A Bayesian deep learning framework for reliable fault diagnosis in wind turbine gearboxes under various operating conditions
Wind Engineering · 2024-04 · 48 (2) · 297-309
DOI: 10.1177/0309524x231206723 ↗Kurz gefasst
Fachartikel in der Zeitschrift Wind Engineering, online erschienen am 18.11.2023. Verfasst von Abdelrahman Amin und 3 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 33 Literaturangaben.
Abstract (Originalsprache)
Vibration-based fault diagnostics combined with deep learning approaches has promising applications in detecting and diagnosing faults in wind turbine gearboxes. Specifically when time series vibration data is transformed to a 2-dimensional cyclic spectral coherence maps, the accuracy of deep neural networks in classifying faults increases. Nevertheless, standard deep learning techniques are vulnerable to inaccurate predictions when tested with new data originating from unseen faults or unusual operating conditions. To address some of these shortcomings in the context of wind turbine gearboxes, this paper investigates fault diagnostics using Bayesian convolutional neural network which provide accurate results with uncertainty bounds reducing wrong overconfident classifications. The performance of Bayesian and standard neural networks is compared using a simulation-based dataset of acceleration signals generated from a multibody dynamic model of a 5 MW wind turbine. The framework proposed in this paper has relevance to fault detection and diagnosis in other rotating machinery applications.
Zitieren
APA
Amin, A., Bibo, A., Panyam, M., & Tallapragada, P. (2024). A Bayesian deep learning framework for reliable fault diagnosis in wind turbine gearboxes under various operating conditions. Wind Engineering, 48(2), 297-309. https://doi.org/10.1177/0309524x231206723
Vancouver
Amin A, Bibo A, Panyam M, Tallapragada P. A Bayesian deep learning framework for reliable fault diagnosis in wind turbine gearboxes under various operating conditions. Wind Engineering. 2024;48(2):297-309. doi:10.1177/0309524x231206723
BibTeX
@article{Amin2024,
author = {Amin, Abdelrahman and Bibo, Amin and Panyam, Meghashyam and Tallapragada, Phanindra},
title = {A Bayesian deep learning framework for reliable fault diagnosis in wind turbine gearboxes under various operating conditions},
journal = {Wind Engineering},
year = {2024},
volume = {48},
number = {2},
pages = {297--309},
doi = {10.1177/0309524x231206723}
}
EUVIMED