ORgram: semi-supervised learning framework for inline bearing diagnosis in varying speed

Based on the fast kurtogram, many previous studies have focused on frequency band selection (FBS) affected by interference due to impulsive noise and varying speed conditions. Recently, machine learning algorithms have been considered effective for bearing diagnosis. However, most of these methods are supervised learning and thus suffer from data imbalance in the practical applications. This study proposes a semi-supervised learning indicator called outlier rate diagram (ORgram) based on the signal changes before and after bearing damage. ORgram is suitable for impulsive noise and varying speed conditions. First, the healthy bearing data is segmented by rotational speed and modeled with one-class support vector machine (SVM) for each frequency band. As bearing defects sprout, the defect response will produce the highest outlier rate in the informative frequency band (IFB). After selecting the IFB, techniques such as envelope analysis and order tracking are used to identify damaged bearing components for an alarm to reduce the losses caused by unplanned downtime.