Boosting for concept design of casting aluminum alloys driven by combining computational thermodynamics and machine learning techniques

Abstract

Casting aluminum alloys are commonly used in industries due to their excellent comprehensive performance. Alloying/microalloying and post-solidification heat treatments are the most common measures to tune the microstructure for enhancing their mechanical properties. However, it is very challenging to achieve accurate and efficient development of novel casting aluminum alloys using the traditional trial-and-error method. With the rapid development of computer technology, the computational thermodynamics (CT) in the framework of the CALculation of PHAse Diagram approach, the data-driven machine learning (ML) technique, and also their combinations have been proved to be effective approaches for the design of casting aluminum alloys. In this review, the state-of-the-art computational alloy design approaches driven by CT and ML techniques, as well as their combinations, were comprehensively summarized. The current status of the thermodynamic database for aluminum alloys, as the core for CT, was also briefly introduced. After that, a variety of successful case studies on the design of different casting aluminum alloys driven by CT, ML, and their combinations were demonstrated, including common applications, CT-driven design of Sc-additional Al-Si-Mg series casting alloys, and design of Srmodified A356 alloys driven by combing CT and ML. Finally, the conclusions of this review were drawn, and perspectives for boosting the computational design approach driven by combining CT and ML techniques were pointed out.

Accelerated discovery of high-performance Al-Si-Mg-Sc casting alloys by integrating active learning with high-throughput CALPHAD calculations

“…Furthermore, the combination of CT and ML techniques, which can establish the quantitative relation ‘composition-process-microstructure-properties’ of target alloys and thus accelerate the design of alloy composition, has been employed to efficiently design the optimal addition of Sr in A356 alloy [ 40 ]. Thus, such a combination of CT and ML techniques may stimulate the efficient composition design in multicomponent alloys [ 41 , 42 ].…”

“…The first big challenge lies in that a large number of datasets are needed to establish the quantitative relation ‘composition-process-microstructure-properties’ of Al- x Si- y Mg- z Sc alloys over high-dimensional composition space. For the casting Al-Si-Mg alloys, it is well known [ 41 , 43 ] that one may obtain a vast amount of data for reliable relation ‘composition-process-microstructure’ by combining the high-throughput CALculation of PHAse Diagrams (CALPHAD) simulations with key experiments. However, there are too limited experimental data in the literature to develop the quantitative relation 'microstructure-properties'.…”

High-Entropy Materials Design by Integrating the First-Principles Calculations and Machine Learning: a Case Study in the Al-Co-Cr-Fe-Ni System

“…Machine learning (ML) is one state-of-the-art computational technique that has been proven remarkably decisive and valuable in many elds in recent years, including materials science [26][27][28][29][30] . Unlike other methods in the computational materials community, ML is extremely computationally e cient.…”

Development of an accurate “composition-process-properties” dataset for SLMed Al-Si-(Mg) alloys and its application in alloy design

“…To solve this problem, a variety of computational methods at different scales, including CALculation of PHAse Diagram (CALPHAD) [25][26][27][28][29][30] , phase-field modeling [31][32][33] , finite element simulation [34] , and machine learning (ML) [28,29,35,36] can be utilized. Among them, ML is one of the most efficient computational methods.…”