The data-driven multi-sensor graph neural network (GNN) method is one of the key technologies for rotating machinery fault diagnosis. This paper innovatively proposes a selective and cooperative serial expansion GNN method for fault diagnosis. It aims to address two key challenges in multi-sensor scenarios: the inherent limitations of the message-passing mechanism in the existing GNN-based fault diagnosis methods, and the dynamic node variations caused by sensor malfunction. For the periodic characteristics presented by the vibration time-series signal of the sensor nodes, this study proposes a series expansion graph network architecture based on Fourier theory, which can effectively enhance the model’s capability in capturing the periodic fault features. Meanwhile, a selective and cooperative strategy is proposed to address the key issues of static data fusion in GNN and the dynamic change of the effective number of sensors. This strategy utilizes a behavior network to determine each sensor node’s behavior status during message-passing and introduces a node selection network to evaluate sensor reliability. The message-passing network realizes dynamic cooperative feature fusion based on the nodes’ behavioral status and reliability information obtained above. Finally, a selective and cooperative Fourier series expansion graph fault diagnosis method with excellent adaptivity and robustness is proposed. The two experimental cases show that the proposed method has a diagnostic accuracy rate of 99%, even under variable rotational speed conditions. More importantly, it can achieve self-adaptation in the event of sensor node failure and maintain a diagnostic accuracy rate of at least 90%.
ZhangYJiJCRenZ, et al. Digital twin-driven partial domain adaptation network for intelligent fault diagnosis of rolling bearing. Reliab Eng Syst Saf2023; 234: 109186.
2.
LiuXChenYXiongL, et al. Intelligent fault diagnosis methods toward gas turbine: a review. Chin J Aeronaut2024; 37: 93–120.
3.
JinYHouLChenY.A Time Series Transformer based method for the rotating machinery fault diagnosis. Neurocomputing2022; 494: 379–395.
4.
XiongYLiuZTanJ, et al. Multi-scale adaptive-routing capsule contrastive network-based intelligent fault diagnosis method for rotating machinery under noisy environment and labels. Adv Eng Inform2024; 62: 102712.
5.
LiXWangYYaoJ, et al. Multi-sensor fusion fault diagnosis method of wind turbine bearing based on adaptive convergent viewable neural networks. Reliab Eng Syst Saf2024; 245: 109980.
6.
ZhouKYangCLiuJ, et al. Deep graph feature learning-based diagnosis approach for rotating machinery using multi-sensor data. J Intell Manuf2023; 34: 1965–1974.
7.
ZhangXWangHWangC, et al. Time-segment-wise feature fusion transformer for multi-modal fault diagnosis. Eng Appl Artif Intell2024; 138: 109358.
8.
ZarchiMShahgholiM.An expert condition monitoring system via fusion of signal processing for vibration of industrial rotating machinery with unseen operational conditions. J Vib Eng Technol2023; 11: 2267–2295.
9.
ZarchiMShahgholiM.A novel information fusion approach using weighted neural networks for intelligent multi-class diagnostics of rotating machinery with unseen working conditions. J Vib Control2023; 29: 5545–5562.
10.
ZhangXShengCOuyangW, et al. Fault diagnosis of marine electric thruster bearing based on fusing multi-sensor deep learning models. Measurement2023; 214: 112727.
11.
WangXMaoDLiX.Bearing fault diagnosis based on vibro-acoustic data fusion and 1D-CNN network. Measurement2021; 173: 108518.
12.
Mohammad-AlikhaniANahid-MobarakehBHsiehMF.One-dimensional LSTM-regulated deep residual network for data-driven fault detection in electric machines. IEEE Trans Ind Electron2024; 71: 3083–3092.
13.
JuniorRFRAreiasIAdosSCamposMM, et al. Fault detection and diagnosis in electric motors using 1d convolutional neural networks with multi-channel vibration signals. Measurement2022; 190: 110759.
14.
ZhouJCuiGHuS, et al. Graph neural networks: a review of methods and applications. AI Open2020; 1: 57–81.
15.
ZhouQXueLHeJ, et al. A rotating machinery fault diagnosis method based on dynamic graph convolution network and hard threshold denoising. Sensors2024; 24: 4887.
16.
YinASunZZhouJ.Hypergraph construction using multi-sensor for helicopter tail-drive system fault diagnosis. Measurement2024; 231: 114586.
17.
ZhangXZhangXLiuJ, et al. Graph features dynamic fusion learning driven by multi-head attention for large rotating machinery fault diagnosis with multi-sensor data. Eng Appl Artif Intell2023; 125: 106601.
18.
XiaoXLiCHeH, et al. Rotating machinery fault diagnosis method based on multi-level fusion framework of multi-sensor information. Inf Fusion2025; 113: 102621.
19.
LiCMoLKwohCK, et al. Noise-robust multi-view graph neural network for fault diagnosis of rotating machinery. Mech Syst Signal Process2025; 224: 112025.
20.
MaJFuYChengT, et al. SCADA data-driven spatio-temporal graph convolutional neural network for wind turbine fault diagnosis. IEEE Trans Instrum Meas2025; 74: 3551875.
21.
KimSLeeSLeeJ, et al. Fault-relevance-based, multi-sensor information integration framework for fault diagnosis of rotating machineries. Mech Syst Signal Process2025; 232: 112742.
22.
FinkelshteinBHuangXBronsteinM, et al. Cooperative graph neural networks. International Conference on Machine Learning. PMLR, ICML 2024(Vienna), 2024, pp. 13633–13659.
23.
PanYHongRChenJ, et al. Performance degradation assessment of wind turbine gearbox based on maximum mean discrepancy and multi-sensor transfer learning. Struct Health Monit2021; 20: 118–138.
24.
ZarchiMShahgholiMTeeKF.An adaptable physics-informed fault diagnosis approach via hybrid signal processing and transferable feature learning for structural/machinery health monitoring. Signal Image Video Process2024; 18: 9051–9066.
25.
WangQYuLHaoL, et al. An adaptive transfer fault detection method for rotary machine with multi-sensor information fusion. J Intell Manuf2025; 36: 4695–4710.
26.
LinCKongYHanQ, et al. An information fusion-based meta transfer learning method for few-shot fault diagnosis under varying operating conditions. Mech Syst Signal Process2024; 220: 111652.
27.
HanPHuangZLiW, et al. Multi-sensor bearing fault diagnosis based on evidential neural network with sensor weights and reliability. Expert Syst Appl2025; 269: 126533.
28.
DuanHChenGYuY, et al. DyGAT-FTNet: a dynamic graph attention network for multi-sensor fault diagnosis and time–frequency data fusion. Sensors2025; 25: 810.
29.
ZhangKZhangQLiuQ, et al. MCAGU-Net: a model for composite fault diagnosis of multi-sensor node networks. Eng Appl Artif Intell2025; 141: 109814.
30.
LiuRZhangQLinD, et al. Causal intervention graph neural network for fault diagnosis of complex industrial processes. Reliab Eng Syst Saf2024; 251: 110328.
KipfTNWellingM.Semi-supervised classification with graph convolutional networks. International Conference on Learning Representations, ICLR 2017, Toulon, 2017, p. 1.
33.
XuKHuWLeskovecJ, et al. How powerful are graph neural networks?International Conference on Learning Representations, ICLR 2019, New Orleans, 2019, p. 1.
34.
DongYLiGTaoY, et al. FAN: fourier analysis networks. arXiv 2024. DOI:10.48550/arXiv.2410.02675.
35.
ChenDLiuRHuQ, et al. Interaction-aware graph neural networks for fault diagnosis of complex industrial processes. IEEE Trans Neural Netw Learn Syst2023; 34: 6015–6028.
36.
VeličkovićPCucurullGCasanovaA, et al. Graph attention networks. International Conference on Learning Representations, ICLR 2018(Vancouver), 2018, p. 1.
37.
LyuLChenC. A novel attribute reconstruction attack in federated learning. arXiv 2021. DOI:10.48550/arXiv.2108.06910.
38.
WangHLiuZLiM, et al. A gearbox fault diagnosis method based on graph neural networks and markov transform fields. IEEE Sens J2024; 24: 25186–25196.
39.
LiTZhaoZSunC, et al. Multireceptive field graph convolutional networks for machine fault diagnosis. IEEE Trans Ind Electron2021; 68: 12739–12749.
40.
QiuZLiWTangT, et al. Denoising graph neural network based hydraulic component fault diagnosis method. Mech Syst Signal Process2023; 204: 110828.
41.
HouLYiHJinY, et al. Inter-shaft bearing fault diagnosis based on aero-engine system: a benchmarking dataset study. J Dyn Monit Diagn2023; 2: 228–242.
42.
JinYHaoLHeX, et al. A multi-scale temporal convolutional capsule network with parameter-free attention module-dynamic routing for intelligent diagnosis of rolling bearing. Meas Sci Technol2025; 36(1): 016151.
43.
SehriMP.University of Ottawa constant and variable speed electric motor vibration and acoustic fault signature dataset. Data Brief2024; 53: 110144.
44.
Mohammad-AlikhaniAPradhanSDhaleS, et al. Fault diagnosis of electric motors by a novel convolutional-based neural network and STFT. In: IEEE International Conference on Power Electronics and Drive Systems, PEDS 2023(Montreal, QC, Canada); 202, pp. :1–6.
