Selective Adversarial Augmentation Network for Bearing Fault Diagnosis with Partial Domain Adaptation
Open Access
- 6 February 2026
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 16 (3) , 1634
Abstract
Condition monitoring of rotating machinery is critical for ensuring industrial safety and operational reliability. As a core component of intelligent diagnostic systems, domain adaptation methods have achieved notable progress in mechanical fault diagnosis. However, most existing approaches presume a fully shared label space between source and target domains, limiting their effectiveness under partial domain adaptation scenarios commonly encountered in industrial practice. In addition, they often struggle with classification uncertainty near decision boundaries. To address these challenges, this paper proposes a Selective Adversarial Augmentation Network (SAAN) for cross-domain rolling bearing fault diagnosis with partial label space alignment. The proposed framework designs a multi-level feature extraction module to enhance transferable feature representation and a Balanced Augmentation Selective Adversarial Module (BASAM) to dynamically balance class distributions and selectively filter irrelevant source classes, thereby mitigating negative transfer and achieving fine-grained class alignment. Furthermore, an uncertainty suppression mechanism is put forth to reinforce classifier boundaries by minimizing the impact of ambiguous samples. Comprehensive experiments conducted on public and proprietary bearing datasets demonstrate that SAAN consistently surpasses state-of-the-art benchmarks in diagnostic accuracy and robustness, providing an effective solution for practical applications under class-imbalanced and variable operating conditions.Keywords
Funding Information
- National Natural Science Foundation of China (52465013)
- National Natural Science Foundation of China (51465035)
- Natural Science Foundation of Gansu Province (20JR5RA466)
- Education department of Gansu Province: Postgraduate ‘Innovation Star’ Project (2026CXZX-494)
This publication has 33 references indexed in Scilit:
- MIST: Multimodal emotion recognition using DeBERTa for text, Semi-CNN for speech, ResNet-50 for facial, and 3D-CNN for motion analysisExpert Systems with Applications, 2025
- Domain generalization for rotating machinery fault diagnosis: A surveyAdvanced Engineering Informatics, 2024
- Attention guided partial domain adaptation for interpretable transfer diagnosis of rotating machineryAdvanced Engineering Informatics, 2024
- ISEANet: An interpretable subdomain enhanced adaptive network for unsupervised cross-domain fault diagnosis of rolling bearingAdvanced Engineering Informatics, 2024
- Semi-supervised learning for industrial fault detection and diagnosis: A systemic reviewISA Transactions, 2023
- A partial domain adaptation scheme based on weighted adversarial nets with improved CBAM for fault diagnosis of wind turbine gearboxEngineering Applications of Artificial Intelligence, 2023
- Rotating machinery fault detection and diagnosis based on deep domain adaptation: A surveyChinese Journal of Aeronautics, 2023
- Partial adversarial domain adaptation by dual-domain alignment for fault diagnosis of rotating machinesISA Transactions, 2022
- Domain adaptation network base on contrastive learning for bearings fault diagnosis under variable working conditionsExpert Systems with Applications, 2022
- A transfer convolutional neural network for fault diagnosis based on ResNet-50Neural Computing and Applications, 2019