Data-Driven Digital Inspection of Photovoltaic Panels Using a Portable Hybrid Model Combining Meteorological Data and Image Processing

被引：4

作者：

Oufadel, Ayoub ^{[1
]}

Azouzoute, Alae ^{[2
]}

Ghennioui, Hicham ^{[1
]}

Soubai, Chaimae ^{[1
]}

Taabane, Ibrahim ^{[3
,4
]}

机构：

[1] Sidi Mohamed Ben Abdellah Univ, Lab Signals Syst & Components, Fes 30000, Morocco

[2] Univ Mohammed First Oujda, Fac Sci, Lab Mech & Energet, Fluid Mech Team, Oujda 60000, Morocco

[3] Univ Rennes, Inst Elect & Digital Technol IETR, F-35000 Rennes, France

[4] Sidi Mohamed Ben Abdellah Univ, Lab Intelligent Syst Georesources & Renewable Ener, Fes 30000, Morocco

来源：

IEEE JOURNAL OF PHOTOVOLTAICS | 2024年 / 14卷 / 06期

关键词：

Inspection; Solar panels; Accuracy; Temperature measurement; Data models; Support vector machines; Temperature distribution; Convolutional neural network (CNN); image processing; innovative inspection; machine learning (ML); maintenance; photovoltaic; PV-MODULES; CLASSIFICATION; ENSEMBLE;

D O I：

10.1109/JPHOTOV.2024.3437736

中图分类号：

TE [石油、天然气工业]; TK [能源与动力工程];

学科分类号：

0807 ; 0820 ;

摘要：

This article proposes a novel approach to photovoltaic panel inspection through the integration of image classification and meteorological data analysis. Utilizing two convolutional neural network models with distinct architectures for classifying thermal and red, green, blue (RGB) images of photovoltaic installations, in addition to an support vector machines model for meteorological data classification, the results from these models are concatenated, allowing the fusion of visual and meteorological information for comprehensive defect detection. Data collection from photovoltaic panels is achieved using a portable device, followed by the application of advanced image processing techniques to identify faults rapidly and accurately with up to 96% accuracy. The inspection results are presented in a user-friendly format, facilitating straightforward interpretation and analysis. This new approach has the potential to significantly enhance the efficiency and durability of solar energy systems, enabling timely maintenance and repair for photovoltaic panel issues.

引用

页码：937 / 950

页数：14

共 49 条

[31] Drone-Based Non-Destructive Inspection of Industrial Sites: A Review and Case Studies [J].

Nooralishahi, Parham ;

Ibarra-Castanedo, Clemente ;

Deane, Shakeb ;

Lopez, Fernando ;

Pant, Shashank ;

Genest, Marc ;

Avdelidis, Nicolas P. ;

Maldague, Xavier P. V. .

DRONES, 2021, 5 (04)

[32]

Oufadel Ayoub, 2023, Proceedings of the 3rd International Conference on Electronic Engineering and Renewable Energy Systems: ICEERE 2022. Lecture Notes in Electrical Engineering (954), P805, DOI 10.1007/978-981-19-6223-3_83

[33]

Oufadel A., 2022, P IEEE 9 INT C WIR N, P5

[34]

Oufadel A., 2023, ENV CHALL, V10

[35]

Pathak Sujata P., 2022, Procedia Computer Science, P698, DOI 10.1016/j.procs.2022.08.084

[36] Defect detection and quantification in electroluminescence images of solar PV modules using U-net semantic segmentation [J].

Pratt, Lawrence ;

Govender, Devashen ;

Klein, Richard .

RENEWABLE ENERGY, 2021, 178 :1211-1222

[37]

Priyam A., 2013, Inter. J. Cur. Engineer. Technol., V3, P334

[38] One- and Two-Phase Software Requirement Classification Using Ensemble Deep Learning [J].

Rahimi, Nouf ;

Eassa, Fathy ;

Elrefaei, Lamiaa .

ENTROPY, 2021, 23 (10)

[39] Convolutional neural networks and Internet of Things for fault detection by aerial monitoring of photovoltaic solar plants [J].

Ramirez, Isaac Segovia ;

Marquez, Fausto Pedro Garcia ;

Chaparro, Jesus Parra .

MEASUREMENT, 2024, 234

[40] Cost-sensitive probability for weighted voting in an ensemble model for multi-class classification problems [J].

Rojarath, Artittayapron ;

Songpan, Wararat .

APPLIED INTELLIGENCE, 2021, 51 (07) :4908-4932

← 1 2 3 4 5 →