Power quality disturbance identification using wavelet packet energy entropy and weighted support vector machines

2008 ◽  
Vol 35 (1-2) ◽  
pp. 143-149 ◽  
Author(s):  
G HU ◽  
F ZHU ◽  
Z REN
Keyword(s):  
Support Vector Machines ◽  
Power Quality ◽  
Wavelet Packet ◽  
Support Vector ◽  
Energy Entropy ◽  
Vector Machines ◽  
Power Quality Disturbance

Material Level Noise Measuring for Steel Ball Coal Mill Based on Energy Entropy of Wavelet Packet and Least Squares Support Vector

2011 ◽  
Vol 383-390 ◽  
pp. 7183-7188
Author(s):  
Zhi Yuan Cai ◽  
Tie Li
Keyword(s):  
Support Vector Machines ◽  
Least Squares ◽  
Wavelet Packet ◽  
Measuring Method ◽  
Steel Ball ◽  
Support Vector ◽  
Energy Entropy ◽  
Vector Machines ◽  
Intelligent Material ◽  
New Material

A new material level noise measuring method of steel ball coal mill was proposed on the basis of energy entropy of wavelet packet and least squares support vector machines. First, four layers wavelet packet decomposition of the acquired noise signals was performed and the wavelet packet energy entropy was extracted; then the eigenvector of wave packet of the noise signals was constructed, the least squares support vector machines were trained to intelligent material level measuring by taking this eigenvector as sample. The simulation result from the proposed method is effective and feasible.

Transient Power Quality Disturbances Identification and Classification Using Wavelet and Support Vector Machines

2012 ◽  
Vol 433-440 ◽  
pp. 1071-1077
Author(s):  
Wen Sheng Sun ◽  
Xiang Ning Xiao ◽  
Shun Tao ◽  
Jian Wang
Keyword(s):  
Wavelet Transform ◽  
Support Vector Machines ◽  
Power Quality ◽  
Support Vector ◽  
Time Frequency ◽  
Vector Machines ◽  
Power Quality Disturbance ◽  
Time Frequency Localization ◽  
Power Quality Disturbances ◽  
Transient Power Quality

Based on wavelet transform and support vector machines, a method of recognition and classification of transient power quality disturbance is presented. Using wavelet transform time-frequency localization characteristics, according to the principle of modulus maxima, realize the automatic detection positioning. After multi-resolution signal decomposition of PQ disturbances, multi-scale information in frequency domain and time domain of the signal can be extracted as the characteristic vectors. After choose and optimization of the eigenvectors based on the method of F-score, support vector machines are used to classify these eigenvectors of power quality disturbances. Effectiveness of the proposed method is verified through Matlab simulation.

Sign in / Sign up

Export Citation Format

Share Document