Non-Gaussian noise reconstruction and physics-guided filtering for aero-engine main bearing fault diagnosis under missing fault sample conditions
- 6 November 2026
- journal article
- Published by SAGE Publications in Structural Health Monitoring
Abstract
In recent years, deep learning has been extensively applied to fault diagnosis with remarkable achievements. However, due to factors such as safety constraints and high costs, it is extremely difficult to obtain aero-engine fault samples. Therefore, this article proposes a diagnostic framework for aero-engine main bearings based on non-Gaussian noise reconstruction and physics-guided filtering, which enables fault diagnosis without measured real fault data. First, a joint time–frequency-calibrated non-Gaussian noise synthesis method is proposed. This algorithm extracts higher-order cumulants and power spectral density features from healthy samples and reconstructs non-Gaussian background noise using Gram–Charlier series expansion and spectral tuning techniques. Subsequently, a physics-guided time–domain filter is constructed. By integrating structural resonance effects, periodic impact pulses, and complex modulation characteristics, this filter achieves deep modulation between the noise field and fault excitation pulses via convolution operators, thereby generating simulated fault data with minor differences from measured data. Finally, a generalized fault diagnosis network is constructed based on the dilated convolution network and contrastive learning to capture long-range temporal dependencies and construct a highly discriminative feature manifold, thereby achieving robust knowledge transfer from the simulated domain to the real domain. Experiments are conducted on the aero-engine bearing dataset, a self-built bearing dataset, and the Shandong University of Science and Technology dataset. Through extensive recognition experiments conducted on the three datasets, the proposed method demonstrates excellent diagnosis performance on tasks without real fault data.Keywords
Funding Information
- The National Natural Science Foundation of China (52375120)
- the Shaanxi Key Research and Development Plan of China (2024CY2GJHX68)
- the Fundamental Research Funds for the Central Universities and the Innovation Fund of Xidian University (YJSJ26002)
- The Natural Science Foundation of Shaanxi Province (2025JCYBMS953)
This publication has 48 references indexed in Scilit:
- Single domain generalization method based on simulation-experiment data fusion and meta-learning for rotating machinery fault diagnosisEngineering Applications of Artificial Intelligence, 2025
- A simulation-to-reality transfer learning method based on Kolmogorov-Arnold network enhanced model for bearing fault diagnosisAdvanced Engineering Informatics, 2025
- Multimodal medical image fusion based on dilated convolution and attention-based graph convolutional networkComputers and Electrical Engineering, 2025
- Moment-based Hermite model for asymptotically small non-GaussianityApplied Mathematical Modelling, 2025
- Fault vibration model driven fault-aware domain generalization framework for bearing fault diagnosisAdvanced Engineering Informatics, 2024
- Dynamic normalization supervised contrastive network with multiscale compound attention mechanism for gearbox imbalanced fault diagnosisEngineering Applications of Artificial Intelligence, 2024
- A transfer learning strategy based on numerical simulation driving 1D Cycle-GAN for bearing fault diagnosisInformation Sciences, 2023
- A bearing fault diagnosis method without fault data in new working condition combined dynamic model with deep learningAdvanced Engineering Informatics, 2022
- Transfer learning for process fault diagnosis: Knowledge transfer from simulation to physical processesComputers & Chemical Engineering, 2020
- A personalized diagnosis method to detect faults in gears using numerical simulation and extreme learning machineKnowledge-Based Systems, 2020