STFT–LoRA–DANN: a lightweight adversarial transfer learning framework for cross-load bearing fault diagnosis

Abstract

Due to the significant differences in energy distribution, noise characteristics, and feature patterns of vibration signals under varying load conditions, cross-load fault diagnosis has become a central challenge in rolling bearing health monitoring. To address the weak cross-domain generalization and high adaptation cost of traditional deep models, this study proposes an integrated lightweight transfer learning framework termed STFT–LoRA–DANN. The method first constructs stable time–frequency representations via STFT to enhance feature consistency across different loads. Subsequently, only a small number of low-rank adaptation parameters are inserted into the pretrained SeResNeXt50 backbone, enabling controllable feature-space adaptation with substantially fewer trainable parameters and reduced optimization cost. Finally, adversarial domain alignment based on DANN is employed to explicitly reduce the feature distribution discrepancy between source and target domains. Across twelve cross-load transfer tasks on the CWRU dataset, the proposed framework achieves near-saturated and competitive performance, reaching an average accuracy of 99.4% and outperforming classical transfer baselines such as MMD, MK-MMD, and DANN in most transfer directions. Confusion matrix and training-dynamics analyses further demonstrate that the framework maintains stable convergence and good generalization behavior with limited parameter updates, suggesting potential practical value for cross-load diagnosis scenarios with data scarcity and varying operating conditions. The results indicate that the combination of LoRA and adversarial domain adaptation provides a scalable parameter-efficient paradigm for low-cost intelligent mechanical fault diagnosis.

Adversarial generative transfer learning with self-selective attention transformer for multi-class fault diagnosis under variable-speed conditions
Ava Foroughi, Javad Hasanpour-Sangelaji, Mostafa Abedi
Scientific Reports5 Oct 2026Peer-reviewedCC BY-NC-ND 4.0Full textCrossref
An Explainable Transfer Learning Framework Based on Acoustic Spectral Portraits for Pipeline Leak Diagnosis Across Composite Operating and Acquisition Conditions.
Zahoor Ahmad, Niamat Ullah, Jong-Myon Kim
Sensors (Basel, Switzerland)14 Oct 2026Peer-reviewedCC BYFull textEurope PMC
Dense121GAN: transfer learning-enhanced conditional generative adversarial network with DenseNet121 for reliable and efficient segmentation in medical and industrial imaging.
Muhammed Davud
PeerJ. Computer science7 Jul 2026Peer-reviewedCC BYFull textEurope PMC
Privacy-preserving collaborative transfer learning with generative adversarial networks (CTL-GAN) for classification of dry eye disease
Bongsang Kim, Yeo Kyoung Won, Hokyun Kim +3
Scientific Reports20 Oct 2026Peer-reviewedCC BY 4.0Full textEpidemiology & public healthCrossref
A Lightweight Multi-Sensor Feature-Level Fusion Framework for Noise-Robust Fault Diagnosis of High-Precision Milling Machines.
Zhi Xu, Ningyun Lu, Liguo Jin
Sensors (Basel, Switzerland)12 Oct 2026Peer-reviewedCC BYFull textEurope PMC

Cite

BibTeX RIS

BibTeX

@article{he2026stftloradann,
  title = {{STFT–LoRA–DANN: a lightweight adversarial transfer learning framework for cross-load bearing fault diagnosis}},
  author = {Wei He and Chunlei Shi and Rongqing Xu},
  journal = {Scientific Reports},
  year = {2026},
  month = sep,
  doi = {10.1038/s41598-026-72200-y},
  url = {https://www.nature.com/articles/s41598-026-72200-y},
  note = {CC BY 4.0},
}

RIS

TY  - JOUR
TI  - STFT–LoRA–DANN: a lightweight adversarial transfer learning framework for cross-load bearing fault diagnosis
AU  - Wei He
AU  - Chunlei Shi
AU  - Rongqing Xu
PY  - 2026
DA  - 2026/09/30
JO  - Scientific Reports
DO  - 10.1038/s41598-026-72200-y
UR  - https://www.nature.com/articles/s41598-026-72200-y
AB  - Due to the significant differences in energy distribution, noise characteristics, and feature patterns of vibration signals under varying load conditions, cross-load fault diagnosis has become a central challenge in rolling bearing health monitoring. To address the weak cross-domain generalization and high adaptation cost of traditional deep models, this study proposes an integrated lightweight transfer learning framework termed STFT–LoRA–DANN. The method first constructs stable time–frequency representations via STFT to enhance feature consistency across different loads. Subsequently, only a small number of low-rank adaptation parameters are inserted into the pretrained SeResNeXt50 backbone, enabling controllable feature-space adaptation with substantially fewer trainable parameters and reduced optimization cost. Finally, adversarial domain alignment based on DANN is employed to explicitly reduce the feature distribution discrepancy between source and target domains. Across twelve cross-load transfer tasks on the CWRU dataset, the proposed framework achieves near-saturated and competitive performance, reaching an average accuracy of 99.4% and outperforming classical transfer baselines such as MMD, MK-MMD, and DANN in most transfer directions. Confusion matrix and training-dynamics analyses further demonstrate that the framework maintains stable convergence and good generalization behavior with limited parameter updates, suggesting potential practical value for cross-load diagnosis scenarios with data scarcity and varying operating conditions. The results indicate that the combination of LoRA and adversarial domain adaptation provides a scalable parameter-efficient paradigm for low-cost intelligent mechanical fault diagnosis.
SN  - 2045-2322
ER  -

Abstract

Related

Cite