With the development of society, there is an increasingly urgent demand for light-weight, high-strength, and high-temperature-resistant structural materials. High-entropy alloys (HEAs) owe much of their unusual properties to the selection among three phases: solid solution (SS), intermetallic compound (IM), and mixed SS and IM (SS and IM). Therefore, accurate phase prediction is crucial for guiding the selection of element combinations to form HEAs with desired properties. Light high-entropy alloys (LHEAs), as a significant branch of HEAs, exhibit excellent performance in terms of specific strength. In this study, we employ a machine learning (ML) method to realize the design of light-weight high-entropy alloys based on solid solutions. We determined the Gradient Boosting Classifier model as the best machine learning model through a two-step feature and model selection, in which its accuracy and F1_Score achieve 0.9166 and 0.8923. According to the predicted results, we obtained Al₂₈Li₃₅Mg₁₅Zn₁₀Cu₁₂ LHEAs, which are mainly composed of 90% solid solution. This alloy accords with the prediction results of machine learning. But it is made up of a two-phase solid solution. In order to obtain a light-weight high-entropy alloy dominated by a single solid solution, we designed Al₂₄Li₁₅Mg₂₆Zn₉Cu₂₆ LHEAs on the basis of machine learning prediction results accompanied by expert experience. Its main structure includes a single-phase solid solution. Our work provides an alternative approach to the computational design of HEAs and provides a direction for future exploration of light-weight high-entropy alloys.

In this paper, the effects of material removal strategies and initial stress states on the machining deformation of aluminum alloy plates were investigated through a combination of finite element simulation and experiments. We developed different machining strategies described by Tm+Bn, which removal m mm materials form top and n mm materials from the bottom of the plate. The results demonstrate that the maximum deformation of structural components with the T10+B0 machining strategy could reach 1.94 mm, whereas with the T3+B7 machining strategy was only 0.065 mm, decreasing by more than 95%. The asymmetric initial stress state had a significant impact on the machining deformation of the thick plate. The machined deformation of thick plates increased with the increase in the initial stress state. The concavity of the thick plates changed with the T3+B7 machining strategy due to the asymmetry of the stress level. The deformation of frame parts was smaller when the frame opening was facing the high-stress level surface during machining than when it was facing the low-stress level. Moreover, the modeling results for the stress state and machining deformation were accurate and in good accordance with the experimental findings.

To investigate the comprehensive effects of the Al and Zr element contents on the microstructure evolution of the AlNbTiVZr series light-weight refractory high entropy alloys (HEAs), five samples were studied. Samples with different compositions were designated Al_1.5NbTiVZr, Al_1.5NbTiVZr_0.5, AlNbTiVZr, AlNbTiVZr_0.5, and Al_0.5NbTiVZr_0.5. The results demonstrated that the actual density of the studied HEA samples ranged from 5.291 to 5.826 g·cm⁻³. The microstructure of these HEAs contains a solid solution phase with a BCC structure and a Laves phase. The Laves phase was further identified as the ZrAlV intermetallic compound by TEM observations. The microstructure of the AlNbTiVZr series HEAs was affected by both the Al and Zr element contents, whereas the Zr element showed a more dominant effect due to Zr atoms occupying the core position of the ZrAlV Laves phase (C14 structure). Therefore, the as-cast Al_0.5NbTiVZr_0.5 sample exhibits the best room temperature compression property with a compression strength (σ_p) of 1783 MPa and an engineering strain of 28.8% due to having the lowest ZrAlV intermetallic compound area fraction (0.7%), as characterized by the EBSD technique.