Physics-Guided Sequential Bayesian Inference for Joint States and Spatio-Temporal Hidden Thermodynamic Parameters in Steam Networks
IEEE Transactions on Automation Science and Engineering · 2026 · 23 · 6711-6723
DOI: 10.1109/tase.2026.3671842 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Automation Science and Engineering, 2026. Verfasst von Wange Li und 2 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Gefördert von: National Natural Sciences Foundation of China, Sci-Tech Talent Innovation Support Program of Dalian.
Abstract (Originalsprache)
The steam heating network (SHN) serves as a critical component of the integrated energy system (IES), where precise transient characterization is essential for enhancing IES flexibility and stability. This paper proposes a physics-guided Bayesian framework for sequential inference of network states and spatio-temporal hidden thermodynamic properties, which are explicitly identified as latent property fields embedded within the PDE-based transition model. In contrast to conventional methods which typically treat thermodynamic properties as lumped parameters or non-interpretable model weights, the proposed method models probabilistic Gaussian process (GP) priors as surrogates for these latent properties, including the derivative-related terms required by the governing dynamics. By integrating thermal-hydraulic governing equations directly as hard constraints within the physics-guided transition model, this framework designs GP-ICM priors as surrogates for latent spatio-temporal properties to capture spatial correlations and heterogeneity across pipelines. Since thermodynamic properties are inseparable from state dynamics, the joint posterior becomes strongly coupled and generally non-Gaussian. The proposed joint sequential inference method combines a moment-matched Gaussian approximation for the state posterior with Monte Carlo marginalization for the thermodynamic posterior is presented, providing an efficient solution for estimating both state and property fields. To verify the performance of the proposed method, a single pipeline system and a real-world industrial superheated steam network are employed. The experimental results demonstrate that the proposed method improves accuracy in both state estimation and thermodynamic-property inference under hard physical constraints, achieving thermodynamically consistent and interpretable results. Note to Practitioners—In integrated energy systems, steam heating networks are indispensable for industrial thermal energy supply. Full-field reconstruction of key states (i.e., temperature, pressure and flow) and spatially-varying thermodynamic property (i.e., density and enthalpy) is essential for monitoring and optimizing steam quality and efficiency. However, there are a few provide measurements only at the source and a limited number of key terminal nodes, leaving the internal states of most pipeline segments unobserved. This observation sparsity makes it difficult to quantify where pressure and heat losses are incurred, to quantify end-user pressure and temperature margins with confidence under varying operating regimes, and to promptly localize emerging faults. As a result, operators often maintain conservative supply pressure and temperature to hedge against uncertainty, leading to persistent over-supply and avoidable energy waste. The proposed physics-guided sequential Bayesian method incorporates thermal-hydraulic PDEs as hard constraints in the transition model and places GP-ICM priors on latent spatio-temporal thermodynamic property fields, together with the derivative-related terms required by the governing dynamics, enabling uncertainty-aware joint inference of network states and properties. Based on the proposed framework, the monitoring application utilizes sparse measurements to support operational decision by quantifying per-segment pressure-drop and heat-loss contributions, assessing terminal pressure and temperature margins for setpoint tuning, and enabling early warning through trend analysis of inferred loss and resistance indicators.
Förderung
- National Natural Sciences Foundation of China
- Sci-Tech Talent Innovation Support Program of Dalian
Zitieren
APA
Li, W., Zhao, J., & Wang, W. (2026). Physics-Guided Sequential Bayesian Inference for Joint States and Spatio-Temporal Hidden Thermodynamic Parameters in Steam Networks. IEEE Transactions on Automation Science and Engineering, 23, 6711-6723. https://doi.org/10.1109/tase.2026.3671842
Vancouver
Li W, Zhao J, Wang W. Physics-Guided Sequential Bayesian Inference for Joint States and Spatio-Temporal Hidden Thermodynamic Parameters in Steam Networks. IEEE Transactions on Automation Science and Engineering. 2026;23:6711-6723. doi:10.1109/tase.2026.3671842
BibTeX
@article{Li2026,
author = {Li, Wange and Zhao, Jun and Wang, Wei},
title = {Physics-Guided Sequential Bayesian Inference for Joint States and Spatio-Temporal Hidden Thermodynamic Parameters in Steam Networks},
journal = {IEEE Transactions on Automation Science and Engineering},
year = {2026},
volume = {23},
pages = {6711--6723},
doi = {10.1109/tase.2026.3671842}
}
EUVIMED