[1]马健凯,石嘉川,*,等.基于支持向量机的光伏系统电弧检测方法[J].山东建筑大学学报,2020,(02):62-67.[doi:10.12077/sdjz.2020.02.009]
 MA Jiankai,SHI Jiachuan,*,et al.The arc fault detection method for photovoltaic system based on support vector machine[J].Journal of Shandong jianzhu university,2020,(02):62-67.[doi:10.12077/sdjz.2020.02.009]
点击复制

基于支持向量机的光伏系统电弧检测方法()
分享到:

《山东建筑大学学报》[ISSN:1673-7644/CN:37-1449/TU]

卷:
期数:
2020年02期
页码:
62-67
栏目:
研究论文
出版日期:
2020-04-15

文章信息/Info

Title:
The arc fault detection method for photovoltaic system based on support vector machine
文章编号:
1673-7644(2020)02-0062-06
作者:
马健凯1石嘉川12*刘林1李树静3
(1.山东建筑大学 信息与电气工程学院,山东 济南 250101;2.山东省智能建筑技术重点实验室,山东 济南 250101;3.山东电力高等专科学校 电气工程系,山东 济南 250002)
Author(s):
MA Jiankai1 SHI Jiachuan12* LIU Lin1LI Shujing3
( 1. School of Information and Electrical Engineering, Shandong Jianzhu University, Jinan 250101, China; 2. Shandong Key Laboratory of Intelligent Building Technology, Jinan 250101, China; 3. Department of Electrical Engineering,Shandong Electric Power College, Jinan 250002, China )
关键词:
光伏系统电弧检测系统仿真支持向量机
Keywords:
photovoltaic system arc detection system simulation support vector machine classifier
分类号:
TG178
DOI:
10.12077/sdjz.2020.02.009
文献标志码:
A
摘要:
光伏发电设备在长期使用中受外力侵袭等因素影响,可能产生电弧故障而引发火灾,准确检测故障电弧是提高光伏系统安全性的关键。文章基于Cassie电弧模型,搭建了光伏系统电弧故障仿真模型,对数种典型环境下的不同故障和正常工况进行仿真,获取了正常工况和电弧故障的电流波形数据,并基于支持向量机对电弧故障特征值进行了分类。结果表明:在正常状态与故障状态下,小波高频分量能量值和模极大值相差两个以上的数量级,可作为电弧检测的故障判据;建立的分类器可以准确检测光伏系统在多种环境条件下不同位置、不同类型的电弧故障,具有较好的泛化能力。
Abstract:
During the long-term utilization of photovoltaic equipment, affected by external forces and other factors, some hidden dangers may lead to arc faults and fire disaster. Accurate detection of arc fault is the key to improve the photovoltaic (PV) system security. Based on Cassie arc model, the simulation model of PV system arc fault is established in this paper, and the current waveform data in normal and various arc faults condition is obtained. Two indexes, the wavelet high frequency component energy value and modulus maximum value, are found to have better discrimination through comparison. The sample data set is formed and the support vector machine (SVM) classifier is trained and tested. The results show that the difference between normal state and fault state is more than two orders of magnitude, which can be used as fault criterion for arc detection. The SVM classifier has the ability to detect arc faults in different positions and various environmental conditions accurately. Simulation results shows generalization ability of the proposed method.

参考文献/References:

[1]郭琳,柯希彪,汤引生,等.新能源汽车电弧故障检测方法及测试系统设计[J].绝缘材料, 2018, 51(11): 74-79. [2]周越,王永兴,邹积岩,等.基于EMD-AR方法的航空串联故障电弧特性研究[J].电器与能效管理技术, 2016(11): 1-6. [3]刘源,汲胜昌,祝令瑜,等.直流电源系统中直流电弧特性及其检测方法研究[J].高压电器,2015,51(2):24-29. [4]Braun H, Buddha S T, Krishnan V, et al. Signal processing for fault detection in photovoltaic arrays[C].Proceedings of IEEE International Conference on Acoustics, 2012:1681-1684. [5]吴春华,冯夏云,袁同浩,等.基于BP神经网络的光伏故障电弧检测方法研究[J].太阳能学报,2016,37(11):2958-2964. [6]韩明,李剑波,邵春莉,等.基于频域能量和小波系数方差的光伏系统故障电弧判断方法[J].合肥工业大学学报(自然科学版), 2017, 40(8): 1070-1073. [7]赵尚程,张认成,杜建华,等.采用小波变换的光伏串联电弧故障检测[J].华侨大学学报(自然科学版),2017,38(1):7-12. [8]王尧,张彦风,牛峰,等.光伏直流电弧电磁辐射特性分析与测量方法[J]. 电工技术学报,2019,34(14):2913-2921. [9]汪金刚,林伟,王志,等.基于紫外检测的开关柜电弧在线检测装置[J].电力系统保护与控制,2011,39(5):128-133,152. [10]Miao W, Liu X, Lam K H, et al. Arc-faults setection in PV systems by measuring pink noise with magnetic sensors[J].IEEE Transactions on Magnetics,2019, 55(7):1-6. [11]段培永,徐丽平,石嘉川,等.基于小波系数均差值的低压电弧故障诊断方法[J].山东建筑大学学报,2014,29(1):1-8. [12]谭秋秋,石嘉川,管铭.基于高频分量周期方差值的故障电弧检测[J].建筑电气,2017,36(3):57-62. [13]牟龙华,王伊健,蒋伟,等.光伏系统直流电弧故障特征及检测方法研究[J].中国电机工程学报,2016,36(19):5236-5244,5405. [14]张国军,杨东建,季淑洁,等.光伏系统直流串联故障电弧特征研究[J].测控技术,2018,37(6):47-50,54. [15]徐鹏威,刘飞,刘邦银,等.几种光伏系统MPPT方法的分析比较及改进[J].电力电子技术,2007(5):3-5. [16]杨明波,龙毅,樊三军,等.基于组合Mayr和Cassie电弧模型的弧光接地故障仿真及分析[J].电测与仪表,2019,56(10):8-13. [17]刘晓明,赵洋,曹云东,等.基于多特征融合的交流系统串联电弧故障诊断[J].电网技术,2014,38(3):795-801. [18]赵尚程,曹建,姚美齐.光伏系统直流电弧故障检测方法综述[J].电器与能效管理技术,2017(19):18-23,34.

备注/Memo

备注/Memo:
收稿日期:2020-03-22 基金项目:山东省高等学校科技计划项目 (J17KZ006) 作者简介:马健凯(1994-),男,在读硕士,主要从事光伏系统故障电弧检测等方面的研究.E-mail: 443072030@qq.com 通讯作者*:石嘉川(1978-),男,副教授,博士,主要从事配电系统运行优化、故障电弧检测与保护等方面的研究. E-mail:jc_shi@sdjzu.edu.cn
更新日期/Last Update: 2020-03-22