A Graph Isomorphic Network with Attention Mechanism for Intelligent Fault Diagnosis of Axial Piston Pump
Source abstract
Abstract
Axial piston pumps play a vital role in fluid power systems, which are widely employed in diverse fields such as aerospace, ocean engineering, and rail transit. It is essential to accurately diagnose faults in these pumps since their reliable operation hinges on it. A graph isomorphic network with a spatio-temporal attention mechanism (GIN-ST) is proposed in this paper for fault diagnosis of hydraulic axial piston pumps; GIN-AM addresses the problem of traditional intelligent fault diagnosis methods being limited to nonlinear mapping and transformation in Euclidean space. Initially, the weighted graphs are constructed from a univariate time series through K-nearest neighbor graph methods. Subsequently, a spatio-temporal attention-based module used to learn the graph representation of piston pump faults is presented, where a novel READOUT function and Transformer encoder provide spatial and temporal interpretability, respectively. Finally, the proposed (GIN-ST) model is compared against other intelligent fault diagnosis methods, and the superiority of the proposed method is proven.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Fault Detection and Control Systems · Advanced Data Processing Techniques · Oil and Gas Production Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Mechanical and Electrical Engineering, Central South University, 932 Lushan South Road, YueLu District, Changsha 410083, China
State Key Laboratory of Precision Manufacturing for Extreme Service Performance, Central South University, Changsha 430074, China
Funding
National Natural Science Foundation of China · Project of State Key Laboratory of Precision Manufacturing for Extreme Service Performance
References (28)
Show source-provided references
1. Condition monitoring of hydraulic transmission system with variable displacement axial piston pump and fixed displacement motor10.1016/j.matpr.2020.09.327 ↗
2. Tool wear prediction via multidimensional stacked sparse autoencoders with feature fusion10.1109/TII.2019.2949355 ↗
3. Fault detection and diagnosis for rotating machinery: A model based on convolutional LSTM, Fast Fourier and continuous wavelet transforms10.1016/j.compind.2020.103378 ↗
4. A sparse multivariate time series model-based fault detection method for gearboxes under variable speed condition10.1016/j.ymssp.2021.108539 ↗
5. Landing gear failures connected with high-pressure hoses and analysis of trends in aircraft technical problems10.3846/aviation.2022.17751 ↗
6. Deep learning for cellular image analysis10.1038/s41592-019-0403-1 ↗
7. Empirical mode reconstruction: Preserving intrinsic components in data augmentation for intelligent fault diagnosis of civil aviation hydraulic pumps10.1016/j.compind.2021.103557 ↗
8. Intelligent fault identification of hydraulic pump using deep adaptive normalized CNN and synchrosqueezed wavelet transform10.1016/j.ress.2022.108560 ↗
9. A supervised ensemble learning method for fault diagnosis in photovoltaic strings10.1016/j.energy.2021.120463 ↗
10. A deep multi-signal fusion adversarial model based transfer learning and residual network for axial piston pump failure diagnosis10.1016/j.measurement.2022.110889 ↗
11. A deep learning method for bearing failure diagnosis based on cyclic spectral coherence and convolutional neural networks10.1016/j.ymssp.2020.106683 ↗
12. Intelligent failure diagnosis of rotating machinery based on continuous wavelet transform-local binary convolutional neural network10.1016/j.knosys.2021.106796 ↗
13. Semi-supervised graph convolutional network to predict position-and speed-dependent tool tip dynamics with limited labeled data10.1016/j.ymssp.2021.108225 ↗
14. The emerging graph neural networks for intelligent fault diagnostics and prognostics: A guideline and a benchmark study10.1016/j.ymssp.2021.108653 ↗
15. Failure diagnosis of wind turbine gearbox using a novel method of fast deep graph convolutional networks10.1109/TIM.2020.3048799 ↗
16. Intelligent acoustic-based failure diagnosis of roller bearings using a deep graph convolutional network10.1016/j.measurement.2020.107585 ↗
17. Semisupervised graph convolution deep belief network for failure diagnosis of electormechanical system with limited labeled data10.1109/TII.2020.3034189 ↗
18. Bearing remaining useful life prediction using self-adaptive graph convolutional networks with self-attention mechanism10.1016/j.ymssp.2022.110010 ↗
19. Multiscale Deep Graph Convolutional Networks for Intelligent Failure diagnosis of Rotor-Bearing System Under Fluctuating Working Conditions10.1109/TII.2022.3161674 ↗
20. A hybrid method for condition monitoring and fault diagnosis of rolling bearings with low system delay10.1109/TIM.2022.3198477 ↗
21. Xu, K., Hu, W., Leskovec, J., and Jegelka, S. (2018). How powerful are graph neural networks?. arXiv.
22. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., and Polosukhin, I. (2017). Attention is all you need. arXiv.
23. Tryon, J., Alfaro, J.G.C., and Trejos, A.L. (2025). Effects of Image Normalization on CNN-Based EEG–EMG Fusion. IEEE Sens. J.10.1109/JSEN.2025.3559438 ↗
24. Graph neural networks with convolutional arma filters
25. Multireceptive field graph convolutional networks for machine failure diagnosis10.1109/TIE.2020.3040669 ↗
26. Failure diagnosis for small samples based on attention mechanism10.1016/j.measurement.2021.110242 ↗
27. Kipf, T.N., and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv.
28. Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., and Bengio, Y. (2017). Graph attention networks. arXiv.