EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MFGAN: Multimodal Fusion for Industrial Anomaly Detection Using Attention-Based Autoencoder and Generative Adversarial Network

Xinji Qu, Zhuo Liu, Chase Q Wu iD, Aiqin Hou, Xiaoyan Yin iD, Zhulian Chen

Sensors · 19.01.2024 · 24 (2) · 637

DOI: 10.3390/s24020637 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 19.01.2024. Verfasst von Xinji Qu und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Technology, Northwest University, Xi'an 710127, China. Die Arbeit wurde bisher 70-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Anomaly detection plays a critical role in ensuring safe, smooth, and efficient operation of machinery and equipment in industrial environments. With the wide deployment of multimodal sensors and the rapid development of Internet of Things (IoT), the data generated in modern industrial production has become increasingly diverse and complex. However, traditional methods for anomaly detection based on a single data source cannot fully utilize multimodal data to capture anomalies in industrial systems. To address this challenge, we propose a new model for anomaly detection in industrial environments using multimodal temporal data. This model integrates an attention-based autoencoder (AAE) and a generative adversarial network (GAN) to capture and fuse rich information from different data sources. Specifically, the AAE captures time-series dependencies and relevant features in each modality, and the GAN introduces adversarial regularization to enhance the model’s ability to reconstruct normal time-series data. We conduct extensive experiments on real industrial data containing both measurements from a distributed control system (DCS) and acoustic signals, and the results demonstrate the performance superiority of the proposed model over the state-of-the-art TimesNet for anomaly detection, with an improvement of 5.6% in F1 score.

Schlagwörter

Stichwörter der Autor:innen

attention-based autoencodergenerative adversarial networkindustrial anomaly detectionmultimodal fusion

Autor:innen und Institutionen

  • School of Information Science and Technology, Northwest University, Xi'an 710127, China.
  • Department of Data Science, New Jersey Institute of Technology, Newark, NJ 07102, USA.

ORCID-Profile: Chase Q Wu, Xiaoyan Yin

Zitieren

APA

Qu, X., Liu, Z., Wu, C. Q., Hou, A., Yin, X., & Chen, Z. (2024). MFGAN: Multimodal Fusion for Industrial Anomaly Detection Using Attention-Based Autoencoder and Generative Adversarial Network. Sensors, 24(2), 637. https://doi.org/10.3390/s24020637

Vancouver

Qu X, Liu Z, Wu CQ, Hou A, Yin X, Chen Z. MFGAN: Multimodal Fusion for Industrial Anomaly Detection Using Attention-Based Autoencoder and Generative Adversarial Network. Sensors. 2024;24(2):637. doi:10.3390/s24020637

BibTeX
@article{Qu2024,
  author = {Qu, Xinji and Liu, Zhuo and Wu, Chase Q and Hou, Aiqin and Yin, Xiaoyan and Chen, Zhulian},
  title = {MFGAN: Multimodal Fusion for Industrial Anomaly Detection Using Attention-Based Autoencoder and Generative Adversarial Network},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {2},
  pages = {637},
  doi = {10.3390/s24020637}
}
Kostenlos starten →