Feature Extraction of Vibration of Centrifugal Fan Based on LLE

2014 ◽  
Vol 1070-1072 ◽  
pp. 1941-1944
Author(s):  
Yong Hao Liao ◽  
Bo Liu
Keyword(s):  
Feature Extraction ◽  
Diagnostic Accuracy ◽  
Wavelet Packet ◽  
Centrifugal Fan ◽  
Analysis Method ◽  
Feature Extraction Method ◽  
Different Types ◽  
Feature Information ◽  
New Feature ◽  
Better Than

In order to improve classification ability and diagnostic accuracy of centrifugal fan signals, a new feature extraction method from fault signals of centrifugal fan vibration based on manifold learning method (MLM) that is a kind of reduction method of data dimension is proposed in this paper.The MLM is able to remain nonlinear information of original signal, to improve the classification and diagnostic ability of fault better than traditional reducing dimension methods. The results in this paper show that, fault feature information of centrifugal fan vibration is extracted effectively by the MLM and the fault feature information of different types are separated effectively in themselves areas. The diagnostic accuracy by feature extracted by the MLM is significantly higher than by the wavelet packet analysis method.

Research on Feature Extraction Method Based on Rub-Impact Acoustic Emission Signals of Mechanical Seal End Faces

2010 ◽  
Vol 36 ◽  
pp. 68-74
Author(s):  
Chuan Jun Liao ◽  
Shuang Fu Suo ◽  
Wei Feng Huang
Keyword(s):  
Acoustic Emission ◽  
Feature Extraction ◽  
Extraction Methods ◽  
Mechanical Seal ◽  
Mechanical Seals ◽  
Feature Extraction Method ◽  
Different Types ◽  
Ae Signal ◽  
Feature Information ◽  
Ae Signals

Acoustic emission (AE) techniques are put forward to monitor rub-impacts between rotating rings and stationary rings of mechanical seals by this paper. By analyzing feature extraction methods of the typical rub-impact AE signal, the method combining of wavelet scalogram and power spectrum is found useful, and can used to attribute the feature information implicated in rub-impact AE signals of mechanical seal end faces. Both simulations and experimental research prove that the method is effective, and are used successfully to identify the typical features of different types of rub-impacts of mechanical seal end faces.

Border and Coastal Surveillance Sound Target Classification Based on Optimum Wavelet Packet Decomposition

2011 ◽  
Vol 225-226 ◽  
pp. 725-728 ◽  
Author(s):  
Yan Wang ◽  
Zhi Li
Keyword(s):  
Feature Extraction ◽  
Bp Neural Network ◽  
Extraction Method ◽  
Wavelet Packet ◽  
Wavelet Packet Decomposition ◽  
Target Classification ◽  
Feature Extraction Method ◽  
Multi Scale ◽  
New Feature ◽  
Sound Target

The present work contributes to the field of border and coastal surveillance sound target classification. A new feature extraction method is proposed based on the optimum wavelet packet decomposition (OWPD). According to the frequency characteristic of border and coastal surveillance sound signals, each signal is decomposed by selective multi-scale wavelet packet decomposition (WPD) and the OWPD tree is obtained. From their high dimension OWPD coefficients, we build the meaningful and compact energy feature vectors, then use them as the input vectors of the BP neural network to classify the border and coastal surveillance sound types. Extensive experimental results show that the classification efficiency is up to 94% using this feature extraction method, improved 6% compared with the method based on WPD.

scholarly journals Fault Diagnosis Method for Hydraulic Pump Based on Fuzzy Entropy of Wavelet Packet and LLTSA

2018 ◽  
Vol 14 (02) ◽  
pp. 60
Author(s):  
Wang Fei ◽  
Fang Liqing ◽  
Qi Ziyuan
Keyword(s):  
Feature Extraction ◽  
Wavelet Packet ◽  
Vibration Signal ◽  
Classification Performance ◽  
Fuzzy Entropy ◽  
Support Vector ◽  
Hydraulic Pump ◽  
Feature Extraction Method ◽  
Diagnosis Method ◽  
New Feature

<p>As the vibration signal <a href="app:ds:characteristic" target="_self">characteristic</a>s of hydraulic pump <a href="app:ds:present%20(a%20certain%20appearance)" target="_self">present</a> non-stationary and the fault features is difficult to extract, a new feature extraction method was proposed .This approach combines wavelet packet analysis techniques, fuzzy entropy and LLTSA (liner local tangent space alignment) which is one of typical manifold learning methods to <a href="app:ds:extract" target="_self">extract</a>ing  <a href="app:ds:fault" target="_self">fault</a>  feature. Firstly, the vibration signals were decomposed into eight signals in different <a href="app:ds:scale" target="_self">scale</a>s, then the fuzzy entropies of signals were calculated to constitute eight <a href="app:ds:many%20dimensions" target="_self">dimensions</a> <a href="app:ds:feature" target="_self">feature</a> vector. Secondly, LLTSA method was applied to compress the high-dimension features into low-dimension features which have a better classification performance. Finally, the SVM (support vector machine) was employed to <a href="app:ds:distinguish" target="_self">distinguish</a> different <a href="app:ds:fault" target="_self">fault</a> features. Experiment results of hydraulic pump feature extraction show that the proposed method can exactly classify different fault type of hydraulic pump and this method has a significant advantage <a href="app:ds:compare" target="_self">compare</a>d with other feature extraction means mentioned in this paper.</p><p> </p>

A novel GNSS deformation feature extraction method based on ensemble improved LMD threshold denoising

2020 ◽  
Vol 14 (4) ◽  
pp. 445-453
Author(s):  
Qian Fan ◽  
Yiqun Zhu
Keyword(s):  
Feature Extraction ◽  
Spline Interpolation ◽  
Simulated Data ◽  
Mining Area ◽  
Deformation Monitoring ◽  
Denoising Method ◽  
Feature Extraction Method ◽  
Deformation Feature ◽  
Mode Decomposition ◽  
Better Than

AbstractIn order to solve the problem that the moving span of basic local mean decomposition (LMD) method is difficult to choose reasonably, an improved LMD method (ILMD), which uses three cubic spline interpolation to replace the sliding average, is proposed. On this basis, with the help of noise aided calculation, an ensemble improved LMD method (EILMD) is proposed to effectively solve the modal aliasing problem in original LMD. On the basis of using EILMD to effectively decompose the data of GNSS deformation monitoring series, GNSS deformation feature extraction model based on EILMD threshold denoising is given by means of wavelet soft threshold processing mode and threshold setting method in empirical mode decomposition denoising. Through the analysis of simulated data and the actual GNSS monitoring data in the mining area, the results show that denoising effect of the proposed method is better than EILMD, ILMD and LMD direct coercive denoising methods. It is also better than wavelet analysis denoising method, and has good adaptability. This fully demonstrates the feasibility and effectiveness of the proposed method in GNSS feature extraction.

Hot Strip Tail Flick Recognition Based on Morphological Pattern Spectrum

2012 ◽  
Vol 572 ◽  
pp. 25-30
Author(s):  
Li Jing Han ◽  
Jian Hong Yang ◽  
Min Lin ◽  
Jin Wu Xu
Keyword(s):  
Feature Extraction ◽  
Extraction Method ◽  
Steel Strip ◽  
Wavelet Packet ◽  
Support Vector ◽  
Tail Flick ◽  
Morphological Pattern ◽  
Feature Extraction Method ◽  
Pattern Spectrum ◽  
Hot Strip

Hot strip tail flick is an abnormal production phenomenon, which brings many damages. To recognize the tail flick signals from all throwing steel strip signals, a feature extraction method based on morphological pattern spectrum is proposed in this paper. The area between signal curves after multiscale opening operation and the horizontal axis is computed as the pattern spectrum value and it reflects the geometric information differences. Then, support vector machine is used as the classifier. Experimental results show that the total correct rate based on pattern spectrum feature reached 96.5%. Compared with wavelet packet energy feature, the total correct rate is 92.1%. So, the feasibility and availability of this new feature extraction method are verified.

scholarly journals Machine Fault Classification Based on Local Discriminant Bases and Locality Preserving Projections

2014 ◽  
Vol 2014 ◽  
pp. 1-12 ◽  
Author(s):  
Qingbo He ◽  
Xiaoxi Ding ◽  
Yuanyuan Pan
Keyword(s):  
Feature Extraction ◽  
Wavelet Packet ◽  
Fault Classification ◽  
Feature Extraction Method ◽  
Locality Preserving Projections ◽  
Vibration Data ◽  
Pattern Structure ◽  
Locality Preserving ◽  
Machine Fault

Machine fault classification is an important task for intelligent identification of the health patterns for a mechanical system being monitored. Effective feature extraction of vibration data is very critical to reliable classification of machine faults with different types and severities. In this paper, a new method is proposed to acquire the sensitive features through a combination of local discriminant bases (LDB) and locality preserving projections (LPP). In the method, the LDB is employed to select the optimal wavelet packet (WP) nodes that exhibit high discrimination from a redundant WP library of wavelet packet transform (WPT). Considering that the obtained discriminatory features on these selected nodes characterize the class pattern in different sensitivity, the LPP is then applied to address mining inherent class pattern feature embedded in the raw features. The proposed feature extraction method combines the merits of LDB and LPP and extracts the inherent pattern structure embedded in the discriminatory feature values of samples in different classes. Therefore, the proposed feature not only considers the discriminatory features themselves but also considers the dynamic sensitive class pattern structure. The effectiveness of the proposed feature is verified by case studies on vibration data-based classification of bearing fault types and severities.

scholarly journals Research on the Fault Feature Extraction Method of Rotor Systems Based on GAW-PSO

2020 ◽  
Vol 2020 ◽  
pp. 1-10 ◽  
Author(s):  
Feng Miao ◽  
Rongzhen Zhao ◽  
Xianli Wang
Keyword(s):  
Feature Extraction ◽  
Optimization Method ◽  
Population Diversity ◽  
Blind Separation ◽  
Feature Extraction Method ◽  
Rotor Systems ◽  
The Difference ◽  
Dynamic Hybrid ◽  
Fault Feature Extraction ◽  
Better Than

In order to solve the problem of blind separation of signals from dynamic hybrid rotor systems, this paper proposed an improved adaptive inertial weight particle swarm optimization method based on genetic mechanism. The method takes the negative entropy of separated signal as the objective function and adaptively adjusts the inertia weight according to the difference of particle fitness, thus reducing the number of invalid iterations. At the same time, genetic hybridization mechanism was introduced to increase population diversity and facilitate the processing of dynamic mixed signals. The orthogonal matrix is expressed as a parameterized form, which can reduce the complexity of the algorithm. The simulation results showed that the performance of the proposed method is better than that of the traditional method for blind separation of dynamic hybrid analog mechanical signals. It can separate the actual dynamic rotor system signals and achieve the purpose of fault feature extraction.

An Insect Song Signal Feature Extraction Method Based on the Wavelet Packet Analysis

2013 ◽  
Vol 423-426 ◽  
pp. 2614-2617
Author(s):  
Jun Xie ◽  
Hong Wei Wang ◽  
Mei Zhao ◽  
Kai Yu Yang
Keyword(s):  
Feature Extraction ◽  
Quality Evaluation ◽  
Evaluation Method ◽  
Wavelet Packet ◽  
Correlation Coefficients ◽  
Sound Quality ◽  
Signal Frequency ◽  
Feature Extraction Method ◽  
Frequency Decomposition ◽  
Cricket Song

The wavelet packet decomposition method was used to two common insects song signal. Frequency decomposition and feature extraction were made, the feature vectors, eigenvalues and the sound quality evaluation parameter vectors were constructed, then the correlation analysis calculation were made between the eigenvalues and the sound quality evaluation parameter vectors. The results show that the correlation coefficients are good, the average correlation coefficients of cricket and grasshopper song signals are 0.8875 and 0.6942, the results of cricket is much better than grasshopper, it proved that the proposed algorithm is more suitable for cricket song signals analysis, a new and effective sound quality evaluation method for typical insect with friction sound mechanism is provided.

Sign in / Sign up

Export Citation Format

Share Document