Predicting Thermal Conductivity of Foamed Concrete via Physics-Informed Neural Networks Coupled with the Maxwell-Eucken Model.
4 affiliations
- 1Xinhua College of Ningxia University, Yinchuan 750021, China.
- 2Ningxia Center for Research on Earthquake Protection and Disaster Mitigation in Civil Engineering, Yinchuan 750021, China.
- 3State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou 310027, China.
- 4School of Mechanical Engineering, Ningxia University, Yinchuan 750021, China.
Abstract
This study investigates a neural network model regularized by the Maxwell-Eucken formulation for predicting the thermal conductivity of foamed concrete. Backed by experimental measurements, the modeling workflow incorporates augmented samples derived from the empirical dataset. A total of 30 experimental records, categorized into five distinct mixture groups, provide the foundational data basis. Bulk density and density-derived porosity serve as model inputs, both reflecting the same underlying variation in material density. Evaluation results demonstrate that the proposed hybrid model achieves a coefficient of determination (R²) of 0.7701, substantially outperforming the standalone Maxwell-Eucken model (R² = 0.4546) and the effective medium theory (R² = 0.3041). Although these indicators reflect an improved in-sample fit, they neither isolate the explicit contribution of the physics-informed penalty nor establish the model's predictive capability for unseen mixtures. The Maxwell-Eucken term functions as an approximate constitutive regularizer, whereas the clustered residuals highlight specific boundary conditions where further model refinement is warranted. Overall, this study validates the feasibility of the hybrid modeling approach within the tested material domain; group-separated validation and comparative benchmarks against purely data-driven models are required to assess its broader generalizability.
Related
- Enhanced thermal conductivity of polyurethane composites via microstructural design of 3D interconnected boron nitride networks
- The Thermal Conductivity of Polymer-Derived Amorphous Si-O-C Compounds and Nano-Composites
- Effect of pyrolysis temperature on the microstructure and thermal conductivity of polymer-derived monolithic and porous SiC ceramics
- Hierarchical sandwich composite film with engineered interfaces for concurrent high-frequency ultra-low dielectric constant and high thermal conductivity
- Emergent coherent-incoherent phonon crossover enables ultralow lattice thermal conductivity in 3D double perovskite
BibTeX
@article{pan2026predicting,
title = {{Predicting Thermal Conductivity of Foamed Concrete via Physics-Informed Neural Networks Coupled with the Maxwell-Eucken Model.}},
author = {Pengfei Pan and Yakun Zhang and Rui Li and Zheng Wang and Xiaolong Ma},
journal = {Materials (Basel, Switzerland)},
year = {2026},
month = oct,
doi = {10.3390/ma19204411},
url = {https://europepmc.org/article/MED/42941152},
note = {CC BY},
}
RIS
TY - JOUR
TI - Predicting Thermal Conductivity of Foamed Concrete via Physics-Informed Neural Networks Coupled with the Maxwell-Eucken Model.
AU - Pengfei Pan
AU - Yakun Zhang
AU - Rui Li
AU - Zheng Wang
AU - Xiaolong Ma
PY - 2026
DA - 2026/10/20
JO - Materials (Basel, Switzerland)
DO - 10.3390/ma19204411
UR - https://europepmc.org/article/MED/42941152
AB - This study investigates a neural network model regularized by the Maxwell-Eucken formulation for predicting the thermal conductivity of foamed concrete. Backed by experimental measurements, the modeling workflow incorporates augmented samples derived from the empirical dataset. A total of 30 experimental records, categorized into five distinct mixture groups, provide the foundational data basis. Bulk density and density-derived porosity serve as model inputs, both reflecting the same underlying variation in material density. Evaluation results demonstrate that the proposed hybrid model achieves a coefficient of determination (R²) of 0.7701, substantially outperforming the standalone Maxwell-Eucken model (R² = 0.4546) and the effective medium theory (R² = 0.3041). Although these indicators reflect an improved in-sample fit, they neither isolate the explicit contribution of the physics-informed penalty nor establish the model's predictive capability for unseen mixtures. The Maxwell-Eucken term functions as an approximate constitutive regularizer, whereas the clustered residuals highlight specific boundary conditions where further model refinement is warranted. Overall, this study validates the feasibility of the hybrid modeling approach within the tested material domain; group-separated validation and comparative benchmarks against purely data-driven models are required to assess its broader generalizability.
SN - 1996-1944
ER -