Detection and Diagnosis of Bearing Faults Under Fixed and Time-Varying Speed Conditions Using Persistence Spectrum and Multi-Scale Structural Similarity Index

Abstract

With the widespread use of variable speed drives, a robust scheme that can detect and diagnose bearing faults under fixed and variable speed conditions becomes essential for reliable operation. Unfortunately, most of the reported methods in the literature are dedicated to working under fixed speed and will face challenges under variable speed conditions. Besides, most of them require detailed bearing information that may be unavailable in the real world. Therefore, in this paper, a new scheme is proposed for bearing faults detection and diagnosis under fixed and time-varying speed conditions. The proposed scheme is based on the analysis of vibration signals using the persistence spectrum that can provide images rich with health-related features largely independent from rotating speed. Then, the produced image is compared with priorly stored images of the persistence spectrum of a healthy case. This comparison is performed using the multi-scale structural similarity index, which is a robust basis for images comparison without the need for training or expert knowledge. The obtained index is compared against an adaptive threshold for fault detection. Upon detecting a fault, the persistence spectrum image is compared with that of stored different fault types for fault diagnosis. The proposed scheme is extensively validated using three experimental datasets under different speed conditions. The results show that it can detect bearing faults in an earlier stage without the need for bearing specifications or shaft speed. Moreover, it can successfully diagnose bearing faults severity with accuracy reaching 100% with the minimum required data.