基于大模型+工业智能体的高炉炼铁智能化新范式
段一凡 , 刘小杰 , 李红玮 , 李宏扬 , 刘然
信阳师范大学学报(自然科学版) ›› 2026, Vol. 39 ›› Issue (3) : 422 -429.
基于大模型+工业智能体的高炉炼铁智能化新范式
A new intelligent paradigm for blast furnace ironmaking based on large language model + industrial agents
立足大语言模型(Large Language Model, LLM)的高阶认知推理与工业智能体自主执行的协同优势,首先构建了高炉炼铁垂直LLM(Vertical LLM, V-LLM)与工业智能体的协同架构,并进一步设计“毫秒级-小时级-日度级-月度级”的嵌套式信息反馈与迭代更新机制,为基于LLM+工业智能体的高炉炼铁智能化新范式提供理论参考。随后,基于高炉炼铁实际场景,提出“1中枢+5层级”通用实施路径以及涵盖V-LLM、工业智能体及二者协同效能的三维评价体系。最后,通过构建高炉炉温智能监测、预警、决策智能体开展实例验证,并剖析了现存关键挑战及针对性应对措施。研究结果有助于推动高炉炼铁智能化向“认知-决策-执行-反馈-迭代”的全链路闭环协同体系演进,同时为未来LLM+工业智能体的规模化推广提供技术参考。
With the collaborative advantages of high-order cognitive reasoning of large language model (LLM) and autonomous execution of industrial agents taken into consideration, a collaborative framework between vertical LLM (V-LLM) for blast furnace ironmaking and industrial agents was established, and a nested information feedback and iterative updating mechanism covering millisecond, hourly, daily and monthly scales was designed to provide theoretical basis for the new intelligent paradigm of blast furnace ironmaking based on LLM and industrial agents. A universal implementation path of "one center and five levels" and a three-dimensional evaluation system involving V-LLM, industrial agent and their collaborative efficiency were put forward according to actual production scenarios of blast furnace ironmaking. Case verification was performed by developing the intelligent agents for blast furnace temperature monitoring, early warning and decision making, and existing major challenges and corresponding coping strategies were analyzed. The research results facilitated the development of intelligent blast furnace ironmaking into a full-chain closed-loop collaborative system featuring cognition, decision-making, execution, feedback and iteration, and technical references were provided for the large-scale application of LLM and industrial agents.
| [1] |
张福成. 钢铁行业发展新质生产力路径的思考[J]. 钢铁,2024,59(11):1-11. |
| [2] |
蔡九菊,孙文强,岳强, |
| [3] |
何家雷,唐珏,储满生, |
| [4] |
刘小杰,李天顺,李欣, |
| [5] |
段一凡,刘小杰,李欣, |
| [6] |
段一凡,刘然,刘小杰, |
| [7] |
张玉洁,刘然,刘小杰, |
| [8] |
段一凡,刘然,刘小杰, |
| [9] |
王丽娜,高明洋,李卓卿. 基于生成式时序大模型的高炉透气性指数预测方法[J]. 冶金自动化,2025,49(4):81-91. |
| [10] |
刘然,段一凡,刘小杰, |
| [11] |
刘小杰,温梁亦欣,张玉洁, |
| [12] |
古志远,吕东澔,李向丽, |
| [13] |
姜峒伯,朱德鑫,吴宏辉, |
| [14] |
袁雷,张子谦,李立和, |
| [15] |
|
| [16] |
余志刚,卢春苗,梁青艳, |
| [17] |
曲泰安,刘常鹏,刘洋, |
| [18] |
刘劲松,窦克勤,刘欣, |
国家重点研发计划项目(2024YFB3713901)
河北省自然科学基金资助项目(E2024209101)
河北省创新能力提升计划项目(23560301D)
华北理工大学研究生创新项目(CXZZBS2025150)
/
| 〈 |
|
〉 |