EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing Acoustic Leak Detection with Data Augmentation: Overcoming Background Noise Challenges

Deniz Quick, Jens Denecke, Jürgen Schmidt

AI · 24.06.2025 · 6 (7) · 136

DOI: 10.3390/ai6070136 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AI, online erschienen am 24.06.2025. Verfasst von Deniz Quick und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Evonik Operations GmbH, BASF SE, Covestro AG, and Siemens AG.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

A leak detection method is developed for leaks typically encountered in industrial production. Leaks of 1 mm diameter and less are considered at operating pressures up to 10 bar. The system uses two separate datasets—one for the leak noises and the other for the background noises—both are linked using a developed mixup technique and thus simulate leaks trained in background noises. A specific frequency window between 11 and 20 kHz is utilized to generate a quadratic input for image recognition. With this method, detection accuracies of over 95% with a false alarm rate under 2% can be achieved on a test dataset under the background noises of hydraulic machines in laboratory conditions.

Förderung

  • Evonik Operations GmbH, BASF SE, Covestro AG, and Siemens AG

Zitieren

APA

Quick, D., Denecke, J., & Schmidt, J. (2025). Enhancing Acoustic Leak Detection with Data Augmentation: Overcoming Background Noise Challenges. AI, 6(7), 136. https://doi.org/10.3390/ai6070136

Vancouver

Quick D, Denecke J, Schmidt J. Enhancing Acoustic Leak Detection with Data Augmentation: Overcoming Background Noise Challenges. AI. 2025;6(7):136. doi:10.3390/ai6070136

BibTeX
@article{Quick2025,
  author = {Quick, Deniz and Denecke, Jens and Schmidt, Jürgen},
  title = {Enhancing Acoustic Leak Detection with Data Augmentation: Overcoming Background Noise Challenges},
  journal = {AI},
  year = {2025},
  volume = {6},
  number = {7},
  pages = {136},
  doi = {10.3390/ai6070136}
}
Kostenlos starten →