| 引用本文: | 白 浩,潘姝慧,邵向潮,等.基于小波去噪与随机森林的配电网高阻接地故障
半监督识别方法[J].电力系统保护与控制,2022,50(20):79-87.[点击复制] |
| BAI Hao,PAN Shuhui,SHAO Xiangchao,et al.A high impedance grounding fault semi-supervised identification method based onwavelet denoising and random forest[J].Power System Protection and Control,2022,50(20):79-87[点击复制] |
|
| 摘要: |
| 针对配电网高阻接地故障识别易受噪声干扰、无标签数据难以利用的难题，提出一种基于小波去噪与随机森林的高阻接地故障半监督识别方法。区别于监督式学习方法仅利用标签数据，基于协同训练方法能够充分利用有标签数据与无标签数据。首先，使用小波阈值去噪算法消除零序电流中的噪声。其次，采用波峰波谷故障启动算法判断线路是否发生故障或扰动事件。运用小波变换提取零序电流的小波系数作为故障特征。最后，基于小波系数故障特征构建两个随机森林作为半监督分类器进行协同训练，从而实现高阻接地故障的检测识别。仿真结果表明，所提配电网高阻接地故障半监督识别方法可以充分挖掘配电网既有的故障案例中无标注数据蕴含的关键特征，从而提高故障分类准确率，具有较强的准确性和灵敏性。 |
| 关键词: 配电网 高阻接地故障 小波变换 半监督学习 随机森林 |
| DOI：DOI: 10.19783/j.cnki.pspc.226429 |
| 投稿时间：2021-12-10修订日期：2022-03-17 |
| 基金项目:南方电网公司科技项目资助(GDKJXM20198281) |
|
| A high impedance grounding fault semi-supervised identification method based onwavelet denoising and random forest |
| BAI Hao,PAN Shuhui,SHAO Xiangchao,GAO Jianhong,LI Wei,LEI Jinyong,GUO Moufa |
| (1. Electric Power Research Institute, China Southem Grid, Guangzhou 510663, China; 2. Dongguan Power Supply
Bureau, Guangdong Power Grid Co., Ltd., Dongguan 530600, China; 3. College of Electrical
Engineering and Automation, Fuzhou University, Fuzhou 350108, China) |
| Abstract: |
| To solve the problem that the identification of a high impedance grounding fault (HIF) in distribution networks is easily affected by noise, and the fact that it is difficult to use unlabeled data, a semi-supervised identification method of a high resistance grounding fault based on wavelet denoising and random forest is proposed. Different from supervised learning only using labeled data, the method can make full use of labeled and unlabeled data by collaborative training. First, the wavelet threshold denoising algorithm is used to filter the noise of zero-sequence currents. Secondly, the occurrence of an HIF can be detected by the peak and valley fault triggering algorithm. Then, applying wavelet transform to zero-sequence currents, the wavelet coefficients are extracted as fault features. Finally, two random forests are collaboratively trained with selected features to construct a semi-supervised classifier to detect the HIF. The simulation results show that the proposed method can use fully the key features in unlabeled data in the existed fault cases in distribution network to improve the accuracy of fault calssification. It has strong reliability and flexibility.
This work is supported by the Science and Technology Project of China Southern Grid Co., Ltd. (No. GDKJXM 20198281). |
| Key words: distribution network high impedance grounding fault wavelet transform semi-supervised learning random forest |
