| 引用本文: | 邵振国,林潇,张嫣,陈飞雄,林洪洲.基于特征集重构与多标签分类模型的谐波源定位方法[J].电力自动化设备,2024,44(2):147-154. |
| SHAO Zhenguo,LIN Xiao,ZHANG Yan,CHEN Feixiong,LIN Hongzhou.Harmonic source location method based on feature set reconstruction and multi-label classification model[J].Electric Power Automation Equipment,2024,44(2):147-154. |
|
| 本文已被：浏览 5993次 下载 792次 |
码上扫一扫！ |
|
|
| 基于特征集重构与多标签分类模型的谐波源定位方法 |
|
邵振国1,2, 林潇1,2, 张嫣1,2, 陈飞雄1,2, 林洪洲1,2
|
|
1.福州大学 电气工程与自动化学院，福建 福州 350108;2.福建省电器智能化工程技术研究中心，福建 福州 350108
|
|
| 摘要: |
| 传统基于谐波状态估计的谐波源定位方法需要专门的同步相量量测装置，工程应用受到限制。为此，基于电能质量监测装置所采集的非同步量测数据，提出了基于特征集重构与多标签分类模型的谐波源定位方法。利用监测数据的充分统计量来挖掘量测时段的谐波信息，同时利用标签特定特征学习算法重构特征集，从而消除冗余特征以及无关特征对于谐波源定位精度的影响；提出基于邻接矩阵以及灵敏度分析的测点配置方法，结合电路网络拓扑信息实现测点的优化配置；提出基于改进极限学习机的谐波源定位方法，该方法以重构特征集为输入，建立多标签分类模型，实现谐波源定位。通过仿真与算例分析，验证了所提方法的可行性及有效性。 |
| 关键词: 电能质量 谐波源定位 非同步谐波监测数据 极限学习机 标签特定特征学习算法 |
| DOI：10.16081/j.epae.202306002 |
| 分类号: |
| 基金项目:国家自然科学基金面上项目(51777035)；福建自然科学基金重点项目(2020J02028) |
|
| Harmonic source location method based on feature set reconstruction and multi-label classification model |
|
SHAO Zhenguo1,2, LIN Xiao1,2, ZHANG Yan1,2, CHEN Feixiong1,2, LIN Hongzhou1,2
|
|
1.College of Electrical Engineering and Automation, Fuzhou University, Fuzhou 350108, China;2.Fujian Smart Electrical Engineering Technology Research Center, Fuzhou 350108, China
|
| Abstract: |
| Conventional harmonic source location methods based on harmonic state estimation require phasor measurement units, therefore their engineering applications are limited. Aiming at this problem, a harmonic source location method based on feature set reconstruction and multi-label classification model is proposed based on asynchronous measurement data collected by power quality monitoring devices. The sufficient statistics of the monitoring data is used to mine the harmonic information of the measurement period. Meanwhile, a label-specific feature learning algorithm is used to reconstruct the feature set, so as to eliminate the influence of redundant and irrelevant features on the accuracy of harmonic sources location. Then a configuration method of measurement devices is proposed based on the adjacency matrix and sensitivity analysis, which uses circuit network topology information to achieve measurement device configuration. An improved extreme learning machine based harmonic source location method is proposed, which uses the reconstructed feature set as input and establishes a multi-label classification model to achieve harmonic source location. The feasibility and effectiveness of the proposed method are verified by simulation and arithmetic cases. |
| Key words: power quality harmonic source location asynchronous harmonic monitoring data extreme lear-ning machine learning label-specific feature algorithm |
