EUVIMEDEUVIMED entdecken
Crossref

Is deep learning superior to traditional techniques in machine health monitoring applications

W. Wang, K. Vos, J. Taylor, C. Jenkins, B. Bala, L. Whitehead, Z. Peng

The Aeronautical Journal · 2023-12 · 127 (1318) · 2105-2117

DOI: 10.1017/aer.2023.60 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Aeronautical Journal, online erschienen am 14.08.2023. Verfasst von W. Wang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 14 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, there has been significant momentum in applying deep learning (DL) to machine health monitoring (MHM). It has been widely claimed that DL methodologies are superior to more traditional techniques in this area. This paper aims to investigate this claim by analysing a real-world dataset of helicopter sensor faults provided by Airbus. Specifically, we will address the problem of machine sensor health unsupervised classification. In a 2019 worldwide competition hosted by Airbus, Fujitsu Systems Europe (FSE) won first prize by achieving an F1-score of 93% using a DL model based on generative adversarial networks (GAN). In another comprehensive study, various modified and existing image encoding methods were compared for the convolutional auto-encoder (CAE) model. The best classification result was achieved using the scalogram as the image encoding method, with an F1-score of 91%. In this paper, we use these two studies as benchmarks to compare with basic statistical analysis methods and the one-class supporting vector machine (SVM). Our comparative study demonstrates that while DL-based techniques have great potential, they are not always superior to traditional methods. We therefore recommend that all future published studies of applying DL methods to MHM include appropriately selected traditional reference methods, wherever possible.

Zitieren

APA

Wang, W., Vos, K., Taylor, J., Jenkins, C., Bala, B., Whitehead, L., & Peng, Z. (2023). Is deep learning superior to traditional techniques in machine health monitoring applications. The Aeronautical Journal, 127(1318), 2105-2117. https://doi.org/10.1017/aer.2023.60

Vancouver

Wang W, Vos K, Taylor J, Jenkins C, Bala B, Whitehead L, et al. Is deep learning superior to traditional techniques in machine health monitoring applications. The Aeronautical Journal. 2023;127(1318):2105-2117. doi:10.1017/aer.2023.60

BibTeX
@article{Wang2023,
  author = {Wang, W. and Vos, K. and Taylor, J. and Jenkins, C. and Bala, B. and Whitehead, L. and Peng, Z.},
  title = {Is deep learning superior to traditional techniques in machine health monitoring applications},
  journal = {The Aeronautical Journal},
  year = {2023},
  volume = {127},
  number = {1318},
  pages = {2105--2117},
  doi = {10.1017/aer.2023.60}
}
Kostenlos starten →