Dynamic degradation observer for bearing fault by MTS–SOM system

Rolling element bearings are used in a wide variety of rotating machinery from small hand-held devices to heavy duty industrial systems. Bearing fault or even failure is one of the foremost causes of breakdown in such rotating machines, resulting in costly system downtime. This paper presents a dynamic degradation observer for the identification and assessment of bearing degradation based on Mahalanobis–Taguchi system (MTS) and self-organization mapping (SOM) network called MTS–SOM system. It helps to differentiate especially the incipient fault stage and track the dynamic degradation trend of the running bearing by real-time vibration observations. The feature parameters from multifractal aspects are calculated first and further optimized by the MTS statistical method. Mappings of different degradation levels are then presented by SOM with optimal multifractal features, which help to differentiate each degradation stage and describe a degradation trajectory of the in-service bearing. The found results are validated by experiment, and a comparative study is carried out to verify the effectiveness of the proposed method. The contribution of the method considering both current and predictive perspectives on the fault degradation behavior is also showed for the elaborate maintenance management.

► The presented method is used to differentiate each degradation stage of running bearings.
► It also can track the degradation trend of the running bearings.
► Multifractal features are first studied especially to identify the incipient fault of bearings.
► MTS method is then used to select the optimal features and assess the degradation level.
► MTS–SOM system is used to provide dynamic degradation trajectories.