EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Dynamics-Driven Dual-Stream Graph Neural Network with Adaptive Gated Fusion for Gearbox Fault Diagnosis

Jiashuo Yu, Hanbin Xiao, Min Liu, Dinglong Zhu

Machines · 05.08.2026 · 14 (8) · 889

DOI: 10.3390/machines14080889 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machines, online erschienen am 05.08.2026. Verfasst von Jiashuo Yu und 3 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Conventional data-driven networks for gearbox fault diagnosis process multi-sensor streams as isolated sequences, failing to capture spatial-topological kinetic correlations and structural energy propagation pathways governed by multi-stage gearbox dynamics. To address these limitations, this study proposes a graph neural network-based fault diagnosis methodology integrating multi-dimensional attention and dynamic topological priors (KT-GNN-CBAM). Mesh stiffness characteristics are analytically evaluated to initialize physical topology edge weights, while a convolutional block attention module filters spatio-temporal features to suppress background noise. Node features are subsequently aggregated through a parallel dual-stream architecture comprising a physics-prior kinetic stream and a data-driven attention stream, which are dynamically fused via an adaptive gated mechanism. Experimental validation on the HP-GBS-2023 testbed under mixed operations and 6 dB noise shows that the proposed framework achieves an optimal diagnostic accuracy of 98.87%. Ablation evaluations confirm that omitting the mechanics-driven prior branch induces a 282.30% relative surge in the model’s misclassification rate. Ultimately, embedding mechanical invariants as a physical inductive bias mitigates purely data-driven black-box constraints, offering an interpretable and robust solution for advanced intelligent fault diagnosis in complex gearbox systems.

Zitieren

APA

Yu, J., Xiao, H., Liu, M., & Zhu, D. (2026). Dynamics-Driven Dual-Stream Graph Neural Network with Adaptive Gated Fusion for Gearbox Fault Diagnosis. Machines, 14(8), 889. https://doi.org/10.3390/machines14080889

Vancouver

Yu J, Xiao H, Liu M, Zhu D. Dynamics-Driven Dual-Stream Graph Neural Network with Adaptive Gated Fusion for Gearbox Fault Diagnosis. Machines. 2026;14(8):889. doi:10.3390/machines14080889

BibTeX
@article{Yu2026,
  author = {Yu, Jiashuo and Xiao, Hanbin and Liu, Min and Zhu, Dinglong},
  title = {Dynamics-Driven Dual-Stream Graph Neural Network with Adaptive Gated Fusion for Gearbox Fault Diagnosis},
  journal = {Machines},
  year = {2026},
  volume = {14},
  number = {8},
  pages = {889},
  doi = {10.3390/machines14080889}
}
Kostenlos starten →