|
|
|
| Adaboost-based single-phase-to-ground fault detection in distribution systems |
| Zeng Xiaodan1,2, Chen Yongwang3, Guo Moufa1, Chen Dunyu2 |
1. College of Electrical Engineering and Automation, Fuzhou University, Fuzhou 350108;
2. Department of Electrical Engineering, Yuan Ze University, Chung Li, Taiwan 32003;
3. State Grid Fujian Jinjiang County Electric Power Supply Co., Ltd, Quanzhou, Fujian 362200; |
|
|
|
|
Abstract Faulty feeder detection timely and accurately in resonant grounding distribution systems is still a focus of research. The conventional methods commonly use single faulty feeder detection methods, such as wavelet transform method, transient energy method, and the fifth harmonic current method, ect. However, their reliability is not satisfied due to the partial fault information is considered. A novel approach to identify the faulty feeder based on discrete wavelet packet transform (DWPT) and machine learning is proposed in this paper. The time-frequency matrices are acquired by utilizing the DWPT to the collected transient zero-sequence current signals of the faulty feeder and sound feeders. The feature vectors will be extracted manually by calculating time-frequency matrices with statistical quantities. The Adaboost classifier is trained by a large number of feature vectors under various kinds of fault conditions and factors. The faulty feeder detection can be achieved by the trained two classifiers. A PSCAD/EMTDC simulator is established to simulate a practical 10kV resonant grounding distribution system. Verification results of the testing cases reveal that the proposed approach of fault protection is able to achieve good identification accuracy.
|
|
Received: 25 September 2017
Published: 19 March 2018
|
|
|
|
| Cite this article: |
|
Zeng Xiaodan,Chen Yongwang,Guo Moufa等. Adaboost-based single-phase-to-ground fault detection in distribution systems[J]. Electrical Engineering, 2018, 19(3): 70-75.
|
|
|
|
| URL: |
|
http://dqjs.cesmedia.cn/EN/Y2018/V19/I3/70
|
[1] 姜健, 鲍光海. 小电流接地系统单相接地故障选线方法综述[J]. 电气技术, 2015, 16(12): 1-5.
[2] 赵建文, 李科, 随晓娜, 等. 多级数据模糊融合选线新方法[J]. 电力系统及其自动化学报, 2016, 28(2): 56-60.
[3] 束洪春. 配电网络故障选线[M]. 北京: 机械工业出版社, 2008.
[4] 郭谋发, 王鹏, 杨耿杰. 基于HHT和SVM的谐振接地系统故障选线新方法[J]. 电工电能新技术, 2014, 33(9): 68-73, 80.
[5] 王磊, 曹现峰, 骆玮. 基于改进PSO优化模糊神经网络的配电网故障选线研究[J]. 电气技术, 2016, 17(3): 30-35.
[6] 廖桂源, 李彩林, 施伟, 等. 基于EMD聚类算法的配电网单相接地故障选线方法[J]. 电力科学与工程, 2014(2): 57-61.
[7] 牛云涛, 李华, 宋志宏, 等. 谐振接地系统多判据多周期信息融合故障选线方法[J]. 电工技术学报, 2015(S1): 512-517.
[8] 郭谋发, 刘世丹, 杨耿杰. 采用Hilbert谱带通滤波和暂态波形识别的谐振接地系统故障选线新方法[J]. 电工电能新技术, 2013, 32(3): 67-74.
[9] 刘林飞, 方珊, 辛自立. 基于小波分析的小电流接地系统故障选线[J]. 科技视界, 2014(21): 139-140, 193.
[10] 苏战涛, 吕艳萍. 一种基于小波包分析的小电流接地电网单相接地故障选线新方法[J]. 电网技术, 2004, 28(12): 30-33.
[11] 张淑清, 马跃, 李盼, 等. 基于改进的广义谐波小波包分解和混沌振子的小电流接地系统故障选线[J]. 电工技术学报, 2015, 30(3): 13-20, 43.
[12] 郭谋发, 刘世丹, 杨耿杰. 利用时频谱相似度识别的配电线路接地选线方法[J]. 中国电机工程学报, 2013, 33(19): 183-190.
[13] 宗欣露, 熊盛武, 朱国锋. 基于肤色和AdaBoost算法的彩色人脸图像检测[J]. 计算机应用研究, 2007, 24(10): 178-180, 184. |
|
|
|
2018, Vol. 19 
