面向离散行业智能工厂的工业大模型技术路径与体系架构研究

doi:10.12267/j.issn.2096-5931.2026.08.013

信息通信技术与政策 ›› 2026, Vol. 52 ›› Issue (8): 91-96.doi: 10.12267/j.issn.2096-5931.2026.08.013

技术与标准上一篇

面向离散行业智能工厂的工业大模型技术路径与体系架构研究

Research on technology path and architecture of industrial large-scale model for intelligent factory in discrete industry

郭晓彤, 谢润彬, 吴迪, 夏鹏

中国信息通信研究院信息化与工业化融合研究所, 北京 100191

收稿日期:2026-03-23 出版日期:2026-08-25 发布日期:2026-09-02
通讯作者: 夏鹏
作者简介:
郭晓彤,中国信息通信研究院信息化与工业化融合研究所工程师,主要从事智能制造、制造业数字化转型、新一代信息技术在工业领域的融合应用等方面的研究工作;
谢润彬,中国信息通信研究院信息化与工业化融合研究所工程师,主要从事工业人工智能、数字化转型等方面的研究工作;
吴迪,中国信息通信研究院信息化与工业化融合研究所工程师,主要从事工业人工智能、工业互联网等方面的研究工作

GUO Xiaotong, XIE Runbin, WU Di, XIA Peng

Institute of Integration of Informatization and Industrialization, China Academy of Information and Communications Technology, Beijing 100191, China

Received:2026-03-23 Online:2026-08-25 Published:2026-09-02
Contact: XIA Peng

摘要/Abstract

摘要：

针对离散制造产品工艺多样、设计变更频繁、生产过程控制复杂的行业特点,界定了工业大模型的概念内涵,明确了面向离散行业的工业大模型需具备的核心能力;梳理了当前国内外产业界发展工业大模型的主流技术路径,分析了各路径的技术特征、典型应用与局限性;创新性地提出了未来工业大模型的体系架构,可为离散行业智能工厂建设工业大模型提供参考借鉴。

关键词: 工业大模型, 离散行业, 智能工厂, 生成式人工智能, 技术路径

Abstract:

Aiming at the characteristics of discrete manufacturing products, such as diverse process, frequent design changes and complex production process control, this paper defines the concept of industrial large-scale model, the core competence of industrial large-scale models for discrete industries is defined, and the mainstream technology paths of industrial large-scale models at home and abroad are reviewed. The architecture of future industrial large-scale model is proposed innovatively, which provides reference for the construction of industrial large-scale model of intelligent factory in discrete industry.

Key words: industrial large-scale model, discrete industry, smart factory, generative artificial intelligence, technology path

中图分类号:

TN929.5

郭晓彤, 谢润彬, 吴迪, 夏鹏. 面向离散行业智能工厂的工业大模型技术路径与体系架构研究[J]. 信息通信技术与政策, 2026, 52(8): 91-96.

GUO Xiaotong, XIE Runbin, WU Di, XIA Peng. Research on technology path and architecture of industrial large-scale model for intelligent factory in discrete industry[J]. Information and Communications Technology and Policy, 2026, 52(8): 91-96.

导出引用管理器 EndNote|Ris|BibTeX

链接本文:

http://ictp.caict.ac.cn/CN/10.12267/j.issn.2096-5931.2026.08.013

http://ictp.caict.ac.cn/CN/Y2026/V52/I8/91

参考文献 9

[1]	European Parliament and Council. Regulation (EU) 2024/1689 on laying down harmonised rules on artificial intelligence[EB/OL]. (2024-06-13)[2026-04-26]. https://eur-lex.europa.eu/eli/reg/2024/1689/oj.
[2]	Autio C, Schwarta R, Dunietz J, et al. Artificial intelligence risk management framework: generative artificial intelligence profile[EB/OL]. (2024-07-26)[2026-04-26]. https://doi.org/10.6028/NISE.AI.600-1.
[3]	Knott A, Pedreschi D, Chatila R, et al. State-of-the-art foundation AI models should be accompanied by detection mechanisms as a condition of public release[R], 2023.
[4]	杨宇田, 梁亨源, 杨宇涵, 等. 基于大模型与知识增强的工业领域智能体及其应用[C]//第36届中国过程控制会议(CPCC)会议文集. 宜宾: CPCCF, 2025.
[5]	Wen X, Zhang H, Zheng S, et al. From supervised to generative: a novel paradigm for tabular deep learning with large language models[C]//Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining(ACM SIGKDD). New York: ACM, 2024: 3323-3333.
[6]	Bjorck J, Castañeda F, Cherniadev N, et al. Gr00t n1: an open foundation model for generalist humanoid robots[PP/OL]. arXiv(2025-03-18)[2026-04-26]. https://arxiv.org.htm//2503.147341#AI.
[7]	Gemini Robotics Team, Abeyruwan S, Ainslie J, et al. Gemini robotics: bringing ai into the physical world[PP/OL]. arXiv (2025-03-25)[ 2026-04-26]. https://arxiv.org/abs/2503.20020.
[8]	Fakih M, Dharmaji R, Moghaddas Y, et al. Llm4plc:harnessing large language models for verifiable programming of plcs in industrial control systems[C]//Proceedings of the 46th International Conference on Software Engineering:Software Engineering in Practice(ICSE-SEIP). New York: ACM, 2024: 192-203.
[9]	Hui K H, Sanghi A, Rampini A, et al. Make-a-shape: a ten-million-scale 3D shape model[C]//Proceedings of the Forty-first International Conference on Machine Learning(ICML). Vienna: PMLR, 2024: 20660-20681.

[1]	杨一禾, 马飞, 李哲, 董晓慧. 算力互联网赋能生成式AI视频的内容安全研究[J]. 信息通信技术与政策, 2026, 52(2): 69-77.
[2]	吕文增, 杨正军. 边界重构:生成式人工智能对政府数据开放的新挑战^*[J]. 信息通信技术与政策, 2025, 51(12): 33-39.
[3]	徐明. 生成式人工智能大模型的安全挑战与治理路径研究[J]. 信息通信技术与政策, 2025, 51(1): 10-19.
[4]	苑卫国, 张新跃, 尉迟学彪. 生成式人工智能技术对网络安全领域的影响分析与启示建议[J]. 信息通信技术与政策, 2025, 51(1): 2-9.
[5]	李诗婧, 赵爽. 生成式人工智能应用于制造业的网络安全风险及对策研究[J]. 信息通信技术与政策, 2025, 51(1): 20-24.
[6]	孟楠, 周成胜, 赵勋. 生成式人工智能赋能网络安全运营降噪能力研究[J]. 信息通信技术与政策, 2024, 50(8): 24-31.
[7]	董耀聪, 张倩, 李宝强, 李艺, 董悦. 基于生成式人工智能的工业互联网安全技术与应用研究[J]. 信息通信技术与政策, 2024, 50(8): 32-37.
[8]	武林娜, 宋恺, 王淞鹤. 生成式人工智能对个人信息安全的挑战及应对策略[J]. 信息通信技术与政策, 2024, 50(1): 13-18.
[9]	宋恺, 屈蕾蕾, 杨萌科. 生成式人工智能的治理策略研究[J]. 信息通信技术与政策, 2023, 49(7): 83-88.
[10]	李亚宁, 任禾. 工业互联网协同化制造体系应用发展研究[J]. 信息通信技术与政策, 2020, 46(10): 35-37.

面向离散行业智能工厂的工业大模型技术路径与体系架构研究

Research on technology path and architecture of industrial large-scale model for intelligent factory in discrete industry

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献 9

相关文章 10

编辑推荐

Metrics

本文评价