• CN:11-2187/TH
  • ISSN:0577-6686

机械工程学报 ›› 2025, Vol. 61 ›› Issue (13): 265-281.doi: 10.3901/JME.2025.13.265

• 数字化设计与制造 • 上一篇    

扫码分享

基于云-边协同的分布式协同制造任务生产进度预测方法

朱海华1, 王健杰1, 李霏2, 刘长春1, 蔡祺祥1, 唐敦兵1   

  1. 1. 南京航空航天大学机电学院 南京 210016;
    2. 北京电子工程总体研究所 北京 100854
  • 收稿日期:2024-07-08 修回日期:2024-12-22 发布日期:2025-08-09
  • 作者简介:朱海华(通信作者),男,1985年出生,博士,副教授,硕士研究生导师。主要研究方向为网络协同制造、大数据分析。E-mail:h.zhu@nuaa.edu.cn;王健杰,男,1999年出生,硕士研究生。主要研究方向为制造车间大数据分析、网络协同制造。E-mail:wang126@nuaa.edu.cn;李霏,男,1983年出生,博士。主要研究方向为数字化设计制造。E-mail:leafy777@qq.com;刘长春,男,1995年出生,博士。主要研究方向为增强现实、物联制造车间的智能运维和工业大数据。E-mail:651979759@qq.com;蔡祺祥,男,1984年出生,博士。主要研究方向为智能制造系统。E-mail:cqx@nuaa.edu.cn;唐敦兵,男,1972年出生,博士,教授,博士研究生导师。主要研究方向为智能制造系统、制造系统与自动化、数字化设计与制造。E-mail:d.tang@nuaa.edu.cn
  • 基金资助:
    国家重点研发计划(2021YFB1716304)和江苏高校“青蓝工程”资助项目。

Task Production Progress Prediction Approach in Distributed Cooperative Manufacturing Based on Cloud-edge Collaboration

ZHU Haihua1, WANG Jianjie1, LI Fei2, LIU Changchun1, CAI Qixiang1, TANG Dunbing1   

  1. 1. College of Mechanical & Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016;
    2. Beijing Institute of Electronic System Engineering, Beijing 100854
  • Received:2024-07-08 Revised:2024-12-22 Published:2025-08-09

摘要: 高端装备制造产业链涉及单位多、专业门类广、地域分布广,产品订单被分解为数个子任务下发到不同制造车间进行跨企业生产,具有典型的分布式制造特征。在业务流程和制造系统环境愈发复杂和不稳定的当下,各订单子任务生产进度的精准预测可以及时发现生产计划交期波动,避免整体项目的长时间停滞,确保项目有序推进和交付。针对传统数据分析方法不适用于复杂制造环境、各企业利用分布式制造资源能力较弱的问题,提出一种基于云-边协同的分布式协同制造任务生产进度预测方法。以多车间生产情况和服务需求为导向,实现高自由度和易于管理的分布式协同制造平台架构。基于平台架构,提出云-边数据协同和模型协同两大关键协同机制。针对生产进度预测需求,分别提出车间数据的传输与集成、制造数据预处理和分布式协同制造任务生产进度预测三个关键方法。最后,以分布式制造案例为对象验证了所提方法的可行性和有效性。

关键词: 高端装备制造, 分布式协同制造, 生产进度, 云边协同, 制造服务

Abstract: The high-end equipment manufacturing industrial chain involves multiple enterprises, various professional categories, and wide geographic distribution. The product order is broken down into several sub-tasks, and these sub-tasks are distributed to different manufacturing workshops for cross-enterprise manufacturing. This manufacturing mode has typical characteristics of distributed manufacturing. In the current environment where business processes and manufacturing systems are increasingly complex and unstable, accurate prediction of each sub-task production progress allows for the timely detection of production schedule fluctuations, and helps enterprises avoid long-term stagnation of the overall project, ensuring orderly progress and delivery of the project. In response to the problem that traditional data analysis methods are not suitable for complex manufacturing environment and the ability of enterprises to utilize distributed resources is weak, a task production progress prediction approach in distributed cooperative manufacturing based on Cloud-Edge collaboration is proposed. A distributed collaborative manufacturing platform architecture with high freedom and easy management is realized based on multi-workshop production situation and service demand. Based on the platform architecture, two key collaboration mechanisms of cloud-edge data collaboration and model collaboration are proposed. According to the demand of production progress prediction, three key approaches of workshop data transmission and integration, manufacturing data preprocessing and distributed collaborative manufacturing task production progress prediction are proposed. Finally, a case of distributed manufacturing is used to verify the feasibility and effectiveness of the proposed approach.

Key words: high-end equipment manufacturing, distributed cooperative manufacturing, production progress, cloud-edge collaboration, manufacturing service

中图分类号: