High-entropy alloys (HEAs) have attracted significant attention due to their excellent mechanical properties and broad application prospects. However, accurately predicting their mechanical behavior remains challenging because of the vast compositional design space and complex multi-element interactions. In this study, we propose a stacking learning-based machine learning framework to improve the accuracy and robustness of HEA mechanical property predictions. Key physicochemical features were extracted, and a hierarchical clustering model-driven hybrid feature selection strategy (HC-MDHFS) was employed to identify the most relevant descriptors. Three machine learning algorithms-Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Gradient Boosting (Gradient Boosting)-were integrated into a multi-level stacking ensemble, with Support Vector Regression serving as the meta-learner. To improve model interpretability, the SHapley Additive Explanations (SHAP) method was applied to assess feature importance. The results demonstrate that the proposed stacking framework outperforms individual models in predicting yield strength and elongation, showing improved generalization ability and predictive accuracy.

In this work, selective laser melting (SLM) technology was applied to directly realize the in situ synthesis of medium manganese Mn– x Cu ( x = 30–40 wt.%) alloys based on the blended elemental powders. The effects of heat treatment on the microstructural evolution and damping properties of the SLMed Mn– x Cu alloys were investigated. The metastable miscibility gap was studied by thermodynamic modeling and microhardness measurement. The results showed that γ-(Mn, Cu) phase with dendritic arm spacing (DAS) of 0.9–1.2 μm was the main constituent phase in the as-SLMed alloys, which was one to two orders of magnitude finer than those of the as-cast samples. Aging at 400–480°C for the Mn–30%Cu or 430°C for Mn–40%Cu alloys can induce spinodal decomposition, martensitic transformation, and α-phase precipitation, whose direct evidence was provided for the first time by transmission electron microscopy and 3D atom probe tomography in the work. The miscibility gap obtained from thermodynamics calculation was basically consistent with the microhardness results for the SLMed Mn– x Cu alloys. Solution and aging (SA) treatment can improve the microstructure, tensile and damping properties of the SLMed Mn– x Cu alloys more obviously than aging treatment. A 2.3–2.8 and 4.3–4.5 times increase was produced in damping capacity in the aged SLMed and SLMed+SAed Mn– x Cu samples, respectively.