发表机构
Institute of Material and Process Design, Helmholtz-Zentrum Hereon; Institute of Production Technology and Systems, Leuphana University Lüneburg; Institute of Material Systems Modeling, Helmholtz-Zentrum Hereon; AI for Physical Systems, German Research Center for Artificial Intelligence (DFKI); Saarland University（亥姆霍兹-盖斯特哈赫特研究中心材料与工艺设计研究所; 吕讷堡大学生产技术及系统研究所; 亥姆霍兹-盖斯特哈赫特研究中心材料系统建模研究所; 德国人工智能研究中心物理系统人工智能研究所; 萨尔大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究探索从优化微观结构反向推断合金配方，比较传统统计、视觉嵌入和图神经网络，发现传统描述符在合金识别上最优，且微观结构可辅助工艺参数预测。
AI 中文摘要
金属合金的力学性能由其微观结构和织构决定：晶粒的尺寸、形状以及晶体的取向。这种结构又由配方决定，即合金成分连同加工参数。合金开发正向运行这一链条，调整结构直至达到目标性能。反向运行，即从优化结构到能产生该结构的配方，仍然依赖专家知识。我们探究这一反向步骤是否可以被学习。在一个包含14种合金的107个镁合金挤压条件的内部数据集上，每个条件都有光学显微图像和X射线织构测量，我们比较了三种微观结构和织构的描述符：传统的晶粒和织构统计量、来自预训练图像编码器的视觉嵌入、以及基于晶粒网络的图神经网络。每种描述符都配有两个任务的预测头：给定工艺预测合金成分（任务A），以及给定成分预测工艺参数（任务B）。在5折交叉验证下，传统描述符对65%的留出条件识别出正确的合金，而总是猜测最常见合金的基线为17%，而学习到的嵌入则低于30%。工艺参数可恢复但噪声较大：与仅使用成分相比，微观结构大致将温度误差减半。由于只铸造了几种合金且只使用了少数压力设置，两个答案都是离散的，从这些已知选项中选择并尊重其顺序的预测头比预测自由值的预测头效果更好。
英文摘要
The mechanical properties of a metallic alloy are set by its microstructure and texture: the size and shape of its grains and the orientation of their crystals. That structure is in turn set by a recipe, the alloy composition together with the processing parameters. Alloy development runs this chain forwards, tuning the structure until a target property is met. Running it backwards, from an optimized structure to the recipe that would produce it, still relies on expert knowledge. We ask whether this backwards step can be learned. On an in-house dataset of 107 magnesium alloy extrusion conditions across 14 alloys, each with optical micrographs and an X-ray texture measurement, we compare three descriptors of microstructure and texture: conventional grain and texture statistics, a vision embedding from a pretrained image encoder, and a graph neural network on the grain network. Each is paired with prediction heads for two tasks: the alloy composition given the process (Task A), and the process parameters given the composition (Task B). Under 5-fold cross-validation, the conventional descriptors identify the correct alloy for 65% of held-out conditions, against 17% for always guessing the most common alloy, while the learned embeddings stay below 30%. The process parameters are recoverable but noisier: compared with using the composition alone, the microstructure roughly halves the temperature error. Because only a few alloys were cast and only a few press settings were used, both answers are discrete, and heads that pick from these known options, while respecting their order, worked better than heads that predict a free value.
