引用本文: | 瞿合祚,刘恒,李晓明,黄建明.基于多标签随机森林的电能质量复合扰动分类方法[J].电力系统保护与控制,2017,45(11):1-7.[点击复制] |
QU Hezuo,LIU Heng,LI Xiaoming,HUANG Jianming.Recognition of multiple power quality disturbances using multi-label random forest[J].Power System Protection and Control,2017,45(11):1-7[点击复制] |
|
摘要: |
提出一种多标签随机森林(Multi-label Random Forest, ML-RF)分类算法,并将其应用于电能质量复合扰动分类。ML-RF是基于多标签决策树(Multi-label Decision Tree, ML-DT)的集成学习算法,利用子决策树的组合来增强分类器的整体性能。首先对电能质量扰动信号进行平稳小波变换,计算各层分解系数的小波能量熵作为分类特征向量。然后使用Bootstrap自助法和子空间采样构造不同的训练集训练子决策树。最后组合子决策树得到ML-RF分类器,并对复合电能质量扰动进行分类。仿真结果表明,在不同噪声情况下,该方法均能有效进行复合扰动的分类,具有较好的噪声鲁棒性,是复合电能质量扰动分类的一种可行方法。 |
关键词: 电能质量 复合扰动 多标签分类 随机森林 决策树 |
DOI:10.7667/PSPC160899 |
投稿时间:2016-06-17修订日期:2016-12-12 |
基金项目:国家自然科学基金项目(51277134) |
|
Recognition of multiple power quality disturbances using multi-label random forest |
QU Hezuo,LIU Heng,LI Xiaoming,HUANG Jianming |
(School of Electrical Engineering, Wuhan University, Wuhan 430072, China;Xiaogan Power Supply Company, Hubei Electric Power Company, Xiaogan 432000, China) |
Abstract: |
Multi-label Random Forest (ML-RF) is proposed and applied to the recognition of multiple power quality disturbances. ML-RF is an ensemble learning algorithm based on the Multi-label Decision Tree (ML-DT), by assembling sub-classification decision tree to enhance the overall performance. Firstly, all power quality disturbances are decomposed by steady wavelet transform, and the energy entropy of the wavelet coefficients are extracted as eigenvectors. Then, it uses training sets that are constructed by Bootstrap re-sampling method and subspace sampling method to train sub-DTs. Finally, it combines the sub-DTs by majority voting to predict the type of multiple power quality disturbances. The simulation results show that the ML-RF can effectively recognize the multiple power quality disturbances under different noise conditions, and it is a feasible method with noise robustness. This work is supported by National Natural Science Foundation of China (No. 51277134). |
Key words: power quality multiple disturbances multi-label classification random forests decision tree |