EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Unsupervised Anomaly Detection Method for Drones Based on a 1-D Selective Kernel Convolutional Autoencoder with Bayesian Optimization

Junjie He, Boyang Zhong, Simin Wang, Lin Song, Li Guo, Pengfei Wang, Fei Wang

Machines · 17.07.2026 · 14 (7) · 812

DOI: 10.3390/machines14070812 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machines, online erschienen am 17.07.2026. Verfasst von Junjie He und 6 weiteren Autor:innen. Die Arbeit nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Yibin City Science and Technology Plan Project of Sichuan Province, Talent Program of Chengdu Technological University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The widespread application of drones in complex environments imposes higher demands on flight safety. However, traditional anomaly detection methods often rely on mathematical models or large amounts of labeled samples, which makes them ill suited to address practical challenges such as unmanned aerial vehicle systems, which exhibit strong nonlinear characteristics, a scarcity of fault samples, and highly variable operating conditions. To overcome the above difficulties, this work puts forward a one-dimensional selective kernel convolutional autoencoder (1-D SKCAE) based on Bayesian optimization for unsupervised drone anomaly detection. Relying solely on normal operation data, this model achieves accurate anomaly identification by leveraging the sudden changes in reconstruction error. For the model architecture, this paper designs a multi-scale selective kernel convolution module and combines an attention mechanism to achieve adaptive feature weighting for various receptive fields. This method effectively improves the model’s ability to represent complex operational conditions and subtle fault characteristics. Simultaneously, Bayesian optimization is embedded into the model training process as a hyperparameter search strategy, enabling the adaptive configuration of key hyperparameters to further enhance detection performance. Extensive experiments were conducted using the RflyMAD simulation dataset and the 3DR Solo real flight dataset. The results demonstrate that the 1-D SKCAE outperforms multiple comparative models, exhibiting superior robustness particularly in complex scenarios such as mixed multi-fault superposition. This method enables drone anomaly detection without fault labels, showcasing strong potential for engineering applications.

Förderung

  • Yibin City Science and Technology Plan Project of Sichuan Province
  • Talent Program of Chengdu Technological University

Zitieren

APA

He, J., Zhong, B., Wang, S., Song, L., Guo, L., Wang, P., & Wang, F. (2026). An Unsupervised Anomaly Detection Method for Drones Based on a 1-D Selective Kernel Convolutional Autoencoder with Bayesian Optimization. Machines, 14(7), 812. https://doi.org/10.3390/machines14070812

Vancouver

He J, Zhong B, Wang S, Song L, Guo L, Wang P, et al. An Unsupervised Anomaly Detection Method for Drones Based on a 1-D Selective Kernel Convolutional Autoencoder with Bayesian Optimization. Machines. 2026;14(7):812. doi:10.3390/machines14070812

BibTeX
@article{He2026,
  author = {He, Junjie and Zhong, Boyang and Wang, Simin and Song, Lin and Guo, Li and Wang, Pengfei and Wang, Fei},
  title = {An Unsupervised Anomaly Detection Method for Drones Based on a 1-D Selective Kernel Convolutional Autoencoder with Bayesian Optimization},
  journal = {Machines},
  year = {2026},
  volume = {14},
  number = {7},
  pages = {812},
  doi = {10.3390/machines14070812}
}
Kostenlos starten →