Modified multiscale weighted permutation entropy and optimized support vector machine method for rolling bearing fault diagnosis with complex signals.

Abstract

The rolling bearing vibration signals are complex, non-linear, and non-stationary, it is difficult to extract the sensitive features and diagnose faults by conventional signal processing methods. This paper focuses on the sensitive features extraction and pattern recognition for rolling bearing fault diagnosis and proposes a novel intelligent fault-diagnosis method based on generalized composite multiscale weighted permutation entropy (GCMWPE), supervised Isomap (S-Iso), and marine predators algorithm-based support vector machine (MPA-SVM). Firstly, a novel non-linear technology named GCMWPE was presented, allowing the extraction of bearing features from multiple scales and enabling the construction of a high-dimensional feature set. The GCMWPE uses the generalized composite coarse-grained structure to overcome the shortcomings of the original structure in multiscale weighted permutation entropy and obtain more stable entropy values. Subsequently, the S-Iso algorithm was introduced to obtain the main features and reduce the GCMWPE set dimensionality. Finally, a combination of GCMWPE and S-Iso set was input to the MPA-SVM for diagnosis and identification. The marine predators algorithm (MPA) was used to obtain the optimal SVM parameters. The effectiveness of the proposed fault diagnosis method was confirmed through two bearing fault diagnosis experiments. The results have shown that the proposed method can be used to correctly diagnose bearing states with high diagnostic accuracy.