FAULT DIAGNOSIS WITH DEEP LEARNING FOR STANDARD AND ASYMMETRIC INVOLUTE SPUR GEARS

Basit Öğe Kaydı
dc.authorid0000-0003-1387-907Xen_US
dc.authorscopusid56237466100en_US
dc.contributor.authorKarpat, Fatih
dc.contributor.authorDirik, Ahmet Emir
dc.contributor.authorKalay, Onur Can
dc.contributor.authorYüce, Celalettin
dc.contributor.authorDoğan, Oğuz
dc.contributor.authorKorcuklu, Burak
dc.date.accessioned2022-05-16T07:44:32Z
dc.date.available2022-05-16T07:44:32Z
dc.date.issued2021en_US
dc.departmentBTÜ, Mühendislik ve Doğa Bilimleri Fakültesi, Mekatronik Mühendisliği Bölümüen_US
dc.description.abstractGears are critical power transmission elements used in various industries. However, varying working speeds and sudden load changes may cause root cracks, pitting, or missing tooth failures. The asymmetric tooth profile offers higher load-carrying capacity, long life, and the ability to lessen vibration than the standard (symmetric) profile spur gears. Gearbox faults that cannot be detected early may lead the entire system to stop or serious damage to the machine. In this regard, Deep Learning (DL) algorithms have started to be utilized for gear early fault diagnosis. This study aims to determine the root crack for both symmetric and asymmetric involute spur gears with a DL-based approach. To this end, single tooth stiffness of the gears was obtained with ANSYS software for healthy and cracked gears (50-100%), and then the time-varying mesh stiffness (TVMS) was calculated. A six-degrees-of-freedom dynamic model was developed by deriving the equations of motion of a single-stage spur gear mechanism. The vibration responses were collected for the healthy state, 50% and 100% crack degrees for both symmetric and asymmetric tooth profiles. Furthermore, the white Gaussian noise was added to the vibration data to complicate the early crack diagnosis task. The main contribution of this paper is that it adapts the DL-based approaches used for early fault diagnosis in standard profile involute spur gears to the asymmetric tooth concept for the first time. The proposed method can eliminate the need for large amounts of training data from costly physical experiments. Therefore, maintenance strategies can be improved by early crack detection.en_US
dc.identifier.isbn978-079188569-7
dc.identifier.scopusqualityN/Aen_US
dc.identifier.urihttps://hdl.handle.net/20.500.12885/1974
dc.indekslendigikaynakScopusen_US
dc.institutionauthorYüce, Celalettin
dc.language.isoenen_US
dc.publisherAmerican Society of Mechanical Engineers (ASME)en_US
dc.relation.ispartofASME 2021 International Mechanical Engineering Congress and Expositionen_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectAsymmetric spur gearen_US
dc.subjectDeep learningen_US
dc.subjectEarly fault diagnosisen_US
dc.subjectGear designen_US
dc.titleFAULT DIAGNOSIS WITH DEEP LEARNING FOR STANDARD AND ASYMMETRIC INVOLUTE SPUR GEARSen_US
dc.typeConference Objecten_US

Dosyalar

Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu
Mekatronik Mühendisliği Bölümü Yayın Koleksiyonu