基于四阶混合平均累计量的矩阵束算法在低频振荡在线辨识中的应用  

A Modified Matrix Pencil Method Based on Fourth-order Mixed Mean Cumulant for Low Frequency Oscillation Mode On-line Identification

作　　者：胡楠[1] 李兴源[1] 李宽[1] 穆子龙[2] 朱瑞可[1] 

机构地区：[1]四川大学电气信息学院,四川省成都市610065 [2]重庆市电力公司江北供电局,重庆市江北区500000

出　　处：《中国电机工程学报》2013年第7期53-60,19,共8页Proceedings of the CSEE

基　　金：国家自然科学基金重点项目(51037003);国家863高技术基金项目(2011AA05A119);国家电网公司大电网重大专项资助项目课题(SGCC-MPLG001(003-027)-2012)~~

摘　　要：广域测量系统(wide area monitoring system,WAMS)的发展为电力系统低频振荡在线辨识奠定了基础。WAMS采集的信号含有高斯白噪声,经低通滤波处理后会产生高斯色噪声,因此会对模式识别的准确性产生不利影响。针对这一问题,提出以实测信号的四阶混合平均累计量(fourth-order mixed mean cumulant,FOMMC)的对角切片来代替实测信号,并结合矩阵束(matrix pencil,MP)算法对振荡模式进行识别的方法。仿真结果表明,FOMMC-MP算法能够有效从色噪声环境中辨识出系统主导模态。With the rapid development of synchrophasor based wide area monitoring systems（WAMSs）,measurements from the phasor measurement units（PMUs） can be used for online identification of the low frequency oscillations in power systems.To solve the problem that colored Gaussian noise produced by low pass filters may impact the accuracy of oscillation mode indentification,this paper proposed a modified matrix pencil method based on fourth-order mixed mean cumulant（FOMMC） for oscillation mode identificaion.Substituting the sampled signal by its fourth-order mixed mean cumulant sequence along the diagonal line,the method can reduce the impact of the noise effectively.The simulation result shows using the proposed method,the dominant oscillation modes can be identified in the environment with additive colored Gaussian noise.

关 键 词：广域测量系统 低频振荡 四阶混合平均累积量 矩阵束 高斯色噪声 相量测量单元 

分 类 号：TM71[电气工程—电力系统及自动化]