Optimization of high-entropy alloy coating design using machine learning methods

This study focuses on optimizing the design of high-entropy alloy coatings to enhance corrosion resistance in lead-bismuth eutectic environments. Using machine learning methods, including artificial neural networks (ANN), random forest (RF), eXtreme gradient boosting (XGBoost), and support vector machine (SVM), the research predicts the corrosion and mechanical properties of AlCrFeMoTi high-entropy alloy coatings. ANN showed the best comprehensive predictive ability. The study validates the use of machine learning (ML) for optimizing high-entropy alloy (HEA) coating design, offering a novel approach to improving material performance in high-temperature liquid metal environments. This work provides a theoretical foundation for developing corrosion-resistant coatings for advanced nuclear reactors.