cs.LGNov 19, 2026

Thermodynamically Consistent Neural Networks for a Universal Fluid Gibbs Free Energy Equation of State

Authors: Xurui Li, Zhiguo Gan, Jiaming Zhang, Hongxi Zeng, Diannan Lu

Organizations: Department of Chemical Engineering, Tsinghua University, Beijing 100084, People’s Republic of China · School of Engineering, The University of Edinburgh, King’s Buildings, Edinburgh EH9 3DW, United Kingdom

Abstract

Over the past three centuries, many thermodynamics researchers have worked to develop fluid equations of state with both high accuracy and broad applicability, proposing various theoretical frameworks and models. Building on these efforts, this study uses Gibbs free energy as the starting point and introduces thermodynamically consistent neural networks to construct a fluid equation of state based on Gibbs free energy (GEoS). This approach establishes a novel machine learning framework that provides a unified representation of fluid states. GEoS performs well on the vapor- and liquid-phase density test sets, with average absolute relative deviations (AARDs) of 5.25% and 3.96%, respectively. It outperforms conventional volume-translated cubic equations of state and existing machine learning models, demonstrating its effectiveness. Further analysis using the UMAP dimensionality reduction method shows that most molecules in the test set belong to extrapolation systems, confirming the strong generalization ability of the model. Finally, the test results show that the PC-SAFT equation fitted using GEoS maintains high predictive accuracy, providing a reliable basis for its practical application in industry.

Figures & tables

Explore similar work

CardsList
  1. Clapeyron Neural Networks for Single-Species Vapor-Liquid Equilibria

    Feb 20, 2026Jan Pavšek, Alexander Mitsos, Elvis J. Sim +1Molecular Property PredictionMaterials Property Prediction

  2. Differentiable Thermodynamic Phase-Equilibria for Machine Learning

    Mar 11, 2026Karim K. Ben Hicham, Moreno Ascani, Jan G. Rittig +1Scientific MLDifferentiable Programming

  3. GIMLET: Generalizable and Interpretable Model Learning through Embedded Thermodynamics

    Dec 22, 2025Suguru Shiratori, Elham Kiyani, Khemraj Shukla +1Scientific MLPhysics-Informed ML