EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Hybrid Deep Learning Framework for Enhanced Fault Diagnosis in Industrial Robots

Jun Wu, Yuepeng Zhang, Bo Gao, Linzhong Xia, Xueli Zhu, Hui Wang, Xiongbo Wan

Algorithms · 10.12.2025 · 18 (12) · 779

DOI: 10.3390/a18120779 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Algorithms, online erschienen am 10.12.2025. Verfasst von Jun Wu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Shenzhen University of Information Technology, Major Research Plan of the National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Predominant fault diagnosis in industrial robots depends on dedicated vibration or acoustics sensors. However, their practical deployment is often limited by installation constraints, susceptibility to environmental noise, and cost considerations. Applying Energy-Based Maintenance (EBM) principles to achieve enhanced fault diagnosis under practical industrial conditions, we propose a hybrid deep learning framework, the Multi-head Graph Attention Network (MGAT) with Multi-scale CNNBiLSTM Fusion (MGAT-MCNNBiLSTM) for industrial robots. This approach obviates the need for additional dedicated sensors, effectively mitigating associated deployment complexities. The framework embodies four core innovations: (1) Based on the EBM paradigm, motor current is established as the most effective and practical choice for enabling cost-efficient and scalable industrial robot fault diagnosis. A corresponding dataset of motor current has been acquired from industrial robots operating under diverse fault scenarios. (2) An integrated MGAT-MCNNBiLSTM architecture that synergistically models multiscale local features and complex dynamics through its MCNNBiLSTM module while capturing nonlinear interdependencies via MGAT. This comprehensive feature representation enables robust and highly accurate fault detection. (3) The study found that the application of spectral preprocessing techniques yields a marked and statistically significant enhancement in diagnostic performance. A comprehensive and systematic analysis was undertaken to uncover the underlying reasons for this observed performance improvement. (4) To emulate challenging industrial settings and cost-sensitive implementations, noise signal injection was employed to evaluate model robustness in high-electromagnetic-interference environments and low-cost, low-resolution ADC implementations. Experimental validation on real-world industrial robot datasets demonstrates that MGAT-MCNNBiLSTM achieves a superior diagnostic accuracy of 90.7560%. This performance marks a significant absolute improvement of 1.51–8.55% over competing models, including LCNNBiLSTM, SCNNBiLSTM, MCCBiLSTM, GAT, and MGAT. Under challenging noise and low-resolution conditions, the proposed model consistently outperforms CNNBiLSTM variants, GAT, and MGAT with an improvement of 1.37–10.26% and enhanced industrial utility and deployment potential.

Förderung

  • Shenzhen University of Information Technology
  • Major Research Plan of the National Natural Science Foundation of China

Zitieren

APA

Wu, J., Zhang, Y., Gao, B., Xia, L., Zhu, X., Wang, H., & Wan, X. (2025). A Hybrid Deep Learning Framework for Enhanced Fault Diagnosis in Industrial Robots. Algorithms, 18(12), 779. https://doi.org/10.3390/a18120779

Vancouver

Wu J, Zhang Y, Gao B, Xia L, Zhu X, Wang H, et al. A Hybrid Deep Learning Framework for Enhanced Fault Diagnosis in Industrial Robots. Algorithms. 2025;18(12):779. doi:10.3390/a18120779

BibTeX
@article{Wu2025,
  author = {Wu, Jun and Zhang, Yuepeng and Gao, Bo and Xia, Linzhong and Zhu, Xueli and Wang, Hui and Wan, Xiongbo},
  title = {A Hybrid Deep Learning Framework for Enhanced Fault Diagnosis in Industrial Robots},
  journal = {Algorithms},
  year = {2025},
  volume = {18},
  number = {12},
  pages = {779},
  doi = {10.3390/a18120779}
}
Kostenlos starten →