Enhanced Bearing Fault Diagnosis Through Trees Ensemble Method and Feature Importance Analysis
Journal of Vibration Engineering & Technologies · 2024-12 · 12 (S1) · 109-125
DOI: 10.1007/s42417-024-01405-0 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Vibration Engineering & Technologies, online erschienen am 11.05.2024. Verfasst von Amir Alhams und 4 weiteren Autor:innen. Die Arbeit wurde bisher 57-mal zitiert (Crossref) und nennt 82 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Auckland.
Abstract (Originalsprache)
Purpose
This research introduces a groundbreaking method for bearing defect detection. It leverages ensemble machine learning (ML) models and conducts comprehensive feature importance analysis. The key innovation is the training and benchmarking of three tree ensemble models—Decision Tree (DT), Random Forest (RF), and Extreme Gradient Boosting (XGBoost)—on an extensive experimental dataset (QU-DMBF) collected from bearing tests with seeded defects of varying sizes on the inner and outer raceways under different operating conditions.
Method
The dataset was meticulously prepared with categorical variable encoding and Min–Max data normalization to ensure consistent class distribution and model accuracy. Implementing the ML models involved a grid search method for hyperparameter tuning, focusing on reporting the models’ accuracy. The study also explores applying ensemble methods and using supervised and unsupervised learning algorithms for bearing fault detection. It underscores the value of feature importance analysis in understanding the contributions of specific inputs to the model’s performance. The research compares the ML models to traditional methods and discusses their potential for advanced fault diagnosis in bearing systems. Results and Conclusions The XGBoost model, trained on data from actual bearing tests, outperformed the others, achieving 92% accuracy in detecting bearing health and fault location. However, a deeper analysis of feature importance reveals that the models weigh certain experimental conditions differently—such as sensor location and motor speed. This research’s primary novelties and contributions are comparative evaluation, experimental validation, accuracy benchmarking, and interpretable feature importance analysis. This comprehensive methodology advances the bearing health monitoring field and has significant practical implications for condition-based maintenance, potentially leading to substantial cost savings and improved operational efficiency.
Förderung
- University of Auckland
Zitieren
APA
Alhams, A., Abdelhadi, A., Badri, Y., Sassi, S., & Renno, J. (2024). Enhanced Bearing Fault Diagnosis Through Trees Ensemble Method and Feature Importance Analysis. Journal of Vibration Engineering & Technologies, 12(S1), 109-125. https://doi.org/10.1007/s42417-024-01405-0
Vancouver
Alhams A, Abdelhadi A, Badri Y, Sassi S, Renno J. Enhanced Bearing Fault Diagnosis Through Trees Ensemble Method and Feature Importance Analysis. Journal of Vibration Engineering & Technologies. 2024;12(S1):109-125. doi:10.1007/s42417-024-01405-0
BibTeX
@article{Alhams2024,
author = {Alhams, Amir and Abdelhadi, Ahmed and Badri, Yousif and Sassi, Sadok and Renno, Jamil},
title = {Enhanced Bearing Fault Diagnosis Through Trees Ensemble Method and Feature Importance Analysis},
journal = {Journal of Vibration Engineering & Technologies},
year = {2024},
volume = {12},
number = {S1},
pages = {109--125},
doi = {10.1007/s42417-024-01405-0}
}
EUVIMED