A Fault Feature Extraction Method Based on LMD and MSE for Reciprocating Compressor

2014 ◽  
Vol 530-531 ◽  
pp. 345-348
Author(s):  
Min Qiang Xu ◽  
Hai Yang Zhao ◽  
Jin Dong Wang
Keyword(s):  
Feature Extraction ◽  
Extraction Method ◽  
Vibration Signal ◽  
Multiscale Entropy ◽  
Reciprocating Compressor ◽  
Feature Extraction Method ◽  
Feature Vectors ◽  
Euclidean Distances ◽  
Coupling Characteristics ◽  
Fault Feature Extraction

This paper presents a feature extraction method based on LMD and MSE for reciprocating compressor according to the strong nonstationarity, nonlinearity and features coupling characteristics of vibration signal. The vibration signal was decomposed into a set of PFs, and then multiscale entropy of the first several PFs were calculated as feature vectors with different scale factors. Based on the maximum of average Euclidean distances, the feature vectors which have the best divisibility were selected. The feature vectors of reciprocating compressor at different bearing clearance states were extracted using this method, and superiority of this method is verified by comparing with the results of sample entropy.

scholarly journals Fault Feature Extraction for Anchor Bolt Loosening of Escalator Based on EWT and Bispectrum Analysis

CONVERTER ◽  
2021 ◽  
pp. 681-695
Author(s):  
Zheng Yan
Keyword(s):  
Feature Extraction ◽  
Public Transportation ◽  
Extraction Method ◽  
Large Scale ◽  
Anchor Bolt ◽  
Feature Extraction Method ◽  
Feature Vectors ◽  
Empirical Wavelet Transform ◽  
Bolt Loosening ◽  
Fault Feature Extraction

Escalator is an essential large-scale public transportation equipment. Once the failure occurs, it will inevitably affect the operation and even cause safety accidents.  As an important part of the structure of escalator, the loosening of the anchor bolt will lead to abnormal operation of escalator.  Aiming at the current difficultyin extracting the fault features of anchor bolt loosening, a fault feature extraction method of escalator anchor loosening is constructed based on empirical wavelet transform (EWT) and bispectrum analysis. First, perform EWT decomposition of the original footing vibration acceleration signal to obtain a series of empirical mode functions(EMFs).Then, for each empirical mode function, the bispectrum was calculated by using bispectrum analysis method, and six texture features of the bispectrum were extracted as fault feature vectors by means of gray-gradient co-occurrence matrix.  Finally, the extracted multi-scale fault feature vectors and bi-directional longshort-term memory (BI-LSTM) were used to classify and identify the four types of fault signals with different degrees of foot loosening, and the fault types of foot loosening were determined. The results show that the feature extraction method based on empirical wavelet decomposition and bispectrum analysis can more effectively identify the loosening level of anchor bolts.

scholarly journals Multistage Fault Feature Extraction of Consistent Optimization for Rolling Bearings Based on Correlated Kurtosis

2020 ◽  
Vol 2020 ◽  
pp. 1-16
Author(s):  
Long Zhang ◽  
Binghuan Cai ◽  
Guoliang Xiong ◽  
Jianmin Zhou ◽  
Wenbin Tu ◽  
...  
Keyword(s):  
Feature Extraction ◽  
Fault Diagnosis ◽  
Vibration Signal ◽  
Diagnostic Methods ◽  
Rolling Bearings ◽  
Feature Extraction Method ◽  
Transmission Path ◽  
The Individual ◽  
Envelope Spectrum ◽  
Fault Feature Extraction

Fault diagnosis of rolling bearings is not a trivial task because fault-induced periodic transient impulses are always submerged in environmental noise as well as large accidental impulses and attenuated by transmission path. In most hybrid diagnostic methods available for rolling bearings, the problems lie in twofolds. First, most optimization indices used in the individual signal processing stage do not take the periodical characteristic of fault transient impulses into consideration. Second, the individual stages make use of different optimization indices resulting in inconsistent optimization directions and possibly an unsatisfied diagnosis. To solve these problems, a multistage fault feature extraction method of consistent optimization for rolling bearings based on correlated kurtosis (CK) is proposed where maximum correlated kurtosis deconvolution (MCKD) is employed to attenuate the influence of transmission path followed by tunable Q factor wavelet transform (TQWT) to further enhance fault features by decomposing the preprocessed signals into multiple subbands under different Q values. The major contribution of the proposed approach is to consistently use CK as an optimization index of both MCKD and TQWT. The subband signal with the maximum CK which is an index being able to measure the periodical transient impulses in vibration signal yields an envelope spectrum, from which fault diagnosis is implemented. Simulated and experimental signals verified the effectiveness and advantages of the proposed method.

Sign in / Sign up

Export Citation Format

Share Document