基于数据融合与增强图卷积的装备系统级智能故障诊断方法

孔运; 张洁; 吕宇璠; 祁俊辉; 陈科; 董明明; 刘辉; 褚福磊

doi:10.12382/bgxb.2025.0588

您当前的位置：

首页 >

文章列表页 >

基于数据融合与增强图卷积的装备系统级智能故障诊断方法

更新时间：2026-05-06

- 基于数据融合与增强图卷积的装备系统级智能故障诊断方法
- Equipment System-level Intelligent Fault Diagnosis Method Based on Data Fusion and Enhanced Graph Convolution
- 兵工学报 2026年47卷第4期页码：250588
- 作者机构：
  
  北京理工大学机械与车辆学院，北京 100081
  北京理工大学唐山研究院，河北唐山 063015
  重庆大学高端装备机械传动全国重点实验室，重庆 400044
  内蒙古第一机械集团股份有限公司，内蒙古包头 014032
  清华大学机械工程系，北京 100084
- 作者简介：
  
  通信作者邮箱：kongyun@bit.edu.cn;
  通信作者邮箱：chenke@bit.edu.cn
- 基金信息：
  
  国家自然科学基金项目(52575094;52105108);北京市自然科学基金项目(3252008);中国科协青年人才托举工程项目(2023QNRC001);河北省自然科学基金面上项目(E2023105039);北京市科协青年人才托举工程项目(BYESS2024294);高端装备机械传动全国重点实验室开放基金项目(SKLMT-MSKFKT-202304)
- DOI：10.12382/bgxb.2025.0588
  中图分类号： TH17
- 收稿：2025-07-01，
  
  网络首发：2025-12-25，
  
  纸质出版：2026-04
- 稿件说明：
移动端阅览
孔运, 张洁, 吕宇璠, 等. 基于数据融合与增强图卷积的装备系统级智能故障诊断方法[J]. 兵工学报, 2026,47(4):250588.

KONG Yun, ZHANG Jie, LÜ Yufan, et al. Equipment System-level Intelligent Fault Diagnosis Method Based on Data Fusion and Enhanced Graph Convolution[J]. Acta Armamentarii, 2026, 47(4): 250588.
孔运, 张洁, 吕宇璠, 等. 基于数据融合与增强图卷积的装备系统级智能故障诊断方法[J]. 兵工学报, 2026,47(4):250588. DOI： 10.12382/bgxb.2025.0588.

KONG Yun, ZHANG Jie, LÜ Yufan, et al. Equipment System-level Intelligent Fault Diagnosis Method Based on Data Fusion and Enhanced Graph Convolution[J]. Acta Armamentarii, 2026, 47(4): 250588. DOI： 10.12382/bgxb.2025.0588.

摘要

针对现有部件级诊断方法无法捕捉复杂装备多部件间的故障耦合关系，易导致装备系统级故障诊断出现特征混淆、误判等问题，提出一种基于数据融合与增强图卷积的装备系统级智能故障诊断方法。通过计算各通道信号的信息熵值，采用自适应分配权重策略，实现多通道数据级信息融合。为每个部件构建独立的卷积神经网络以获取节点属性特征，构建反映装备系统级真实物理结构的空间拓扑关系图作为先验知识，设计增强图卷积核，建模部件间的故障耦合关系。将各部件的系统级关联特征输入各部件的诊断分类器，实现装备系统级智能故障诊断。采用列车转向架传动系统数据集进行实验验证，实验结果表明：所提方法在电机、齿轮箱、左轴箱与右轴箱4个部件上均获得了100%的优异诊断精度，优于现有前沿对比方法，验证了所提方法实现装备系统级故障诊断的优越性能。

Abstract

The existing component-level fault diagnosis methods fail to capture the fault coupling relationships between multiple components

leading to feature confusion and misjudgment in system-level fault diagnosis. This paper proposes a system-level fault diagnosis method for equipment based on data fusion and enhanced graph convolution. First

the information entropy values of each channel signal are calculated

and the multi-channel data-level information fusion is realized using an daptive weight allocation strategy. Second

an independent convolutional neural network (CNN) is constructed for each component to obtain node attribute features. Then

a spatial topological relationship graph that reflects the real physical structure of the equipment system level is constructed as a priori knowledge

and an enhanced graph convolution (EGC) kernel is designed to model the fault coupling relationship between components. Finally

the system-level association features of each component are input into the diagnostic classifiers of each component to achieve system-level fault diagnosis. Experiments using a train bogie transmission system dataset for verification show that the proposed method achieves 100% diagnostic accuracy for all four components of the driving motor

gearbox

left axlebox

and right axlebox. It outperforms other fault diagnosis methods

verifying the superior performance of the proposed method to realize system-level fault diagnosis of equipment.

关键词

Keywords

references

崔素晓，武哲，崔彦平，等.基于频率切片小波变换和注意力增强ConvNeXt模型的行星齿轮箱故障诊断[J].兵工学报，2025，46（2）：240329.

CUI S X, WU Z, CUI Y P, et al. Fault diagnosis of planetary gearbox based on frequency slice wavelet transform and attentionenhanced ConvNeXt model [J]. Acta Armamentarii, 2025, 46 (2): 240329. (in Chinese)

郭一鸣，童一飞，何非，等.基于多通道数据双层增强的样本不平衡故障诊断方法[J].兵工学报，2025，46（2）：240012.

GUO Y M, TONG Y F, HE F, et al. Sample imbalanced fault diagnosis method based on multi-channel data double augmentation [J]. Acta Armamentarii, 2025, 46 (2): 240012. (in Chinese)

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 Y G, JIA F, KONG D T, 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)

ZHANG J, KONG Y, HAN Q K, et al. Multimodal data imputation and fusion for trustworthy fault diagnosis of mechanical systems [J]. Engineering Applications of Artificial Intelligence, 2025, 150:110663.

ZHANG J, KONG Y, CHEN Z Y, et al. CBAM-CRLSGAN:a novel fault diagnosis method for planetary transmission systems under small samples scenarios [J]. Measurement, 2024, 234:114795.

XU Z B, LEE C K M, WONG C N. A novel fault diagnosis method based on deep stable learning for bearings with imbalanced data samples [J]. Expert Systems with Applications, 2025, 281:127634.

DONG Y T, JIANG H K, JIANG W X, et al. Dynamic normalization supervised contrastive network with multiscale compound attention mechanism for gearbox imbalanced fault diagnosis [J]. Engineering Applications of Artificial Intelligence, 2024, 133:108098.

FU Z Y, LIU Z, PING S R, et al. TRA-ACGAN:a motor bearing fault diagnosis model based on an auxiliary classifier generative adversarial network and transformer network [J]. ISA Transactions, 2024, 149:381-393.

ZHANG S, LIU Z W, CHEN Y P, et al. Selective kernel convolution deep residual network based on channel-spatial attention mechanism and feature fusion for mechanical fault diagnosis [J]. ISA Transactions, 2023, 133:369-383.

YAN S, SHAO H D, WANG X D, et al. Few-shot classincremental learning for system-level fault diagnosis of wind turbine [J]. IEEE/ASME Transactions on Mechatronics, 2024, Early Access:1-10.

DING A, QIN Y, WANG B, et al. Evolvable graph neural network for system-level incremental fault diagnosis of train transmission systems [J]. Mechanical Systems and Signal Processing, 2024, 210:111175.

XU W H, YUAN K H, LI W T, et al. An emerging fuzzy feature selection method using composite entropy-based uncertainty measure and data distribution [J]. IEEE Transactions on Emerging Topics in Computational Intelligence, 2022, 7 (1): 76-88.

SHEN C X, ZHANG H Y, MENG S P, et al. Augmented data driven self-attention deep learning method for imbalanced fault diagnosis of the HVAC chiller [J]. Engineering Applications of Artificial Intelligence, 2023, 117:105540.

SHANG Z W, ZHANG J, LI W X, et al. A novel small samples fault diagnosis method based on the self-attention Wasserstein generative adversarial network [J]. Neural Processing Letters, 2023, 55 (5): 6377-6407.

CUI L, TIAN X C, WEI Q Z, et al. A self-attention based contrastive learning method for bearing fault diagnosis [J]. Expert Systems with Applications, 2024, 238:121645.

DING A, QIN Y, WANG B, et al. Brownian distance covariancebased few-shot learning framework considering noisy labels for fault diagnosis of train transmission systems [J].IEEE Transactions on Industrial Informatics, 2025, 21 (1): 136-145.

WANG N, JIA L M, QIN Y, et al. Dual-stage manifold preserving mixed supervised learning for bogie fault diagnosis under variable conditions [J]. Engineering Applications of Artificial Intelligence, 2025, 149:110512.

QIN Y, WANG Y R, LI Z S, et al. An in-depth tutorial on BJTU-RAO bogie datasets for fault diagnosis [J]. IEEE Access, 2025, 13:60879-60888.

CAI T T, MA R. Theoretical foundations of t-SNE for visualizing high-dimensional clustered data [J]. Journal of Machine Learning Research, 2022, 23 (301): 1-54.

GOVE R, CADALZO L, LEIBY N, et al. New guidance for using t-SNE:alternative defaults, hyperparameter selection automation, and comparative evaluation [J]. Visual Informatics, 2022, 6 (2): 87-97.

浏览量

下载量

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

长期贮存装备组件补充方案评估及确定方法

基于数据融合的无人机自主择址技术

增材制造技术在美海军装备维修保障方面的应用分析研究