The phase design of high entropy alloys (HEAs) is an important issue since the phase structure affects the comprehensive properties of HEAs. Accurate prediction of phase classification can accelerate material design. In this paper, a new phase prediction framework is proposed using machine learning (ML) and an improved information fusion approach based on the Dempster-Shafer (DS) evidence theory. Considering that the classification results of different ML algorithms may conflict, and the traditional DS evidence theory cannot solve the problem of high conflict, we propose an improved information fusion approach based on the DS evidence theory. The basic probability assignment function is constructed using the ML algorithms. 761 HEAs samples are collected consisting of amorphous phase (AM), solid solution (SS), intermetallic compound (IM), and a mixture of SS and IM (SS + IM). For the small dataset of HEAs, we use a conditional generative adversarial network (CGAN) for data augmentation. Based on the enhanced dataset, the ML model is optimized by sparrow search algorithm (SSA), which can accelerate searching speed of model hyperparameters and improve the performance of the model. The results show that the proposed information fusion method performs better than several other existing techniques on the test set, and the prediction accuracy reaches 94.78 %. Meanwhile, the prediction accuracy of the proposed method is higher than that of the existing technology (93.17 %). It is proved that the proposed method can solve the high conflict problem effectively. Moreover, we present the interpretability analysis of the features by the Shapley additive explanations (SHAP) and the sensitivity matrix. A smaller atomic size difference δ (<6.6 %) is conducive to the formation of SS phase, while a larger δ (>6.6 %) is conducive to the formation of AM phase. A smaller enthalpy of mixing Δ tends to form AM phase. In binary and ternary alloy systems, IM phase can be extracted by the mixing enthalpy Δ < 10. In addition, we find that mean bulk modulus () and standard deviation of melting temperature (σ) are critical features to distinguish between SS and SS + IM.

中文翻译：

---

基于机器学习和改进的信息融合方法的高熵合金相预测

高熵合金（HEA）的相设计是一个重要问题，因为相结构影响HEA的综合性能。准确预测相分类可以加速材料设计。本文利用机器学习（ML）和基于 Dempster-Shafer（DS）证据理论的改进信息融合方法提出了一种新的相位预测框架。考虑到不同ML算法的分类结果可能会发生冲突，而传统的DS证据理论无法解决高度冲突的问题，我们提出了一种基于DS证据理论的改进信息融合方法。基本概率分配函数是使用 ML 算法构建的。收集了 761 个 HEA 样品，其中包括非晶相 (AM)、固溶体 (SS)、金属间化合物 (IM) 以及 SS 和 IM 的混合物 (SS + IM)。对于 HEA 的小数据集，我们使用条件生成对抗网络（CGAN）进行数据增强。基于增强数据集，通过麻雀搜索算法（SSA）对ML模型进行优化，可以加快模型超参数的搜索速度，提高模型的性能。结果表明，所提出的信息融合方法在测试集上的表现优于其他几种现有技术，预测精度达到94.78%。同时，该方法的预测精度高于现有技术（93.17%）。事实证明，该方法能够有效解决高冲突问题。此外，我们还通过沙普利附加解释（SHAP）和敏感性矩阵对特征进行了可解释性分析。较小的原子尺寸差δ（<6.6%）有利于SS相的形成，而较大的δ（>6.6%）有利于AM相的形成。混合焓Δ越小，越容易形成AM相。在二元和三元合金体系中，可以通过混合焓 Δ < 10 提取 IM 相。此外，我们发现平均体积模量 () 和熔化温度标准差 (σ) 是区分 SS 和 SS + 的关键特征我是。