电工电气杂志社

一种光伏阵列串联电弧故障智能检测方法

来源：电工电气发布时间：2023-02-06 16:06 浏览次数：344

一种光伏阵列串联电弧故障智能检测方法

金辉，高伟，杨耿杰

(福州大学电气工程与自动化学院，福建福州 350108)

摘要：由于串联电弧故障特征表现不足以及样本不平衡的问题，导致传统的诊断算法检测效果不佳。提出了一种基于图像识别的光伏阵列串联电弧故障诊断方法：利用格拉姆角和场(GASF)将发生串联电弧故障时的暂态电流数据编码为二维图像，从而放大电弧故障的本质特征；深度卷积生成对抗网络(DCGAN)被用来增扩电弧故障 GASF 特征图像，以均衡正常与故障样本数量；训练一个 LeNet-5 诊断模型完成电弧故障的识别。经过实验验证，所提方法有效提升了光伏阵列串联电弧故障的辨识度，且具备优秀的抗干扰能力，对实测数据的整体识别准确率高达99.5%。

关键词： 光伏阵列；串联电弧故障；格拉姆角和场；深度卷积生成对抗网络

中图分类号：TM615 文献标识码：A 文章编号：1007-3175(2023)01-0043-05

An Intelligent Detection Method for Series Arc Fault of Photovoltaic Array

JIN Hui, GAO Wei, YANG Geng-jie

（College of Electrical Engineering and Automation, Fuzhou University, Fuzhou 350108, China）

Abstract: The traditional diagnostic algorithms have poor performance because of inadequate characteristic expression of series arc fault (SAF) and sample imbalance. A detection method for series arc fault of photovoltaic array based on image recognition is put forward. First,according to Gramian angular summation field (GASF), the paper encodes the transient current data of SAF into two-dimensional image which amplifies the essential characteristics of SAF. Second, the deep convolution generative adversarial network (DCGAN) is adopted to enlarge GASF fault characteristic expression image of SAF to achieve balance between normal and fault sample numbers. Finally, a LeNet-5 diagnostic model is trained to recognize SAF. The experimental results show that this method efficiently improves the SAF of photovoltaic arrays identification accuracy to 99.5% and has great anti-interference ability.

Key words: photovoltaic array; series arc fault; Gramian angular summation field; deep convolution generative adversarial network

参考文献

[1] 李博彤，李明睿，刘梦晴. 基于通径分析和相空间重构的光伏发电预测模型[J] . 电测与仪表，2022，59(11)：79-87.

[2] DHAR S, PATNAIK R K, DASH P K.Fault detection and location of photo voltaic based DC microgrid using differential protection strategy[J].IEEE Transactions on Smart Grid，2018，9(5)：4303-4312.

[3] 屈建宇，马龙涛，陈思磊，等. 光伏系统直流串联故障电弧检测方法[J] . 电网与清洁能源，2021，37(3)：125-130.

[4] AMIRI A, SAMET H, GHANBARI T.Recurrence Plots based method for detecting series arc faults inphotovoltaic systems[J].IEEE Transactions on Industrial Electronics，2022，69(6)：6308-6315.

[5] 陈永辉，熊兰，范禹邑，等. 基于互感器电压信号的光伏电弧故障检测方法[J] . 太阳能学报，2021，42(10)：68-75.

[6] 邸振国，熊庆，张琛，等. 基于加权差分电流的直流故障电弧检测方法[J] . 西安交通大学学报，2022，56(5)：141-148.

[7] AHMADI M , SAMET H , GHANBARI T . A new method for detecting series arc fault in photovoltaic systems based on the blind-source separation[J].IEEE Transactions on Industrial Electronics，2020，67(6) ：5041-5049.

[8] LU S, MA R, SIROJAN T, et al.Lightweight transfer nets and adversarial data augmentation for photovoltaic series arc fault detection with limited fault data[J].International Journal of Electrical Power & Energy Systems，2021，130 ：107035.

[9] LU S, SIROJAN T, PHUNG B T, et al.DA-DCGAN:An effective methodology for DC series arc fault diagnosis in photovoltaic systems[J].IEEE Access，2019，7：45831-45840.

[10] LIU S, DONG L, LIAO X, et al.Application of the variational mode decomposition-based time and time–frequency domain analysis on series DC arc fault detection of photovoltaic arrays[J].IEEE Access，2019，7：126177-126190.

[11] 郑炜，林瑞全，王俊，等. 基于 GAF 与卷积神经网络的电能质量扰动分类[J] . 电力系统保护与控制，2021，49(11)：97-104.

[12] YIN J , XU M , ZHENG H . Fault diagnosis of bearing based on symbolic aggregate approximation and Lempel-Ziv[J].Measurement，2019，138：206-216.

[13] 裴莉莉，孙朝云，孙静，等. 基于 DCGAN 的路面裂缝图像生成方法[J]. 中南大学学报(自然科学版)，2021，52(11)：3899-3906.

[14] 赵小强，罗维兰. 改进卷积 Lenet-5 神经网络的轴承故障诊断方法[J] . 电子测量与仪器学报，2022，36(6)：113-125.

[15] LU S B, PHUNG B T, ZHANG D.A comprehensive review on DC arc faults and their diagnosis methods in photovoltaic systems[J].Renewable and Sustainable Energy Reviews，2018，89：88-98.

返回索引列表

Article retrieval

文章检索

一种光伏阵列串联电弧故障智能检测方法