Accelerated discovery of single-phase refractory high entropy alloys assisted by machine learning

[Display omitted] •The design of novel single-phase refractory high entropy alloys via machine learning.•Extended dataset and optimal input features for machine learning algorithms.•Machine learning model validation by mechanical alloying experiment. Herein, we proposed a strategy to design single-phase refractory high entropy alloys (RHEAs) with the assistance of machine learning algorithms. Based on an extensive dataset (1807 entries) built in this work, we applied multiple machine learning algorithms to train the dataset. After the blind test, we found that the Gradient boosting (GB) model can distinguish the single-phase-solid solution and non-single-phase-solid solution alloys with a test accuracy of 96.41%. Given the GB model, we predicted over 100 equiatomic oxidation-resistance RHEAs from the composition space of eight metallic elements. After that, we synthesized ten of these predicted single-phase RHEAs by mechanical alloying. The XRD patterns show that all of them are single-phase BCC solid solution. The experimental results agree well with the prediction results, indicating the excellent performance of the machine learning model in single-phase RHEAs prediction. With the aid of the machine learning method, single-phase oxidation-resistant RHEAs were successfully designed. Our work presents a novel strategy with outstanding performance and evident effectiveness on the accelerated discovery of novel metallic materials used for extreme environments.