Fault Diagnosis Based on Multi-Scale Redefined Dimensionless Indicators and Density Peak Clustering With Geodesic Distances

• Published in: IEEE access Vol. 8; pp. 84777 - 84791
• Main Authors: Hu, Qin, Zhang, Qi, Si, Xiao-Sheng, Qin, Ai-Song, Zhang, Qing-Hua
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Clustering; clustering algorithms; Complexity theory; Density; Dimensionless analysis; Discriminant analysis; Fault diagnosis; Feature extraction; Indicators; knowledge engineering; machine learning; mechanical engineering; Multiscale analysis; nearest neighbor searches; pattern recognition; Petrochemicals; Roller bearings; Rolling bearings; unsupervised learning; Vibration measurement; Vibrations
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2020.2989460

A novel fault diagnosis method for rolling bearings based on multi-scale redefined dimensionless indicators and an unsupervised feature selection method using density peak clustering with geodesic distances is proposed in this paper. First, a new feature extraction method is proposed based on redefined dimensionless indicators and multi-scale analysis called multi-scale redefined dimensionless indicators. Then, density peak clustering with geodesic distances is utilized to automatically find the important multi-scale redefined dimensionless indicators. To the best of our knowledge, this is the first study to use density peak clustering with geodesic distances to explore unsupervised feature selection in the fault diagnosis field. Finally, the selected multi-scale redefined dimensionless indicators are fed into a quadratic discriminant analysis classifier to simultaneously identify 12 different conditions of rolling bearings. Experimental results demonstrated that the proposed method can successfully differentiate 12 localized fault types, fault severities, and fault orientations of rolling bearings.