arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.02513cs.LGcond-mat.mtrl-sci
收藏

学习有序的多模态表示以进行复合材料设计

Learning ORDER-Aware Multimodal Representations for Composite Materials Design

University of Electronic Science and Technology of China(电子科技大学);Tongji University(同济大学);A*STAR CFAR(新加坡A*STAR CFAR)

Xinyao Li, Hangwei Qian, Jingjing Li, Lei Zhu, Ivor Tsang

AI总结:

本研究提出了一种基于有序性的多模态预训练框架ORDER,用于复合材料设计,通过整合异构数据源来捕捉纤维分布,从而在连续设计空间中实现有效的属性预测和微结构生成。

摘要:

人工智能在材料发现和性质预测中展现出显著的成功,尤其是在晶体和聚合物系统中,其中材料性质和结构主要由离散图表示主导。这种图中心范式在复合材料中失效,因为复合材料具有连续和非线性的设计空间。通用复合描述符,例如纤维体积和偏移角度,无法完全捕捉决定微结构特性的纤维分布,需要通过多模态学习整合异构数据源。现有的对齐导向框架在离散、唯一的图-性质映射假设下对大量晶体或聚合物数据有效,但在极端数据稀缺的情况下无法解决高度连续的复合设计空间。在本工作中,我们引入了ORDinal-aware imagE-tabulaR alignment(ORDER),一种多模态预训练框架,将有序性作为材料表示的核心原则。ORDER确保具有相似目标属性的材料在潜在空间中占据附近区域,这有效地保持了复合材料属性的连续性,并在稀疏观察设计之间实现了有意义的插值。我们评估了ORDER在纳米纤维增强复合材料数据集和碳纤维T700数据集上的表现。ORDER及其变体在属性预测、跨模态检索和微结构生成任务中均优于对齐导向和定制属性意识对比基线。我们进一步引入基于物理的有序替代信号,避免了预训练过程中需要完整的属性注释。我们的工作证明了学习连续多模态特征对于复合材料是基础性的,并提供了一条通往数据高效通用多模态智能系统可靠路径。

英文摘要:

Artificial intelligence has shown remarkable success in materials discovery and property prediction, particularly for crystalline and polymer systems where material properties and structures are dominated by discrete graph representations. Such graph-central paradigm breaks down on composite materials, which possess continuous and nonlinear design spaces. General composite descriptors, e.g., fiber volume and misalignment angle, cannot fully capture the fiber distributions that determine microstructural characteristics, necessitating the integration of heterogeneous data sources through multimodal learning. Existing alignment-oriented frameworks have proven effective on abundant crystal or polymer data under discrete, unique graph-property mapping assumptions, but fail to address the highly continuous composite design space under extreme data scarcity. In this work we introduce ORDinal-aware imagE-tabulaR alignment (ORDER), a multimodal pretraining framework that establishes ordinality as a core principle for material representations. ORDER ensures that materials with similar target properties occupy nearby regions in the latent space, which effectively preserves the continuous nature of composite properties and enables meaningful interpolation between sparsely observed designs. We evaluate ORDER on a Nanofiber-reinforced composite dataset and a carbon fiber T700 dataset. ORDER and its variants outperform both alignment-oriented and customized property-aware contrastive baselines across property prediction, cross-modal retrieval, and microstructure generation tasks. We further introduce physics-based ordinal surrogate signals avoiding the need for full property annotation during pretrain. Our work demonstrates learning continuous multimodal features are fundamental for composite materials, and provides a reliable pathway toward data-efficient universal multimodal intelligent systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑