Abstract

The premise of bearing fault prediction lies in early fault diagnosis and degradation state tracking and recognition. However, early fault characteristic signals of rolling bearings are often submerged in noise and difficult to detect and identify. To solve this problem, from the point of view of enhancing the fault signal, a method for early fault degradation state recognition of bearings based on fast spectral kurtosis and Multipoint Optimal Minimum Entropy Deconvolution Adjusted (MOMEDA) was proposed, and the fault information could be sensed from the complex signals to realize early fault degradation state recognition. The simulation results show that the proposed method is effective for early fault diagnosis of bearings. The experimental verification results based on IMS bearing dataset show that the proposed method can effectively realize the early fault discovery time node moving forward.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call