面向工业5.0的多智能体云边端协同智慧制造体系架构与作业调度

doi:10.3901/JME.260590

摘要/Abstract

摘要： 随着工业5.0概念的提出，全球智能制造范式正从“效率优先”的工业4.0向“以人为本、可持续、弹性化”的新阶段转变。在这一背景下，首先回顾了人工智能技术的发展趋势，并分析人类与人机协同工作并相互补充增强彼此能力的关键问题，阐明人机协同在智能制造中的必要性；接着归纳总结多智能体发展历程以及其在分布式环境下的挑战，介绍了融合多智能体与大语言模型为人工智能带来的突破；在此基础上，提出了一种基于大推理模型的多智能体云边端协同智慧制造体系架构，通过其“全量模型—边缘轻量模型”的协同调度机制，结合复杂网络建模、知识蒸馏与联邦迁移学习，实现生产调度任务的智能化、弹性化与可解释性的提升。实验结果表明，大模型在制造语境下具备替代传统深度强化学习模型执行部分高层调度逻辑的潜力，而多智能体云边端协同架构将为面向工业5.0多智能体的下一代智能制造作业调控提供更为高效、可信、弹性的支持。

关键词: 工业5.0, 大语言模型, 推理智能, 智能制造, 多智能体, 生产调度

Abstract: With the advent of the Industry 5.0 paradigm, global smart manufacturing is transitioning from the “efficiency-first” focus of Industry 4.0 to a new stage characterized by human-centricity, sustainability, and resilience. Against this backdrop, this paper first reviews the development trends of artificial intelligence (AI) technologies and analyzes key issues in human-machine collaboration, where humans and smart systems work together to enhance each other’s capabilities. The necessity of such collaboration in smart manufacturing is emphasized. Subsequently, the evolution of multi-agent systems and explores the challenges they face in distributed environments is summarized. It introduces the integration of multi-agent systems with large language models (LLMs), highlighting the breakthroughs this synergy brings to AI. Building on these insights, a cloud-edge-end collaborative wisdom manufacturing architecture based on large reasoning models and multi-agent systems is proposed. By leveraging a coordinated scheduling mechanism between “full-scale models” and “lightweight edge models”, and integrating techniques such as complex network modeling, knowledge distillation, and federated transfer learning, the proposed framework enhances the intelligence, resilience, and interpretability of production scheduling tasks. Experimental results demonstrate that LLMs have the potential to replace traditional deep reinforcement learning models in executing certain high-level scheduling logic in manufacturing contexts. Furthermore, the proposed collaborative architecture offers a more efficient, trustworthy, and resilient foundation for next-generation smart manufacturing operations with multi-agents in the Industry 5.0 era.

Key words: Industry 5.0, large language model, reasoning intelligence, smart manufacturing, multi-agent systems, production scheduling

中图分类号:

姚锡凡, 胡坤, 李佳蔚. 面向工业5.0的多智能体云边端协同智慧制造体系架构与作业调度[J]. 机械工程学报, 2026, 62(11): 102-115.

YAO Xifan, HU Kun, LI Jiawei. Wisdom Manufacturing Architecture and Scheduling for Industry 5.0 Based on Cloud-edge-end Collaboration of AI Agents[J]. Journal of Mechanical Engineering, 2026, 62(11): 102-115.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://www.cjmenet.com.cn/CN/10.3901/JME.260590

http://www.cjmenet.com.cn/CN/Y2026/V62/I11/102

参考文献

[1] GARTNER. Gartner top 10 strategic technology trends for 2025[R]. Gartner，2025.
[2] BREQUE M，DE NUL L，PETRIDIS A. Industry 5.0：Towards a sustainable，human-centric and resilient European industry[R]. Luxembourg，LU: European Commission，Directorate-General for Research and Innovation，2021.
[3] XIAN W，YU K，HAN F，et al. Advanced manufacturing in Industry 5.0：A survey of key enabling technologies and future trends[J]. IEEE Transactions on Industrial Informatics，2024，20：1055-1068.
[4] 庄存波，刘检华，张雷. 工业5.0的内涵、体系架构和使能技术[J]. 机械工程学报，2022，58(18)：75-87. ZHUANG Cunbo，LIU Jianhua，ZHANG Lei. Connotation，architecture and enabling technology of Industrial 5.0[J]. Journal of Mechanical Engineering，2022，58(18)：75-87.
[5] 姚锡凡，马南峰，张存吉，等. 以人为本的智能制造：演进与展望[J]. 机械工程学报，2022，58(18)：2-15. YAO Xifan，MA Nanfeng，ZHANG Cunji，et al. Human-centric smart manufacturing：Evolution and outlook[J]. Journal of Mechanical Engineering，2022，58(18)：2-15.
[6] BARATA J，KAYSER I. Industry 5.0– Past，present，and near future[J]. Procedia Computer Science，2023，219： 778-788.
[7] AKUNDI A，EURESTI D，LUNA S，et al. State of Industry 5.0—Analysis and identification of current research trends[J]. Applied System Innovation，2022，5(1)：27.
[8] GOLOVIANKO M，TERZIYAN V，BRANYTSKYI V，et al. Industry 4.0 vs. Industry 5.0：Co-existence，transition，or a hybrid[J]. Procedia Computer Science，2023，117：102-113.
[9] MUSTAPHA K B. A survey of emerging applications of large language models for problems in mechanics，product design，and manufacturing[J]. Advanced Engineering Informatics，2025，64，103066.
[10] LI Y，ZHAO H，JIANG H，et al. Large language models for manufacturing[EB/OL]. [2025-04-25]，https：//arxiv. org/abs/2410.21418，arXiv：2410.21418.
[11] ZHANG C，XU Q，YU Y，et al. A survey on potentials，pathways and challenges of large language models in new-generation intelligent manufacturing[J]. Robotics and Computer-Integrated Manufacturing，2025，92：102883.
[12] LENG J，SHA W，WANG B，et al. Industry 5.0：Prospect and retrospect[J]. Journal of Manufacturing Systems，2022，65：279-295.
[13] XU X，LU Y，VOGEL-HEUSER B，et al. Industry 4.0 and Industry 5.0—Inception，conception and perception[J]. Journal of Manufacturing Systems，2021，61：530-535.
[14] HUANG S，WANG B，LI X，et al. Industry 5.0 and Society 5.0—Comparison，complementation and co-evolution[J]. Journal of Manufacturing Systems，2022，64：424-428.
[15] 程鼎豪，娄山河，郑浩，等. 面向人本智造的工业外骨骼：挑战、进展和展望[J]. 计算机集成制造系统，2024，30(12)：4179-4197. CHENG Dinghao，LOU Shanhe，ZHENG Hao，et al. Industrial exoskeleton for human-centric smart manufacturing：Challenges，progress and prospects[J]. Computer Integrated Manufacturing Systems，2024，30(12)：4179-4197.
[16] 蒋周明矩，熊异，王柏村. 面向工业5.0的人机协作增材制造[J]. 机械工程学报，2024，60(3)：238-253. JIANG Zhoumingju，XIONG Yi，WANG Baicun. Human-machine collaborative additive manufacturing for Industry 5.0[J]. Journal of Mechanical Engineering，2024，60(3)：238-253.
[17] 马南峰，姚锡凡，陈飞翔，等. 面向工业5.0的人本智造[J]. 机械工程学报，2022，58(18)：88-102. MA Nanfeng，YAO Xifan，CHEN Feixiang，et al. Human-centric smart manufacturing for Industry 5.0[J]. Journal of Mechanical Engineering，2022，58(18)：88-102.
[18] WU D，ZHENG P，ZHAO Q，et al. Empowering natural human–robot collaboration through multimodal language models and spatial intelligence：Pathways and perspectives[J/OL]. Robotics and Computer-Integrated Manufacturing，https://doi.org/10.1016/j.rcim.2025.103064.
[19] 黄思翰，陈建鹏，徐哲，等. 基于大语言模型和机器视觉的智能制造系统人机自主协同作业方法[J]. 机械工程学报，2025，61(3)：130-141. HUANG Sihan CHEN Jianpeng，XU Zhe，et al. Human-robot autonomous collaboration method of smart manufacturing systems based on large language model and machine vision[J]. Journal of Mechanical Engineering，2025，61(3)：130-141.
[20] BUSONIU L，BABUSKA R，DE SCHUTTER B. A comprehensive survey of multiagent reinforcement learning[J]. IEEE Transactions on Systems，Man，and Cybernetics，Part C (Applications and Reviews)，2008，38(2)：156-172.
[21] OLIEHOEK F A，AMATO C. A concise introduction to decentralized POMDPs[M]. Cham：Springer，2016.
[22] SILVER D，HUANG A，MADDISON C J，et al. Mastering the game of Go with deep neural networks and tree search[J]. Nature，2016，529(7587)：484-489.
[23] VINYALS O，BABUSCHKIN I，CZARNECKI W M，et al. Grandmaster level in Star Craft II using multi-agent reinforcement learning[J]. Nature，2019，757(7782)：350-354.
[24] VASWANI A，SHAZEER N，PARMAR N，et al. Attention is all you need [C]// 31st Conference on Neural Information Processing Systems，Long Beach，CA，USA，2017：6000-6010.
[25] SILVER D，SUTTON R S. Welcome to the era of experience [EB/OL].(2025-04-26). https://storage.googleapis. com/deepmind-media/Era-of-Experience%20/The%20Era%20of%20Experience%20Paper.pdf.
[26] 卢秉恒，邵新宇，张俊，等. 离散型制造智能工厂发展战略[J]. 中国工程科学，2018，20(4)：45-50. LU Bingheng，SHAO Xinyu，ZHANG Jun，et al. Development strategy for intelligent factory in discrete manufacturing[J]. Chinese Engineering Science，2018，20(4)：45-50.
[27] 丁汉，江平宇，张洁，等. 前言——工业互联网专辑[J]. 中国科学(技术科学)，2022，52(1)：1-2. DING H，JIANG P Y，ZHANG J，et al. Preface——special issue：Industrial internet[J]. Sci Sin Tech，2022，52(1)：1-2.
[28] YAO X，MA N，ZHANG J，et al. Enhancing wisdom manufacturing as industrial metaverse for industry and society 5.0[J]. Journal of Intelligent Manufacturing，2024，35(1)：235-255.
[29] ZHOU J，ZHOU Y，WANG B，et al. Human–cyber– physical systems (HCPSs) in the context of new- generation intelligent manufacturing[J]. Engineering，2019，5(4)：624-636.
[30] 景轩，姚锡凡. 走向社会信息物理生产系统[J]. 自动化学报，2019，45(4)：637-656. JING Xuan，YAO Xifan. Towards social cyber physical production systems[J]. Acta Automatica Sinica，2019，45(4)：637-656.
[31] 姚锡凡，练肇通，杨屹，等. 智慧制造——面向未来互联网的人机物协同制造新模式[J]. 计算机集成制造系统，2014，20(6)：1490-1498. YAO Xifan，LIAN Zhaotong，YANG Yi，et al. Wisdom manufacturing：New humans-computers- things collaborative manufacturing model[J]. Computer Integrated Manufacturing Systems，2014，20(6)：1490-1498.
[32] 马南峰，姚锡凡，王柯赛. 面向未来互联网的智慧制造研究现状与展望[J]. 中国科学：技术科学，2022，52(1)：55-75. MA Nanfeng，YAO Xifan，WANG Kesai. Current status and prospect of future Internet-oriented wisdom manufacturing[J]. Sci Sin Tech，2022，52(1)：55-75.
[33] 姚锡凡，黄宇，黄岩松，等. 自主智能制造：社会—信息—物理交互、参考体系架构与运作机制[J]. 计算机集成制造系统，2022，28(2)：325-338. YAO Xifan，HUANGYu，HUANG Yansong，et al. Autonomous smart manufacturing：Social-cyber-physical interaction，reference architecture and operation mechanism[J]. Computer Integrated Manufacturing Systems，2022，28(2)：325-338.