A machine learning–based classification approach for phase diagram prediction. (March 2022)

• Record Type: Journal Article
• Authors: Deffrennes, Guillaume; Terayama, Kei; Abe, Taichi; Tamura, Ryo
• Is Part Of: Materials & design. Volume 215(2022)
• Publication Date: 2022-03
• Subjects: Phase diagrams -- Machine learning -- Alloys -- CALPHAD; Materials -- Periodicals; Engineering design -- Periodicals; Matériaux -- Périodiques; Conception technique -- Périodiques; Electronic journals; 620.11
• DOI: 10.1016/j.matdes.2022.110497
• Languages: English
• ISSNs: 0264-1275

Abstract

Graphical abstract: Highlights: The number of coexisting phases across the 800 K section of the Al-Cu-Mg-Si-Zn quinary ternaries is predicted via machine learning. An average prediction accuracy of 84% is achieved. The predictions are useful for guiding experimental investigations of phase diagrams, even when using small datasets. Important machine learning features can be generated from CALPHAD extrapolations from binaries into higher-order systems. Abstract: Knowledge of phase diagrams is essential for material design as it helps in understanding microstructure evolution during processing. The determination of phase diagrams is thus one of the central tasks in materials science. When exploring new materials for which the phase diagram is unknown, experimentalists often try to determine the key experiments that should be performed by referencing known phase diagrams of similar systems. To enhance this practical strategy, we attempted to estimate unknown phase diagrams based on known phase diagrams using a machine learning–based classification approach. As a proof of concept, we focused on predicting the number of coexisting phases across the 800 K isothermal section of each of the 10 ternaries of the Al-Cu-Mg-Si-Zn system from the other 9 sections. To increase the prediction accuracy, we introduced new descriptors generated from the thermodynamic properties of the elements and CALPHAD extrapolations from lower-order systems. Using the random forest method, the presence of single-, two-, and three-phase domains was predicted with an average accuracy of 84% across all 10 considered sections with a standard deviation of 11%. The proposed approach represents a promising tool for assisting the investigator in developing new materials and determining phase equilibria efficiently.