Research of Feature Extraction Method Based on Sparse Reconstruction and Multiscale Dispersion Entropy

Abstract

As one of the most important components in rotating machinery, it's necessary and essential to monitor the rolling bearing operating condition to prevent equipment failure or accidents. However, in vibration signal processing, the bearing initial fault detection under background noise is quite difficult. Therefore, in this paper a new feature extraction method combining sparse reconstruction and Multiscale Dispersion Entropy (MDErms) is proposed. Firstly, the Sliding Matrix Sequences (SMS) truncation and sparse reconstruction by Hankel-matrix are applied to the vibration signal. Then MDErms is utilized as a characteristic index of vibration signal, which is suitable for a short time series. Additionally, the MDErms is employed in the sparse reconstructed matrix sequences to achieve the Multiscale Fusion Entropy Value Sequence (MFEVS). The MFEVS keeps the fault potential feature information in different scales and is superior in distinguishing fault periodic impulses from heavy background noise. Finally, the designed FIR bandpass filter based on the MFEVS, shows prominent features in denoising and detecting weak bearing faults, which is separately verified by simulation studies and artificial fault experiments in different cases. By comparison with traditional methods like EEMD, Wavelet Packet (WP), and fast kurtogram, it can be concluded that the proposed method has a remarkable ability in removing noise and detecting rolling bearing faint fault.

Combining Multi-Scale Wavelet Entropy and Kernelized Classification for Bearing Multi-Fault Diagnosis

“…One notable feature of this function is that it can show features of hidden failures [ 6 , 7 , 8 , 9 ]. Based on these time-frequency methods for signal decomposition, different entropy features have been used such as Wiener-Shannon’s entropy [ 10 , 11 ], energy entropy [ 12 , 13 ], wavelet energy entropy [ 14 ], samples entropy [ 15 ], multiscale entropy [ 16 , 17 ], permutation entropy (PE) [ 18 , 19 , 20 , 21 ], multi-scale permutation entropy [ 22 , 23 ], generalized composite multiscale permutation entropy [ 24 ], multi-scale fuzzy entropy [ 25 ], composite multi-scale fuzzy entropy [ 26 ], dispersion entropy (DE) [ 27 ], multiscale dispersion entropy [ 28 ], and improved multiscale dispersion entropy [ 29 ]. These entropy features are, in turn, passed on to classifiers such as artificial neural networks (ANN) [ 3 , 30 , 31 , 32 ] or support vector machines (SVM) [ 12 , 17 , 18 , 24 , 26 , 33 , 34 ].…”

Noise Reduction Method of Underwater Acoustic Signals Based on CEEMDAN, Effort-To-Compress Complexity, Refined Composite Multiscale Dispersion Entropy and Wavelet Threshold Denoising

“…MDE is an interval method based on DE for measuring the complexity and regularity of time series. and the specific steps of MDE are summarized as follows [ 36 , 37 ]:…”

Separation of Magnetotelluric Signals Based on Refined Composite Multiscale Dispersion Entropy and Orthogonal Matching Pursuit

“…Multiscale entropy (MSE) was proposed to quantify the complexity of signals on multiple temporal scales. Multiscale dispersion entropy (MDE) is a parameter to evaluate the multiple scales dynamic complexity of time-series (Zhang et al 2018). The refined composite MDE (RCMDE) can increase the accuracy of entropy estimation and decrease the probability of the faced with the undefined entropy, and overcome the shortcoming of multiscale entropy (MSE) and MDE, which can combine the information of multiple coarse-grained sequences, reduce the standard deviation of entropy, make the entropy more reliable, and improve numerical stability (Azami et al 2017).…”