Semi-Supervised Transfer Graph Representation Learning with Few-Shot Adaptation for gearbox diagnostics under extraneous transient noise
- 4 February 2026
- journal article
- Published by SAGE Publications in Structural Health Monitoring
Abstract
Gearboxes are critical mechanical components widely deployed in industrial applications, where their reliable operation directly impacts system safety and efficiency. However, conventional fault diagnostic approaches face significant challenges when operating under extraneous transient noise conditions, particularly with limited labeled fault samples. These challenges manifest as performance degradation with extremely sparse labeled datasets, vulnerability in pseudo-label generation mechanisms under intense transient noise, and inconsistent feature scale representations due to noise-induced interference. Furthermore, existing methods struggle to maintain diagnostic accuracy when confronted with both data scarcity and transient disturbances, often resulting in compromised model generalization and unreliable fault classification. To address these limitations, this research proposes the Semi-Supervised Transfer Graph Representation Learning with Few-Shot Adaptation (SSTGRL-FSA) framework, featuring three innovative components: a novel pseudo-label reliability enhancement mechanism leveraging systematic knowledge transfer from established source domains, an advanced label transmission and matching strategy exploiting homologous signal patterns across operational domains, and an integrated first-order Markov state probability transition matrix with amplitude-constrained scaling. SSTGRL-FSA significantly advances the field by effectively handling both labeled data scarcity and transient noise interference while enhancing model robustness through sophisticated temporal dependency modeling and stable feature scale maintenance, ultimately providing a more reliable and practical solution for industrial gearbox fault diagnosis under challenging operational conditions.Keywords
Funding Information
- Natural Science Foundation of Anhui Province (2108085QE229)
- China Postdoctoral Science Foundation (2023M740021)
- Basic and Applied Basic Research Foundation of Guangdong Province (2025A1515012256)
- National Natural Science Foundation of China (52105111)
- National Natural Science Foundation of China (52305085)
- National Natural Science Foundation of China (52375078)
- National Natural Science Foundation of China (52405009)
- National Natural Science Foundation of China (U23B20104)
This publication has 45 references indexed in Scilit:
- Progressive contrastive representation learning for defect diagnosis in aluminum disk substrates with a bio-inspired vision sensorExpert Systems with Applications, 2025
- Physics-informed dual guidance method using physical envelope harmonic distribution and transfer learning for few-shot gear fault classificationEngineering Applications of Artificial Intelligence, 2025
- Spatial-temporal graph attention contrastive learning for semi-supervised bearing fault diagnosis with limited labeled samplesComputers & Industrial Engineering, 2025
- Cross-operating-condition fault diagnosis of a small module reactor based on CNN-LSTM transfer learning with limited dataEnergy, 2024
- Towards Exploring the Limitations of Test Selection Techniques on Graph Neural Networks: An Empirical StudyEmpirical Software Engineering, 2024
- Subgraph generation applied in GraphSAGE deal with imbalanced node classificationSoft Computing, 2024
- A review of the wavelet transform for durability and structural health monitoring in automotive applicationsAlexandria Engineering Journal, 2024
- A novel hybrid model based on Empirical Mode Decomposition and Echo State Network for wind power forecastingEnergy, 2024
- Data-driven fault diagnosis of PEMFC water management with segmented cell and deep learning technologiesInternational Journal of Hydrogen Energy, 2024
- Semi-supervised fault diagnosis of machinery using LPS-DGAT under speed fluctuation and extremely low labeled ratesAdvanced Engineering Informatics, 2022