引用本文: | 杜 林,李 欣,司马文霞,戴 斌.S变换模矩阵和最小二乘SVM在雷电及操作过电压识别中的应用[J].电力自动化设备,2012,32(8): |
| DU Lin,LI Xin,SIMA Wenxia,DAI Bin.Application of S-transform modular matrix and LS-SVM in identification of lightning and switching overvoltages[J].Electric Power Automation Equipment,2012,32(8): |
|
摘要: |
提出一种基于S变换模矩阵和最小二乘支持向量机(SVM)的雷电及操作过电压识别方法。通过对零序过电压信号的S变换模矩阵进行奇异值分解,将过电压信号的特征信息分解到不同的时频特征子空间,提取奇异值的5类统计特征参量作为过电压识别的特征向量,并将其输入最小二乘SVM分类器,实现雷电及操作过电压的类型识别。过电压实测数据表明:所提特征方法的特征量维数低,抗干扰能力强;采用的识别方法训练次数少,识别率高,可较好地应用于雷电及操作过电压的识别。 |
关键词: S变换模矩阵 奇异值分解 最小二乘支持向量机 雷过电压 操作过电压 过电压识别 |
DOI: |
分类号: |
基金项目:国家创新研究群体基金资助项目(51021005);国家重点基础研究发展计划(973计划)(2009CB724504) |
|
Application of S-transform modular matrix and LS-SVM in identification of lightning and switching overvoltages |
DU Lin1, LI Xin1, SIMA Wenxia1, DAI Bin2
|
1.State Key Laboratory of Power Transmission Equipment & System Security and New Technology,Chongqing University,Chongqing 400044,China;2.Yunnan Electric Power Design Institute,Kunming 650051,China
|
Abstract: |
S-transform modular matrix and LS-SVM(Least Square-Support Vector Machine) are applied to identify the lightning overvoltage and switching overvoltage. The singular value decomposition decomposes the S-transform modular matrix of zero sequence overvoltage signals into different time-frequency characteristic subspaces,from which five statistical features are extracted and used as the input vectors of the LS-SVM classifiers to identify the lightning and switching overvoltages. Results of the test with measured overvoltage data indicate that,the characteristic dimension is small,the features are immune to electromagnetic noises,the training times is low,and the recognition rate is high. The proposed method can be well applied in identification of lightning and switching overvoltages. |
Key words: S-transform modular matrix singular value decomposition least square-support vector machine lighting overvoltage switching overvoltage overvoltage identification |