The MFBD: a novel weak features extraction method for rotating machinery

Abstract

For the fault diagnosis of rotating machinery, the demodulation algorithm of the monitoring signals plays a key role in fault feature extraction. Especially for weak fault features extraction, existing single narrow band demodulation methods have worse performance under low signal to noise ratio condition. According to the mechanism of rotating machinery, both narrow and broad frequency band modulated signals exist simultaneously. Therefore, weak fault features can be obtained through demodulation of multiple narrow frequency bands rather than only one resonance narrow band. In this study, a novel weak feature extraction method is proposed based on used as a good filtermultiple frequency bands demodulation. The superiority of the proposed method is corroborated by simulation analysis and applications of a centrifugal pump and a propeller. By simulation analysis, the proposed multiple frequency bands demodulation (MFBD) method has better demodulation performance than Fast Kurtogram, Autogram and Fast-SC for weak modulation features. The applications results suggested that the proposed MFBD provided a clearer characteristic frequency identification than Fast Kurtogram, Autogram and Fast-SC, especially in weak modulation condition. Therefore, the proposed MFBD method provides a reliable basis for weak fault signal extraction, which shows good engineering significance for fault diagnosis of rotating machinery and passive detection of propeller.

Traction Machine State Recognition Method Based on DPCA Algorithm and Convolution Neural Network

“…The time-frequency distribution matrix reveals the variation patterns of signals in both time and frequency dimensions, providing a basis for subsequent principal component analysis and feature extraction [ 17 ].…”

On-Line Monitoring and Intelligent Diagnosis Technology of Rail Transit Ventilation System

“…According to the research status of demodulation algorithm based on high-order statistics, although the demodulation algorithm based on high-order statistics can obtain better demodulation accuracy, its computational efficiency is low, and its noise resistance needs to be further improved, so it is difficult to realize the online analysis of monitoring signals. For these defaults, the DPCA method, which is a demodulation method based on TFA and PCA, was proposed by Song et al [27,28]. Based on this method, the dimension of time-frequency distribution matrix can be reduced to realize the fast demodulation of signals.…”

Research on State Recognition Technology of Elevator Traction Machine Based on Modulation Feature Extraction

“…In addition, the above methods can extract the characteristics of vibration signals, but the collected vibration signals usually contain background noise and unknown frequency interference. To eliminate noise component and extract the fault feature information of raw vibration signals, several demodulation techniques have been applied to past research, such as Hilbert transform (HT) [ 16 ], empirical mode composition (EMD) [ 17 ], spectral kurtosis (SK) [ 18 ], nonstationary analysis [ 19 , 20 , 21 ], and cyclostationary analysis [ 22 , 23 , 24 ]. These methods have been applied to modulation frequency extraction already, which noted the modulation mechanism in a rotating machine.…”

“…Most vibration signals of traction machine are non-stationary signals, but they are cyclostationary signals, namely, the correlation function of traction machine signals is periodic function of time. In view of the cyclostationary analysis theory, a variety of methodologies have been proposed, in which cyclic modulation spectrum (CMS) and fast spectral correlation (Fast-SC) are two typical cyclostationary tools [ 22 ]. However, they did not gain its deserved attention because of high computational cost.…”