摘要
随着敏感性设备的大量应用,电能质量问题已日益受到关注。对各种电能质量扰动进行分类是采取适当措施降低扰动带来影响的前提。小波包是在小波变换的基础上发展起来的,能够提供更为丰富的时频信息。文章分别选取小波包分解终节点的能量和熵作为特征矢量,应用Fisher线性分类器设计了分段线性分类器,对扰动分类进行了仿真识别。仿真结果表明,以熵为特征矢量的分类方法有较高的识别正确率。
Along with the wide application of sensitive equipments more and more attentions are paid to power quality. Classifying various disturbances to power quality is the premise of adopting appropriate measures to reduce the influences brought by disturbances. On the basis of wavelet transform the wavelet packet is developed, it can offer plentiful time-frequency information. Here, choosing the energy and entropy of terminal nodes through wavelet packet decomposition as feature vectors respectively and applying Fisher linear classifier, the piecewise linear classifier is designed and the simulation and analysis of disturbance classification are carried out. The simulation results show that the classification method, in which the entropy is used as feature vector, possesses higher classification correctness.
出处
《电网技术》
EI
CSCD
北大核心
2004年第15期78-82,共5页
Power System Technology
关键词
电力系统
电网
仿真
小波包分解
电能质量
Computer simulation
Entropy
Frequencies
Vectors
Wavelet transforms
