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

Entropy ◽  
2019 ◽  
Vol 21 (2) ◽  
pp. 152 ◽  
Author(s):  
Nibaldo Rodriguez ◽  
Pablo Alvarez ◽  
Lida Barba ◽  
Guillermo Cabrera-Guerrero
Keyword(s):  
Feature Extraction ◽  
Wavelet Packet ◽  
Vibration Signal ◽  
Work Conditions ◽  
Extraction Methods ◽  
Rolling Element Bearing ◽  
Bearing Failure ◽  
Wavelet Entropy ◽  
Multi Scale ◽  
Diagnosis Accuracy

Discriminative feature extraction and rolling element bearing failure diagnostics are very important to ensure the reliability of rotating machines. Therefore, in this paper, we propose multi-scale wavelet Shannon entropy as a discriminative fault feature to improve the diagnosis accuracy of bearing fault under variable work conditions. To compute the multi-scale wavelet entropy, we consider integrating stationary wavelet packet transform with both dispersion (SWPDE) and permutation (SWPPE) entropies. The multi-scale entropy features extracted by our proposed methods are then passed on to the kernel extreme learning machine (KELM) classifier to diagnose bearing failure types with different severities. In the end, both the SWPDE–KELM and the SWPPE–KELM methods are evaluated on two bearing vibration signal databases. We compare these two feature extraction methods to a recently proposed method called stationary wavelet packet singular value entropy (SWPSVE). Based on our results, we can say that the diagnosis accuracy obtained by the SWPDE–KELM method is slightly better than the SWPPE–KELM method and they both significantly outperform the SWPSVE–KELM method.

A fractal-dimension-based envelope demodulation for rolling element bearing fault feature extraction from vibration signals

2016 ◽  
Vol 230 (18) ◽  
pp. 3194-3211 ◽  
Author(s):  
Juanjuan Shi ◽  
Ming Liang
Keyword(s):  
Feature Extraction ◽  
Fractal Dimension ◽  
Search Algorithm ◽  
Vibration Signal ◽  
Rolling Element Bearing ◽  
Vibration Signals ◽  
Bearing Fault ◽  
Bearing Condition Monitoring ◽  
Interference Frequency ◽  
Fault Feature Extraction

Vibration analysis has been extensively used as an effective tool for bearing condition monitoring. The vibration signal collected from a defective bearing is, however, a mixture of several signal components including the fault feature (i.e. fault-induced impulses), periodic interferences from other mechanical/electrical components, and background noise. The incipient impulses which excite as well as modulate the resonance frequency of the system are easily masked by compounded effects of periodic interferences and noise, making it challenging to do a reliable fault diagnosis. As such, this paper proposes an envelope demodulation method termed short time fractal dimension (STFD) transform for fault feature extraction from such vibration signal mixture. STFD transform calculation related issues are first addressed. Then, by STFD, the original signal can be quickly transformed into a STFD representation, where the envelope of fault-induced impulses becomes more pronounced whereas interferences are partly weakened due to their morphological appearance differences. It has been found that the lower the interference frequency, the less effect the interference has on STFD representations. When interference frequency keeps increasing, more effects on STFD representations will be resulted. Such effects can be reduced by the proposed kurtosis-based peak search algorithm (KPSA). Therefore, bearing fault signature is kept and interferences are further weakened in the STFD-KPSA representation. The proposed method has been favourably compared with two widely used enveloping methods, i.e. multi-morphological analysis and energy operator, in terms of extracting impulse envelopes from vibration signals obscured by multiple interferences. Its performance has also been examined using both simulated and experimental data.

Fan Fault Feature Extraction Based on Wavelet Packet Transform

2014 ◽  
Vol 668-669 ◽  
pp. 999-1002
Author(s):  
Xin Li ◽  
Pan Feng Guo
Keyword(s):  
Feature Extraction ◽  
Fault Diagnosis ◽  
Wavelet Packet ◽  
Vibration Signal ◽  
Wavelet Packet Transform ◽  
Research Topic ◽  
Signal Characteristic ◽  
Manufacturing Enterprises ◽  
Important Position ◽  
Fault Feature Extraction

Fan occupies the important position in many industry, it give rise to that fault diagnosis become the new hot research topic, also is the urgent demand of many manufacturing enterprises. This paper based on the theory of wavelet packet transform, selecting wavelet packet transform and energy spectrum to wavelet de-noising and fault feature extraction the fan vibration signal. And use the MATLAB get the fan vibration signal characteristic vector, lay the foundation for the fan fault diagnosis.

scholarly journals A Novel Feature Extraction Method for Power Transformer Vibration Signal Based on CEEMDAN and Multi-Scale Dispersion Entropy

Entropy ◽  
2021 ◽  
Vol 23 (10) ◽  
pp. 1319
Author(s):  
Haikun Shang ◽  
Junyan Xu ◽  
Yucai Li ◽  
Wei Lin ◽  
Jinjuan Wang
Keyword(s):  
Feature Extraction ◽  
Fault Diagnosis ◽  
Extraction Method ◽  
Vibration Signal ◽  
Practical Significance ◽  
Stable Operation ◽  
Intrinsic Mode Functions ◽  
Vibration Signals ◽  
Feature Extraction Method ◽  
Multi Scale

Effective diagnosis of vibration fault is of practical significance to ensure the safe and stable operation of power transformers. Aiming at the traditional problems of transformer vibration fault diagnosis, a novel feature extraction method based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and multi-scale dispersion entropy (MDE) was proposed. In this paper, CEEMDAN method is used to decompose the original transformer vibration signal. Additionally, then MDE is used to capture multi-scale fault features in the decomposed intrinsic mode functions (IMFs). Next, the principal component analysis (PCA) method is employed to reduce the feature dimension and extract the effective information in vibration signals. Finally, the simplified features are sent into density peak clustering (DPC) to get the fault diagnosis results. The experimental data analysis shows that CEEMDAN-MDE can effectively extract the information of the original vibration signals and DPC can accurately diagnose the types of transformer faults. By comparing different algorithms, the practicability and superiority of this proposed method are verified.

Learning Advanced Brain Computer Interface Technology

2019 ◽  
Vol 15 (3) ◽  
pp. 14-27
Author(s):  
Wang Tao ◽  
Wu Linyan ◽  
Li Yanping ◽  
Gao Nuo ◽  
Zhang Weiran
Keyword(s):  
Feature Extraction ◽  
Classification Accuracy ◽  
Wavelet Packet ◽  
Extraction Methods ◽  
Support Vector ◽  
Wavelet Packet Analysis ◽  
Accuracy Rate ◽  
Desirable Outcome ◽  
Eeg Data ◽  
System Data

Feature extraction is an important step in electroencephalogram (EEG) processing of motor imagery, and the feature extraction of EEG directly affects the final classification results. Through the analysis of various feature extraction methods, this article finally selects Common Spatial Patterns (CSP) and wavelet packet analysis (WPA) to extract the feature and uses Support Vector Machine (SVM) to classify and compare these extracted features. For the EEG data provided by GRAZ University, the accuracy rate of feature extraction using CSP algorithm is 85.5%, and the accuracy rate of feature extraction using wavelet packet analysis is 92%. Then this paper analyzes the EEG data collected by Emotiv epoc+ system. The classification accuracy of wavelet packet extracted features can still be maintained at more than 80%, while the classification accuracy of CSP extracted feature is decreased obviously. Experimental results show that the method of wavelet packet analysis towards competition data and Emotiv epoc+ system data can both get a desirable outcome.

scholarly journals Comparison of different feature extraction methods for the analysis of uterine magnetomyography signals to predict term labor

2018 ◽  
Vol 7 (3.29) ◽  
pp. 1
Author(s):  
T Ananda Babu ◽  
Dr P. Rajesh Kumar
Keyword(s):  
Feature Extraction ◽  
Wavelet Transform ◽  
Discrete Wavelet Transform ◽  
Wavelet Packet ◽  
Extraction Methods ◽  
Wavelet Packet Transform ◽  
Svm Classifier ◽  
Discrete Wavelet ◽  
Term Labor

The prediction of term labor by analyzing the uterine magnetomyographic signals attempted in this research. The existing works did not focus on the classification of the signals. Publicly available MIT-BIH database records were divided into term-labor and term-nonlabor groups. This research presents two methods for feature extraction, discrete wavelet transform and wavelet packet transform. Energy, standard deviation, variance, entropy and waveform length of transform coefficients used in the first method. The normalized logarithmic energy of wavelet coefficients from each packet of the total wavelet packet tree used as the feature space for the second method. The labor assessment done through the classification of the features by using five different classifiers for different mother wavelet families. Discrete wavelet transform features extracted using coif5 wavelet with random subspace classification gives the accuracy, precision and FPrates of 93.9286%, 94.2014% and 5.7986% respectively. Using sym8 wavelet for wavelet packet transform features classified with SVM classifier performed well with 95.8763% accuracy, 95.9719% precision and 4.0281% FPrate. The results obtained from the research will be helpful in term labor assessment and understanding the parturition process.  

Weak feature extraction of rolling element bearing based on self-adaptive blind de-convolution and enhanced envelope spectral

2021 ◽  
pp. 107754632110507
Author(s):  
HongChao Wang ◽  
WenLiao Du ◽  
Haiyi Li ◽  
Zhiwei Li ◽  
Jiale Hu
Keyword(s):  
Feature Extraction ◽  
Vibration Signal ◽  
Rolling Element Bearing ◽  
Enhancement Effect ◽  
Minimum Entropy ◽  
Rolling Element ◽  
Element Bearing ◽  
Repetitive Impact ◽  
The Impact ◽  
Fault Feature Extraction

As the most commonly used support component in engineering, rolling element bearing is also the most prone-to-failure part. The vibration signal of faulty bearing will take on repetitive impact and modulation characteristics, and the two features are often difficult to be extracted by conventional fault feature extraction methods such as envelope spectral. The main reasons are due to the influence of strong background noise, the signal attenuation of the acquisition path, and the early weak failure characteristics. To solve the above problem, a weak fault feature extraction method of rolling element bearing by combing improved minimum entropy de-convolution with enhanced envelope spectral is proposed in the paper. The enhancement effect of improved minimum entropy de-convolution on impact features and the satisfactory extraction effect of EES on repetitive impact and modulation features are utilized comprehensively by the proposed method. Firstly, improved minimum entropy de-convolution is used to filter the vibration signal of faulty bearing to enhance the impact characteristics, and the influence of signal acquisition path on the attenuation of the signal characteristics is also weakened at the same time. Then, enhanced envelope spectral is performed on the filtered signal, and the repetitive impact and modulation characteristics of vibration signal are extracted synchronously. In order to solve the shortcomings of the current commonly used de-convolution methods, an improved minimum entropy de-convolution method based on D-norm is proposed, which can solve the interference caused by random impulsive signals effectively. In addition, compared with the conventional method such as envelope spectral, the enhanced envelope spectral method could extract the repetitive impact and modulation characteristics of the faulty signal simultaneously much more effectively. Effectiveness and superiority of the proposed method are verified through simulation, experiment, and engineering application.

The Research of the Rolling Element Bearing Fault Signal Frequency Domain Feature Extraction Method Based on the Wavelet Packet Decomposition

2014 ◽  
Vol 937 ◽  
pp. 351-356 ◽  
Author(s):  
Shi Yin Qiu ◽  
Rui Bo Yuan
Keyword(s):  
Pattern Recognition ◽  
Feature Extraction ◽  
Euclidean Distance ◽  
Wavelet Packet ◽  
Feature Space ◽  
Rolling Element Bearing ◽  
Signal Spectrum ◽  
Wavelet Packet Decomposition ◽  
Bearing Fault ◽  
Optimal Feature

The wavelet packet decomposition can be used to extract the frequency band containing bearing fault feature, because the fault signal can be decomposed into different frequency bands by using the wavelet packet decomposition, that is to say the optimal wavelet packet decomposition node needs to be found. A method applying the average Euclidean distance to find the optimal wavelet packet decomposition node was presented. First of all, the bearing fault signals were decomposed into three layers wavelet coefficients by which the bearing fault signals were reconstructed. The peak values extracted from the reconstructing signal spectrum constructed a feature space. Then, the minimum average Euclidean distance calculated from the feature space indicated the optimal wavelet packet node. The optimal feature space could be constructed by the feature points extracted from the signals reconstructed by the optimal wavelet packet nodes. Finally, the optimal feature space was used for the K-means clustering. The feature extraction and pattern recognition test of the four kinds of bearing conditions under four kinds of rotation speeds was detailed. The test results show this method, which can extract the bearing fault feature efficiently and make the fault feature space have the lowest within-class scatter, wons a high pattern recognition accuracy.

scholarly journals Online monitoring and diagnosis of high voltage circuit breaker faults: feature extraction analysis of vibration signals

2019 ◽  
Vol 10 ◽  
pp. 13 ◽  
Author(s):  
Long Li ◽  
Jianfeng Xiao ◽  
Bin Wu ◽  
Mengge Zhou ◽  
Qian Wang
Keyword(s):  
Feature Extraction ◽  
High Voltage ◽  
Extraction Method ◽  
Wavelet Packet ◽  
Circuit Breaker ◽  
Vibration Signal ◽  
Normal Operation ◽  
Support Vector ◽  
Feature Extraction Method ◽  
High Voltage Circuit Breaker

The development of power grid system not only increases voltage and capacity, but also increases power risk. This paper briefly introduces the feature extraction method of the vibration signal of high voltage circuit breaker and support vector machine (SVM) algorithm and then analyzed the high voltage circuit breaker in three states: normal operation, fixed screw loosening and falling of opening spring, using the SVM based on the above feature extraction method. The results showed that the accuracy and precision rates of fault identification of circuit breaker were the highest by using the wavelet packet energy entropy extraction features, the false alarm rate was the lowest, and the detection time was the shortest.

Forearm EMG Signal Classification Based on Singular Value Decomposition and Wavelet Packet Transform Features

2012 ◽  
Vol 433-440 ◽  
pp. 912-916 ◽  
Author(s):  
Mohammad Karimi
Keyword(s):  
Feature Extraction ◽  
Singular Value Decomposition ◽  
Wavelet Packet ◽  
Extraction Methods ◽  
Wavelet Packet Transform ◽  
Singular Value ◽  
Wrist Flexion ◽  
Emg Signal ◽  
Value Decomposition ◽  
Svd Method

The myoelectric signal (MES) with broad applications in various areas especially in prosthetics and myoelectric control, is one of the biosignals utilized in helping humans to control equipments. In this paper, a technique for feature extraction of forearm electromyographic (EMG) signals using wavelet packet transform (WPT) and singular value decomposition (SVD) is proposed. In the first step, the WPT is employed to generate a wavelet decomposition tree from which features are extracted. In the second step, an algorithm based on singular value decomposition (SVD) method is introduced to compute the feature vectors for every hand motion. This technique can successfully identify eight hand motions including forearm pronation, forearm supination, wrist flexion, wrist abduction, wrist adduction, chuck grip, spread fingers and rest state. These motions can be obtained by measuring the surface EMG signal through sixteen electrodes mounted on the pronator and supinator teres, flexor digitorum, sublimas, extensor digitorum communis, and flexor and extensor carpi ulnaris. Moreover, through quantitative comparison with other feature extraction methods like entropy concept in this paper, SVD method has a better performance. The results showed that proposed technique can achieve a classification recognition accuracy of over 96% for the eight hand motions.

Sign in / Sign up

Export Citation Format

Share Document