Abstract:Digital twins provide a powerful paradigm for diagnostic and prognostic tasks in the monitoring and control of engineered systems; however, their deployment for complex structures remains challenged by model-form uncertainty, arising from unknown nonlinear dynamics, and by sparse sensing. These limitations hinder reliable online state estimation using either purely physics-based or purely data-driven approaches. This work introduces the Physics-Guided Graph Neural ODE (PiGGO) framework, a physics-informed, graph-based Bayesian state estimation approach in which a learned graph neural ordinary differential equation (GNODE) serves as the continuous-time state-transition model within an extended Kalman filter. The graph representation explicitly defines the system state-space, while physics-guided inductive biases encode known structural relationships and constrain the learning of nonlinear dynamics. By integrating graph-native learned dynamics with recursive Bayesian filtering, the proposed PiGGO framework enables online virtual sensing and uncertainty-aware state estimation for nonlinear systems with unknown model form, while maintaining generalisation across topologically similar structures. Numerical case studies demonstrate improved robustness to model uncertainty and measurement noise, outperforming both open-loop graph neural models and conventional filtering approaches in online prediction tasks.
| Subjects: | Machine Learning (cs.LG); Applied Physics (physics.app-ph) |
| Cite as: | arXiv:2604.26593 [cs.LG] |
| (or arXiv:2604.26593v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.26593 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Marcus Haywood-Alexander [view email]
[v1]
Wed, 29 Apr 2026 12:22:08 UTC (7,408 KB)