Hyperbolic Hypergraph Neural Networks for Hierarchical Fault Diagnosis in Rotating Machinery
Sensors · 17.07.2026 · 26 (14) · 4549
DOI: 10.3390/s26144549 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 17.07.2026. Verfasst von Lingzheng Pan und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Materials Science and Engineering, Faculty of Engineering, Monash University, Melbourne 3800, Australia. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Intelligent fault diagnosis of rotating machinery is essential for ensuring the safety and reliability of industrial systems. While hypergraph neural networks (HGNNs) have recently shown promise for modeling high-order dependencies beyond pairwise graph methods, most existing variants operate in Euclidean space, which is not explicitly aligned with hierarchical fault-response structure (root cause to fault mode to observed response). To address this limitation, we propose Hyperbolic Hypergraph Neural Network (H2GNN), a framework that integrates hyperbolic geometry with hypergraph neural networks for fault diagnosis. Specifically, H2GNN constructs fault-response-aware hyperedges over diagnostic views of vibration signals and performs message passing in the Poincaré ball model, a Riemannian manifold of constant negative curvature commonly used for hierarchical representation learning. We introduce Poincaré hyperedge aggregation via an iterative Fréchet-mean solver, a learnable curvature parameter for adaptive manifold fitting, and a tangent-space classification head. Experiments are conducted on two public benchmarks, namely the Case Western Reserve University (CWRU) bearing dataset and the Machinery Failure Prevention Technology (MFPT) bearing dataset, and report mean accuracies of 99.87% and 99.75%, respectively, outperforming six competing methods, including CNN, GCN, HGNN, dynamic-HGNN, contrastive-HGNN, and spatial-temporal HGNN. Ablation studies indicate that hyperbolic geometry and the adaptive curvature mechanism both contribute to the observed performance gain.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Materials Science and Engineering, Faculty of Engineering, Monash University, Melbourne 3800, Australia.
- School of Research, Swinburne University of Technology Sarawak, Kuching 93350, Malaysia.
- School of Engineering, Swinburne University of Technology, Melbourne 3122, Australia.
ORCID-Profile: Kyaw Hlaing Bwar, Rifai Chai, Yuqi Wang, Boon Xian Chai
Zitieren
APA
Pan, L., Bwar, K. H., Chai, R., Wang, Y., & Chai, B. X. (2026). Hyperbolic Hypergraph Neural Networks for Hierarchical Fault Diagnosis in Rotating Machinery. Sensors, 26(14), 4549. https://doi.org/10.3390/s26144549
Vancouver
Pan L, Bwar KH, Chai R, Wang Y, Chai BX. Hyperbolic Hypergraph Neural Networks for Hierarchical Fault Diagnosis in Rotating Machinery. Sensors. 2026;26(14):4549. doi:10.3390/s26144549
BibTeX
@article{Pan2026,
author = {Pan, Lingzheng and Bwar, Kyaw Hlaing and Chai, Rifai and Wang, Yuqi and Chai, Boon Xian},
title = {Hyperbolic Hypergraph Neural Networks for Hierarchical Fault Diagnosis in Rotating Machinery},
journal = {Sensors},
year = {2026},
volume = {26},
number = {14},
pages = {4549},
doi = {10.3390/s26144549}
}
EUVIMED