A nearly end-to-end deep learning approach to fault diagnosis of wind turbine gearboxes under nonstationary conditions

Zhang, L.Department of Industrial Engineering, Dongguan University of Technology, Dongguan, 523808, China (author)

Validerad;2023;Nivå 2;2023-03-21 (joosat);Funder: National Natural Science Foundation of China (71801045); DGUT, China (GC300502-46); Department of Education of Guangdong in China (2021ZDJS083)
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.

NATURVETENSKAP Data- och informationsvetenskap Datavetenskap hsv//swe
NATURAL SCIENCES Computer and Information Sciences Computer Sciences hsv//eng
TEKNIK OCH TEKNOLOGIER Maskinteknik Annan maskinteknik hsv//swe
ENGINEERING AND TECHNOLOGY Mechanical Engineering Other Mechanical Engineering hsv//eng
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
Drift och underhållsteknik

Fan, Q.School of Creative Design, Dongguan City University, Dongguan, 523419, China (author)
Lin, JingLuleå tekniska universitet,Mälardalens universitet,Innovation och produktrealisering,Division of Operation and Maintenance, Luleå University of Technology, Luleå, 97187, Sweden,Drift, underhåll och akustik,Division of Product Realization, Mälardalen University, 63220, Eskilstuna, Sweden(Swepub:ltu)linjan (author)
Zhang, Z.Department of Industrial Engineering, Dongguan University of Technology, Dongguan, 523808, China (author)
Yan, X.Department of Industrial Engineering, Dongguan University of Technology, Dongguan, 523808, China (author)
Li, C.Department of Industrial Engineering, Dongguan University of Technology, Dongguan, 523808, China (author)
Department of Industrial Engineering, Dongguan University of Technology, Dongguan, 523808, ChinaSchool of Creative Design, Dongguan City University, Dongguan, 523419, China (creator_code:org_t)

In:Engineering applications of artificial intelligence: Elsevier Ltd1190952-19761873-6769

By the author/editor: Zhang, L.; Fan, Q.; Lin, Jing; Zhang, Z.; Yan, X.; Li, C.

About the subject

NATURAL SCIENCES: NATURAL SCIENCES; and Computer and Inf ...; and Computer Science ...

ENGINEERING AND TECHNOLOGY: ENGINEERING AND ...; and Mechanical Engin ...; and Other Mechanical ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.