电能质量复合扰动特征选择与最优决策树构建

被引：126

作者：

黄南天 ^{[1
]}

彭华 ^{[1
]}

蔡国伟 ^{[1
]}

徐殿国 ^{[2
]}

机构：

[1] 东北电力大学电气工程学院

[2] 哈尔滨工业大学电气工程及自动化学院

来源：

中国电机工程学报 | 2017年 / 37卷 / 03期

关键词：

电能质量; 复合扰动; S变换; 分类回归树; Gini重要度; 1-标准误差规则;

D O I：

暂无

中图分类号：

TM711 [网络分析、电力系统分析];

学科分类号：

083903 [网络与系统安全];

摘要：

针对电能质量(power quality,PQ)复合扰动识别中缺少特征选择与最优决策树自动构建方法的不足,提出采用分类回归树的PQ特征选择与最优决策树构建方法。首先,通过S变换提取64种PQ特征,构成原始特征集;然后,采用嵌入式特征选择方法,获取特征Gini重要度及排序,确定最优特征子集;最后,应用1-标准误差规则子树评估法,进行代价复杂度剪枝,获得最优分类树。实验证明,新方法能够根据训练集自动构建最优决策树,并实现最优特征选择;最优决策树可准确识别不同噪声环境下,含多种复合扰动的PQ信号,分类准确率高于概率神经网络和支持向量机方法,具有良好的鲁棒性与抗噪性。

引用

页码：776 / 786

页数：11

共 10 条

[1]

An effective Power Quality classifier using Wavelet Transform and Support Vector Machines [J].

De Yong, D. ;

Bhowmik, S. ;

Magnago, F. .

EXPERT SYSTEMS WITH APPLICATIONS, 2015, 42 (15-16) :6075-6081

[2]

Power-quality issues and the need for reactive-power compensation in the grid integration of wind power.[J].Muhammad A. Saqib;Ali Z. Saleem.Renewable and Sustainable Energy Reviews.2015,

[3]

A critical review of detection and classification of power quality events.[J].Om Prakash Mahela;Abdul Gafoor Shaik;Neeraj Gupta.Renewable and Sustainable Energy Reviews.2015, Jan.

[4]

Automatic recognition system of underlying causes of power quality disturbances based on S-Transform and Extreme Learning Machine.[J].Hüseyin Erişti;Özal Yıldırım;Belkıs Erişti;Yakup Demir.International Journal of Electrical Power and Energy Systems.2014,

[5]

Detection and characterization of multiple power quality disturbances with a fast S-transform and decision tree based classifier [J].

Biswal, Milan ;

Dash, P. K. .

DIGITAL SIGNAL PROCESSING, 2013, 23 (04) :1071-1083

[6]

Optimal feature selection for classification of the power quality events using wavelet transform and least squares support vector machines.[J].Hüseyin Eri?ti;?zal Y?ld?r?m;Belk?s Eri?ti;Yakup Demir.International Journal of Electrical Power and Energy Systems.2013,

[7]

Classification of power quality events – A review.[J].Manish Kumar Saini;Rajiv Kapoor.International Journal of Electrical Power and Energy Systems.2012, 1

[8]

Power quality disturbances classification based on S-transform and probabilistic neural network.[J].Nantian Huang;Dianguo Xu;Xiaosheng Liu;Lin Lin.Neurocomputing.2012,

[9]

基于S变换与PNN的电能质量多扰动检测 [J].