Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.16005 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915937428439040 |
|---|---|
| author | Yang, Penghui Zhao, Chendong Tang, Bijun Zhang, Zhonghan Wang, Xinrun Deng, Yanchen Dong, Xuyu Lu, Yuhao Huang, Jianguo Li, Yixuan Xiao, Yushan Guan, Cuntai Liu, Zheng An, Bo |
| author_facet | Yang, Penghui Zhao, Chendong Tang, Bijun Zhang, Zhonghan Wang, Xinrun Deng, Yanchen Dong, Xuyu Lu, Yuhao Huang, Jianguo Li, Yixuan Xiao, Yushan Guan, Cuntai Liu, Zheng An, Bo |
| contents | Alloy discovery is constrained by vast compositional spaces, competing objectives, and prohibitive experimental costs. Although simulations and machine learning have each accelerated parts of this process, unifying scientific knowledge, scalable search, and experimental confirmation into a data-efficient workflow remains challenging. Here, we present AutoMAT, a hierarchical autonomous framework spanning ideation to experimental validation. Integrating large language models, automated CALPHAD simulations, residual-learning-based correction, and AI-guided optimization, AutoMAT translates design targets into candidate alloys, refines compositions through closed-loop computational search, and validates results experimentally without hand-curated datasets. Targeting lightweight, high-strength alloys, AutoMAT identifies a titanium alloy 8.1% less dense and 13.0% stronger than the aerospace benchmark Ti-185, achieving the highest specific strength among benchmarked systems. In a second case, AutoMAT discovers a high-entropy alloy with 28.2% higher yield strength than the baseline while preserving high ductility. AutoMAT compresses alloy discovery from years to weeks, establishing a generalizable route toward autonomous materials design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_16005 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Autonomous Multi-objective Alloy Design through Simulation-guided Optimization Yang, Penghui Zhao, Chendong Tang, Bijun Zhang, Zhonghan Wang, Xinrun Deng, Yanchen Dong, Xuyu Lu, Yuhao Huang, Jianguo Li, Yixuan Xiao, Yushan Guan, Cuntai Liu, Zheng An, Bo Materials Science Artificial Intelligence Machine Learning Alloy discovery is constrained by vast compositional spaces, competing objectives, and prohibitive experimental costs. Although simulations and machine learning have each accelerated parts of this process, unifying scientific knowledge, scalable search, and experimental confirmation into a data-efficient workflow remains challenging. Here, we present AutoMAT, a hierarchical autonomous framework spanning ideation to experimental validation. Integrating large language models, automated CALPHAD simulations, residual-learning-based correction, and AI-guided optimization, AutoMAT translates design targets into candidate alloys, refines compositions through closed-loop computational search, and validates results experimentally without hand-curated datasets. Targeting lightweight, high-strength alloys, AutoMAT identifies a titanium alloy 8.1% less dense and 13.0% stronger than the aerospace benchmark Ti-185, achieving the highest specific strength among benchmarked systems. In a second case, AutoMAT discovers a high-entropy alloy with 28.2% higher yield strength than the baseline while preserving high ductility. AutoMAT compresses alloy discovery from years to weeks, establishing a generalizable route toward autonomous materials design. |
| title | Autonomous Multi-objective Alloy Design through Simulation-guided Optimization |
| topic | Materials Science Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2507.16005 |