Continuous-scale mathematical morphology-based optimal scale band demodulation of impulsive feature for bearing defect diagnosis

Multimodal deep support vector classification with homologous features and its application to gearbox fault diagnosis

“…In the time modality, Raad et al [15] employed cyclostationarity as an indicator for gear diagnosis. In the frequency modality, Li and Liang [16] suggested an optimal mathematical morphology demodulation technique to extract impulsive feature for bearing defect diagnosis. In the wavelet modality, different statistical parameters have been introduced to classify fault patterns [17].…”

Natural gas pipeline small leakage feature extraction and recognition based on LMD envelope spectrum entropy and SVM

“…The kurtosis value increases significantly as the number of impact components of a signal increases [23]. During a pipeline leak, the turbulent jets formed by the leaking gas are mainly experienced as impacts on the walls of the aperture, and the kurtosis value is proportional to the number of impact components in the signal; correspondingly, a pipeline leakage signal will contain more impact components.…”

The application of a general mathematical morphological particle as a novel indicator for the performance degradation assessment of a bearing

“…As a powerful nonlinear methodology for the quantitative analysis of geometrical structures, MM theory has become a popular method in various aspects of signal processing in recent years [2]. Many articles focusing on applying MM theory for detecting machinery faults have been published because it can efficiently extract impulsive signals that are purely based on time-domain analysis with a fast calculation [27][28][29][30][31]. Related research studies on MM theory for mechanical signal processing can be summarized as the following three aspects.…”