Automatic Fault Detection of Photovoltaic Modules Using Recurrent Neural Network

Q3 Engineering Russian Electrical Engineering Pub Date : 2024-06-14 DOI:10.3103/s1068371224700330

Parveen Kumar, Manish Kumar, Ajay Kumar Bansal

{"title":"Automatic Fault Detection of Photovoltaic Modules Using Recurrent Neural Network","authors":"Parveen Kumar, Manish Kumar, Ajay Kumar Bansal","doi":"10.3103/s1068371224700330","DOIUrl":null,"url":null,"abstract":"<h3 data-test=\"abstract-sub-heading\">Abstract</h3><p>Everywhere in the globe, the total capacity of photovoltaic (PV) panels is expanding at an exponential rate. Arc faults, open-circuit (OC) faults, bypass diode failures, mismatch faults, and short circuit faults are only a few of the most common types of problems that may occur in PV arrays. Not recognizing and correcting these issues quickly might affect power plant production. Fault detection in PV modules helps stabilize PV plant output. Machine learning techniques can automatically identify PV module issues. This paper portrayed fault detection using Multi-Layer Perceptron (MLP) and Recurrent Neural Network (RNN). Two methods identify PV defects based on normalizing factors. MLP has nonlinear problems and is slow to compute. The suggested RNN proved to be a superior detection approach for 10 weeks of testing on 2.4 KW monocrystalline solar panels. MLP has 75.62% fault detection accuracy whereas RNN has 98.95% in 4s-2p PV panels. Therefore, the findings of the simulation indicate that the proposed RNN technique achieves the necessary level of speed and accuracy.</p>","PeriodicalId":39312,"journal":{"name":"Russian Electrical Engineering","volume":"31 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Russian Electrical Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3103/s1068371224700330","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Engineering","Score":null,"Total":0}

引用次数: 0

Abstract

Everywhere in the globe, the total capacity of photovoltaic (PV) panels is expanding at an exponential rate. Arc faults, open-circuit (OC) faults, bypass diode failures, mismatch faults, and short circuit faults are only a few of the most common types of problems that may occur in PV arrays. Not recognizing and correcting these issues quickly might affect power plant production. Fault detection in PV modules helps stabilize PV plant output. Machine learning techniques can automatically identify PV module issues. This paper portrayed fault detection using Multi-Layer Perceptron (MLP) and Recurrent Neural Network (RNN). Two methods identify PV defects based on normalizing factors. MLP has nonlinear problems and is slow to compute. The suggested RNN proved to be a superior detection approach for 10 weeks of testing on 2.4 KW monocrystalline solar panels. MLP has 75.62% fault detection accuracy whereas RNN has 98.95% in 4s-2p PV panels. Therefore, the findings of the simulation indicate that the proposed RNN technique achieves the necessary level of speed and accuracy.

Abstract Image

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

利用递归神经网络自动检测光伏组件故障

摘要在全球各地，光伏（PV）电池板的总容量正以指数级速度增长。电弧故障、开路 (OC) 故障、旁路二极管故障、不匹配故障和短路故障只是光伏阵列中可能出现的几种最常见的问题。如果不能快速识别和纠正这些问题，可能会影响发电厂的生产。光伏模块的故障检测有助于稳定光伏电站的输出。机器学习技术可以自动识别光伏模块问题。本文介绍了使用多层感知器（MLP）和循环神经网络（RNN）进行故障检测的方法。这两种方法基于归一化因子识别光伏缺陷。MLP 存在非线性问题，计算速度较慢。在对 2.4 千瓦单晶硅太阳能电池板进行的 10 周测试中，所建议的 RNN 被证明是一种出色的检测方法。在 4s-2p 光伏板中，MLP 的故障检测准确率为 75.62%，而 RNN 的准确率为 98.95%。因此，模拟结果表明，拟议的 RNN 技术达到了必要的速度和准确度水平。

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分钟内获得全文去求助

来源期刊

Russian Electrical Engineering Engineering-Electrical and Electronic Engineering

CiteScore

1.50

自引率

0.00%

发文量

期刊介绍： Russian Electrical Engineering is a journal designed for the electrical engineering industry and publishes the latest research results on the design and utilization of new types of equipment for that industry and on the ways of improving the efficiency of existing equipment.