Rolling Bearing Fault Diagnosis via Temporal-Graph Convolutional Fusion
Open Access
Abstract
To address the challenge of incomplete fault feature extraction in rolling bearing fault diagnosis under small-sample conditions, this paper proposes a Temporal-Graph Convolutional Fusion Network (T-GCFN). The method enhances diagnostic robustness through collaborative extraction and dynamic fusion of features from time-domain and frequency-domain branches. First, Variational Mode Decomposition (VMD) was employed to extract time-domain Intrinsic Mode Functions (IMFs). These were then input into a Temporal Convolutional Network (TCN) to capture multi-scale temporal dependencies. Simultaneously, frequency-domain features obtained via Fast Fourier Transform (FFT) were used to construct a K-Nearest Neighbors (KNN) graph, which was processed by a Graph Convolutional Network (GCN) to identify spatial correlations. Subsequently, a channel attention fusion layer was designed. This layer utilized global max pooling and average pooling to compress spatio-temporal features. A shared Multi-Layer Perceptron (MLP) then established inter-channel dependencies to generate attention weights, enhancing critical features for more complete fault information extraction. Finally, a SoftMax classifier performed end-to-end fault recognition. Experiments demonstrated that the proposed method significantly improved fault recognition accuracy under small-sample scenarios. These results validate the strong adaptability of the T-GCFN mechanism.Keywords
Funding Information
- Henan Provincial Major Science and Technology Special Project (221100220100)
This publication has 19 references indexed in Scilit:
- An intelligent fault diagnosis for rotating machine under strong noise based on cross-attention-driven spatial-temporal feature fusion and duplexing time sequence convolution optimizationEngineering Applications of Artificial Intelligence, 2025
- Bi-structural spatial–temporal network for few-shot fault diagnosis of rotating machineryMechanical Systems and Signal Processing, 2025
- Systematic Review of Bearing Component Failure: Strategies for Diagnosis and Prognosis in Rotating MachineryArabian Journal for Science and Engineering, 2024
- Lightweight CNN architecture design for rolling bearing fault diagnosisMeasurement Science and Technology, 2024
- Review of research on signal decomposition and fault diagnosis of rolling bearing based on vibration signalMeasurement Science and Technology, 2024
- A review on convolutional neural network in rolling bearing fault diagnosisMeasurement Science and Technology, 2024
- Fault diagnosis of rotating machinery using novel self-attention mechanism TCN with soft thresholding methodMeasurement Science and Technology, 2024
- A fault diagnosis method based on feature-level fusion of multi-sensor information for rotating machineryMeasurement Science and Technology, 2023
- Improved signal processing for bearing fault diagnosis in noisy environments using signal denoising, time–frequency transform, and deep learningJournal of the Brazilian Society of Mechanical Sciences and Engineering, 2023
- The emerging graph neural networks for intelligent fault diagnostics and prognostics: A guideline and a benchmark studyMechanical Systems and Signal Processing, 2022