Sign in Subscribe
Machine learning

Machine Learning Predicts High-Hardness Alloys for Novel Applications

Strategic Insights

— 1 min read

Researchers at Anhui University of Technology have leveraged machine learning models to predict the composition and hardness of a novel seven-component high-entropy alloy, discovering that it exhibits high hardness without a brittle sigma phase. This breakthrough promises to unlock new applications for this innovative material. The study's findings demonstrate the potential of machine learning in materials science, paving the way for further research and development.

Key Takeaways:

  • The research utilized five machine learning algorithms to predict the composition and hardness of the seven-component Al-Co-Cr-Fe-Ni-Mo-Ti high-entropy alloy.
  • The XGBoost algorithm produced the best prediction results, with a coefficient of determination (R2) of 0.95 and a root mean square error (RMSE) of only 43.37.
  • The study found that there is no relationship between the predicted hardness and the Al content in the novel HEAs when the predicted hardness is higher than 800 HV.
  • Two alloys with greater predicted hardness were chosen for fabrication and hardness measurements, with results showing good agreement between predicted and experimental values.
  • The research concluded that high-hardness seven-component Al-Co-Cr-Fe-Ni-Mo-Ti HEAs without a brittle sigma phase are worth further study for applications.
  • Financial supporters for this research include National Natural Science Foundation of China (NSFC), Overseas Visit and Training Project of Young Backbone Teachers in Anhui Province, Natural Science Foundation of Anhui Provincial Education Department, Army Research Office Project, National Science Foundation (NSF), Air Force Office of Scientific Research (AFOSR), and United States Department of Energy (DOE).

Statistics:

  • The predicted values for hardness were 858 HV and 816 HV, which are in good agreement with the experimental test values of 851 HV and 786 HV.
  • The root mean square error (RMSE) for the XGBoost algorithm was only 43.37.
  • The coefficient of determination (R2) for the XGBoost algorithm was 0.95.

Sources:

  • VerticalNews, "Investigators Discuss New Findings in Machine Learning", 2025 OCT 13
  • Machine Learning of Hardness and Composition In Al-co-cr-fe-ni-mo-ti High-entropy Alloys, Materials Chemistry and Physics, 2025;343.
  • Elsevier Science Sa, "Materials Chemistry and Physics", www.journals.elsevier.com/materials-chemistry-and-physics/
  • NewsRx, "Findings from Anhui University of Technology Yields New Findings on Machine Learning (Machine Learning of Hardness and Composition In Al-co-cr-fe-ni-mo-ti High-entropy Alloys)", Journal of Engineering, October 13, 2025; p 621.

Read more