Accelerated Design for High-Entropy Alloys Based on Machine Learning and Multiobjective Optimization.

High-entropy alloys (HEAs) with high hardness and high ductility can be considered as candidates for wear-resistant applications. However, designing novel HEAs with multiple desired properties using traditional alloy design methods remains challenging due to the enormous composition space. In this work, we proposed a machine-learning-based framework to design HEAs with high Vickers hardness (H) and high compressive fracture strain (D). Initially, we constructed data sets containing 172,467 data with 161 features for D and H, respectively. Four-step feature selection was performed, with the selection of 12 and 8 features for the D and H prediction models based on the optimal algorithms of the support vector machine (SVR) and light gradient boosting machine (LightGBM), respectively. The R2 of the well-trained models reached 0.76 and 0.90 for the 10-fold cross validation. Nondominated sorting genetic algorithm version II (NSGA-II) and virtual screening were employed to search for the optimal alloying compositions, and four recommended candidates were synthesized to validate our methods. Notably, the D of three candidates have shown significant improvements compared to the samples with similar H in the original data sets, with increases of 135.8, 282.4, and 194.1% respectively. Analyzing the candidates, we have recommended suitable atomic percentage ranges for elements such as Al (2-14.8 at %), Nb (4-25 at %), and Mo (3-9.9 at %) in order to design HEAs with high hardness and ductility.

Efficient Coarse-Grained Superplasticity of a Gigapascal Lightweight Refractory Medium Entropy Alloy.

Superplastic metals that exhibit exceptional ductility (>300%) are appealing for use in high-quality engineering components with complex shapes. However, the wide application of most superplastic alloys has been constrained due to their poor strength, the relatively long superplastic deformation period, and the complex and high-cost grain refinement processes. Here these issues are addressed by the coarse-grained superplasticity of high-strength lightweight medium entropy alloy (Ti43.3 V28 Zr14 Nb14 Mo0.7 , at.%) with a microstructure of ultrafine particles embedded in the body-centered-cubic matrix. The results demonstrate that the alloy reached a high coarse-grained superplasticity greater than ≈440% at a high strain rate of 10-2 s-1 at 1173 K and with a gigapascal residual strength. A consecutively triggered deformation mechanism that sequences of dislocation slip, dynamic recrystallization, and grain boundary sliding in such alloy differs from conventional grain-boundary sliding in fine-grained materials. The present results open a pathway for highly efficient superplastic forming, broaden superplastic materials to the high-strength field, and guide the development of new alloys.

Frictional Wear and Corrosion Behavior of AlCoCrFeNi High-Entropy Alloy Coatings Synthesized by Atmospheric Plasma Spraying.

High-entropy alloy coatings (HEAC) exhibit good frictional wear and corrosion resistances, which are of importance for structure materials. In this study, the microstructure, surface morphology, hardness, frictional wear and corrosion resistance of an AlCoCrFeNi high-entropy alloy coating synthesized by atmospheric plasma spraying (APS) were investigated. The frictional wear and corrosion resistance of the coating are simultaneously improved with an increase of the power of APS. The influence of the APS process on the microstructure and mechanical behavior is elucidated. The mechanisms of frictional wear and corrosion behavior of the AlCoCrFeNi HEAC are discussed in detail.