GNNePCSAFT Project

The project focuses on using Graph Neural Networks (GNN) to estimate the pure-component parameters of the Equation of State ePC-SAFT.

This work is motivated by the need to use a robust Equation of State, ePC-SAFT, without the need for experimental data. Equations of State are important for calculating thermodynamic properties and are prerequisites in process simulators.

Currently, the model takes into account the hard-chain, dispersive, and associative terms of ePC-SAFT. Future work on polar and ionic terms is being studied.

Code is being developed mainly in Pytorch (PyG).

You can find a model deployed at GNNePCSAFT Web App and a Desktop App at SourceForge.

A CLI to use a model can be found at GNNePCSAFT CLI and installed with pipx:

pipx install gnnepcsaftcli

Model checkpoints can be found at Hugging Face.

Use cases of this package are demonstrated in Jupyter Notebooks:

• compare.ipynb (Open in Colab): comparison of the performance of trained models
• demo.ipynb (Open in Colab): pt-br demonstration of models capabilities
• training.ipynb (Open in Colab): notebook for model training
• tuning.ipynb (Open in Colab): notebook for hyperparameter tuning

---

Work in progress.