Fault diagnosis of multistage centrifugal pump unit using non-local means-based vibration signal denoising

Abstract

In real industry environment, the signal characteristics of multistage centrifugal pump vibration signal are easily submerged by strong background noise. To settle this problem, the nonlocal means (NLM) approach is proposed for the denoising of multistage centrifugal pump in this paper. Utilizing the similarity theory, the NLM method has achieved a wide range of applications in the fields of image processing and biomedical signal denoising. Due to the periodic characteristics and redundancy, NLM is successfully applied to the de-noising of 1-D machinery vibration signal. The numerical simulation experiments with different SNRs verify the effectiveness and the superiority of the proposed method. Besides, the selection principles of core parameters in NLM are discussed. The real engineering cases analysis demonstrates that the NLM can effectively filter out the background noise and realize the weak fault feature enhancements. The proposed noise reduction method is superior to traditional wavelet coefficient method.