电能质量扰动分类的贝叶斯方法
|
摘要
随着非线性负荷的大量使用,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．为此,对电能质量扰动信号进行小波包分解,分别以小波包分解终结点的能量和熵作为特征向量。用贝叶斯分类器进行分类识别,对扰动分类做出了仿真分析,仿真结果验证了该方法的有效性．通过与Fisher分段线性分类器进行比较,表明以熵为特征向量的贝叶斯分类方法有较高的识别正确率．
With the proliferation of nonlinear loads,more attention has been given to power quality problems. In order to mitigate the influence,various power quality disturbances must be classified before an appropriate measure can be taken.Wavelet packet is developed on the basis of wavelet transform,which can provide more plenteous time-frequency information.This paper uses wavelet packet to decompose power quality disturbance signals,then selects energy and entropy of terminal nodes through wavelet packet decomposition as eigenvector respectively,and uses Bayes classifier to classify the disturbances,which are simulated and analyzed.The sim- ulation results validate the effectiveness of this method.It's showed that the entropy acted as eigenvector has higher recognition accurate ratio compared with Fisher piecewise linear classifier.
With the proliferation of nonlinear loads,more attention has been given to power quality problems. In order to mitigate the influence,various power quality disturbances must be classified before an appropriate measure can be taken.Wavelet packet is developed on the basis of wavelet transform,which can provide more plenteous time-frequency information.This paper uses wavelet packet to decompose power quality disturbance signals,then selects energy and entropy of terminal nodes through wavelet packet decomposition as eigenvector respectively,and uses Bayes classifier to classify the disturbances,which are simulated and analyzed.The sim- ulation results validate the effectiveness of this method.It's showed that the entropy acted as eigenvector has higher recognition accurate ratio compared with Fisher piecewise linear classifier.
引文
[1]Gauda A M,Salama M M A,Sultan M B,et al.Power quality detection and classification using wavelet-multiresolution signal decomposition[J].IEEE Transactions on Power Delivery,1999,14(4):1469—1476.
[2]Gauda A M,Kanoun S H,Salama M M A,et al.Waveletbased signal processing for disturbance classification and measurement [J].Generation,Transmission and Distribution,IEE Proceedings,2002,149(3):310—318.
[3]王晶，束洪春，陈学允．动态电能质量的分形指数小波分析方法[J]．中国电机工程学报，2004，24(5)：40—45．Wang Jing,Shu Hongchun,Chen Xueyun.Fractal exponent wavelet analysis of dynamic power quality [J].Proceedings of CSEE,2004,24(5):40—45(in Chinese).
[4]Ghosh A K,Lubkeman D L.The classification of power system disturbance waveforms using a neural network approach [J].IEEE Transactions on Power Delivery,1995,10(1):109—115.
[5]张智远，李庚银，冯任卿．基于小波和进化网络的电能质量动态扰动自动识别[J]．华北电力大学学报，2002，29(3)：1—4．Zhang Zhiyuan,Li Gengyin,Feng Renqing.Auto recognition of power quality disturbance based on wavelet and genetic net [J]Journal of North China Electric Power University,2002,29(3):1—4(in Chinese).
[6]Youssef A M,Abdel-Galil T K,EI-Saadany E F,et al.Disturbance classification utilizing dynamic time warping classifier [J].IEEE Transactions on Power Delivery,2004,19(1):272—278.
[7]王成山，王继东．基于小波包分解的电能质量扰动分类方法[J]．电网技术，2004，28(15)：78—82．Wang Chengshan,Wang Jidong.Classification method of power quality disturbance based on wavelet packet decomposition [J].Power System Technology,2004,28(15):78—82(in Chinese).
[8]Antonini G,Orlandi A.Wavelet packet-based EMI signal processing and source identification[J].IEEE Transactions on Electromagnetic Compatibility,2001,43(2):140—148.
[9]Yen G G,Lin K C.Wavelet packet feature extraction for vibration monitoring [J].IEEE Transactions on Industrial Electronics,2000,47(3):650—667.
[10]彭玉华．小波变换与工程应用[M]．北京：科学出版社，1999．Peng Yuhua.Wavelet Transform and Engineering Application [M].Beijing:Science Press,1999(in Chinese).
[11]胡昌华，张君波，夏军，等．基于MATLAB的系统分析与设计——小波分析[M]．西安：西安电子科技大学出版社，1999．Hu Changhua,Zhang Junbo,Xia Jun,et al.System Analysis and Design Based on MATLAB——Wavelet Analysis [M].Xi'an:Xidian University Press,1999(in Chinese).
[12]王碧泉，陈祖荫．模式识别——理论、方法和应用[M]．北京：地震出版社，1989．Wang Biquan,Chen Zuyin.Pattern Recognition——Theory,Method and Application[M].Beijing:Seismological Press,1989 (in Chinese).
[13]刘凤玉，李千目，衷宜．基于贝叶斯分类的分布式网络故障诊断模型[J]．南京理工大学学报，2003，27(5)：546—550．Liu Fengyu,Li Qianmu,Zhong Yi.A distributed network fault diagnosis model based on Bayesian classification [J].Journal of Nanjing University of Science and Technology,2003,27(5):546—550(in Chinese).
[14]Fukunaga K,Flick T E.A test of the Gaussian-ness of a data set using clustering [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,8(2):240—247.
[2]Gauda A M,Kanoun S H,Salama M M A,et al.Waveletbased signal processing for disturbance classification and measurement [J].Generation,Transmission and Distribution,IEE Proceedings,2002,149(3):310—318.
[3]王晶，束洪春，陈学允．动态电能质量的分形指数小波分析方法[J]．中国电机工程学报，2004，24(5)：40—45．Wang Jing,Shu Hongchun,Chen Xueyun.Fractal exponent wavelet analysis of dynamic power quality [J].Proceedings of CSEE,2004,24(5):40—45(in Chinese).
[4]Ghosh A K,Lubkeman D L.The classification of power system disturbance waveforms using a neural network approach [J].IEEE Transactions on Power Delivery,1995,10(1):109—115.
[5]张智远，李庚银，冯任卿．基于小波和进化网络的电能质量动态扰动自动识别[J]．华北电力大学学报，2002，29(3)：1—4．Zhang Zhiyuan,Li Gengyin,Feng Renqing.Auto recognition of power quality disturbance based on wavelet and genetic net [J]Journal of North China Electric Power University,2002,29(3):1—4(in Chinese).
[6]Youssef A M,Abdel-Galil T K,EI-Saadany E F,et al.Disturbance classification utilizing dynamic time warping classifier [J].IEEE Transactions on Power Delivery,2004,19(1):272—278.
[7]王成山，王继东．基于小波包分解的电能质量扰动分类方法[J]．电网技术，2004，28(15)：78—82．Wang Chengshan,Wang Jidong.Classification method of power quality disturbance based on wavelet packet decomposition [J].Power System Technology,2004,28(15):78—82(in Chinese).
[8]Antonini G,Orlandi A.Wavelet packet-based EMI signal processing and source identification[J].IEEE Transactions on Electromagnetic Compatibility,2001,43(2):140—148.
[9]Yen G G,Lin K C.Wavelet packet feature extraction for vibration monitoring [J].IEEE Transactions on Industrial Electronics,2000,47(3):650—667.
[10]彭玉华．小波变换与工程应用[M]．北京：科学出版社，1999．Peng Yuhua.Wavelet Transform and Engineering Application [M].Beijing:Science Press,1999(in Chinese).
[11]胡昌华，张君波，夏军，等．基于MATLAB的系统分析与设计——小波分析[M]．西安：西安电子科技大学出版社，1999．Hu Changhua,Zhang Junbo,Xia Jun,et al.System Analysis and Design Based on MATLAB——Wavelet Analysis [M].Xi'an:Xidian University Press,1999(in Chinese).
[12]王碧泉，陈祖荫．模式识别——理论、方法和应用[M]．北京：地震出版社，1989．Wang Biquan,Chen Zuyin.Pattern Recognition——Theory,Method and Application[M].Beijing:Seismological Press,1989 (in Chinese).
[13]刘凤玉，李千目，衷宜．基于贝叶斯分类的分布式网络故障诊断模型[J]．南京理工大学学报，2003，27(5)：546—550．Liu Fengyu,Li Qianmu,Zhong Yi.A distributed network fault diagnosis model based on Bayesian classification [J].Journal of Nanjing University of Science and Technology,2003,27(5):546—550(in Chinese).
[14]Fukunaga K,Flick T E.A test of the Gaussian-ness of a data set using clustering [J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1986,8(2):240—247.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心