| 引用本文: | 张凯,关根志,龙望成,刘功能.基于多分辨率标准差及自组织映射网络的电能质量扰动分类识别[J].电力自动化设备,2008,(8): |
| .Power quality disturbance classification based on standard deviation of multi-resolution analysis and self-organizing feature mapping[J].Electric Power Automation Equipment,2008,(8): |
|
|
| 摘要: |
| 基于小波多分辨率分析和自组织映射网络,提出了一种电力系统电能质量扰动问题的分类识别方法.在多分辨率分析中,利用小波方程和尺度方程可以对信号进行多层分解.对各层信号进行统计分析得到标准差,相当于对分解后的信号进行了特征提取,可以反映信号的离散度并作为各层的特征值,且特征明显、数值量小.对得到的特征值,采用自组织映射网络进行聚类分析,就可以实现电能质量扰动类别的智能判断.仿真结果表明该方法判别精度高、速度快,可供电能质量问题的监测分析参考. |
| 关键词: 电能质量 扰动 多分辨率分析 小波 标准差 自组织映射 |
| DOI： |
| 分类号:TM76 |
| 基金项目: |
|
| Power quality disturbance classification based on standard deviation of multi-resolution analysis and self-organizing feature mapping |
|
ZHANG Kai GUAN Genzhi LONG Wangcheng LIU Gongneng
|
| Abstract: |
| A power quality disturbance classification method of power system is proposed,which is based on the standard deviation of multi - resolution analysis and self - organizing feature map. In multi-resolution analysis,the wavelet functions and scaling functions are used as building blocks to decompose signals at different resolution levels. The standard deviation of each level is quantified as its feature,which is clear and simple. The self - organizing feature mapping is proposed to intelligently classify deferent power quality disturbances. Simulation results show that,this method has higher precision and speed,which gives reference to the power quality monitoring and analysis. |
| Key words: power quality,disturbance,multi-resolution analysis,wavelet,standard deviation,self-organizing feature mapping |
