迁移拓扑规划的机械设备群体协同智能诊断方法

doi:10.3901/JME.260101

机械工程学报 ›› 2026, Vol. 62 ›› Issue (4): 1-11.doi: 10.3901/JME.260101

• 仪器科学与技术 • 上一篇

扫码分享

迁移拓扑规划的机械设备群体协同智能诊断方法

杨彬, 李雅宁, 雷亚国, 李响, 曹军义, 武通海

西安交通大学现代设计及转子轴承系统教育部重点实验室西安 710049

收稿日期:2025-03-17 修回日期:2025-10-12 发布日期:2026-04-02
作者简介:杨彬,男,1992年出生,助理教授,硕士研究生导师。主要研究方向为新一代人工智能诊断理论及应用、高端装备大数据智能运维。E-mail:binyang@xjtu.edu.cn
雷亚国(通信作者),男,1979年出生,教授,博士研究生导师。主要研究方向为大数据智能诊断与预测、机械状态健康监测与智能维护、机械装备智能运维大模型。E-mail:yaguolei@mail.xjtu.edu.cn
基金资助:
国家重点研发计划(2022YFB3402100)、国家自然科学基金(52305129，52435003)和中央高校基本科研业务费专项资金资助项目。

Collaborative Swarm Intelligent Diagnosis Method for Machine Groups with Transferability Topology Planning

YANG Bin, LI Yaning, LEI Yaguo, LI Xiang, CAO Junyi, WU Tonghai

Key Laboratory of Education Ministry for Modern Design and Rotor-bearing System, Xi'an Jiaotong University, Xi'an 710049

Received:2025-03-17 Revised:2025-10-12 Published:2026-04-02

摘要/Abstract

摘要： 机械设备群体协同服役是实现网络化协同制造的核心载体，对设备群体进行数据中心化的智能诊断，存在数据流通壁垒、个体差异显著的挑战难题。为突破数据流通壁垒、提升诊断模型的群体适应性，现有研究尝试建立去中心化、分布式的协同诊断架构，然而，在规划设备群体诊断任务时存在盲目性，且在融合各设备节点的局部诊断模型过程中，忽视了个体重要度分布不均的客观事实。对此，提出迁移拓扑规划的群体协同智能诊断方法，首先建立迁移拓扑结构，描述各设备节点之间诊断知识的流出与流入关系；然后综合考虑数据质量、可用数据量、诊断知识可迁移性、通信资源、个体重要度等多重因素，优化求解迁移拓扑规划问题，以确定设备群体诊断知识的流向关系与个体重要度分布；最后建立个体重要度加权的协同诊断架构，训练适用于设备群体的全局诊断模型。通过多台设备的轴承故障数据对提出方法进行验证，结果表明：优化后的迁移拓扑结构，能够有效地反映设备群体诊断知识的最佳流向关系，提高了全局模型的诊断精度与群体适应性。

关键词: 机械设备, 群体智能, 协同智能诊断, 迁移拓扑规划

Abstract: Machine group collaborative service is central to networked collaborative manufacturing. Performing data-centralized intelligent diagnosis for such groups faces challenges like data barriers and individual differences. To overcome data barriers and enhance model adaptability, current approaches based on federated learning and multi-domain adaptation establish decentralized diagnosis architectures. However, they exhibit blindness in group task planning and neglect uneven individual importance when integrating local models. To address this, we propose a collaborative swarm intelligent diagnosis method with transferability topology planning. First, a transferability topology structure is established to define diagnosis knowledge flow among machine nodes. Second, the topology planning is optimized by comprehensively considering data quality, available data amount, diagnosis knowledge transferability, communication resources, and individual importance, thus determining knowledge flow relationships and individual importance distribution. Finally, an individual importance-weighted decentralized diagnosis architecture is built to collaboratively train a global diagnosis model for the machine group. Validation experiments using bearing fault data from multiple devices show that the optimized transferability topology can effectively reflect knowledge flow relationships among machine nodes. This improves the diagnosis accuracy of global model and enables its adaptability for machine group diagnosis.

Key words: machine groups, swarm intelligence, collaborative intelligent diagnosis, transferability topology planning

中图分类号:

TH17

杨彬, 李雅宁, 雷亚国, 李响, 曹军义, 武通海. 迁移拓扑规划的机械设备群体协同智能诊断方法[J]. 机械工程学报, 2026, 62(4): 1-11.

YANG Bin, LI Yaning, LEI Yaguo, LI Xiang, CAO Junyi, WU Tonghai. Collaborative Swarm Intelligent Diagnosis Method for Machine Groups with Transferability Topology Planning[J]. Journal of Mechanical Engineering, 2026, 62(4): 1-11.

参考文献

[1] COMPARE M，BARALDI P，ZIO E. Challenges to IoT-enabled predictive maintenance for industry 4.0[J]. IEEE Internet of Things Journal，2020，7(5)：4585-4597.
[2] KHAN S，YAIRI T. A review on the application of deep learning in system health management[J]. Mechanical Systems and Signal Processing，2018，107：241-265.
[3] LEI Yaguo，LI Naipeng，LI Xiang. Big data-driven intelligent fault diagnosis and prognosis for mechanical systems[M]. Berlin：Springer，2022.
[4] 雷亚国，杨彬，李乃鹏，等. 跨设备的机械故障靶向迁移诊断方法[J]. 机械工程学报，2022，58(12)：1-9. LEI Yaguo，YANG Bin，LI Naipeng，et al. Targeted transfer diagnosis method across different machines[J]. Journal of Mechanical Engineering，2022，58(12)：1-9.
[5] XIAO Renbin. Four development stages of collective intelligence[J]. Frontiers of Information Technology & Electronic Engineering，2024，25(7)：903-916.
[6] 李响，付春霖，雷亚国，等. 保证数据隐私的装备协同智能故障诊断联邦迁移学习方法[J]. 机械工程学报，2023，59(6)：1-9. LI Xiang，FU Chunlin，LEI Yaguo，et al. Federated transfer learning method for privacy-preserving collaborative intelligent machinery fault diagnostics[J]. Journal of Mechanical Engineering，2023，59(6)：1-9.
[7] 雷亚国，李熹伟，李响，等. 面向机械设备通用健康管理的智能运维大模型[J]. 机械工程学报，2025，61(6)：1-13. LEI Yaguo，LI Xiwei，LI Xiang，et al. Research on large model for general prognostics and health management of machinery[J]. Journal of Mechanical Engineering，2025，61(6)：1-13.
[8] LI Tian，SAHU A K，TALWALKAR A，et al. Federated learning： Challenges，methods，and future directions[J]. IEEE Signal Processing Magazine，2020，37(3)：50-60.
[9] QIAN Quan，ZHANG Bin，LI Chuan，et al. Federated transfer learning for machinery fault diagnosis：A comprehensive review of technique and application[J]. Mechanical Systems and Signal Processing，2025，223：111837.
[10] FEHSENFELD M，KÜHN J，KORTMANN K-P. Multi-source domain adaptation for fault diagnosis of belt drives[J]. IFAC-PapersOnLine，2023，56(2)：11305-11310.
[11] RUSSELL M，WANG Peng. Maximizing model generalization for machine condition monitoring with self-supervised learning and federated learning[J]. Journal of Manufacturing Systems，2023，71：274-285.
[12] 邵海东，肖一鸣，闵志闪，等. 区块链和边缘计算赋能的联邦学习故障诊断框架[J]. 机械工程学报，2023，59(21)：283-292. SHAO Haidong，XIAO Yiming，MIN Zhishan，et al. Blockchain and edge computing enabled federated learning fault diagnosis framework[J]. Journal of Mechanical Engineering，2023，59(21)：283-292.
[13] MCMAHAN H B，MOORE E，RAMAGE D，et al. Communication-efficient learning of deep networks from decentralized data[C]// Proceedings of the 20th International Conference on Artificial Intelligence and Statistics in FL，USA，April 20-22，2017：1273-1282.
[14] BEN-DAVID S，BLITZER J，CRAMMER K，et al. A theory of learning from different domains[J]. Machine Learning，2010，79：151-175.
[15] WANG Su，HOSSEINALIPOUR S，BRINTON C G，et al. Multi-source to multi-target decentralized federated domain adaptation[J]. IEEE Transactions on Cognitive Communications and Networking，2024，10(3)：1011- 1025.
[16] YANG Bin，LEI Yaguo，LI Xiang，et al. Deep targeted transfer learning along designable adaptation trajectory for fault diagnosis across different machines[J]. IEEE Transactions on Industrial Electronics，2023，70(9)：9463-9473.
[17] MOZAFFARI M，SAAD W，BENNIS M，et al. Mobile unmanned aerial vehicles (UAVs) for energy-efficient internet of things communications[J]. IEEE Transactions on Wireless Communications，2017，16(11)：7574-7589.
[18] SCHULMAN J，LEVINE S，MORITZ P，et al. Trust region policy optimization[C]//Proceedings of the 32nd International Conference on Machine Learning in Lille，France，July 6-11，2015：1889-1897.
[19] YUROCHKIN M，AGARWAL M，GHOSH S，et al. Bayesian nonparametric federated learning of neural networks[C]//Proceedings of the 36th International Conference on Machine Learning in California，USA，June 9-15，2019：7252-7261.

迁移拓扑规划的机械设备群体协同智能诊断方法

Collaborative Swarm Intelligent Diagnosis Method for Machine Groups with Transferability Topology Planning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

编辑推荐

Metrics

本文评价

[1]	雷亚国, 李熹伟, 李响, 李乃鹏, 杨彬. 面向机械设备通用健康管理的智能运维大模型[J]. 机械工程学报, 2025, 61(6): 1-13.
[2]	任萌, 朱丽娜, 于鹤龙, 邢志国, 王海斗, 徐滨士. 面向机械损伤状态监测的智能材料研究进展[J]. 机械工程学报, 2023, 59(18): 42-53.
[3]	雷亚国, 杨彬, 李乃鹏, 李响, 武通海. 跨设备的机械故障靶向迁移诊断方法[J]. 机械工程学报, 2022, 58(12): 1-9.
[4]	陈祝云, 钟琪, 黄如意, 廖奕校, 李霁蒲, 李巍华. 基于增强迁移卷积神经网络的机械智能故障诊断[J]. 机械工程学报, 2021, 57(21): 96-105.
[5]	雷亚国, 陈吴, 李乃鹏, 林京. 自适应多核组合相关向量机预测方法及其在机械设备剩余寿命预测中的应用[J]. 机械工程学报, 2016, 52(1): 87-93.
[6]	何正嘉;曹宏瑞;訾艳阳;李兵. 机械设备运行可靠性评估的发展与思考[J]. , 2014, 50(2): 171-186.
[7]	焦建新;李宗耀;赵振英;查建中. 复杂机械设备智能诊断集成策略及其实现[J]. , 1995, 31(6): 78-82，9.