Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
November 21, 2025Scientific ReportsOpen Access

Research on bearing fault diagnosis based on machine learning and SHAP interpretability analysis

View Full Paper
Ask AI
Bookmark
Share

Authors

LWLulu WangWMWu Menghua

Discussion

Loading...

Member takes

Implication

Analysis identifies optimal machine learning algorithms for diagnosing bearing faults in rotating machinery, suggesting further feature engineering optimization.

Key Points

  • Diagnostic methods improve through advanced machine learning techniques, effectively diagnosing bearing faults.
  • XGBoost yielded a high accuracy of 91.0% and a recall of 98.9% for fault detection in normal and faulty bearings.
  • The comprehensive evaluation compared multiple algorithms, including Random Forest and others, across various metrics.
  • SHAP analysis enhances interpretability, leading to better understanding and optimization of diagnostic features.

Cite This Study

Wang et al. (2025) studied this question.

synapsesocial.com/papers/6924e3ffc0ce034ddc34f6d7https://doi.org/10.1038/s41598-025-25083-4
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. 1Highly accurate interpretable bearing fault diagnosis based on SHAP-RFE with Bayesian optimization support vector machines2025 · 4 citations
  2. 2Bearing Fault Diagnosis using Machine Learning Models2024
  3. 3Machine learning-based bearing fault detection using statistical feature engineering and explainable XGBoost classification2026
  4. 4Research on bearing fault diagnosis technology based on machine learning2024 · 1 citations
  5. 5Research on Fault Diagnosis of Mechanical Bearings Based on Transfer Learning2025 · 3 citations