IDEAS home Printed from https://ideas.repec.org/a/eee/renene/v179y2021icp502-516.html
   My bibliography  Save this article

Automatic fault classification in photovoltaic modules using Convolutional Neural Networks

Author

Listed:
  • Fonseca Alves, Ricardo Henrique
  • Deus Júnior, Getúlio Antero de
  • Marra, Enes Gonçalves
  • Lemos, Rodrigo Pinto

Abstract

Photovoltaic (PV) power systems have a significant potential to reduce greenhouse gases and diversify the electricity generation mix. Faults and damages that cause energy losses are common during either the fabrication or lifetime of PV modules. The development of automatic and reliable techniques to identify and classify faults in PV modules can help to improve the reliability and performance of PV systems and reduce operation and maintenance costs. A combination of infrared thermography and machine learning methods has been proven effective in the automatic detection of faults in large-scale PV plants. However, so far, few studies have assessed the challenges and efficiency of these methods applied to the classification of different defect classes in PV modules. In this study, we investigate the effect of data augmentation techniques to increase the performance of our proposed convolutional neural network (CNNs) to classify anomalies, between up to eleven different classes, in PV modules through thermographic images in an unbalanced dataset. Confusion matrices are used to investigate the high within- and between-class variation in different classes, which can be a challenge when creating an automatic tool to classify a large range of defects in PV plants. Through a cross-validation method, the CNN's testing accuracy was estimated as 92.5% for the detection of anomalies in PV modules and 78.85% to classify defects for eight selected classes.

Suggested Citation

  • Fonseca Alves, Ricardo Henrique & Deus Júnior, Getúlio Antero de & Marra, Enes Gonçalves & Lemos, Rodrigo Pinto, 2021. "Automatic fault classification in photovoltaic modules using Convolutional Neural Networks," Renewable Energy, Elsevier, vol. 179(C), pages 502-516.
    • Handle: RePEc:eee:renene:v:179:y:2021:i:c:p:502-516
    DOI: 10.1016/j.renene.2021.07.070
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0960148121010752
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.renene.2021.07.070?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Ko, Suk Whan & Ju, Young Chul & Hwang, Hye Mi & So, Jung Hun & Jung, Young-Seok & Song, Hyung-Jun & Song, Hee-eun & Kim, Soo-Hyun & Kang, Gi Hwan, 2017. "Electric and thermal characteristics of photovoltaic modules under partial shading and with a damaged bypass diode," Energy, Elsevier, vol. 128(C), pages 232-243.
    2. Huerta Herraiz, Álvaro & Pliego Marugán, Alberto & García Márquez, Fausto Pedro, 2020. "Photovoltaic plant condition monitoring using thermal images analysis by convolutional neural network-based structure," Renewable Energy, Elsevier, vol. 153(C), pages 334-348.
    3. J. C. Teo & Rodney H. G. Tan & V. H. Mok & Vigna K. Ramachandaramurthy & ChiaKwang Tan, 2018. "Impact of Partial Shading on the P-V Characteristics and the Maximum Power of a Photovoltaic String," Energies, MDPI, vol. 11(7), pages 1-22, July.
    4. Giovanni Cipriani & Antonino D’Amico & Stefania Guarino & Donatella Manno & Marzia Traverso & Vincenzo Di Dio, 2020. "Convolutional Neural Network for Dust and Hotspot Classification in PV Modules," Energies, MDPI, vol. 13(23), pages 1-17, December.
    5. Romênia G. Vieira & Fábio M. U. de Araújo & Mahmoud Dhimish & Maria I. S. Guerra, 2020. "A Comprehensive Review on Bypass Diode Application on Photovoltaic Modules," Energies, MDPI, vol. 13(10), pages 1-21, May.
    6. Maghami, Mohammad Reza & Hizam, Hashim & Gomes, Chandima & Radzi, Mohd Amran & Rezadad, Mohammad Ismael & Hajighorbani, Shahrooz, 2016. "Power loss due to soiling on solar panel: A review," Renewable and Sustainable Energy Reviews, Elsevier, vol. 59(C), pages 1307-1316.
    7. Chine, W. & Mellit, A. & Lughi, V. & Malek, A. & Sulligoi, G. & Massi Pavan, A., 2016. "A novel fault diagnosis technique for photovoltaic systems based on artificial neural networks," Renewable Energy, Elsevier, vol. 90(C), pages 501-512.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Amal Hichri & Mansour Hajji & Majdi Mansouri & Kamaleldin Abodayeh & Kais Bouzrara & Hazem Nounou & Mohamed Nounou, 2022. "Genetic-Algorithm-Based Neural Network for Fault Detection and Diagnosis: Application to Grid-Connected Photovoltaic Systems," Sustainability, MDPI, vol. 14(17), pages 1-14, August.
    2. Waqas Ahmed & Muhammad Umair Ali & M. A. Parvez Mahmud & Kamran Ali Khan Niazi & Amad Zafar & Tamas Kerekes, 2023. "A Comparison and Introduction of Novel Solar Panel’s Fault Diagnosis Technique Using Deep-Features Shallow-Classifier through Infrared Thermography," Energies, MDPI, vol. 16(3), pages 1-16, January.
    3. Mohamed Benghanem & Adel Mellit & Chourouk Moussaoui, 2023. "Embedded Hybrid Model (CNN–ML) for Fault Diagnosis of Photovoltaic Modules Using Thermographic Images," Sustainability, MDPI, vol. 15(10), pages 1-20, May.
    4. Mellit, Adel & Kalogirou, Soteris, 2022. "Assessment of machine learning and ensemble methods for fault diagnosis of photovoltaic systems," Renewable Energy, Elsevier, vol. 184(C), pages 1074-1090.
    5. Naveen Venkatesh Sridharan & Jerome Vasanth Joseph & Sugumaran Vaithiyanathan & Mohammadreza Aghaei, 2023. "Weightless Neural Network-Based Detection and Diagnosis of Visual Faults in Photovoltaic Modules," Energies, MDPI, vol. 16(15), pages 1-17, August.
    6. Mohammad Mahdi Forootan & Iman Larki & Rahim Zahedi & Abolfazl Ahmadi, 2022. "Machine Learning and Deep Learning in Energy Systems: A Review," Sustainability, MDPI, vol. 14(8), pages 1-49, April.
    7. Ding, Kun & Chen, Xiang & Weng, Shuai & Liu, Yongjie & Zhang, Jingwei & Li, Yuanliang & Yang, Zenan, 2023. "Health status evaluation of photovoltaic array based on deep belief network and Hausdorff distance," Energy, Elsevier, vol. 262(PB).
    8. Wang, Mengyuan & Xu, Xiaoyuan & Yan, Zheng, 2023. "Online fault diagnosis of PV array considering label errors based on distributionally robust logistic regression," Renewable Energy, Elsevier, vol. 203(C), pages 68-80.
    9. Tang, Wuqin & Yang, Qiang & Dai, Zhou & Yan, Wenjun, 2024. "Module defect detection and diagnosis for intelligent maintenance of solar photovoltaic plants: Techniques, systems and perspectives," Energy, Elsevier, vol. 297(C).
    10. Kellil, N. & Aissat, A. & Mellit, A., 2023. "Fault diagnosis of photovoltaic modules using deep neural networks and infrared images under Algerian climatic conditions," Energy, Elsevier, vol. 263(PC).
    11. Khaled Osmani & Ahmad Haddad & Mohammad Alkhedher & Thierry Lemenand & Bruno Castanier & Mohamad Ramadan, 2023. "A Novel MPPT-Based Lithium-Ion Battery Solar Charger for Operation under Fluctuating Irradiance Conditions," Sustainability, MDPI, vol. 15(12), pages 1-31, June.
    12. Mojgan Hojabri & Samuel Kellerhals & Govinda Upadhyay & Benjamin Bowler, 2022. "IoT-Based PV Array Fault Detection and Classification Using Embedded Supervised Learning Methods," Energies, MDPI, vol. 15(6), pages 1-18, March.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Teo, J.C. & Tan, Rodney H.G. & Mok, V.H. & Ramachandaramurthy, Vigna K. & Tan, ChiaKwang, 2020. "Impact of bypass diode forward voltage on maximum power of a photovoltaic system under partial shading conditions," Energy, Elsevier, vol. 191(C).
    2. Jeisson Vélez-Sánchez & Juan David Bastidas-Rodríguez & Carlos Andrés Ramos-Paja & Daniel González Montoya & Luz Adriana Trejos-Grisales, 2019. "A Non-Invasive Procedure for Estimating the Exponential Model Parameters of Bypass Diodes in Photovoltaic Modules," Energies, MDPI, vol. 12(2), pages 1-20, January.
    3. Høiaas, Ingeborg & Grujic, Katarina & Imenes, Anne Gerd & Burud, Ingunn & Olsen, Espen & Belbachir, Nabil, 2022. "Inspection and condition monitoring of large-scale photovoltaic power plants: A review of imaging technologies," Renewable and Sustainable Energy Reviews, Elsevier, vol. 161(C).
    4. Livera, Andreas & Theristis, Marios & Makrides, George & Georghiou, George E., 2019. "Recent advances in failure diagnosis techniques based on performance data analysis for grid-connected photovoltaic systems," Renewable Energy, Elsevier, vol. 133(C), pages 126-143.
    5. Heinrich, Matthias & Meunier, Simon & Samé, Allou & Quéval, Loïc & Darga, Arouna & Oukhellou, Latifa & Multon, Bernard, 2020. "Detection of cleaning interventions on photovoltaic modules with machine learning," Applied Energy, Elsevier, vol. 263(C).
    6. Georgios Goudelis & Pavlos I. Lazaridis & Mahmoud Dhimish, 2022. "A Review of Models for Photovoltaic Crack and Hotspot Prediction," Energies, MDPI, vol. 15(12), pages 1-24, June.
    7. Peinado Gonzalo, Alfredo & Pliego Marugán, Alberto & García Márquez, Fausto Pedro, 2020. "Survey of maintenance management for photovoltaic power systems," Renewable and Sustainable Energy Reviews, Elsevier, vol. 134(C).
    8. Li, B. & Delpha, C. & Diallo, D. & Migan-Dubois, A., 2021. "Application of Artificial Neural Networks to photovoltaic fault detection and diagnosis: A review," Renewable and Sustainable Energy Reviews, Elsevier, vol. 138(C).
    9. Rouani, Lahcene & Harkat, Mohamed Faouzi & Kouadri, Abdelmalek & Mekhilef, Saad, 2021. "Shading fault detection in a grid-connected PV system using vertices principal component analysis," Renewable Energy, Elsevier, vol. 164(C), pages 1527-1539.
    10. Segovia Ramírez, Isaac & Pliego Marugán, Alberto & García Márquez, Fausto Pedro, 2022. "A novel approach to optimize the positioning and measurement parameters in photovoltaic aerial inspections," Renewable Energy, Elsevier, vol. 187(C), pages 371-389.
    11. Chiwu Bu & Tao Liu & Tao Wang & Hai Zhang & Stefano Sfarra, 2023. "A CNN-Architecture-Based Photovoltaic Cell Fault Classification Method Using Thermographic Images," Energies, MDPI, vol. 16(9), pages 1-13, April.
    12. Hassan M. H. Farh & Mohd F. Othman & Ali M. Eltamaly & M. S. Al-Saud, 2018. "Maximum Power Extraction from a Partially Shaded PV System Using an Interleaved Boost Converter," Energies, MDPI, vol. 11(10), pages 1-18, September.
    13. Hanifi, Hamed & Pander, Matthias & Zeller, Ulli & Ilse, Klemens & Dassler, David & Mirza, Mark & Bahattab, Mohammed A. & Jaeckel, Bengt & Hagendorf, Christian & Ebert, Matthias & Gottschalg, Ralph & S, 2020. "Loss analysis and optimization of PV module components and design to achieve higher energy yield and longer service life in desert regions," Applied Energy, Elsevier, vol. 280(C).
    14. Alkharusi, Tarik & Huang, Gan & Markides, Christos N., 2024. "Characterisation of soiling on glass surfaces and their impact on optical and solar photovoltaic performance," Renewable Energy, Elsevier, vol. 220(C).
    15. Fabiana Lisco & Farwah Bukhari & Soňa Uličná & Kenan Isbilir & Kurt L. Barth & Alan Taylor & John M. Walls, 2020. "Degradation of Hydrophobic, Anti-Soiling Coatings for Solar Module Cover Glass," Energies, MDPI, vol. 13(15), pages 1-15, July.
    16. Mostafa. F. Shaaban & Amal Alarif & Mohamed Mokhtar & Usman Tariq & Ahmed H. Osman & A. R. Al-Ali, 2020. "A New Data-Based Dust Estimation Unit for PV Panels," Energies, MDPI, vol. 13(14), pages 1-17, July.
    17. Onwuemezie, Linus & Gohari Darabkhani, Hamidreza, 2024. "Oxy-hydrogen, solar and wind assisted hydrogen (H2) recovery from municipal plastic waste (MPW) and saltwater electrolysis for better environmental systems and ocean cleanup," Energy, Elsevier, vol. 301(C).
    18. Mahmoud Dhimish & Pavlos I. Lazaridis, 2022. "Approximating Shading Ratio Using the Total-Sky Imaging System: An Application for Photovoltaic Systems," Energies, MDPI, vol. 15(21), pages 1-16, November.
    19. Ghaith, Ahmad F. & Epplin, Francis M. & Frazier, R. Scott, 2017. "Economics of grid-tied household solar panel systems versus grid-only electricity," Renewable and Sustainable Energy Reviews, Elsevier, vol. 76(C), pages 407-424.
    20. Kara Mostefa Khelil, Chérifa & Amrouche, Badia & Benyoucef, Abou soufiane & Kara, Kamel & Chouder, Aissa, 2020. "New Intelligent Fault Diagnosis (IFD) approach for grid-connected photovoltaic systems," Energy, Elsevier, vol. 211(C).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:renene:v:179:y:2021:i:c:p:502-516. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.journals.elsevier.com/renewable-energy .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.