边云协同下数字孪生驱动的齿轮传动系统在线监测技术

doi:10.3901/JME.260559

机械工程学报 ›› 2026, Vol. 62 ›› Issue (12): 87-97.doi: 10.3901/JME.260559

• 特邀专栏：数字孪生赋能的高端装备智能运维 • 上一篇

扫码分享

边云协同下数字孪生驱动的齿轮传动系统在线监测技术

朱本然^1,2, 潮群^1,2, 王忠睿^1,2, 刘成良¹

1. 上海交通大学机械与动力工程学院上海 200240;
2. 重庆大学高端装备机械传动全国重点实验室重庆 400044

收稿日期:2025-06-13 修回日期:2025-09-30 发布日期:2026-08-03
作者简介:朱本然，男，2001年出生。主要研究方向为数字孪生与智能运维。E-mail:zhubenran@sjtu.edu.cn
潮群(通信作者)，男，1990年出生，博士，副教授，博士研究生导师。主要研究方向为高性能液压元件设计与电液驱控技术、重大电液装备健康管理、复杂机电液系统数字孪生技术。E-mail:chaoqun@sjtu.edu.cn
基金资助:
高端装备机械传动全国重点实验室开放基金资助项目(SKLMT-MSKFKT-202413)。

Online Monitoring Technology for Gear Transmission Systems Driven by Digital Twin under Edge-Cloud Collaboration

ZHU Benran^1,2, CHAO Qun^1,2, WANG Zhongrui^1,2, LIU Chengliang¹

1. School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240;
2. State Key Laboratory of Mechanical Transmission for Advanced Equipment, Chongqing University, Chongqing 400044

Received:2025-06-13 Revised:2025-09-30 Published:2026-08-03

摘要/Abstract

摘要： 齿轮传动系统在高端装备中应用广泛，其结构性能传统评估方法依赖离线有限元仿真，计算耗时较长，难以满足在线监测的高时效性要求。为此，提出一种边云协同的数字孪生在线监测技术。构建由物理层、边缘层、云层和通信层组成的数字孪生总体框架，并明确各层功能与技术路线；针对有限元模型的非结构化网格拓扑，设计一种基于图神经网络的代理模型，用于齿轮传动系统结构性能快速预测；搭建齿轮传动试验台在线监测平台，在边云协同框架下完成状态信号采集、结构性能预测与云端可视化渲染全流程，验证所提技术的可行性。结果表明，设计的代理模型预测结果与离线有限元仿真结果的吻合度超过90%，在线监测全流程响应时间小于4 s，能够精确、快速监测齿轮传动系统核心部件的全域结构性能，为高端装备的实时状态监测提供了可行的新途径。

关键词: 齿轮传动系统, 在线监测, 数字孪生, 边云协同, 图网络

Abstract: Conventional evaluation methods of structural performance in gear-transmission systems rely on offline finite-element analysis, which is time-consuming and cannot satisfy the timeliness requirements of online condition monitoring in high-end equipment. To overcome this limitation, an edge-cloud collaborative digital-twin technique is proposed for online condition monitoring. A digital-twin framework containing physical, edge, cloud, and communication layers is established with clearly defined function and road-map of each layer. A graph neural network-based surrogate model is developed to rapidly predict structural performance, addressing the unstructured mesh topology of finite-element models. An online condition monitoring platform is implemented on a gear transmission test bench, integrating real-time signal acquisition, structural prediction, and cloud-based visualization. Results demonstrate that the surrogate model achieves more than 90% consistency with offline finite-element analyses with a total response time within 4 s, enabling a rapid and accurate structure monitoring of core components in gear transmission systems, and providing a feasible new approach for real-time condition monitoring of high-end equipment.

Key words: gear transmission system, online monitoring, digital twin, edge-cloud collaboration, graph network

中图分类号:

TH132
TP391

朱本然, 潮群, 王忠睿, 刘成良. 边云协同下数字孪生驱动的齿轮传动系统在线监测技术[J]. 机械工程学报, 2026, 62(12): 87-97.

ZHU Benran, CHAO Qun, WANG Zhongrui, LIU Chengliang. Online Monitoring Technology for Gear Transmission Systems Driven by Digital Twin under Edge-Cloud Collaboration[J]. Journal of Mechanical Engineering, 2026, 62(12): 87-97.

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.260559

http://www.cjmenet.com.cn/CN/Y2026/V62/I12/87

参考文献

[1] 董怀玉，何立东，贾兴运，等. 齿轮箱箱体高精度模态识别方法研究及结构优化设计[J]. 机械传动，2023，47(9):31-36. DONG Huaiyu，HE Lidong，JIA Xingyun，et al. Research on high precision modal identification method and structural optimization design of gearboxes[J]. Journal of Mechanical Transmission，2023，47(9):31-36.
[2] 唐进元，刘艳平. 直齿面齿轮加载啮合有限元仿真分析[J]. 机械工程学报，2012，48(5):124-131. TANG Jinyuan，LIU Yanping. Loaded meshing simulation of face-gear drive with spur involute pinion based on finite element analysis[J]. Journal of Mechanical Engineering，2012，48(5):124-131.
[3] SALAMEH J P，CAUET S，ETIEN E，et al. Gearbox condition monitoring in wind turbines:A review[J]. Mechanical Systems and Signal Processing，2018，111:251-264.
[4] FENG K，JI J C，NI Q，et al. A review of vibration-based gear wear monitoring and prediction techniques[J]. Mechanical Systems and Signal Processing，2023，182:109605.
[5] 陶飞，刘蔚然，刘检华，等. 数字孪生及其应用探索[J]. 计算机集成制造系统，2018，24(1):1-18. TAO Fei，LIU Weiran，LIU Jianhua，et al. Digital twin and its potential application exploration[J]. Computer Integrated Manufacturing Systems，2018，24(1):1-18.
[6] 陶飞，刘蔚然，张萌，等. 数字孪生五维模型及十大领域应用[J]. 计算机集成制造系统，2019，25(1):1-18. TAO Fei，LIU Weiran，ZHANG Meng，et al. Five-dimension digital twin model and its ten applications[J]. Computer Integrated Manufacturing Systems，2019，25(1):1-18.
[7] 石健，刘冬，王少萍. 基于数字孪生的机电液系统PHM关键技术综述[J]. 机械工程学报，2024，60(4):66-81. SHI Jian，LIU Dong，WANG Shaoping. Digital twin for complex electromechanical-hydraulic system PHM:A review[J]. Journal of Mechanical Engineering，2024，60(4):66-81.
[8] 唐贤炬，胡志安，佘亦曦，等. 数字孪生驱动的齿轮传动系统振动状态监测方法[J/OL]. 机械传动:1-8[2025-04-18]. http://kns.cnki.net/kcms/detail/41.1129.TH.20250113.1503.002.html. TANG Xianju，HU Zhian，SHE Yixi，et al. Digital twin-driven vibration state monitoring method for gear transmission systems[J/OL]. Journal of Mechanical Transmission:1-8[2025-04-18]. http://kns.cnki.net/kcms/detail/41.1129.TH.20250113.1503.002.html.
[9] MOGHADAM F K，NEJAD A R. Online condition monitoring of floating wind turbines drivetrain by means of digital twin[J]. Mechanical Systems and Signal Processing，2022，162:108087.
[10] FENG K，JI J C，ZHANG Y，et al. Digital twin-driven intelligent assessment of gear surface degradation[J]. Mechanical Systems and Signal Processing，2023，186: 109896.
[11] 宋学官，来孝楠，何西旺，等. 重大装备形性一体化数字孪生关键技术[J]. 机械工程学报，2022，58(10):298–325. SONG Xueguan，LAI Xiaonan，HE Xiwang，et al. Key technologies of shape-performance integrated digital twin for major equipment[J]. Journal of Mechanical Engineering，2022，58(10):298-325.
[12] 袁美霞，谢晓瑄，马利平. 基于结构与性能结合的数字孪生研究进展[J]. 科学技术与工程，2024，24(27):11505-11518. YUAN Meixia，XIE Xiaoxuan，MA Liping. Review of digital twin based on the combination of shape and performance[J]. Science Technology & Engineering，2024，24(27):11505-11518.
[13] LAI X，HE X，WANG S，et al. Building a lightweight digital twin of a crane boom for structural safety monitoring based on a multifidelity surrogate model[J]. Journal of Mechanical Design. 2022，144(6):021701.
[14] LAI X，HE X，PANG Y，et al. A scalable digital twin framework based on a novel adaptive ensemble surrogate model[J]. Journal of Mechanical Design，2023，145(2):021701.
[15] 李梦龙. 基于数字孪生的桁架机械手运维系统关键技术研究[D]. 太原:中北大学，2024. LI Menglong. Research on key technology of operation and maintenance system of truss manipulator based on digital twin[D]. Taiyuan:North University of China，2024.
[16] ZHANG J，WAN C，WANG J，et al. Research on the“shape-performance-control”integrated digital twin system for boom-type roadheaders[J]. Scientific Reports，2024，14(1):5780.
[17] WU J，DU C，DILLENBURGER B，et al. Fast prediction of stress distribution:A GNN-based surrogate model for unstructured mesh FEA[C]//Proceedings of the IASS 2024 Symposium:Redefining the Art of Structural Design. International Association for Shell and Spatial Structures，2024.
[18] GLADSTONE R J，RAHMANI H，SURYAKUMAR V，et al. Mesh-based GNN surrogates for time-independent PDEs[J]. Scientific Reports，2024，14(1):3394.
[19] GULAKARA R，MARKERT B，STOFFEL M. Graph neural network enhanced finite element modelling[J]. PAMM，2023，22(1):e202200306.
[20] MOU S，BU K，REN S，et al. Digital twin modeling for stress prediction of single-crystal turbine blades based on graph convolutional network[J]. Journal of Manufacturing Processes，2024，116:210-223.
[21] VO T，DAVE P，BAJPAI G，et al. Edge，fog，and cloud computin:An overview on challenges and applications[J]. arXiv preprint:2211.01863，2022.
[22] LI Z，FEI F，ZHANG G. Edge-to-cloud IIoT for condition monitoring in manufacturing systems with ubiquitous smart sensors[J]. Sensors，2022，22(15):5901.
[23] REAÑO C，RIERA J V，ROMERO V，et al. A cloud-edge computing architecture for monitoring protective equipment[J]. Journal of Cloud Computing，2024，13:82.

边云协同下数字孪生驱动的齿轮传动系统在线监测技术

Online Monitoring Technology for Gear Transmission Systems Driven by Digital Twin under Edge-Cloud Collaboration

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	杨毅晟, 李明, 杨泽源, 闫喜强, 严思杰, 丁汉. 数字技术赋能风洞全生命周期体系[J]. 机械工程学报, 2026, 62(7): 97-113.
[2]	王金龙, 宣泳辉, 冀秀坤, 鲍永杰, 石泽宇. 基于单向降阶高保真代理模型的CFRP机翼力学状态数字孪生研究[J]. 机械工程学报, 2026, 62(7): 126-138.
[3]	罗忠, 李洪雨, 李雷, 董胤哲. 数字孪生驱动的转子系统变工况难测点响应实时预测方法[J]. 机械工程学报, 2026, 62(7): 221-233.
[4]	杨泽浩, 董威, 黄思翰, 阴艳超, 董李扬, 郑祖杰. 基于数字孪生和强化学习的智能生产线实时调度仿真优化方法[J]. 机械工程学报, 2026, 62(5): 12-25.
[5]	许鸿伟, 刘丽兰, 张洁, 秦威, 邢宏文, 汪玮, 刘思仁, 吕佑龙. 工业大模型驱动的航空智能制造AI孪生控制方法体系[J]. 机械工程学报, 2026, 62(5): 61-73.
[6]	吴锦辉, 陈永昶, 吴亚男, 郝会乾, 袁翔, 陶友瑞. 数字孪生驱动的反射面天线运行状态监测与虚拟调试方法[J]. 机械工程学报, 2026, 62(5): 263-273.
[7]	杨亮亮, 龚壮壮, 何西旺, 王沐晨, 闵强, 阚子云, 宋学官. 面向结构损伤识别的数字孪生建模[J]. 机械工程学报, 2026, 62(4): 328-341.
[8]	李雨露, 李俊峰, 万章艺, 魏正英. 基于YOLO算法的激光粉末床熔融成形层形貌分类识别与成形质量预测研究[J]. 机械工程学报, 2026, 62(3): 218-234.
[9]	刘素艳, 董一林, 乔一鸣, 马增强. 基于改进蜣螂优化算法的轴承数字孪生模型的动态故障注入研究[J]. 机械工程学报, 2026, 62(3): 446-457.
[10]	王世博, 葛世荣, 管增伦, 周士林, 王丽杰, 李雪峰, 王赟, 袁晓明, 马广军. 面向数字孪生的采煤机滚筒实时截割载荷模型研究[J]. 机械工程学报, 2026, 62(3): 479-491.
[11]	刘海波, 邓平, 迟庆宇, 刘天然, 刘阔, 李特, 黄祖广, 刘行健, 薄其乐, STEVEN Y LIANG, 王永青. 智能加工中数据使能技术与应用[J]. 机械工程学报, 2026, 62(2): 407-444.
[12]	冯珂, 张紫琳, 倪清, 杨彬, 胡亚安, 孟理华, 雷亚国. 认知数字孪生赋能航空装备：新范式与研究前沿[J]. 机械工程学报, 2026, 62(12): 1-21.
[13]	胡文扬, 李奇, 林起鉴, 王天杨, 阎绍泽, 褚福磊. 面向旋转机械健康监测和早期故障检测的Diffusion-Ramanujan数字孪生架构[J]. 机械工程学报, 2026, 62(12): 77-86.
[14]	李孝斌, 黄文明, 江沛, 尹超, 曹华军. 数字孪生驱动的承压设备设计制造运维跨阶段数据集成方法[J]. 机械工程学报, 2026, 62(11): 48-60.
[15]	杨振, 李健, 赵柯枫, 陈志成, 胡正, 邱勋林, 项延训. 基于CCBT压电陶瓷换能器的高温长时在线超声监测[J]. 机械工程学报, 2026, 62(10): 83-92.