https://www.mdu.se/

mdu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
A nearly end-to-end deep learning approach to fault diagnosis of wind turbine gearboxes under nonstationary conditions
Department of Industrial Engineering, Dongguan University of Technology, Dongguan, 523808, China.
School of Creative Design, Dongguan City University, Dongguan, 523419, China.
Mälardalen University, School of Innovation, Design and Engineering, Innovation and Product Realisation. Division of Operation and Maintenance, Luleå University of Technology, Luleå, 97187, Sweden.ORCID iD: 0000-0002-7458-6820
Department of Industrial Engineering, Dongguan University of Technology, Dongguan, 523808, China.
Show others and affiliations
2023 (English)In: Engineering applications of artificial intelligence, ISSN 0952-1976, E-ISSN 1873-6769, Vol. 119, article id 105735Article in journal (Refereed) Published
Abstract [en]

Fault diagnosis of wind turbine gearboxes is crucial in ensuring wind farms’ reliability and safety. However, nonstationary working conditions, such as load change or speed regulation, may result in an accuracy deterioration of many existing fault diagnosis approaches. To overcome the issue, this research proposes a nearly end-to-end deep learning approach to fault diagnosis of wind turbine gearboxes using vibration signals. Concretely, we adopt Empirical Mode Decomposition (EMD) to decompose vibration signals into a series of Intrinsic Mode Functions (IMFs). Then, the multi-channel IMFs are fed into a 1D Convolutional Neural Network (CNN) for automatic feature learning and fault classification. Since EMD is a signal processing technique requiring no prior knowledge, the model architecture can be viewed as nearly end-to-end. The proposed approach was validated in a real-world dataset; it proved deep learning models have an overwhelming advantage in representation capacity over traditional shallow models. It also demonstrated that the introduction of EMD as a preprocessing step improves both the training efficiency and the generalization ability of a deep model, thus leading to a better fault diagnosis efficacy under variable working conditions.

Place, publisher, year, edition, pages
Elsevier Ltd , 2023. Vol. 119, article id 105735
Keywords [en]
Convolutional neural network, Deep learning, Empirical mode decomposition, End-to-end learning, Fault diagnosis, Convolution, Convolutional neural networks, Deterioration, Failure analysis, Fault detection, Intrinsic mode functions, Wind power, Wind turbines, Condition, End to end, Faults diagnosis, Learning approach, Vibration signal, Wind turbine gearboxes
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:mdh:diva-61421DOI: 10.1016/j.engappai.2022.105735ISI: 000912326600001Scopus ID: 2-s2.0-85144823492OAI: oai:DiVA.org:mdh-61421DiVA, id: diva2:1723886
Available from: 2023-01-04 Created: 2023-01-04 Last updated: 2023-02-08Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Lin, Jing

Search in DiVA

By author/editor
Lin, Jing
By organisation
Innovation and Product Realisation
In the same journal
Engineering applications of artificial intelligence
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 80 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf