.png){kind=icon}
返回
Self-supervised AI for decoding and designing disordered metamaterials
.png){kind=icon}
PRE
AI
DOI：10.1126/sciadv.adx7389.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Disordered microstructures are key to the distinct multifunctional properties of many natural materials. However, understanding the relationship between their microstructures and physical functions remains formidable, hindering engineering applications. Here, we introduce a physics-guided, self-supervised artificial intelligence (AI) framework called generative networks for disordered metamaterials (GNDM), trained on a progressively expanding dataset starting from a few initial samples. We integrate a formula writing module in the training process of neural networks to enforce the identification of the most selective set of hidden geometric invariants that dictate bulk properties. By inversely solving the formulae, GNDM manipulate disordered geometric features to extrapolate property space and design previously unknown structures via its generator module, validated by experiments. GNDM offers an all-in-one AI framework that closes the loop of feature extraction, property prediction, formula writing, and inverse design, unraveling the regulative role of disorder, a critical challenge in the study of metamaterials with complex microstructures.
Keyword:
TOPOLOGY OPTIMIZATION
期刊
IF:
12.5
论文数:
2.1W
被引数:
18.1W
机构
引用论文
Growth rules for irregular architected materials with programmable properties具有可编程属性的不规则建筑材料的生长规则.png)
Science
ScienceIF0
PREAI
分享收藏Functionally graded porous scaffolds in multiple patterns: New design method, physical and mechanical properties多种模式的功能梯度多孔支架: 新的设计方法，物理和机械性能MATERIALS & DESIGN
OAAI
MATERIALS & DESIGNIF7.9
OAAI分享收藏Optimally-Tailored Spinodal Architected Materials for Multiscale Design and Manufacturing用于多尺度设计和制造的最佳定制的旋节线架构材料ADVANCED MATERIALSOAAI
ADVANCED MATERIALSIF26.8
OAAI分享收藏
查看更多内容