An explainable AI-based fault diagnosis model for bearings.

Hasan, Md. Junayed; Sohaib, Muhammad; Kim, Jong-Myon

Abstract

In this paper, an explainable AI-based fault diagnosis model for bearings is proposed with five stages, i.e., (1) a data preprocessing method based on the Stockwell Transformation Coefficient (STC) is proposed to analyze the vibration signals for variable speed and load conditions, (2) a statistical feature extraction method is introduced to capture the significance from the invariant pattern of the analyzed data by STC, (3) an explainable feature selection process is proposed by introducing a wrapper-based feature selector—Boruta, (4) a feature filtration method is considered on the top of the feature selector to avoid the multicollinearity problem, and finally, (5) an additive Shapley ex-planation followed by k-NN is proposed to diagnose and to explain the individual decision of the k-NN classifier for debugging the performance of the diagnosis model. Thus, the idea of explaina-bility is introduced for the first time in the field of bearing fault diagnosis in two steps: (a) incorpo-rating explainability to the feature selection process, and (b) interpretation of the classifier performance with respect to the selected features. The effectiveness of the proposed model is demon-strated on two different datasets obtained from separate bearing testbeds. Lastly, an assessment of several state-of-the-art fault diagnosis algorithms in rotating machinery is included.

Citation

HASAN, M.J., SOHAIB, M. and KIM, J.-M. 2021. An explainable AI-based fault diagnosis model for bearings. Sensors [online], 21(12): sensing technologies for fault diagnostics and prognosis, article 4070. Available from: https://doi.org/10.3390/s21124070

• Journal Article Type: Article
• Acceptance Date: Jun 11, 2021
• Online Publication Date: Jun 13, 2021
• Publication Date: Jun 30, 2021
• Deposit Date: May 13, 2022
• Publicly Available Date: May 30, 2022
• Journal: Sensors
• Print ISSN: 1424-8220
• Publisher: MDPI
• Peer Reviewed: Peer Reviewed
• Volume: 21
• Issue: 12
• Article Number: 4070
• DOI: https://doi.org/10.3390/s21124070
• Keywords: Bearing; Boruta; Condition-based monitoring; Explainable AI; Fault diagnosis; Model interpretability; SHAP; Stockwell transform
• Public URL: https://rgu-repository.worktribe.com/output/1664562