Fault Diagnosis Based on Physics-Guided Multifractal Detrended Fluctuation Analysis for Marine Electric Thrusters

Abstract

This article presents a physics-guided multifractal detrended fluctuation analysis (PMFDFA) method for bearing fault diagnosis in marine electric thrusters (METs). Phase-current signals acquired from the MET are used to construct physically interpretable multifractal features for noninvasive diagnosis. Bearing fault characteristic frequencies guide both VMD mode localization and period-synchronized multifractal detrended fluctuation analysis (MFDFA) box-length construction, thereby replacing empirical feature-extraction choices with physically traceable criteria. The method offers three main benefits: 1) phase-current sensing enables noninvasive monitoring while multifractal detrending suppresses low-frequency trends caused by marine load fluctuations; 2) multiscale descriptors capture fault-related nonlinear fluctuations for subsequent classification; and 3) the selected VMD modes and MFDFA box lengths have an explicit physical origin. In the within-platform closed-set experiments on the evaluated MET prototype, PMFDFA outperformed the implemented reference methods.