Pipeline Leakage Recognition Based on the Projection Singular Value Features and Support Vector Machine

2010 ◽  
Author(s):  
Mingda Wang ◽  
Laibin Zhang ◽  
Wei Liang ◽  
Jinqiu Hu
Keyword(s):  
Support Vector Machine ◽  
Feature Extraction ◽  
Field Experiments ◽  
Small Sample ◽  
Singular Value ◽  
Support Vector ◽  
Leakage Detection ◽  
Feature Extraction Method ◽  
Standard Bases ◽  
Value Decomposition

Identification of negative pressure waveform is the key of pipeline leakage detection. The feature extraction and the choice of the classifier are two main contents to solve the recognition problem. In this paper, a new feature extraction method based on the Projection Singular Value is presented. First of all, the two orthogonal singular value decomposition matrixes of the typical leakage waveform are extracted as the standard bases. Then the projection singular value features of the other pressure wave matrixes are extracted by being projected to the two standard bases. As the pipeline leakage is a small probability event, it is difficult to obtain the leakage samples. A multi-classification Support Vector Machine, which has the advantage of small sample learning, is constructed to classify these features in this paper. The field experiments indicate that the leakage detection based on this feature extraction and recognition model has a higher accuracy of leakage recognition.

scholarly journals Identification Method for Voltage Sags Based on K-means-Singular Value Decomposition and Least Squares Support Vector Machine

Energies ◽  
2019 ◽  
Vol 12 (6) ◽  
pp. 1137 ◽  
Author(s):  
Haoyuan Sha ◽  
Fei Mei ◽  
Chenyu Zhang ◽  
Yi Pan ◽  
Jianyong Zheng
Keyword(s):  
Support Vector Machine ◽  
Singular Value Decomposition ◽  
Least Squares ◽  
Short Circuit ◽  
Singular Value ◽  
Support Vector ◽  
Voltage Sag ◽  
Svm Classifier ◽  
Identification Algorithm ◽  
Value Decomposition

Voltage sag is one of the most serious problems in power quality. The occurrence of voltage sag will lead to a huge loss in the social economy and have a serious effect on people’s daily life. The identification of sag types is the basis for solving the problem and ensuring the safe grid operation. Therefore, with the measured data uploaded by the sag monitoring system, this paper proposes a sag type identification algorithm based on K-means-Singular Value Decomposition (K-SVD) and Least Squares Support Vector Machine (LS-SVM). Firstly; each phase of the sag sample RMS data is sparsely coded by the K-SVD algorithm and the sparse coding information of each phase data is used as the feature matrix of the sag sample. Then the LS-SVM classifier is used to identify the sag type. This method not only works without any dependence on the sag data feature extraction by artificial ways, but can also judge the short-circuit fault phase, providing more effective information for the repair of grid faults. Finally, based on a comparison with existing methods, the accuracy advantages of the proposed algorithm with be presented.

A Kind of Network Intrusion Detection Method Using Improved Support Vector Machine Based on Ant Colony Algorithm

2012 ◽  
Vol 263-266 ◽  
pp. 2995-2998
Author(s):  
Xiaoqin Zhang ◽  
Guo Jun Jia
Keyword(s):  
Genetic Algorithm ◽  
Support Vector Machine ◽  
Feature Extraction ◽  
Ant Colony Algorithm ◽  
Small Sample ◽  
Ant Colony ◽  
Support Vector ◽  
Algorithm Selection ◽  
Data Set ◽  
Network Intrusion

Support vector machine (SVM) is suitable for the classification problem which is of small sample, nonlinear, high dimension. SVM in data preprocessing phase, often use genetic algorithm for feature extraction, although it can improve the accuracy of classification. But in feature extraction stage the weak directivity of genetic algorithm impact the time and accuracy of the classification. The ant colony algorithm is used in genetic algorithm selection stage, which is better for the data pretreatment, so as to improve the classification speed and accuracy. The experiment in the KDD99 data set shows that this method is feasible.

Fault feature extraction and classification based on WPT and SVD: Application to element bearings with artificially created faults under variable conditions

2016 ◽  
Vol 231 (22) ◽  
pp. 4186-4196 ◽  
Author(s):  
Mourad Kedadouche ◽  
Zhaoheng Liu
Keyword(s):  
Support Vector Machine ◽  
Singular Value Decomposition ◽  
Wavelet Packet ◽  
Rolling Bearing ◽  
Wavelet Packet Transform ◽  
Singular Value ◽  
Support Vector ◽  
Rolling Bearings ◽  
The Matrix ◽  
Value Decomposition

Achieving a precise fault diagnosis for rolling bearings under variable conditions is a problematic challenge. In order to enhance the classification and achieves a higher precision for diagnosing rolling bearing degradation, a hybrid method is proposed. The method combines wavelet packet transform, singular value decomposition and support vector machine. The first step of the method is the decomposition of the signal using wavelet packet transform and then instantaneous amplitudes and energy are computed for each component. The Second step is to apply the singular value decomposition to the matrix constructed by the instantaneous amplitudes and energy in order to reduce the matrix dimension and obtaining the fault feature unaffected by the operating condition. The features extracted by singular value decomposition are then used as an input to the support vector machine in order to recognize the fault mode of rolling bearings. The method is applied to a bearing with faults created using electro-discharge machining under laboratory conditions. Test results show that the proposed methodology is effective to classify rolling bearing faults with high accuracy.

Text Document Classification Using Support Vector Machine with Feature Selection Using Singular Value Decomposition

2014 ◽  
Vol 905 ◽  
pp. 528-532
Author(s):  
Hoan Manh Dau ◽  
Ning Xu
Keyword(s):  
Support Vector Machine ◽  
Singular Value Decomposition ◽  
Decision Tree ◽  
Document Classification ◽  
Singular Value ◽  
Multidimensional Data ◽  
Support Vector ◽  
Text Document ◽  
Text Document Classification ◽  
Value Decomposition

Text document classification is content analysis task of the text document and then giving decision (or giving a prediction) whether this text document belongs to which group among given text document ones. There are many classification techniques such as decision method basing on Naive Bayer, decision tree, k-Nearest neighbor (KNN), neural network, Support Vector Machine (SVM) method. Among those techniques, SVM is considered the popular and powerful one, especially, it is suitable to huge and multidimensional data classification. Text document classification with characteristics of very huge dimensional numbers and selecting features before classifying impact the classification results. Support Vector Machine is a very effective method in this field. This article studies Support Vector Machine and applies it in the problem of text document classification. The study shows that Support Vector Machine method with choosing features by singular value decomposition (SVD) method is better than other methods and decision tree.

Research on Fault Feature Extraction Method of the Wind Turbine Gearbox Based on SVD and Improved HHT

2012 ◽  
Vol 220-223 ◽  
pp. 785-788
Author(s):  
Chang Zheng Chen ◽  
Quan Gu ◽  
Bo Zhou
Keyword(s):  
Feature Extraction ◽  
Singular Value Decomposition ◽  
Wind Turbine ◽  
Extraction Method ◽  
Random Noise ◽  
Singular Value ◽  
Wind Turbine Gearbox ◽  
Feature Extraction Method ◽  
Value Decomposition ◽  
Fault Feature Extraction

This paper researches fault feature extraction method based on singular value decomposition and the improved HHT method for non-stationary characteristics of wind turbine gearbox vibration signal. Firstly, through the signal phase space reconstruction, the singular value decomposition as a pre-filter, to preprocessing the signal, effectively weaken the random noise. Then using EEMD to improve the HHT method, decompose the denoising signal into a series of different time scales component of intrinsic mode functions. The fault characteristics of the signal are extracted by the Hilbert transform. Finally, simulating gearbox fault experiment to verify the effectively of the proposed method.

Sign in / Sign up

Export Citation Format

Share Document