Objective To address low reliability of fault diagnosis in ship motor rolling bearings, caused by weak fault signals and the difficulty of extracting fault features, this paper proposed a feature extraction method that integrates variational mode decomposition (VMD) with wavelet packet fuzzy entropy (WPFE). Furthermore, a support vector machine model optimized by the black-winged kite algorithm (BKA-SVM) is introduced to enhance diagnostic accuracy.

Method First, the collected vibration signals of motor bearings are decomposed using VMD, and the optimal intrinsic mode function (IMF) components are selected based on the principle of minimum envelope entropy. Next, the selected IMF components are further processed using wavelet packet decomposition, and their fuzzy entropy values are calculated. Finally, a BKA-SVM model is constructed, and the extracted feature data are used for fault diagnosis and classification.

Results Simulation experiments with SVM optimized by different algorithms, combined with validation on a self-constructed experimental platform, show that the diagnostic accuracy of the BKA-SVM model for three different sample sets reaches 98.33%–100%. Compared with SVM models optimized by the particle swarm optimization (PSO) algorithm, sparrow search algorithm (SSA) and newton-raphson-based optimizer (NRBO), the BKA-SVM demonstrates superior classification performance and higher accuracy in the extraction and diagnosis of rolling bearing faults.

Conclusion The findings of this study provide a valuable reference for the fault diagnosis of ship motor bearings.