摘要
针对样本同时属于多个类别(或标签)现象的电力系统电能质量复合扰动,提出采用多标签分类方法来解决其分类识别问题。引入了电能质量复合扰动以及多标签分类的概念,提出了多标签分类器的评判指标,采用3种典型多标签分类器对电能质量复合扰动进行分类识别。仿真实验结果表明,在不同噪声条件下,多标签分类方法可以有效分类识别由电压暂降、电压暂升、电压短时中断、脉冲暂态、谐波和闪变等电能质量单一扰动组合而成的复合扰动。
The multi-label classification method was proposed to solve the classification problem of the multiple power qual- ity （PQ） disturbances where each instance may belong to more than one class（label） in power systems. Firstly, the con- ceptions of the multiple PQ disturbances and the multi-label classification method were introduced. Then the evaluation met- rics for multi-label classifier were proposed. Finally, three typical multi-label classifiers were used to classify the PQ multi- ple disturbances. The simulation results show that the multi-label classification method can recognize the multiple power quality disturbances including voltage sag, voltage swell, interruption, impulsive transient, harmonics, flicker effectively under different noise conditions.
出处
《重庆邮电大学学报（自然科学版）》
北大核心
2010年第5期618-623,共6页
Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition)
基金
重庆邮电大学自然科学基金(A2009-41)~~
关键词
电能质量
模式识别
多标签
复合扰动
支持向量机
power quality （ PQ ）
pattern recognization
multi-label
multiple disturbances
support vector machine （SVM）
