摘要
提出了一种基于S变换和多级支持向量机(SVMs)的电能质量扰动检测和识别方法。首先通过S变换对电能质量扰动信号进行时频分析,有效实现对各种扰动的检测输出。然后对检测输出进行时频特征提取,并通过一个N?1级支持向量机器分类器,最后实现N种电能质量扰动信号的分类识别。测试结果表明,该方法能有效识别参数大范围内随机变化的各种电能质量扰动,识别正确率高,且训练时间很短,实时性能好。
A new method based on S-transform and multi-lay support vector machines （SVMs） is presented for power quality（PQ） disturbances detection and identification, Through S-transform time-frequency analysis, the method detects and out put kinds of PQ disturbances effectively. Then, feature components are extracted from the detecting outputs for classification. With an N-1 lay SVMs classifier, N kinds of PQ disturbances are classified by N-1 turns finally. The testing results show that the proposed method could detect and classify the PQ disturbances effectively. The classifier has an excellent performance on training speed and correct ratio.
出处
《电工技术学报》
EI
CSCD
北大核心
2006年第1期121-126,共6页
Transactions of China Electrotechnical Society
关键词
电能质量扰动
检测
识别
S变换
多级支持向量机
PQ disturbances, detection, identification, S-transform, multi-lay SVMs
