Physics-integrated neural network modeling of heat and mass transfer in cryogenic liquid storage under static and dynamic conditions
Abstract
Accurate system-level prediction of cryogenic liquid storage remains challenging because reduced-order models rely on regime-dependent closures for unresolved heat and mass transfer, particularly under sloshing. We present a physics-integrated neural-network framework that combines a conservation-based zero-dimensional nodal model with data-driven closures for wall and interfacial heat transfer, phase change, pressurant quality, and liquid thermal-boundary-layer evolution. Thermal stratification and mixing within the liquid are represented through a first-order dynamical model for the boundary-layer thickness, while four operating-regime-specific neural networks infer the closure parameters for self-pressurization and relaxation, active pressurization, venting, and lateral sloshing. The framework was identified and evaluated using a dedicated database of 48 multi-stage cryogenic-tank experiments conducted in an optically accessible facility operated with liquid nitrogen. The experiments combine controlled wall heating, vapor injection and evacuation, and forced lateral sloshing, thereby covering both slowly evolving thermal states and strongly transient operating conditions. Generalization was assessed through experiment-level K-fold cross-validation, while an entropy-production penalty was included in the loss function to discourage violations of the second law of thermodynamics. Across the investigated cross-validation configurations, the global normalized root-mean-square error remained under 3%, with sloshing representing the most demanding regime. A final model trained on the complete database reconstructed the experiments with a global error of 1.6%. These results demonstrate that the proposed framework can extract physically interpretable and computationally efficient closure laws from a limited but information-rich experimental database.
Related
- Characterization of Next Generation Power Over Fiber Systems under Cryogenic Conditions for Advanced Physics Instrumentation
- Retrainable physics-integrated neural differentiable modeling of sintering across material systems
- Compact Modeling of Oxide-Semiconductor, 2D Material, Carbon Nanotube, and Cryogenic Transistors with Experiment Verification
- Kinetic modeling of molecular beam formation in a cryogenic buffer-gas cell
- Helium-Gas-Cooled Cryogenic Current Comparator Integrated with a Quantum Resistance Standard
BibTeX
@misc{marques2026physicsintegrated,
title = {{Physics-integrated neural network modeling of heat and mass transfer in cryogenic liquid storage under static and dynamic conditions}},
author = {Pedro Afonso Marques and Samuel Akatchi Ahizi and Miguel Alfonso Mendez},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2609.00019},
eprint = {2609.00019},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.00019},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Physics-integrated neural network modeling of heat and mass transfer in cryogenic liquid storage under static and dynamic conditions
AU - Pedro Afonso Marques
AU - Samuel Akatchi Ahizi
AU - Miguel Alfonso Mendez
PY - 2026
DA - 2026/10/05
PB - arXiv
DO - 10.48550/arxiv.2609.00019
UR - https://arxiv.org/abs/2609.00019
AB - Accurate system-level prediction of cryogenic liquid storage remains challenging because reduced-order models rely on regime-dependent closures for unresolved heat and mass transfer, particularly under sloshing. We present a physics-integrated neural-network framework that combines a conservation-based zero-dimensional nodal model with data-driven closures for wall and interfacial heat transfer, phase change, pressurant quality, and liquid thermal-boundary-layer evolution. Thermal stratification and mixing within the liquid are represented through a first-order dynamical model for the boundary-layer thickness, while four operating-regime-specific neural networks infer the closure parameters for self-pressurization and relaxation, active pressurization, venting, and lateral sloshing. The framework was identified and evaluated using a dedicated database of 48 multi-stage cryogenic-tank experiments conducted in an optically accessible facility operated with liquid nitrogen. The experiments combine controlled wall heating, vapor injection and evacuation, and forced lateral sloshing, thereby covering both slowly evolving thermal states and strongly transient operating conditions. Generalization was assessed through experiment-level K-fold cross-validation, while an entropy-production penalty was included in the loss function to discourage violations of the second law of thermodynamics. Across the investigated cross-validation configurations, the global normalized root-mean-square error remained under 3%, with sloshing representing the most demanding regime. A final model trained on the complete database reconstructed the experiments with a global error of 1.6%. These results demonstrate that the proposed framework can extract physically interpretable and computationally efficient closure laws from a limited but information-rich experimental database.
ER -