IDEAS home Printed from https://ideas.repec.org/a/eee/energy/v342y2026ics0360544225052533.html

Synergistic integration of text-to-image generation and deep learning for photovoltaic system inspection

Author

Listed:
  • Waqar Akram, M.
  • Bai, Jianbo

Abstract

The autonomous photovoltaic (PV) system inspection experiences challenges like data acquisition constraints as well as large and diverse data requirement. Addressing these challenges, this study firstly proposes first-of-its-kind of text-to-image generation method to generate electroluminescence (EL) images of PV modules. Therein, several text-to-image models were trained on text-image pairs data of PV modules collected from accelerated ageing experiments. The stable diffusion v2-based model generates realistic data with multi-defects and diverse representations, and can work on shorter prompt instructions. The study also deals with prompt engineering and understanding the model capabilities to explore the performance in terms of conditioning, biasness, and unrealistic generations. The developed text-to-image model and dataset are openly contributed.

Suggested Citation

  • Waqar Akram, M. & Bai, Jianbo, 2026. "Synergistic integration of text-to-image generation and deep learning for photovoltaic system inspection," Energy, Elsevier, vol. 342(C).
    • Handle: RePEc:eee:energy:v:342:y:2026:i:c:s0360544225052533
    DOI: 10.1016/j.energy.2025.139611
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0360544225052533
    Download Restriction: Full text for ScienceDirect subscribers only
    File URL: https://libkey.io/10.1016/j.energy.2025.139611?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

    for a different version of it.

    References listed on IDEAS

    as
    1. Akram, M. Waqar & Li, Guiqiang & Jin, Yi & Chen, Xiao & Zhu, Changan & Zhao, Xudong & Khaliq, Abdul & Faheem, M. & Ahmad, Ashfaq, 2019. "CNN based automatic detection of photovoltaic cell defects in electroluminescence images," Energy, Elsevier, vol. 189(C).
    2. Waqar Akram, M. & Li, Guiqiang & Jin, Yi & Chen, Xiao, 2022. "Failures of Photovoltaic modules and their Detection: A Review," Applied Energy, Elsevier, vol. 313(C).
    3. Pratt, Lawrence & Govender, Devashen & Klein, Richard, 2021. "Defect detection and quantification in electroluminescence images of solar PV modules using U-net semantic segmentation," Renewable Energy, Elsevier, vol. 178(C), pages 1211-1222.
    4. 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).
    5. Zhang, Jinxia & Chen, Xinyi & Wei, Haikun & Zhang, Kanjian, 2024. "A lightweight network for photovoltaic cell defect detection in electroluminescence images based on neural architecture search and knowledge distillation," Applied Energy, Elsevier, vol. 355(C).
    6. Zhou, Peng & Wang, Rui & Wang, Chuhan & Chen, Haiyong & Liu, Kun, 2024. "SIIF: Semantic information interactive fusion network for photovoltaic defect segmentation," Applied Energy, Elsevier, vol. 371(C).
    7. Li, Guiqiang & Akram, M.W. & Jin, Yi & Chen, Xiao & Zhu, Changan & Ahmad, Ashfaq & Arshad, R.H. & Zhao, Xudong, 2019. "Thermo-mechanical behavior assessment of smart wire connected and busbarPV modules during production, transportation, and subsequent field loading stages," Energy, Elsevier, vol. 168(C), pages 931-945.
    8. Buratti, Yoann & Javier, Gaia M.N. & Abdullah-Vetter, Zubair & Dwivedi, Priya & Hameiri, Ziv, 2024. "Machine learning for advanced characterisation of silicon photovoltaics: A comprehensive review of techniques and applications," Renewable and Sustainable Energy Reviews, Elsevier, vol. 202(C).
    Full references (including those not matched with items on IDEAS)

    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. Buratti, Yoann & Javier, Gaia M.N. & Abdullah-Vetter, Zubair & Dwivedi, Priya & Hameiri, Ziv, 2024. "Machine learning for advanced characterisation of silicon photovoltaics: A comprehensive review of techniques and applications," Renewable and Sustainable Energy Reviews, Elsevier, vol. 202(C).
    2. 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).
    3. Chen, Xin & Li, Baojie & Braid, Jennifer L. & Byford, Brandon & Colvin, Dylan J. & Glaws, Andrew & Jost, Norman & Pierce, Benjamin & Rabade, Salil & Springer, Martin & Jain, Anubhav, 2025. "Open data sets for assessing photovoltaic system reliability," Applied Energy, Elsevier, vol. 395(C).
    4. Chang, Zhonghao & Han, Te, 2024. "Prognostics and health management of photovoltaic systems based on deep learning: A state-of-the-art review and future perspectives," Renewable and Sustainable Energy Reviews, Elsevier, vol. 205(C).
    5. Qu, Zhaoyang & Zang, Jiye & Li, Lingcong & Dong, Yunchang & Qu, Nan, 2024. "Biomimetic model of photovoltaic cell defect detection based on mimic vision," Applied Energy, Elsevier, vol. 376(PA).
    6. Wang, Haoxuan & Chen, Huaian & Wang, Ben & Jin, Yi & Li, Guiqiang & Kan, Yan, 2022. "High-efficiency low-power microdefect detection in photovoltaic cells via a field programmable gate array-accelerated dual-flow network," Applied Energy, Elsevier, vol. 318(C).
    7. Zhang, Jinxia & Chen, Xinyi & Wei, Haikun & Zhang, Kanjian, 2024. "A lightweight network for photovoltaic cell defect detection in electroluminescence images based on neural architecture search and knowledge distillation," Applied Energy, Elsevier, vol. 355(C).
    8. Lei, Xinyue & Zhang, Jinxia & He, Ying & Fang, Shixiong & Zhang, Kanjian & Wei, Haikun, 2026. "Knowledge distillation based on fast normalization attention and auxiliary multi-label recognition for continual photovoltaic defect segmentation," Renewable Energy, Elsevier, vol. 256(PG).
    9. Drir, Nadia & Chekired, Fathia & Mellit, Adel & Blasuttigh, Nicola, 2025. "Hybrid CNN-EML model for fault diagnosis in electroluminescence images of photovoltaic cells," Renewable Energy, Elsevier, vol. 250(C).
    10. Zhao, Xiaolong & Song, Chonghui & Zhang, Haifeng & Sun, Xianrui & Zhao, Jing, 2023. "HRNet-based automatic identification of photovoltaic module defects using electroluminescence images," Energy, Elsevier, vol. 267(C).
    11. Zhou, Peng & Wang, Rui & Wang, Chuhan & Chen, Haiyong & Liu, Kun, 2024. "SIIF: Semantic information interactive fusion network for photovoltaic defect segmentation," Applied Energy, Elsevier, vol. 371(C).
    12. Waqar Akram, M. & Li, Guiqiang & Jin, Yi & Chen, Xiao, 2022. "Failures of Photovoltaic modules and their Detection: A Review," Applied Energy, Elsevier, vol. 313(C).
    13. Zhang, Haoran & Yu, Xiaohong & Gao, Zixuan, 2025. "Is the end of AI in photovoltaic power? Evidence from China," Energy Economics, Elsevier, vol. 145(C).
    14. 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.
    15. Liu, Qiao & Shi, Haotian & Zhu, Yuyu & Chen, Lei & Liu, Manlu & Cao, Wen & Huang, Qi, 2025. "An efficient fault diagnosis method combining multi-angle feature expansion and visual image neural networks for solar photovoltaic modules," Energy, Elsevier, vol. 333(C).
    16. Akram, M. Waqar & Li, Guiqiang & Jin, Yi & Chen, Xiao & Zhu, Changan & Zhao, Xudong & Khaliq, Abdul & Faheem, M. & Ahmad, Ashfaq, 2019. "CNN based automatic detection of photovoltaic cell defects in electroluminescence images," Energy, Elsevier, vol. 189(C).
    17. Pratt, Lawrence & Govender, Devashen & Klein, Richard, 2021. "Defect detection and quantification in electroluminescence images of solar PV modules using U-net semantic segmentation," Renewable Energy, Elsevier, vol. 178(C), pages 1211-1222.
    18. Shan, Chuan & Sun, Kangwen & Ji, Xinzhe & Cheng, Dongji, 2023. "A reconfiguration method for photovoltaic array of stratospheric airship based on multilevel optimization algorithm," Applied Energy, Elsevier, vol. 352(C).
    19. Li, Guanglei & Wang, Guohao & Luo, Tengqi & Hu, Yuxiao & Wu, Shouyuan & Gong, Guanghui & Song, Chenchen & Guo, Zhiling & Liu, Zhengguang, 2024. "SolarSAM: Building-scale photovoltaic potential assessment based on Segment Anything Model (SAM) and remote sensing for emerging city," Renewable Energy, Elsevier, vol. 237(PA).
    20. Cheng Yang & Fuhao Sun & Yujie Zou & Zhipeng Lv & Liang Xue & Chao Jiang & Shuangyu Liu & Bochao Zhao & Haoyang Cui, 2024. "A Survey of Photovoltaic Panel Overlay and Fault Detection Methods," Energies, MDPI, vol. 17(4), pages 1-37, February.

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;
    ;

    Statistics

    Access and download statistics

    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:energy:v:342:y:2026:i:c:s0360544225052533. 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/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.