| Chat-microreactor: A large-language-model-based assistant for designing continuous flow systems | |
Pan, Yongqi1; Xiao, Qinfan2; Zhao, Fangyu1; Li ZH(李振豪)3 ; Liu, Jianyang4; Ullah, Shafqat1; Lim, Kang Hui5; Huang, Tianyi1; Yu, Zhiyuan1; Li, Claudia5; Zhang, Dingyan6; Xue, Qiangqiang1,5; Chen, Qiang7; Kawi, Sibudjing5; Wang, Yujun1; Luo, Guangsheng1
| |
| 发表期刊 | CHEMICAL ENGINEERING SCIENCE
 |
| 2025-06-01 | |
| 卷号 | 311 |
| DOI | 10.1016/j.ces.2025.121567 |
| 产权排序 | 第3完成单位 |
| 收录类别 | SCI |
| 关键词 | Flow chemistry Microreactor Large language models Machine learning Multi-phase dispersion |
| 摘要 | Flow reactors and microreactors are increasingly important for automated chemical synthesis, offering improved safety, cost-effectiveness, stability, etc. However, the complexity of chemical reactions presents significant challenges for microreactor design. To overcome these obstacles, this study introduces a tool that uses large language models (LLMs) to extract essential flow information from scientific literature. A self-optimizing workflow based on neural network reduces the extraction time from 24 to 16 s after analyzing only 10 research papers. The collected data is then processed by ensemble learning models, which achieve F1 scores exceeding 70% in classifying flow patterns. These advancements enable the efficient design of microreactor systems in piperacillin synthesis with low error rates. This research provides synthetic chemists with an easy-touse LLM tool for flow reaction system design. Furthermore, it introduces a paradigm for applying machine learning methods and LLMs even in fields with relatively limited literature. |
| 资助项目 | National Natural Science Foundation of China[22378227]; Shijiazhuang Science and Technology Bureau[231790163A]; Center of High performance computing, Tsinghua University |
| 项目资助者 | National Natural Science Foundation of China[22378227] ; Shijiazhuang Science and Technology Bureau[231790163A] ; Center of High performance computing, Tsinghua University |
| 语种 | 英语 |
| 学科领域 | 化学工程 ; 计算机科学技术 |
| 文章类型 | Article |
| 出版者 | PERGAMON-ELSEVIER SCIENCE LTD |
| 出版地 | THE BOULEVARD, LANGFORD LANE, KIDLINGTON, OXFORD OX5 1GB, ENGLAND |
| ISSN | 0009-2509 |
| URL | 查看原文 |
| WOS记录号 | WOS:001463054100001 |
| WOS研究方向 | Engineering |
| WOS类目 | Engineering, Chemical |
| 引用统计 | |
| 文献类型 | 期刊论文 |
| 版本 | 出版稿 |
| 条目标识符 | http://ir.ynao.ac.cn/handle/114a53/28253 |
| 专题 | 其他 |
| 作者单位 | 1.Tsinghua Univ, Dept Chem Engn, State Key Lab Chem Engn, Beijing 100084, Peoples R China; 2.Tsinghua Univ, Dept Elect Engn, Beijing 100084, Peoples R China; 3.Chinese Acad Sci, Yunnan Observ, Kunming 650216, Peoples R China; 4.Tsinghua Univ, Dept Comp Sci & Technol, Beijing 100084, Peoples R China; 5.Natl Univ Singapore, Dept Chem & Biomol Engn, Singapore 119260, Singapore; 6.Peking Univ, Coll Environm Sci & Engn, Beijing 100084, Peoples R China; 7.Southwest Univ, Coll Chem & Chem Engn, Chongqing 400715, Peoples R China |
| 推荐引用方式 GB/T 7714 | Pan, Yongqi,Xiao, Qinfan,Zhao, Fangyu,et al. Chat-microreactor: A large-language-model-based assistant for designing continuous flow systems[J]. CHEMICAL ENGINEERING SCIENCE,2025,311. |
| APA | Pan, Yongqi.,Xiao, Qinfan.,Zhao, Fangyu.,李振豪.,Liu, Jianyang.,...&Luo, Guangsheng.(2025).Chat-microreactor: A large-language-model-based assistant for designing continuous flow systems.CHEMICAL ENGINEERING SCIENCE,311. |
| MLA | Pan, Yongqi,et al."Chat-microreactor: A large-language-model-based assistant for designing continuous flow systems".CHEMICAL ENGINEERING SCIENCE 311(2025). |
| 条目包含的文件 | ||||||
| 文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
| Chat-microreactor_ A（8171KB） | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | 浏览 请求全文 | |
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。
修改评论