Non-stationary signal analysis based on general parameterized time–frequency transform and its application in the feature extraction of a rotary machine

2017 ◽  
Vol 13 (2) ◽  
pp. 292-300 ◽  
Author(s):  
Peng Zhou ◽  
Zhike Peng ◽  
Shiqian Chen ◽  
Yang Yang ◽  
Wenming Zhang
Keyword(s):  
Feature Extraction ◽  
Signal Analysis ◽  
Time Frequency ◽  
Rotary Machine ◽  
Non Stationary Signal

Vibration Analysis of Gears with Fatigue Crack in Tooth Root

2006 ◽  
Vol 324-325 ◽  
pp. 835-838
Author(s):  
Aleš Belšak ◽  
Jože Flašker
Keyword(s):  
Fatigue Crack ◽  
Laboratory Test ◽  
Signal Analysis ◽  
Vibration Analysis ◽  
Operating Conditions ◽  
Test Plant ◽  
Tooth Root ◽  
Unit Operation ◽  
Time Frequency ◽  
Non Stationary Signal

A crack in the tooth root, which often leads to failure in gear unit operation, is the most undesirable damage caused to gear units. This article deals with fault analyses of gear units with real damages. Numerical simulations of real operating conditions have been used in relation to the formation of those damages. A laboratory test plant has been used and a possible damage can be identified by monitoring vibrations. The influences of defects of a single-stage gear unit upon the vibrations they produce are presented. Signal analysis has been performed also in concern to a non-stationary signal, using the Time Frequency Analysis tools. Typical spectrograms, which are the result of reactions to damages, are a very reliable indication of the presence of damages.

scholarly journals Screening of sleep movement disorders via EMG signal analysis

2021 ◽  
Author(s):  
Mehrnaz Shokrollahi
Keyword(s):  
Feature Extraction ◽  
Sparse Representation ◽  
Movement Disorders ◽  
Dictionary Learning ◽  
Signal Analysis ◽  
Compact Set ◽  
Emg Signal ◽  
Increased Risk ◽  
Non Stationary Signal ◽  
Representation Techniques

It is estimated that 50 to 70 million Americans suffer from a chronic sleep disorder, which hinders their daily life, affects their health, and incurs a significant economic burden to society. Untreated Periodic Leg Movement (PLM) or Rapid Eye Movement Behaviour Disorder (RBD) could lead to a three to four-fold increased risk of stroke and Parkinson’s disease respectively. These risks bring about the need for less costly and more available diagnostic tools that will have great potential for detection and prevention. The goal of this study is to investigate the potentially clinically relevant but under-explored relationship of the sleep-related movement disorders of PLMs and RBD with cerebrovascular diseases. Our objective is to introduce a unique and efficient way of performing non-stationary signal analysis using sparse representation techniques. To fulfill this objective, at first, we develop a novel algorithm for Electromyogram (EMG) signals in sleep based on sparse representation, and we use a generalized method based on Leave-One-Out (LOO) to perform classification for small size datasets. In the second objective, due to the long-length of these EMG signals, the need for feature extraction algorithms that can localize to events of interest increases. To fulfill this objective, we propose to use the Non-Negative Matrix Factorization (NMF) algorithm by means of sparsity and dictionary learning. This allows us to represent a variety of EMG phenomena efficiently using a very compact set of spectrum bases. Yet EMG signals pose severe challenges in terms of the analysis and extraction of discriminant features. To achieve a balance between robustness and classification performance, we aim to exploit deep learning and study the discriminant features of the EMG signals by means of dictionary learning, kernels, and sparse representation for classification. The classification performances that were achieved for detection of RBD and PLM by means of implicating these properties were 90% and 97% respectively. The theoretical properties of the proposed approaches pertaining to pattern recognition and detection are examined in this dissertation. The multi-layer feature extraction provide strong and successful characterization and classification for the EMG non-stationary signals and the proposed sparse representation techniques facilitate the adaptation to EMG signal quantification in automating the identification process.

Investigating Vibration Sources of Faulty Gear Units

2008 ◽  
Vol 385-387 ◽  
pp. 601-604
Author(s):  
Ales Belsak ◽  
Joze Flasker
Keyword(s):  
Signal Analysis ◽  
Analysis Tool ◽  
Tooth Root ◽  
Dynamic Parameters ◽  
Unit Operation ◽  
Time Frequency ◽  
Tooth Stiffness ◽  
Non Stationary Signal ◽  
High Degree ◽  
Very High

A crack in the tooth root is the least desirable damage of gear units, which often leads to failure of gear unit operation. A possible damage can be identified by monitoring vibrations. The influences that a crack in the tooth root of a single-stage gear unit has upon vibrations are dealt with. Changes in tooth stiffness are much more expressed in relation to a fatigue crack in the tooth root, whereas in relation to other faults, changes of other dynamic parameters are more expressed. Signal analysis has been performed in relation to a non-stationary signal, by means of the Time Frequency Analysis tool, such as Wavelets. Typical scalogram patterns resulting from reactions to faults or damages indicate the presence of faults or damages with a very high degree of reliability.

scholarly journals Screening of sleep movement disorders via EMG signal analysis

2021 ◽  
Author(s):  
Mehrnaz Shokrollahi
Keyword(s):  
Feature Extraction ◽  
Sparse Representation ◽  
Movement Disorders ◽  
Dictionary Learning ◽  
Signal Analysis ◽  
Compact Set ◽  
Emg Signal ◽  
Increased Risk ◽  
Non Stationary Signal ◽  
Representation Techniques

It is estimated that 50 to 70 million Americans suffer from a chronic sleep disorder, which hinders their daily life, affects their health, and incurs a significant economic burden to society. Untreated Periodic Leg Movement (PLM) or Rapid Eye Movement Behaviour Disorder (RBD) could lead to a three to four-fold increased risk of stroke and Parkinson’s disease respectively. These risks bring about the need for less costly and more available diagnostic tools that will have great potential for detection and prevention. The goal of this study is to investigate the potentially clinically relevant but under-explored relationship of the sleep-related movement disorders of PLMs and RBD with cerebrovascular diseases. Our objective is to introduce a unique and efficient way of performing non-stationary signal analysis using sparse representation techniques. To fulfill this objective, at first, we develop a novel algorithm for Electromyogram (EMG) signals in sleep based on sparse representation, and we use a generalized method based on Leave-One-Out (LOO) to perform classification for small size datasets. In the second objective, due to the long-length of these EMG signals, the need for feature extraction algorithms that can localize to events of interest increases. To fulfill this objective, we propose to use the Non-Negative Matrix Factorization (NMF) algorithm by means of sparsity and dictionary learning. This allows us to represent a variety of EMG phenomena efficiently using a very compact set of spectrum bases. Yet EMG signals pose severe challenges in terms of the analysis and extraction of discriminant features. To achieve a balance between robustness and classification performance, we aim to exploit deep learning and study the discriminant features of the EMG signals by means of dictionary learning, kernels, and sparse representation for classification. The classification performances that were achieved for detection of RBD and PLM by means of implicating these properties were 90% and 97% respectively. The theoretical properties of the proposed approaches pertaining to pattern recognition and detection are examined in this dissertation. The multi-layer feature extraction provide strong and successful characterization and classification for the EMG non-stationary signals and the proposed sparse representation techniques facilitate the adaptation to EMG signal quantification in automating the identification process.

A New Kind of FRFT Analysis Method for Multi-Component LFM Signals

2011 ◽  
Vol 204-210 ◽  
pp. 973-978
Author(s):  
Qiang Guo ◽  
Ya Jun Li ◽  
Chang Hong Wang
Keyword(s):  
Feature Extraction ◽  
Frequency Analysis ◽  
Signal Analysis ◽  
Fractional Fourier Transform ◽  
Analysis Method ◽  
Time Frequency Analysis ◽  
Time Frequency ◽  
Low Snr ◽  
The Time Domain ◽  
Signal Analysis Method

To effectively detect and recognize multi-component Linear Frequency-Modulated (LFM) emitter signals, a multi-component LFM emitter signal analysis method based on the complex Independent Component Analysis(ICA) which was combined with the Fractional Fourier Transform(FRFT) was proposed. The idea which was adopted to this method was the time-domain separation and then time-frequency analysis, and in the low SNR cases, the problem which is generally plagued by noised of feature extraction of multi-component LFM signal based on FRFT is overcame. Compared to the traditional method of time-frequency analysis, the computer simulation results show that the proposed method for the multi-component LFM signal separation and feature extraction was better.

Non-Stationary Signal Analysis Based on Hilbert-Huang Transform and Median Filter

2014 ◽  
Vol 1049-1050 ◽  
pp. 1694-1697
Author(s):  
Xiao Li Wang ◽  
Dian Hong Wang
Keyword(s):  
White Noise ◽  
Frequency Analysis ◽  
Signal Analysis ◽  
Median Filter ◽  
Low Noise ◽  
Analytic Framework ◽  
Noise Resistance ◽  
Hilbert Huang Transform ◽  
Time Frequency ◽  
Non Stationary Signal

The Hilbert-Huang Transform (HHT) is a new time-frequency analysis with adaptability and orthogonality, but it is rather weak in terms of noise resistance, even low noise can disturb the HHT result greatly. The paper launches an investigation on how noises affect the HHT result and proposes the method to solve the problem. The analytic framework for HHT is first introduced, the feature of the test signal is extracted by HHT. Median filter is adopted to reduce the frequency leakage of certain signal component caused by white noise. The method proposed is experimentally simulated and the results demonstrate its effectiveness.

An investigation into machine pattern recognition based on time-frequency image feature extraction using a support vector machine

2010 ◽  
Vol 224 (4) ◽  
pp. 981-994 ◽  
Author(s):  
H Li ◽  
P Zhou ◽  
Z Zhang
Keyword(s):  
Pattern Recognition ◽  
Feature Extraction ◽  
Working Conditions ◽  
Signal Analysis ◽  
Feature Vector ◽  
Rolling Bearing ◽  
Image Feature ◽  
Small Samples ◽  
Support Vector ◽  
Time Frequency

In this article, a new method of pattern recognition for machine working conditions is presented that is based on time-frequency image (TFI) feature extraction and support vector machines (SVMs). In this study, the Hilbert time-frequency spectrum (HTFS) is used to construct TFIs because of its good performance in non-stationary and non-linear signal analysis. Cyclostationarity signal analysis is a pre-processing method for improving the performance of the HTFS in the construction of TFIs. Feature extraction for TFIs is investigated in detail to construct a feature vector for pattern recognition. Gravity centre and information entropy of TFIs are used to construct the feature vector for pattern recognition. SVMs are used for different working conditions classification by the constructed feature vector because of its powerful performance even for small samples. In the end, rolling bearing pattern recognition is used as an example to testify the effectiveness of this method. According to the result analysis, it can be concluded that this method will contribute to the development of preventative maintenance.

Sign in / Sign up

Export Citation Format

Share Document