Mechanical compound fault diagnosis is a thorny issue in the industry. To overcome this problem, a method named morphological filter - recursive least squares (MF-RLS) is proposed in this paper. In the proposed method, MF-RLS is used to sequentially separate the different fault impulse features by decomposing the observed signal into a series of iterative morphological filtering components (IMFCs). First, the measured signal is decomposed into different scales by the multi-scale morphological filter. Then, the product of kurtosis and envelope harmonic-to-noise ratio (PKEHNR) index is used to select the best IMFC. Finally, the IMFC is input to RLS to separate other fault features. After continuous iterations, the separation and extraction of the compound fault impulse features are achieved. The simulation and experiment of the mechanical compound fault have verified the effectiveness of the proposed method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.