Application of GA and SVM based hybrid algorithm for the classification of power-quality disturbances
Journal Title: Science Paper Online - Year 2009, Vol 4, Issue 2
Abstract
For the classification of power quality disturbances, we present a GA and SVM based hybrid algorithm. Firstly, a wavelet transform technique is used for feature extraction. Then a genetic algorithm is proposed for feature selection. The support vector machine technique is used for classification of selected features. Numerical experiments validate the effectiveness of the proposed algorithm.
Authors and Affiliations
Liang SUN , Yanchun LIANG
Keywords
Related Articles
- EP ID EP91448
- DOI -
- Views 269
- Downloads 0
ISG型并联式混合动力车多能源动力总成的开发
本文以某国产ISG型并联式轻度混合动力车为对象，研究了包括驾驶员驱动力需求分析和发动机工作区优化为基础的功率分配策略，以及不影响ABS控制的并联式制动能量回收策略，并进行多能源动力总成控制器的硬件及软件系统开发。在此基础上，利...
CFD-DEM simulation of gas-solid reacting flows in catalytic reactor
An extended CFD-DEM coupled approach is used to simulate the complex gas-solid reacting flows in fluid catalytic cracking (FCC) processes accommodated in riser reactor in a transient manner. Considering the solid catalyz...
The synthesis of MFI zeolite membrane on large H-ZSM-5 crystal
Using in-situ hydrothermal synthesis to prepare large H-ZSM-5 crystal and the MFI zeolite membrane was synthesized on it. The X-ray diffraction (XRD), optical microscope, scanning electron microscope (SEM) and Uv-vis dif...
The FEM analysis of the fracture characters of the rock <br /> under shear-box load<br />
This paper introduces the research state of mode Ⅱ fracture, pointing out that the modeⅡ load is not due to the mode Ⅱ fracture. Using the Shear-box loading condition to restrict mode Ⅰ fracture, therefore the true mode...
Research on the growth and development of Texel, Dorper,<br /> short-tailed, their crossbred F1<br />
125 lambs are selected in this experiment, which included Texel lamb ( groupⅠ), Dorper lamb ( group Ⅱ), the crossbred lamb F1 from Texel and short-tailed as the female parent ( group Ⅲ), the crossbred lamb F1 from Dorper...