
| Source Sets | University of Novi Sad |
| Language | Serbian |
| Detected Language | English |
| Type | PhD thesis |
Page generated in 0.0506 seconds