Deep transfer multi-wavelet auto-encoder for intelligent fault diagnosis of gearbox with few target training samplesShow others and affiliations
2020 (English)In: Knowledge-Based Systems, ISSN 0950-7051, E-ISSN 1872-7409, Vol. 191, article id 105313Article in journal (Refereed) Published
Abstract [en]
Lack of typical fault samples remains a huge challenge for intelligent fault diagnosis of gearbox. In this paper, a novel approach named deep transfer multi-wavelet auto-encoder is presented for gearbox intelligent fault diagnosis with few training samples. Firstly, new-type deep multi-wavelet auto-encoder is designed for learning important features of the collected vibration signals of gearbox. Secondly, high-quality auxiliary samples are selected based on similarity measure to well pre-train a source model sharing similar characteristics with the target domain. Thirdly, parameter knowledge acquired from the source model is transferred to target model using very few target training samples. Transfer diagnosis cases for different fault severities and compound faults of gearbox confirm the feasibility of the proposed approach even if the working conditions have significant changes.
Place, publisher, year, edition, pages
Elsevier, 2020. Vol. 191, article id 105313
Keywords [en]
Deep transfer multi-wavelet auto-encode, Gearbox fault, Transfer diagnosis, Variable working conditions, Few target training samples
National Category
Other Civil Engineering
Research subject
Operation and Maintenance
Identifiers
URN: urn:nbn:se:ltu:diva-77568DOI: 10.1016/j.knosys.2019.105313ISI: 000517663200035Scopus ID: 2-s2.0-85076527537OAI: oai:DiVA.org:ltu-77568DiVA, id: diva2:1389904
Note
Validerad;2020;Nivå 2;2020-03-02 (alebob)
2020-01-302020-01-302022-10-28Bibliographically approved