当前位置: X-MOL 学术Acta Mater. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Steel design based on a large language model
Acta Materialia ( IF 8.3 ) Pub Date : 2024-12-17 , DOI: 10.1016/j.actamat.2024.120663
Shaohan Tian, Xue Jiang, Weiren Wang, Zhihua Jing, Chi Zhang, Cheng Zhang, Turab Lookman, Yanjing Su

The success of artificial intelligence (AI) in materials research heavily relies on the integrity of structured data and the construction of precise descriptors. In this study, we present an end-to-end pipeline from materials text to properties for steels based on a large language model. The objective is to enable quantitative predictions of properties with high-accuracy and explore new steels. The pipeline includes a materials language encoder, named SteelBERT, and a multimodal deep learning framework that maps the composition and text sequence of complex fabrication processes to mechanical properties. We demonstrate high accuracy on mechanical properties, including yield strength (YS), ultimate tensile strength (UTS), and elongation (EL) by predicting determination coefficients (R2) reaching 78.17 % ( ± 3.40 %), 82.56 % ( ± 1.96 %), and 81.44 % ( ± 2.98 %) respectively. Further, through an additional fine-tuning strategy for the design of specific steels with small datasets, we show how the performance can be refined. With only 64 experimental samples of 15Cr austenitic stainless steels, we obtain an optimized model with R2 of 89.85 % ( ± 6.17 %), 88.34 % ( ± 5.95 %) and 87.24 % ( ± 5.15 %) for YS, UTS and EL, that requires the user to input composition and text sequence for processing and which outputs mechanical properties. The model efficiently optimizes the text sequence for the fabrication process by suggesting a secondary round of cold rolling and tempering to yield an exceptional YS of 960 MPa, UTS of 1138 MPa, and EL of 32.5 %, exceeding those of reported 15Cr austenitic stainless steels.

中文翻译:


基于大型语言模型的钢结构设计



人工智能 (AI) 在材料研究中的成功在很大程度上取决于结构化数据的完整性和精确描述符的构建。在本研究中,我们提出了一个基于大型语言模型的钢材从材料文本到属性的端到端管道。目标是实现高精度的特性定量预测并探索新钢材。该管道包括一个名为 SteelBERT 的材料语言编码器和一个多模态深度学习框架,该框架将复杂制造过程的组成和文本序列映射到机械性能。我们通过预测决定系数 (R 2 ) 分别达到 78.17% (±3.40%)、82.56% (±1.96%) 和 81.44% (±2.98%) 来证明机械性能的准确性,包括屈服强度 (YS)、极限拉伸强度 (UTS) 和伸长率 (EL)。此外,通过对具有小数据集的特定钢材进行设计的额外微调策略,我们展示了如何优化性能。仅用 64 个 15Cr 奥氏体不锈钢实验样品,我们得到了一个 YS、UTS 和 EL 的 R 2 为 89.85% (±6.17%)、88.34% (±5.95%) 和 87.24% (±5.15%) 的优化模型,需要用户输入成分和文本序列进行处理,并输出机械性能。该模型通过建议进行第二轮冷轧和回火,有效地优化了制造过程的文本序列,以产生 960 MPa 的 YS、1138 MPa 的 UTS 和 32.5% 的 EL,超过了已报道的 15Cr 奥氏体不锈钢。
更新日期:2024-12-20
down
wechat
bug