《基于高阶累积量的暂态电能质量扰动分类研究_赵静》.pdf

第35 卷 第5 期 电 网 技 术 Vol. 35 No. 5 2011 年5 月 Power System Technology May 2011 文章编号：1000-3673 （2011 ）05-0103-07 中图分类号：TM 712 文献标志码：A 学科代码：470·4054 基于高阶累积量的暂态电能质量扰动分类研究 赵静，何正友，贾勇，钱清泉 （西南交通大学电气工程学院，四川省 成都市 610031 ） Classification of Transient Power Quality Disturbances Based on High-Order Cumulants ZHAO Jing, HE Zhengyou, JIA Yong, QIAN Qingquan (School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, Sichuan Province, China) ABSTRACT: To improve the precision of classification and 有效分类识别这2 类暂态扰动，在训练样本为50 组，核函 recognition of transient power quality disturbances, a new 数选择为线性核函数时，识别率可达到 99% ；当混合有其 classification and recognition algorithm for transient power 他扰动分量时，该方法也有效。 quality disturbance signals, which is based on high-order 关键词：暂态电能质量；高阶累积量；支持向量机；混合 cumulants (HOC) and support vector machine (SVM), is 扰动 proposed. In the proposed algorithm, the 3-order and 4-order impulse statistical characteristics of two kinds of disturbances, 0 引言 i.e., the impulse transient and oscillation transient, are 随着经济社会的发展以及构建和谐社会的需 extracted from HOC, and eight characteristic quantities, i.e., the number of maximum values, the number of minimum 求，电力作为一种环保、高效的能源倍受关注，随 values, the maximum and the minimum in 3-order and 之而来的是现代大电网互联的迅速发展，电力系统 4-order statistical results respectively, are chosen as the input 规模的日益庞大以及各种电力电子设备、冲击性与 of SVM. The proposed algorithm is verified by Matlab to 非线性负荷的大量投入，导致了电压暂降、电压暂 obtain simulation data. Simulation results