Composition Design and Property Prediction for AlCoCrCuFeNi High-Entropy Alloy Based on Machine Learning

Based on the innovative mode driven by “data + artificial intelligence”, in this study, three methods, namely Gaussian noise (GAUSS Noise), the Generative Adversarial Network (GAN), and the optimized Generative Adversarial Network (GANPro), are adopted to expand and enhance the collected dataset of element contents and the hardness of the AlCoCrCuFeNi high-entropy alloy. Bayesian optimization with grid search is used to determine the optimal combination of hyperparameters, and two interpretability methods, SHAP and permutation importance, are employed to further explore the relationship between the element features of high-entropy alloys and hardness. The results show that the optimal data augmentation method is Gaussian noise enhancement; its accuracy reaches 97.4% under the addition of medium noise (σ = 0.003), and an optimal performance prediction model based on the existing dataset is finally constructed. Through the interpretability method, it is found that the contributions of Al and Ni are the most prominent. When the Al content exceeds 0.18 mol, it has a positive promoting effect on hardness, while Ni and Cu exhibit a critical effect of promotion–inhibition near 0.175 mol and 0.14 mol, respectively, revealing the nonlinear regulation law of element contents. This study solves the problem of revealing the mutual relationship between the element contents and hardness of high-entropy alloys in the case of a lack of alloy data and provides theoretical guidance for further improving the performance of high-entropy alloys.