High-entropy alloys (HEAs) are a new class of solid-solution alloys that have attracted worldwide attention for their outstanding properties. Owing to the demand from transportation and defense industries, light-weight HEAs have also garnered widespread interest from scientists for use as potential structural materials. Great efforts have been made to study the phase-formation rules of HEAs to accelerate and refine the discovery process. In this paper, many proposed solid-solution phase-formation rules are assessed, based on a series of known and newly-designed light-weight HEAs. The results indicate that these empirical rules work for most compositions but also fail for several alloys. Light-weight HEAs often involve the additions of Al and/or Ti in great amounts, resulting in large negative enthalpies for forming solid-solution phases and/or intermetallic compounds. Accordingly, these empirical rules need to be modified with the new experimental data. In contrast, CALPHAD (acronym of the calculation of phase diagrams) method is demonstrated to be an effective approach to predict the phase formation in HEAs as a function of composition and temperature. Future perspectives on the design of light-weight HEAs are discussed in light of CALPHAD modeling and physical metallurgy principles.

Guided by CALPHAD (Calculation of Phase Diagrams) modeling, the refractory medium-entropy alloy MoNbTaV was synthesized by vacuum arc melting under a high-purity argon atmosphere. A body-centered cubic solid solution phase was experimentally confirmed in the as-cast ingot using X-ray diffraction and scanning electron microscopy. The measured lattice parameter of the alloy (3.208 Å) obeys the rule of mixtures (ROM), but the Vickers microhardness (4.95 GPa) and the yield strength (1.5 GPa) are about 4.5 and 4.6 times those estimated from the ROM, respectively. Using a simple model on solid solution strengthening predicts a yield strength of approximately 1.5 GPa. Thermodynamic analysis shows that the total entropy of the alloy is more than three times the configurational entropy at room temperature, and the entropy of mixing exhibits a small negative departure from ideal mixing.

The Larson–Miller parameter (LMP) offers an efficient and fast scheme to estimate the creep rupture life of alloy materials for high-temperature applications; however, poor generalizability and dependence on the constant C often result in sub-optimal performance. In this work, we show that the direct rupture life parameterization without intermediate LMP parameterization, using a gradient boosting algorithm, can be used to train ML models for very accurate prediction of rupture life in a variety of alloys (Pearson correlation coefficient >0.9 for 9–12% Cr and >0.8 for austenitic stainless steels). In addition, the Shapley value was used to quantify feature importance, making the model interpretable by identifying the effect of various features on the model performance. Finally, a variational autoencoder-based generative model was built by conditioning on the experimental dataset to sample hypothetical synthetic candidate alloys from the learnt joint distribution not existing in both 9–12% Cr ferritic–martensitic alloys and austenitic stainless steel datasets.

The class of 9–12% Cr ferritic-martensitic alloys (FMA) and austenitic stainless steels have received considerable attention due to their numerous applications in high temperature power generation industries. To design high strength steels with prolonged service life requires a thorough understanding of the long-term properties, e.g., creep rupture strength, rupture life, etc., as a function of the chemical composition and processing parameters that govern the microstructural characteristics. In this article, the creep rupture strength of both 9–12% Cr FMA and austenitic stainless steel has been parameterized using curated experimental datasets with a gradient boosting machine. The trained model has been cross validated against unseen test data and achieved high predictive performance in terms of correlation coefficient ( $$R^{2} > 0.98 $$R 2 > 0.98 for 9–12% Cr FMA and $$R^{2} > 0.95 $$R 2 > 0.95 for austenitic stainless steel) thus bypassing the need for additional comprehensive tensile test campaigns or physical theoretical calculations. Furthermore, the feature importance has been computed using the Shapley value analysis to understand the complex interplay of different features.