EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Acoustic-Based Industrial Diagnostics: A Scalable Noise-Robust Multiclass Framework for Anomaly Detection

Bo Peng, Danlei Li, Kevin I-Kai Wang, Waleed H. Abdulla

Processes · 14.02.2025 · 13 (2) · 544

DOI: 10.3390/pr13020544 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Processes, online erschienen am 14.02.2025. Verfasst von Bo Peng und 3 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 16 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: China Scholarship Council.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study proposes a framework for anomaly detection in industrial machines with a focus on robust multiclass classification using acoustic data. Many state-of-the-art methods only have binary classification capabilities for each machine, and suffer from poor scalability and noise robustness. In this context, we propose the use of Smoothed Pseudo Wigner–Ville Distribution-based Mel-Frequency Cepstral Coefficients (SPWVD-MFCCs) in the framework which are specifically tailored for noisy environments. SPWVD-MFCCs, with better time–frequency resolution and perceptual audio features, improve the accuracy of detecting anomalies in a more generalized way under variable signal-to-noise ratio (SNR) conditions. This framework integrates a CNN-LSTM model that efficiently and accurately analyzes spectral and temporal information separately for anomaly detection. Meanwhile, the dimensionality reduction strategy ensures good computational efficiency without losing critical information. On the MIMII dataset involving multiple machine types and noise levels, it has shown robustness and scalability. Key findings include significant improvements in classification accuracy and F1-scores, particularly in low-SNR scenarios, showcasing its adaptability to real-world industrial environments. This study represents the first application of SPWVD-MFCCs in industrial diagnostics and provides a noise-robust and scalable method for the detection of anomalies and fault classification, which is bound to improve operational safety and efficiency within complex industrial scenarios.

Förderung

  • China Scholarship Council

Zitieren

APA

Peng, B., Li, D., Wang, K. I., & Abdulla, W. H. (2025). Acoustic-Based Industrial Diagnostics: A Scalable Noise-Robust Multiclass Framework for Anomaly Detection. Processes, 13(2), 544. https://doi.org/10.3390/pr13020544

Vancouver

Peng B, Li D, Wang KI, Abdulla WH. Acoustic-Based Industrial Diagnostics: A Scalable Noise-Robust Multiclass Framework for Anomaly Detection. Processes. 2025;13(2):544. doi:10.3390/pr13020544

BibTeX
@article{Peng2025,
  author = {Peng, Bo and Li, Danlei and Wang, Kevin I-Kai and Abdulla, Waleed H.},
  title = {Acoustic-Based Industrial Diagnostics: A Scalable Noise-Robust Multiclass Framework for Anomaly Detection},
  journal = {Processes},
  year = {2025},
  volume = {13},
  number = {2},
  pages = {544},
  doi = {10.3390/pr13020544}
}
Kostenlos starten →