Bearing Fault Vibration Signal Feature Extraction and Recognition Method Based on EEMD Superresolution Sparse Decomposition

Abstract

This paper aims at the shortcomings of the current conventional processing methods of bearing fault vibration signals in improving signal-to-noise ratio, fine feature extraction, and recognition. A feature extraction and recognition method of abnormal vibration signals based on Ensemble Empirical Mode Decomposition (EEMD) superresolution sparse decomposition is designed. First of all, the superresolution sparse decomposition method is used to refine the set of IMF components of vibration signals after EEMD decomposition. Secondly, the features of the set are extracted and their corresponding energy entropy is calculated. Thirdly, the classification and recognition are carried out. Finally, the effectiveness and feasibility of the method are verified by experiments. It has been proved that this method can better realize the denoising and fine processing aimed at abnormal vibration signals. It has certain theoretical significance and applied value.