Time-Frequency Image Representation Aided Deep Feature Extraction-Based Grid Connected Solar PV Fault Classification Framework

IF 1.204 Q3 Energy
Ananya Chakraborty, Ratan Mandal, Soumya Chatterjee
{"title":"Time-Frequency Image Representation Aided Deep Feature Extraction-Based Grid Connected Solar PV Fault Classification Framework","authors":"Ananya Chakraborty,&nbsp;Ratan Mandal,&nbsp;Soumya Chatterjee","doi":"10.3103/S0003701X23601667","DOIUrl":null,"url":null,"abstract":"<p>Accurate detection of faults in grid connected solar PV systems is important to ensure the reliability of power systems with distributed generation. Considering the aforesaid fact, here, a smoothed pseudo-Wigner-Ville distribution (SPWVD) and stacked sparse autoencoder (SSA) based automated feature extraction technique is proposed for accurate detection of faults in grid connected solar PV systems. To this end, three phase current data of normal as well as different fault scenarios obtained from point of common coupling (PCC) were converted into direct (<i>d</i>) and quadrature (<i>q</i>) axis using extended Park’s vector approach. Then, the obtained <i>d</i>-axis (<i>I</i><sub><i>d</i></sub>) and <i>q</i>-axis (<i>I</i><sub><i>q</i></sub>) currents were converted to 2D time-frequency images using SPWVD. The converted time-frequency spectrum of the normal as well as faulty current data were used as inputs to the proposed SSA model for deep feature extraction. After extraction of deep features using SSA, analysis of variance (ANOVA) test and false discovery rate (FDR) correction was employed to select the most discriminative features. The feature selection was followed by classification using machine learning classifiers. It has been observed that the proposed technique achieved mean fault recognition accuracy of 98.79 and 97.56% for <i>d</i>-axis and <i>q</i>-axis currents respectively, respectively. The present approach can be used for accurate diagnosis of faults in grid connected solar PV systems.</p>","PeriodicalId":475,"journal":{"name":"Applied Solar Energy","volume":null,"pages":null},"PeriodicalIF":1.2040,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied Solar Energy","FirstCategoryId":"1","ListUrlMain":"https://link.springer.com/article/10.3103/S0003701X23601667","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Energy","Score":null,"Total":0}
引用次数: 0

Abstract

Accurate detection of faults in grid connected solar PV systems is important to ensure the reliability of power systems with distributed generation. Considering the aforesaid fact, here, a smoothed pseudo-Wigner-Ville distribution (SPWVD) and stacked sparse autoencoder (SSA) based automated feature extraction technique is proposed for accurate detection of faults in grid connected solar PV systems. To this end, three phase current data of normal as well as different fault scenarios obtained from point of common coupling (PCC) were converted into direct (d) and quadrature (q) axis using extended Park’s vector approach. Then, the obtained d-axis (Id) and q-axis (Iq) currents were converted to 2D time-frequency images using SPWVD. The converted time-frequency spectrum of the normal as well as faulty current data were used as inputs to the proposed SSA model for deep feature extraction. After extraction of deep features using SSA, analysis of variance (ANOVA) test and false discovery rate (FDR) correction was employed to select the most discriminative features. The feature selection was followed by classification using machine learning classifiers. It has been observed that the proposed technique achieved mean fault recognition accuracy of 98.79 and 97.56% for d-axis and q-axis currents respectively, respectively. The present approach can be used for accurate diagnosis of faults in grid connected solar PV systems.

Abstract Image

Abstract Image

基于时频图像表征辅助深度特征提取的并网太阳能光伏故障分类框架
摘要 准确检测并网太阳能光伏系统中的故障对于确保分布式发电电力系统的可靠性非常重要。考虑到上述事实,本文提出了一种基于平滑伪维格纳-维尔分布(SPWVD)和堆叠稀疏自动编码器(SSA)的自动特征提取技术,用于准确检测并网太阳能光伏系统中的故障。为此,使用扩展的帕克矢量方法将从公共耦合点 (PCC) 获取的正常和不同故障情况下的三相电流数据转换为直交 (d) 轴和正交 (q) 轴。然后,利用 SPWVD 将获得的 d 轴 (Id) 和 q 轴 (Iq) 电流转换为二维时频图像。转换后的正常和故障电流数据的时频谱被用作拟议的 SSA 模型的输入,以进行深度特征提取。使用 SSA 提取深度特征后,采用方差分析 (ANOVA) 检验和误发现率 (FDR) 校正来选择最具区分度的特征。特征选择之后,使用机器学习分类器进行分类。据观察,所提出的技术对 d 轴和 q 轴电流的平均故障识别准确率分别达到 98.79% 和 97.56%。本方法可用于准确诊断并网太阳能光伏系统的故障。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Applied Solar Energy
Applied Solar Energy Energy-Renewable Energy, Sustainability and the Environment
CiteScore
2.50
自引率
0.00%
发文量
0
期刊介绍: Applied Solar Energy  is an international peer reviewed journal covers various topics of research and development studies on solar energy conversion and use: photovoltaics, thermophotovoltaics, water heaters, passive solar heating systems, drying of agricultural production, water desalination, solar radiation condensers, operation of Big Solar Oven, combined use of solar energy and traditional energy sources, new semiconductors for solar cells and thermophotovoltaic system photocells, engines for autonomous solar stations.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信