Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
December 7, 2025SensorsOpen Access

Research on Fault Diagnosis of Mechanical Bearings Based on Transfer Learning

View Full Paper
Ask AI
Bookmark
Share

Authors

XGXuefeng GaoChinese University of Hong KongYZYizhi ZhangOriginWater (China)ZYZhifeng YouPLA Army Engineering University

Discussion

Loading...

Member takes

Implication

Analysis shows transfer learning improved accuracy to 97.6% in mechanical bearings, highlighting its applicability in fault diagnosis.

Key Points

  • Fault diagnosis with transfer learning achieved an F1 score of 0.9631, outperforming legacy models.
  • The transfer learning method increased classification accuracy by 27.3 percentage points compared to direct applications.
  • Utilizing gradient boosting machine and random forest, accuracy comparisons demonstrated the effectiveness of transfer learning.
  • Feature importance analysis using SHAP revealed critical insights into model decision-making processes.

Cite This Study

Gao et al. (2025) studied this question.

synapsesocial.com/papers/694020f72d562116f28fb229https://doi.org/10.3390/s25247446
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Intelligent Fault Diagnosis for Rotating Machinery via Transfer Learning and Attention Mechanisms: A Lightweight and Adaptive Approach2025 · 4 citations
  2. 2Research on intelligent diagnosis of mechanical rolling bearing faults through transfer learning2026 · 1 citations
  3. 3A novel algorithm for complex transfer conditions in bearing fault diagnosis2024 · 10 citations
  4. 4An interpretable transfer learning method for bearing diagnosis across different systems, faults, and signal types2025 · 3 citations
  5. 5Research on bearing fault diagnosis based on machine learning and SHAP interpretability analysis2025