联邦学习的社群化制造韧性能力预测建模

张富强; 王浩杰; 惠记庄; 丁凯

doi:10.7652/xjtuxb202508002

您当前的位置：

首页 >

文章列表页 >

联邦学习的社群化制造韧性能力预测建模

专题　工业互联网与制造服务 | 更新时间：2025-07-30

- 联邦学习的社群化制造韧性能力预测建模
- Federated Learning-Based Predictive Modeling of Resilience Capability in Social Manufacturing
- 西安交通大学学报 2025年59卷第8期页码：11-19
- 作者机构：
  
  1.长安大学道路施工技术与装备教育部重点实验室， 710064，西安
  2.长安大学智能制造系统研究所， 710064，西安
- 作者简介：
  
  张富强（1984—），男，副教授
  丁凯，男，教授。
- 基金信息：
  
  国家重点研发计划资助项目(2021YFB3301701)
- DOI：10.7652/xjtuxb202508002
  中图分类号： TP166
- 收稿：2025-01-06，
  
  网络首发：2025-04-22，
  
  纸质出版：2025-08-10
- 稿件说明：
移动端阅览
张富强, 王浩杰, 惠记庄, 等. 联邦学习的社群化制造韧性能力预测建模[J]. 西安交通大学学报, 2025,59(8):11-19.

ZHANG Fuqiang, WANG Haojie, HUI Jizhuang, et al. Federated Learning-Based Predictive Modeling of Resilience Capability in Social Manufacturing[J]. Journal of Xi’an Jiaotong University, 2025, 59(8): 11-19.
张富强, 王浩杰, 惠记庄, 等. 联邦学习的社群化制造韧性能力预测建模[J]. 西安交通大学学报, 2025,59(8):11-19. DOI： 10.7652/xjtuxb202508002.

ZHANG Fuqiang, WANG Haojie, HUI Jizhuang, et al. Federated Learning-Based Predictive Modeling of Resilience Capability in Social Manufacturing[J]. Journal of Xi’an Jiaotong University, 2025, 59(8): 11-19. DOI： 10.7652/xjtuxb202508002.

摘要

针对社群化制造资源分散化布局的特点，以及传统集中式建模面临的数据隐私与信息孤岛等问题，提出了一种基于联邦学习的韧性能力预测框架，从多角度分析不同因素对产品生产加工工时的影响。首先，考虑不同工序中断情况，以订单交付周期为目标函数，搭建了工时扰动模型计算损失时间，进而基于分布式学习范式，搭建了联邦学习网络模型；其次，设计了联邦小批量梯度下降（FedMBGD）算法，明确算法流程并进行本地训练；最后，结合工时扰动模型和算法，对社群化制造的韧性能力进行预测，通过与其他算法的对比，验证了所提算法的可行性与有效性。研究结果表明：所提出的算法能够显著提升收敛性与寻优能力，可将预测精确度提高至90%以上，并且在不共享原始数据的前提下，实现了社群化制造韧性的动态精准预测，解决了数据隐私与协同建模之间的矛盾。该研究为社群化制造模式下韧性能力预测提供了理论参考，为隐私数据的算法训练、参数上传及信息共享提供了一定的指导意义。

Abstract

Considering the characteristics of decentralized resource layouts in social manufacturing

as well as the issues of data privacy and information silos faced by traditional centralized modeling

this paper proposes a resilience capability prediction framework based on federated learning. The framework analyzes the impact of various factors on product processing time from multiple perspectives. First

considering different interruption scenarios in production processes

a working hour disturbance model is established with the order delivery cycle as the objective function to calculate loss time. Subsequently

a federated learning network model is constructed based on a distributed learning paradigm. Next

a federated mini-batch gradient descent (FedMBGD) algorithm is designed

detailing the algorithmic process and performing local training. Finally

the resilience capability of social manufacturing is predicted in conjunction with the working hour disturbance model and the algorithm. The feasibility and effectiveness of the proposed algorithm are validated through comparisons with other algorithms. The research results indicate that the proposed algorithm significantly enhances convergence and optimization capabilities

raising prediction accuracy to over 90%. Furthermore

it enables dynamic and precise prediction of social manufacturing resilience without sharing raw data

resolving the conflict between data privacy and collaborative modeling. This study provides theoretical references for predicting resilience capabilities in social manufacturing models and offers guidance for algorithm training with private data

parameter uploading

and information sharing.

关键词

Keywords

references

LENG Jiewu , ZHONG Yuanwei , LIN Zisheng , et al . Towards resilience in Industry 5.0: a decentralized autonomous manufacturing paradigm [J ] . Journal of Manufacturing Systems , 2023 , 71 : 95 - 114 .

于成龙 , 侯俊杰 , 蒲洪波 , 等 . 基于数据挖掘的机加工生产进度预测方法 [J ] . 现代制造工程 , 2020 ( 2 ): 34 - 41 .

YU Chenglong , HOU Junjie , PU Hongbo , et al . Forecasting method of machine work schedule based on data mining [J ] . Modern Manufacturing Engineering , 2020 ( 2 ): 34 - 41 .

魏法杰 , 都本正 , 田爽 , 等 . 多品种小批量物料采购延迟交付预测 [J ] . 北京航空航天大学学报(社会科学版) , 2018 , 31 ( 3 ): 78 - 83 .

WEI Fajie , DU Benzheng , TIAN Shuang , et al . Prediction of material procurement delays in delivery for multi-variety and small batch manufacturing [J ] . Journal of Beijing University of Aeronautics and Astronautics (Social Sciences Edition) , 2018 , 31 ( 3 ): 78 - 83 .

彭锦永 . 基于汽车行业整车订单交付时间优化方法研究 [D ] . 广州 : 华南理工大学 , 2018 .

温兴漳 , 任卓明 . 基于区域配送中心时空特征预测电子商务平台订单交付时长 [J/OL ] . 运筹与管理 . ( 2022-10-09 ) [ 2024-12-12 ] . http://kns.cnki.net/kcms/detail/34.1133.G3.20221009.0915.002.html http://kns.cnki.net/kcms/detail/34.1133.G3.20221009.0915.002.html .

WEN Xingzhang , REN Zhuoming . Predicting the order delivery time of E-commerce platform based on the temporal and spatial features of regional distribution center [J/OL ] . Operations Research and Management Science . ( 2022-10-09 ) [ 2024-12-12 ] . http://kns.cnki.net/kcms/detail/34.1133.G3.20221009.0915.002.html http://kns.cnki.net/kcms/detail/34.1133.G3.20221009.0915.002.html .

肖雄 , 唐卓 , 肖斌 , 等 . 联邦学习的隐私保护与安全防御研究综述 [J ] . 计算机学报 , 2023 , 46 ( 5 ): 1019 - 1044 .

XIAO Xiong , TANG Zhuo , XIAO Bin , et al . A survey on privacy and security issues in federated learning [J ] . Chinese Journal of Computers , 2023 , 46 ( 5 ): 1019 - 1044 .

王健宗 , 孔令炜 , 黄章成 , 等 . 联邦学习算法综述 [J ] . 大数据 , 2020 , 6 ( 6 ): 64 - 82 .

WANG Jianzong , KONG Lingwei , HUANG Zhangcheng , et al . Research review of federated learning algorithms [J ] . Big Data Research , 2020 , 6 ( 6 ): 64 - 82 .

梁天恺 , 曾碧 , 陈光 . 联邦学习综述：概念、技术、应用与挑战 [J ] . 计算机应用 , 2022 , 42 ( 12 ): 3651 - 3662 .

LIANG Tiankai , ZENG Bi , CHEN Guang . Federated learning survey: concepts, technologies, applications and challenges [J ] . Journal of Computer Applications , 2022 , 42 ( 12 ): 3651 - 3662 .

杨强 , 童咏昕 , 王晏晟 , 等 . 群体智能中的联邦学习算法综述 [J ] . 智能科学与技术学报 , 2022 , 4 ( 1 ): 27 - 44 .

YANG Qiang , TONG Yongxin , WANG Yansheng , et al . A survey on federated learning in crowd intelligence [J ] . Chinese Journal of Intelligent Science and Technology , 2022 , 4 ( 1 ): 27 - 44 .

张雪晴 , 刘延伟 , 刘金霞 , 等 . 面向边缘智能的联邦学习综述 [J ] . 计算机研究与发展 , 2023 , 60 ( 6 ): 1276 - 1295 .

ZHANG Xueqing , LIU Yanwei , LIU Jinxia , et al . An overview of federated learning in edge intelligence [J ] . Journal of Computer Research and Development , 2023 , 60 ( 6 ): 1276 - 1295 .

刘庆祥 , 许小龙 , 张旭云 , 等 . 基于联邦学习的边缘智能协同计算与隐私保护方法 [J ] . 计算机集成制造系统 , 2021 , 27 ( 9 ): 2604 - 2610 .

LIU Qingxiang , XU Xiaolong , ZHANG Xuyun , et al . Federated learning based method for intelligent computing with privacy preserving in edge computing [J ] . Computer Integrated Manufacturing Systems , 2021 , 27 ( 9 ): 2604 - 2610 .

ZHU Konglin , CHEN Wentao , JIAO Lei , et al . Online training data acquisition for federated learning in cloud-edge networks [J ] . Computer Networks , 2023 , 223 : 109556 .

李少波 , 杨磊 , 李传江 , 等 . 联邦学习概述：技术、应用及未来 [J ] . 计算机集成制造系统 , 2022 , 28 ( 7 ): 2119 - 2138 .

LI Shaobo , YANG Lei , LI Chuanjiang , et al . Overview of federated learning: technology, applications and future [J ] . Computer Integrated Manufacturing Systems , 2022 , 28 ( 7 ): 2119 - 2138 .

KONG Lingxuan , ZHENG Ge , BRINTRUP A . A federated machine learning approach for order-level risk prediction in Supply Chain Financing [J ] . International Journal of Production Economics , 2023 , 268 : 109095 .

ROKOSS A , POPKES L , SCHMIDT M . Analysis of the relevance of models, influencing factors and the point in time of the forecast on the prediction quality in order-related delivery time determination using machine learning [C ] // 6th Conference on Production Systems and Logistics . Hannover, Germany : Publish-Ing , 2024 : 415 - 431 .

ABDOLLAHI M , YANG Xinan , NASRI M I , et al . Demand management in time-slotted last-mile delivery via dynamic routing with forecast orders [J ] . European Journal of Operational Research , 2023 , 309 ( 2 ): 704 - 718 .

GAJEWSKA T , KACZOR G , SZKODA M . Forecasting of warranty returns based on the reliability of delivery assessment [J ] . Technical Gazette , 2021 , 28 ( 3 ): 994 - 999 .

MATSUOKA R , KOBAYASHI K , YAMASHITA Y . Online optimization of pickup and delivery problem considering demand forecasting [C ] // 2023 IEEE 12th Global Conference on Consumer Electronics (GCCE) . Piscataway, NJ, USA : IEEE , 2023 : 879 - 880 .

CHU Hongyan , DONG Ke , LI Rui , et al . Integrated modeling and optimization of production planning and scheduling in hybrid flow shop for order production mode [J ] . Computers & Industrial Engineering , 2022 , 174 : 108741 .

ACKERMANN S , FUMERO Y , MONTAGNA J M . Taking advantage of order consolidation in simultaneous batching and scheduling of multiproduct batch plants [J ] . Computers & Chemical Engineering , 2022 , 156 : 107564 .

位世云 . 基于数字孪生的智能车间动态生产过程扰动识别方法研究 [D ] . 济南 : 山东大学 , 2023 .

侯娅楠 . 机器故障下基于工序关系网络的柔性作业车间鲁棒性调度研究 [D ] . 乌鲁木齐 : 新疆大学 , 2020 .

刘道元 , 郭宇 , 黄少华 , 等 . 一种面向订单剩余完工时间预测的SOM-FWFCM特征选择算法 [J ] . 中国机械工程 , 2021 , 32 ( 9 ): 1073 - 1079 .

LIU Daoyuan , GUO Yu , HUANG Shaohua , et al . A SOM-FWFCM based feature selection algorithm for order remaining completion time prediction [J ] . China Mechanical Engineering , 2021 , 32 ( 9 ): 1073 - 1079 .

顾松松 . 具备客户需求预测的生产交付能力提升系统的设计与实现 [D ] . 重庆 : 重庆大学 , 2019 .

周亚勤 , 李蓓智 , 杨建国 , 等 . 响应随机扰动的受影响工序重调度方法研究 [J ] . 制造技术与机床 , 2013 ( 4 ): 105 - 108 .

ZHOU Yaqin , LI Beizhi , YANG Jianguo , et al . Study on an affected operations rescheduling method responding to stochastic disturbances [J ] . Manufacturing Technology & Machine Tool , 2013 ( 4 ): 105 - 108 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

水蒸气掺混对氨裂解气旋流燃烧与排放特性的影响研究

超临界二氧化碳向心透平轮背间隙内风阻损失及流动特性研究

离子液体改性燃料的电流体动力学效应研究

冷库水平空气幕热湿阻隔性能数值模拟研究

采用试验设计方法的第三代CO2气体箔轴承箔片几何参数敏感性分析