Deep learning for CALPHAD modeling: Universal parameter learning solely based on chemical formula

TL;DR

This paper introduces a deep learning method that learns CALPHAD model parameters directly from chemical formulas, enabling automated and comprehensive thermodynamic database creation.

Contribution

It presents a novel approach combining deep learning with CALPHAD, trained solely on chemical formulas, to predict model parameters without extensive experimental data.

Findings

Successfully applied to calculate mixing parameters of liquids

Demonstrates potential for automated CALPHAD modeling

Highlights integration of deep learning with thermodynamic modeling

Abstract

Empowering the creation of thermodynamic and property databases, the CALPHAD (CALculation of PHAse Diagrams) methodology plays a vital role in enhancing materials and manufacturing process design. In this study, we propose a deep learning approach to train parameters in CALPHAD models solely based on chemical formula. We demonstrate its application through an example of calculating the mixing parameter of liquids. This work showcases the integration of CALPHAD and deep learning, highlighting its potential for achieving automated comprehensive CALPHAD modeling.