Cross-device fault diagnosis method based on graph convolution and multi-sensor fusion

SUN Yuanshuai; KONG Fanqin; NIE Xiaoyin; XIE Gang

doi:10.16579/j.issn.1001.9669.2026.02.003

您当前的位置：

首页 >

文章列表页 >

Cross-device fault diagnosis method based on graph convolution and multi-sensor fusion

·Vibration·Noise·Monitoring·Diagnosis· | 更新时间：2026-02-12

- Cross-device fault diagnosis method based on graph convolution and multi-sensor fusion
- Journal of Mechanical Strength Vol. 48, Issue 2, Pages: 21-30(2026)
- 作者机构：
  
  1.太原科技大学电子信息工程学院，太原 030024
  2.先进控制与工业智能山西省重点实验室，太原 030024
- 作者简介：
  
  XIE Gang, E-mail: xiegang@tyust.edu.cn
- 基金信息：
  
  Major Science and Technology Project of Shanxi Province(202201090301013);Key Research and Development Plan of Shanxi Province(202102020101002;202202100401002;202202150401005);Basic Research Plan General Program of Shanxi Province(20210302123206;202203021211194;202203021221142;202203021222186)
- DOI：10.16579/j.issn.1001.9669.2026.02.003
  CLC： TP277
- Received：05 May 2024，
  
  Published：15 February 2026
- 稿件说明：
移动端阅览
孙元帅，孔繁钦，聂晓音，等. 基于图卷积和多传感融合的跨设备故障诊断方法［J］. 机械强度，2026，48（2）：21-30.

SUN Yuanshuai，KONG Fanqin，NIE Xiaoyin，et al. Cross-device fault diagnosis method based on graph convolution and multi-sensor fusion［J］. Journal of Mechanical Strength，2026，48（2）：21-30.
孙元帅，孔繁钦，聂晓音，等. 基于图卷积和多传感融合的跨设备故障诊断方法［J］. 机械强度，2026，48（2）：21-30. DOI： 10.16579/j.issn.1001.9669.2026.02.003.

SUN Yuanshuai，KONG Fanqin，NIE Xiaoyin，et al. Cross-device fault diagnosis method based on graph convolution and multi-sensor fusion［J］. Journal of Mechanical Strength，2026，48（2）：21-30. DOI： 10.16579/j.issn.1001.9669.2026.02.003.

摘要

目的

针对实际生产中机械设备的标记故障数据获取困难、跨设备数据概率分布不同导致诊断准确率低的问题，提出一种基于图卷积和多传感融合的跨设备故障诊断方法——卷积域图卷积网络（Convolutional Domain Graph Convolution Network

CDGCN），实现对类标签、域标签和数据特征结构的统一建模。

方法

首先，利用卷积神经网络从原始信号中提取初步特征；其次，通过图生成层挖掘样本间的特征结构关系，构建实例图，并利用多感受野图卷积网络（Multi-Receptive Field Graph Convolutional Network

MRF-GCN）进行建模，提取更具表达力的节点特征；同时，提出一种高层特征融合方式实现多传感器信息集成；最后，令最大均值差异度量、分类器与域判别器协同工作，通过极小极大博弈实现域自适应（Domain Adaptation

DA）。

结果

试验结果表明，CDGCN的平均准确率达到75.33%，相较于域对抗迁移网络（Domain-Adversarial Neural Network

DANN）、条件对抗域自适应网络（Conditional Domain Adversarial Network

CDAN）、联合自适应网络（Joint Adaptation Network

JAN）、深度自适应网络（Deep Adaptation Network

DAN）方法分别提升了29.23、30.35、15.20、12.70百分点。消融试验证明了多感受野特征提取、数据特征结构建模以及多传感器信息融合对提升迁移诊断精度的有效性。

Abstract

Objective

To address the problems of difficulty in obtaining labeled fault data for mechanical equipment and low diagnosis accuracy caused by different probability distributions of cross-device data in actual production

a cross-device fault diagnosis method based on graph convolution and multi-sensor fusion

named convolutional domain graph convolution network (CDGCN)

is proposed

realizing the unified modeling of class labels

domain labels

and data feature structures.

Methods

Firstly

a convolutional neural network (CNN) was utilized to extract preliminary features from raw signals. Secondly

an instance graph was constructed by mining the feature structural relations among samples through a graph generation layer

and a multi-receptive field graph convolutional network (MRF-GCN) was employed for modeling to extract more expressive node features. Meanwhile

a high-level feature fusion method was proposed to achieve multi-sensor information integration. Finally

let the maximum mean discrepancy (MMD) metric

the classifier and the domain discriminator work synergistically to achieve domain adaptation (DA) through a minimax game.

Results

Test results show that the average accuracy of CDGCN reaches 75.33%

which is improved by 29.23

30.35

15.20 and 12.70 percentage points compared with the domain-adversarial neural network (DANN)

conditional domain adversarial network (CDAN)

joint adaptation network (JAN)

and deep adaptation network (DAN) method

respectively. Ablation test verifies the effectiveness of multi-receptive field feature extraction

data feature structure modeling

and multi-sensor information fusion in improving transfer diagnosis accuracy.

关键词

Keywords

references

LEI Y G ， YANG B ， JIANG X W ， et al . Applications of machine learning to machine fault diagnosis：a review and roadmap ［J］. Mechanical Systems and Signal Processing ， 2020 ， 138 ： 106587 .

雷亚国，许学方，蔡潇，等 . 面向机械装备健康监测的数据质量保障方法研究［J］. 机械工程学报， 2021 ， 57 （ 4 ）： 1 - 9 .

LEI Yaguo ， XU Xuefang ， CAI Xiao ， et al . Research on data quality assurance for health condition monitoring of machinery ［J］. Journal of Mechanical Engineering ， 2021 ， 57 （ 4 ）： 1 - 9 . （In Chinese）

WANG T Y ， HAN Q K ， CHU F L ， et al . Vibration based condition monitoring and fault diagnosis of wind turbine planetary gearbox：a review ［J］. Mechanical Systems and Signal Processing ， 2019 ， 126 ： 662 - 685 .

MA M ， MAO Z . Deep-convolution-based LSTM network for remaining useful life prediction ［J］. IEEE Transactions on Industrial Informatics ， 2021 ， 17 （ 3 ）： 1658 - 1667 .

雷亚国，贾峰，孔德同，等 . 大数据下机械智能故障诊断的机遇与挑战［J］. 机械工程学报， 2018 ， 54 （ 5 ）： 94 - 104 .

LEI Yaguo ， JIA Feng ， KONG Detong ， et al . Opportunities and challenges of machinery intelligent fault diagnosis in big data era ［J］. Journal of Mechanical Engineering ， 2018 ， 54 （ 5 ）： 94 - 104 . （In Chinese）

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 .

HOANG D T ， KANG H J . A survey on Deep Learning based bearing fault diagnosis ［J］. Neurocomputing ， 2019 ， 335 ： 327 - 335 .

LEI Y G ， LI N P ， GUO L ， et al . Machinery health prognostics：a systematic review from data acquisition to RUL prediction ［J］. Mechanical Systems and Signal Processing ， 2018 ， 104 ： 799 - 834 .

王廷轩，王贵勇，刘韬，等 . 域适应网络与平衡动态分布自适应的轴承变工况故障迁移诊断研究［J］. 机械强度， 2023 ， 45 （ 3 ）： 509 - 518 .

WANG Tingxuan ， WANG Guiyong ， LIU Tao ， et al . Study of domain adaptive network and balanced dynamic distribution adaptive fault migration diagnosis of bearing under variable conditions ［J］. Journal of Mechanical Strength ， 2023 ， 45 （ 3 ）： 509 - 518 . （In Chinese）

ZHANG S Y ， SU L ， GU J F ， et al . Rotating machinery fault detection and diagnosis based on deep domain adaptation：a survey ［J］. Chinese Journal of Aeronautics ， 2023 ， 36 （ 1 ）： 45 - 74 .

YANG B ， LEI Y G ， JIA F ， et al . A polynomial kernel induced distance metric to improve deep transfer learning for fault diagnosis of machines ［J］. IEEE Transactions on Industrial Electronics ， 2020 ， 67 （ 11 ）： 9747 - 9757 .

XU K ， LI S M ， JIANG X X ， et al . A renewable fusion fault diagnosis network for the variable speed conditions under unbalanced samples ［J］. Neurocomputing ， 2020 ， 379 ： 12 - 29 .

吴定海，王怀光，宋彬，等 . 一种基于对称极坐标优化的轴承深度迁移诊断方法［J］. 机械强度， 2022 ， 44 （ 3 ）： 541 - 546 .

WU Dinghai ， WANG Huaiguang ， SONG Bin ， et al . A bearing deep learning transfer diagnosis method based on optimization of symmetric polar coordinates ［J］. Journal of Mechanical Strength ， 2022 ， 44 （ 3 ）： 541 - 546 . （In Chinese）

池福临，杨新宇，邵思羽，等 . 基于深度收缩残差网络的轴承变工况故障诊断［J］. 计算机集成制造系统， 2023 ， 29 （ 4 ）： 1146 - 1156 .

CHI Fulin ， YANG Xinyu ， SHAO Siyu ， et al . Bearing fault diagnosis under variable working conditions based on deep residual shrinkage networks ［J］. Computer Integrated Manufacturing Systems ， 2023 ， 29 （ 4 ）： 1146 - 1156 . （In Chinese）

SHAO H D ， XIA M ， HAN G J ， et al . Intelligent fault diagnosis of rotor-bearing system under varying working conditions with modified transfer convolutional neural network and thermal images ［J］. IEEE Transactions on Industrial Informatics ， 2021 ， 17 （ 5 ）： 3488 - 3496 .

XING S B ， LEI Y G ， WANG S H ， et al . Distribution-invariant deep belief network for intelligent fault diagnosis of machines under new working conditions ［J］. IEEE Transactions on Industrial Electronics ， 2021 ， 68 （ 3 ）： 2617 - 2625 .

YANG C Y ， LIU J ， ZHOU K B ， et al . Transferable graph features-driven cross-domain rotating machinery fault diagnosis ［J］. Knowledge-Based Systems ， 2022 ， 250 ： 109069 .

YANG B ， LEI Y G ， JIA F ， et al . An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings ［J］. Mechanical Systems and Signal Processing ， 2019 ， 122 ： 692 - 706 .

LÜ M Z ， LIU S X ， SU X M ， et al . Deep transfer network with multi-kernel dynamic distribution adaptation for cross-machine fault diagnosis ［J］. IEEE Access ， 2021 ， 9 ： 16392 - 16409 .

WU Z Q ， CHEN H L ， HAN J ， et al . Graph mutual mapping transfer networks for machine fault diagnosis ［J］. IEEE Transactions on Industrial Informatics ， 2024 ， 20 （ 1 ）： 995 - 1006 .

WANG L ， CAO H R ， XU H ， et al . A gated graph convolutional network with multi-sensor signals for remaining useful life prediction ［J］. Knowledge-Based Systems ， 2022 ， 252 ： 109340 .

DEFFERRARD M ， BRESSON X ， VANDERGHEYNST P . Convolutional neural networks on graphs with fast localized spectral filtering ［C］// Proceedings of the 30th Conference on Neural Information Processing Systems （NIPS 2016） . Barcelona ： Curran Associates Inc. ， 2016 ： 3844 - 3852 .

LI T F ， ZHOU Z ， LI S N ， et al . The emerging graph neural networks for intelligent fault diagnostics and prognostics：a guideline and a benchmark study ［J］. Mechanical Systems and Signal Processing ， 2022 ， 168 ： 108653 .

LI T F ， ZHAO Z B ， SUN C ， et al . Multireceptive field graph convolutional networks for machine fault diagnosis ［J］. IEEE Transactions on Industrial Electronics ， 2021 ， 68 （ 12 ）： 12739 - 12749 .

AL SHALABI L ， SHAABAN Z ， KASASBEH B . Data mining：a preprocessing engine ［J］. Journal of Computer Science ， 2006 ， 2 （ 9 ）： 735 - 739 .

Views

132

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Gearbox fault diagnosis method based on multi-sensor data fusion and GAN

FAULT DIAGNOSIS OF GEARBOX UNDER VARIABLE WORKING CONDITION BASED ON WEIGHTED SUBDOMAIN ADAPTIVE ADVERSARIAL NETWORK

Research on fault diagnosis of rotating machinery based on deep learning and SMOTE data enhancement

APPLICATION RESEARCH ON FAULT DIAGNOSIS OF DOUBLE FED WIND TURBINE BEARINGS BASED ON IMPROVED GENERATIVE ADVERSARIAL NETWORKS

Recognition of human tumbles based on improved normalized inertia moment

Related Author

SUN Yuanshuai

KONG Fanqin

NIE Xiaoyin

XIE Gang

YANG Xingyu

SONG Chunsheng

WU Xiaoyang

ZHANG Huiyun

Related Institution

Shanxi Key Laboratory Of Advanced Control and Industrial Intelligence

School of Mechanical and Electrical Engineering, Wuhan University of Technology

School of Intelligent Manufacturing, Chengdu Technological University

College of Mechanical Engineering, Sichuan University

Business School, University of Shanghai for Science and Technology

⁰