Fault Detection and Diagnosis of a Photovoltaic System Based on Deep Learning Using the Combination of a Convolutional Neural Network (CNN) and Bidirectional Gated Recurrent Unit (Bi-GRU)

Author:

Amiri Ahmed Faris12ORCID,Kichou Sofiane3ORCID,Oudira Houcine1ORCID,Chouder Aissa4ORCID,Silvestre Santiago5ORCID

Affiliation:

1. Laboratory of Electrical Engineering (LGE), Electronic Department, University of M’sila, P.O. Box 166 Ichebilia, M’sila 28000, Algeria

2. Laboratory of Signal and System Analysis (LASS), Electronic Department, University of M’sila, P.O. Box 1667 Ichebilia, M’sila 28000, Algeria

3. Czech Technical University in Prague, University Centre for Energy Efficient Buildings, 1024 Třinecká St., 27343 Buštěhrad, Czech Republic

4. Laboratory of Electrical Engineering (LGE), Electrical Engineering Department, University of M’sila, P.O. Box 166 Ichebilia, M’sila 28000, Algeria

5. Department of Electronic Engineering, Universitat Politècnica de Catalunya (UPC), Mòdul C5 Campus Nord UPC, Jordi Girona 1-3, 08034 Barcelona, Spain

Abstract

The meticulous monitoring and diagnosis of faults in photovoltaic (PV) systems enhances their reliability and facilitates a smooth transition to sustainable energy. This paper introduces a novel application of deep learning for fault detection and diagnosis in PV systems, employing a three-step approach. Firstly, a robust PV model is developed and fine-tuned using a heuristic optimization approach. Secondly, a comprehensive database is constructed, incorporating PV model data alongside monitored module temperature and solar irradiance for both healthy and faulty operation conditions. Lastly, fault classification utilizes features extracted from a combination consisting of a Convolutional Neural Network (CNN) and Bidirectional Gated Recurrent Unit (Bi-GRU). The amalgamation of parallel and sequential processing enables the neural network to leverage the strengths of both convolutional and recurrent layers concurrently, facilitating effective fault detection and diagnosis. The results affirm the proposed technique’s efficacy in detecting and classifying various PV fault types, such as open circuits, short circuits, and partial shading. Furthermore, this work underscores the significance of dividing fault detection and diagnosis into two distinct steps rather than employing deep learning neural networks to determine fault types directly.

Publisher

MDPI AG

Reference34 articles.

1. (2023, November 27). Tripling Renewable Power and Doubling Energy Efficiency by 2030: Crucial Steps towards 1.5 °C. Available online: https://www.irena.org/Publications/2023/Oct/Tripling-renewable-power-and-doubling-energy-efficiency-by-2030.

2. Europe, S.P. (2023). Global Market Outlook for Solar Power 2023–2027, European Photovoltaic Industry Association. Available online: https://www.solarpowereurope.org/insights/market-outlooks/global-market-outlook-for-solar-power-2023-2027-1.

3. (2023, November 27). IEA—International Energy Agency—IEA. Available online: https://www.iea.org/reports/worldenergy-outlook-2023.

4. Monitoring and Remote Failure Detection of Grid-Connected PV Systems Based on Satellite Observations;Drews;Sol. Energy,2007

5. Analysis of Current and Voltage Indicators in Grid Connected PV (Photovoltaic) Systems Working in Faulty and Partial Shading Conditions;Silvestre;Energy,2015

Cited by 14 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3