High-entropy alloys (HEAs) are a new class of materials that consist of five or more metallic elements in significant proportions. Unlike conventional alloys, which are usually based on one or two dominant elements, HEAs have a high mixing entropy that can stabilize single-phase or multi-phase solid solutions with diverse and fascinating properties. HEAs have attracted a lot of attention from researchers and engineers in various fields, such as transportation, energy, aerospace, biomedical electronics, and tools.

Some of the novel properties of HEA alloys include high mechanical performance at high temperature, excellent specific strength, exceptional ductility and fracture toughness at cryogenic temperatures, superparamagnetic and superconductivity1. These properties depend on the composition, structure, phase, and microstructure of the HEA, which can be tailored by different alloy design strategies and processing methods. For example, doping with interstitial elements such as boron or carbon can enhance the strength and hardness of HEAs2. Thermomechanical treatment can refine the grain size and improve the ductility of HEAs2. Energy treatments such as thermal spraying can modify the surface layers and further improve the wear and corrosion resistance of HEAs.

However, designing and optimizing HEAs is not an easy task, due to the astronomical composition space and the complex structure-property relationships. Experimental approaches are expensive and time-consuming, while computational approaches are still limited by the accuracy and efficiency of the models. Therefore, machine learning methods have been proposed to accelerate the exploration and discovery of HEAs with desired properties. Machine learning methods can learn from existing data and make predictions for new compositions or conditions. For example, a deep sets model was developed to predict the elastic properties of HEAs based on their compositions4. Association rule mining was applied to analyze the compositional dependence of HEA elastic properties and to suggest potential alloy design rules.

In conclusion, HEAs are a promising material class with unique and unusual properties that can be exploited in various applications. However, there are still many challenges and opportunities in the development and understanding of HEAs. Machine learning methods can provide useful tools for data-driven alloy design and discovery.

Heeger Materials is a professional supplier for HEA alloy ingots, tensile samples as well as other customized HEA alloy products. We offer our customers products with the highest quality and best price. Do not hesitate to contact sales@heegermaterials to get a quote if you are interested.