EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Reliability-Guided Adaptive Feature Fusion Network for Noise-Robust Bearing Fault Diagnosis

Song Yang, Mei Liu iD, Yukang Chen, Jianfeng Zhang, Peng Wang, Pengfei Luo

Sensors · 22.05.2026 · 26 (11) · 3288

DOI: 10.3390/s26113288 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 22.05.2026. Verfasst von Song Yang und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Automation, Guangdong University of Petrochemical Technology, Maoming 525000, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Open Fund of Guangdong Key Laboratory of Modern Control Technology, Guangdong University of Petrochemical Technology, Maoming Green Chemical Research Institute.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cross-noise fault diagnosis remains challenging due to the mismatch between training and testing noise conditions, which degrades feature reliability and model generalization. To address this issue, this paper proposes a reliability-guided adaptive feature fusion framework (RGAF-Net). The method focuses on sample-wise adaptive feature fusion, where the enhanced wide first-layer convolutional neural network(WDCNN) backbone is employed to improve multi-scale feature extraction under noisy environments. In addition, a dual-path architecture is introduced to provide complementary representations, including globally robust structural representations and locally detail-sensitive structural responses. Furthermore, a lightweight reliability estimation module is designed to characterize the signal degradation tendency under noisy conditions of each input sample, based on which a sample-wise routing mechanism dynamically adjusts feature contributions during feature fusion. Experiments on two public bearing datasets (PU and JNU) under cross-noise settings demonstrate that the proposed method achieves improved performance compared with representative approaches, particularly under severe noise conditions. For example, on the JNU dataset at −10 dB, the proposed method improves the Macro-F1 score by over 19 percentage points compared with the baseline WDCNN. Ablation studies and visualization analyses further demonstrate the effectiveness and adaptive fusion behavior of the proposed framework. The results indicate that the proposed method provides an effective solution for robust fault diagnosis under noise mismatch scenarios.

Schlagwörter

Stichwörter der Autor:innen

adaptive feature fusioncross-noisefault diagnosisreliability estimation

Autor:innen und Institutionen

  • School of Automation, Guangdong University of Petrochemical Technology, Maoming 525000, China.
  • Guangdong Provincial Key Laboratory of Intelligent Safety for Petrochemical Equipment, Guangdong University of Petrochemical Technology, Maoming 525000, China.
  • College of Electrical and Control Engineering, Jilin University of Chemical Technology, Jilin 132022, China.

ORCID-Profile: Mei Liu

Förderung

  • National Natural Science Foundation of China
  • Open Fund of Guangdong Key Laboratory of Modern Control Technology
  • Guangdong University of Petrochemical Technology, Maoming Green Chemical Research Institute

Zitieren

APA

Yang, S., Liu, M., Chen, Y., Zhang, J., Wang, P., & Luo, P. (2026). Reliability-Guided Adaptive Feature Fusion Network for Noise-Robust Bearing Fault Diagnosis. Sensors, 26(11), 3288. https://doi.org/10.3390/s26113288

Vancouver

Yang S, Liu M, Chen Y, Zhang J, Wang P, Luo P. Reliability-Guided Adaptive Feature Fusion Network for Noise-Robust Bearing Fault Diagnosis. Sensors. 2026;26(11):3288. doi:10.3390/s26113288

BibTeX
@article{Yang2026,
  author = {Yang, Song and Liu, Mei and Chen, Yukang and Zhang, Jianfeng and Wang, Peng and Luo, Pengfei},
  title = {Reliability-Guided Adaptive Feature Fusion Network for Noise-Robust Bearing Fault Diagnosis},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {11},
  pages = {3288},
  doi = {10.3390/s26113288}
}
Kostenlos starten →