Spectral boundary detecting model: A promising tool for adaptive mode extraction and machinery fault diagnosis

Abstract

Extraction of weak transients is vital for realizing the early machinery fault diagnosis. However, a significant challenge lies in an efficient determination of the spectral boundaries of expected modes for excluding interferential information. Through a new perspective exploration on the fundamental principle of variational mode decomposition, we find a relevance between the filtering structure of variational model and the shape of fault-induced features in spectral domain. Then, we propose a spectral boundary detecting model (SBDM) to identify fault-induced transients efficiently. SBDM comprises three steps. First, spectral structural features of analysis signal are quickly detected based on the found relevance. Second, spectral boundaries with expected modes are calculated based on the located spectral structural features. Third, a filter bank designed on the spectral boundaries is used to extract the expected modes. Furthermore, our SBDM is extended by two observed valuable phenomena to obtain a comprehensive result for downstream diagnosis tasks. Finally, an extended SBDM-based diagnosis procedure is presented for the machinery fault identification. Two experimental cases have validated that our SBDM outperforms eight advanced methods in the machinery fault diagnosis.