Abstract
Rolling element bearing defects are among the main reasons for the breakdown of electrical machines, and therefore, early diagnosis of these is necessary to avoid more catastrophic failure consequences. This paper presents a novel approach for identifying rolling element bearing defects in brushless DC motors under non-stationary operating conditions. Stator current and lateral vibration measurements are selected as fault indicators to extract meaningful features, using a discrete wavelet transform. These features are further reduced via the application of orthogonal fuzzy neighbourhood discriminative analysis. A recurrent neural network is then used to detect and classify the presence of bearing faults. The proposed system is implemented and tested in simulation on data collected from an experimental setup, to verify its effectiveness and reliability in accurately detecting and classifying the various faults.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have