Multiprincipal‐element alloys (MPEAs), including high‐entropy alloys, are a new class of materials whose thermodynamical properties are mainly driven by configuration entropy, rather than enthalpy in the traditional alloys, especially at high temperatures. Herein, the design of a novel soft‐magnetic nonequiatomic, quaternary MPEA is described, via tuning its chemical composition to deliberately manipulate its microstructure, such that it contains ultrafine ferromagnetic body‐centered‐cubic (BCC) coherent nanoprecipitates (3–7 nm) uniformly distributed in a B2‐phase matrix. The new alloy Al1.5Co4Fe2Cr exhibits high saturation magnetization (MS = 135.3 emu g‐1), low coercivity (HC = 127.3 A m‐1), high Curie temperature (TC = 1061 K), and high electrical resistivity (ρ  = 244 μΩ cm), promising for soft magnets. More importantly, these prominent soft‐magnetic properties are observed to be retained even after the alloy is thermally exposed at 873 K for 555 h, apparently attributable to the excellent stability of the coherent microstructure. The versatility of the magnetic properties of this new alloy is discussed in light of the microstructural change induced by tuning the chemical composition, and the enhanced performance of the alloy is compared directly with that of the traditional soft‐magnetic alloys. The perspective is also addressed to design high‐performance soft‐magnetic alloys for high‐temperature applications.

The present work formulated a materials design approach, a cluster-formula-embedded machine learning (ML) model, to search for body-centered-cubic (BCC) β-Ti alloys with low Young's modulus (E) in the Ti-Mo-Nb-Zr-Sn-Ta system. The characteristic parameters, including the Mo equivalence and the cluster-formula approach, are implemented into the ML to ensure the accuracy of prediction, in which the former parameter represents the BCC-β structural stability, and the latter reflects the interactions among elements expressed with a composition formula. Both auxiliary gradient-boosting regression tree and genetic algorithm methods were adopted to deal with the optimization problem in the ML model. This cluster-formula-embedded ML can not only predict alloy property in the forward design, but also design and optimize alloy compositions with desired properties in multicomponent systems efficiently and accurately. By setting different objective functions, several new β-Ti alloys with either the lowest E (E = 48 GPa) or a specific E (E = 55 and 60 GPa) were predicted by ML and then validated by a series of experiments, including the microstructural characterization and mechanical measurements. It could be found that the experimentally obtained E of predicted alloys by ML could reach the desired objective E, which indicates that the cluster-formula-embedded ML model can make the prediction and optimization of composition and property more accurate, effective, and controllable.

No abstract

No abstract

No abstract