A review on phase prediction in high entropy alloys

Abstract

The formation of single phase solid solution in High Entropy Alloys (HEAs) is essential for the properties of the alloys therefore, numerous approach were proposed by many researchers to predict the stability of single phase solid solution in High Entropy Alloy. The present review examines some of the recent developments while using computational intelligence techniques such as parametric approach, CALPHAD, Machine Learning etc. for prediction of various phase formation in multicomponent high entropy alloys. A detail study of this data-driven approaches pertaining to the understanding of structural and phase formation behaviour of a new class of compositionally complex alloys is done in the present investigation. The advantages and drawbacks of the various computational are also discussed. Finally, this review aims at understanding several computational modeling tools complying the thermodynamic criteria for phase formation of novel HEAs which could possibly deliver superior mechanical properties keeping an aim at advanced engineering applications.

Data-driven analysis and prediction of stable phases for high-entropy alloy design

“…Despite the recent progress, phase prediction remains difficult and complex; hence, the accurate determination of the phase formation remains paramount when designing novel HEAs with targeted properties, as it is intricately tied to specific material characteristics 20 – 23 . Phases in HEAs can be a solid solution (SS), intermetallic (IM), amorphous (AM), and a mixture of these phases (SS + IM and SS + AM) 24 .…”

“…These qualities position ML as a highly promising tool to tackle the challenges faced by the theoretical modeling of HEAs. ML plays a multifaceted role in the development of HEAs, as outlined in relevant review papers 20 , 32 , 40 – 43 . It serves various purposes, including predicting stable phases (microstructure) and properties, accelerating simulations, and extracting underlying physical principles from the complex chemical structure of HEAs.…”

A machine learning framework for discovering high entropy alloys phase formation drivers

“…The constituent phase is one of the critical considerations for designing HEAs as it significantly impacts the alloy's mechanical properties. Different methods have been implemented for HEAs phase prediction such as empirical rules [10] , calculation of phase diagram (CALPHAD) [11] , [12] , and density functional theory [13] . However, those methods are suffering from low accuracy [10] , absence of complete datasets and thermodynamic models [9] , and high computational cost [14] , respectively.…”

Microstructural Characterization and Phase Prediction of High Entropy Alloys using Empirical and Machine Learning Based Methodologies

“…As the phase composition of HEAs has been shown to be a significant factor in various properties of HEAs, being able to predict the resultant phases of a given HEA manufactured using a given method is of high importance. However, due to the complex elemental interactions inherent within HEAs, predicting the resulting microstructure of a HEA composition can differ from methods used for traditional alloys [89]. These prediction methods generally fall under one of three categories: empirically developed design parameters, computational simulations, and machine learning based predictions.…”

“…Empirical design parameters tend to be focused around aspects of the previously discussed "four core effects" or with the Humes-Rothery rules for binary solid solution formation, with terms such as mixing entropy (1), mixing enthalpy (2), and root mean squared atomic size difference (3) appearing often as follows [89].…”