Abstract
Güneş enerjisi santrallerindeki kusurların hızlı ve doğru bir şekilde tespit edilmesi, fotovoltaik (PV) sistemlerinde verim kaybını azaltmak ve ömrünü uzatmak açısından büyük bir öneme sahiptir. Bu çalışmada, güneş enerjisi santrallerindeki, PV modüllerdeki hotspot (sıcak nokta) tespiti için You Only Look Once (YOLO) algoritmalarının etkililiği ve avantajları incelenmiştir. YOLO algoritmaları, yüksek hızda çalışarak tek bir taramada görüntüdeki nesneleri tespit edebilme özelliği sayesinde büyük ölçekli santrallerde verimli bir şekilde kullanılabilmektedir. Bu doğrultuda, YOLOv5, YOLOv6, YOLOv7 ve YOLOv8 algoritmalarının performansları karşılaştırılmış ve en iyi sonuç veren model belirlenmiştir. Yapılan deneyler sonucuna göre, veri kümesinde kullanılan insansız hava aracı tarafından elde edilen 100 adet görüntünün %80’i eğitim kümesi %20’si ise test kümesi için kullanılarak YOLO algoritmaları karşılaştırmaları yapılmıştır. Elde edilen sonuçlar doğrultusunda, YOLOv8 algoritmasının %88.7 özgüllük, %80.5 duyarlılık ve %83.8 mAP değerleri ile diğer modellere göre daha iyi sonuçlar verdiğini göstermiştir. Çalışmada kullanılan veri seti gerçek güneş panellerinden elde edilen görüntülerden oluşmuştur ve bu sayede çalışmanın sonuçları gerçek dünya senaryolarına uygun bir şekilde test edilmiştir. Elde edilen sonuçlar, YOLO algoritmalarının güneş panellerindeki sıcak nokta kusurlarının tespiti için etkili bir yöntem olduğunu göstermektedir. Bu çalışma, güneş enerjisi santrallerinin daha verimli hale getirilmesi için nesne tespiti algoritmalarının kullanımının önemini vurgulamaktadır. Ayrıca, ilerideki çalışmalara yol gösteren ve literatüre katkı sağlayan bir çalışma olarak değerlendirilebilir.
Thanks
Veri setinin elde edilme sürecindeki desteklerinden dolayı Sines Enerjiye teşekkür ederiz.
References
- Yilmaz F, Ozturk M, Selbas R. Investigation of the thermodynamic analysis of solar Energy-Based multi-generation plant for sustainable multi-generation. Sustainable Energy Technologies and Assessments, 2022; 53: 102461.
- International Energy Agency (IEA). CO2 Emissions in 2022. IEA, Paris, France. https://www.iea.org/reports/co2-emissions-in-2022 (Erişim tarihi: Mayıs 2023)
- International Energy Agency (IEA). Renewables 2022: Analysis and Forecast to 2027. IEA, Paris, France. https://www.iea.org/reports/renewables-2022 (Erişim tarihi: Mayıs 2023)
- Taşkin O. Kusurlu güneş panelinde (PV) verimlerin ölçülmesi. Uludağ Üniversitesi Mühendislik Fakültesi Dergisi, 2019; 24(1): 289-298.
- Açıkgöz H. Korkmaz D. Elektrolüminesans görüntülerde arızalı fotovoltaik panel hücrelerin evrişimli sinir ağı ile otomatik sınıflandırılması. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 2022; 34(2): 589-600.
- Dhimish M. Defining the best-fit machine learning classifier to early diagnose photovoltaic solar cells hot-spots. Case Studies in Thermal Engineering. 2021; 25, 100980.
- Ali M. U. Khan H. F. Masud M. Kallu K. D. Zafar A. A machine learning framework to identify the hotspot in photovoltaic module using infrared thermography. Solar Energy. 2020; 208: 643-651.
- Goudelis G. Lazaridis P. I. Dhimish M. A review of models for photovoltaic crack and hotspot prediction. Energies. 2022; 15(12): 4303.
- Mustafa R. J. Gomaa M. R. Al-Dhaifallah M. Rezk H. Environmental impacts on the performance of solar photovoltaic systems. Sustainability. 2020; 12(2): 608.
- Niazi K. A. K. Akhtar W. Khan H. A. Yang Y. Athar S. Hotspot diagnosis for solar photovoltaic modules using a Naive Bayes classifier. Solar Energy. 2019; 190, 34-43.
- Chen J. Li Y. Ling Q. (2020, August). Hot-Spot Detection for Thermographic Images of Solar Panels. In 2020 Chinese Control and Decision Conference (CCDC); 22-24 August 2020; Hefei, China: IEEE pp. 4651-4655.
- Prajapati N. Raj, A. Aiyar R. Paraye M. Detection and Identification of faults in a PV Module using CNN-based Algorithm. International Conference for Emerging Technology (INCET); 27-29 May 2022; Belgaum, India: IEEE pp. 1-5.
- Afifah A. N. N. Suyuti A. (2020, December). Hotspot detection in photovoltaic module using Otsu thresholding method. In 2020 IEEE International Conference on Communication, Networks and Satellite (Comnetsat); 17-18 December 2020; Batam, Indonesia: IEEE. pp. 408-412.
- Cipriani G. Boscaino V. Di Dio V. Cardona F. Zizzo G. Di Caro S. (2019, June). Application of thermographic techniques for the detection of failures on photovoltaic modules. In 2019 IEEE international conference on environment and electrical; 11-14 June 2019; Genova, Italy: IEEE. pp. 1-5
- Ren Y. Yu Y. Li J. Zhang W. Design of photovoltaic hotspot detection system based on deep learning. The 2020 3rd International Conference on Computer Information Science and Artificial Intelligence (CISAI); 25-27 September 2020; Inner Mongolia, China: In Journal of Physics: Conference Series 1693(1) pp. 012075)
- Ali M. U. Saleem S. Masood H. Kallu K. D. Masud M. Alvi M. J. Zafar A. Early hotspot detection in photovoltaic modules using color image descriptors: An infrared thermography study. International Journal of Energy Research. 2022;46(2):774-785.
- Sun T. Xing H. Cao S. Zhang Y. Fan S. Liu P. A novel detection method for hot spots of photovoltaic (PV) panels using improved anchors and prediction heads of YOLOv5 network. Energy Reports 2022; 8: 1219-1229
- Sevi M. Aydın İ. Akın E. YOLOv5 ile Topluluk Öğrenmesine Dayalı Olarak Ray Yüzeyindeki Kusurların Tespiti. Demiryolu Mühendisliği 2023; 17: 115-132.
- Kıvrak O. Gürbüz M.Z. Performance Comparison of YOLOv3, YOLOv4 and YOLOv5 algorithms: A Case Study for Poultry Recognition. Avrupa Bilim ve Teknoloji Dergisi 2022; 38: 392-397.
- Ağdaş M.T. Gülseçen Ş. Güvenlik Kameralarında Otomatik Silah ve Bıçak Tespit Sistemi: Karşılaştırmalı YOLO Modelleri. Avrupa Bilim ve Teknoloji Dergisi 2022; 41: 16-22.
- Chen Z. Wu R. Lin Y. Li C. Chen S. Yuan Z. Zou X. (2022). Plant disease recognition model based on improved YOLOv5. Agronomy 2022; 12(2): 365
- Azizah A. N. Fatichah C. Tajweed-YOLO: Object Detection Method for Tajweed by Applying HSV Color Model Augmentation on Mushaf Images. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) 2023; 7(2); 236-245.
- Wei, J., & Qu, Y. (2023). Lightweight improvement of YOLOv6 algorithm for small target detection. https://www.researchsquare.com/article/rs-2687469/v1 (Erişim Tarihi: Mayıs 2023).
- Dewi C. Chen A. P. S. Christanto H. J. Deep Learning for Highly Accurate Hand Recognition Based on Yolov7 Model. Big Data and Cognitive Computing 2023; 7(1): 53.
- Tang F. Yang F. Tian X. Long-Distance Person Detection Based on YOLOv7. Electronics 2023; 12(6); 1502.
- Chen J. Ma B. Ji C. Zhang J. Feng Q. Liu X. Li Y. Apple inflorescence recognition of phenology stage in complex background based on improved YOLOv7. Computers and Electronics in Agriculture 2023; 211: 108048.
- Cao L. Zheng X. Fang, L. The Semantic Segmentation of Standing Tree Images Based on the YOLOv7 Deep Learning Algorithm. Electronics 2023; 12(4); 929.
- Terven J. Cordova-Esparza D. A comprehensive review of YOLO: From YOLOv1 to YOLOv8 and beyond. arXiv preprint arXiv 2023;2304.00501.
- Aboah A. Wang B. Bagci U. Adu-Gyamfi Y. Real-time multi-class helmet violation detection using few-shot data sampling technique and yolov8. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition; 17-24 June 2023; Vancouver, BC, Canada: IEEE pp. 5349-5357.
- Zhao H. Jin J. Liu Y. Guo Y. Shen Y. FSDF: A high-performance fire detection framework. Expert Systems with Applications 2024; 238: 121665.
Abstract
The rapid and accurate detection of defects in solar energy plants is of great importance to reduce efficiency losses and extend the lifespan of photovoltaic systems. In this study, the effectiveness and advantages of You Only Look Once (YOLO) algorithms for hotspot detection in solar energy plants have been investigated. YOLO algorithms can be efficiently used in large-scale facilities due to their ability to detect objects in images in a single scan at high speeds. In this context, the performances of YOLOv5, YOLOv6, YOLOv7, and YOLOv8 algorithms were compared, and the best-performing model was determined. According to the results of the experiments, 80% of the 100 images obtained by an unmanned aerial vehicle in the dataset were used for training, and the remaining 20% were used for testing the YOLO algorithms. The results indicated that the YOLOv8 algorithm outperformed other models with 88.7% specificity, 80.5% sensitivity, and 83.8% mean Average Precision (mAP) values. The dataset used in the study consisted of images obtained from real solar panels, ensuring that the results of the study were tested in accordance with real-world scenarios. The findings demonstrate that YOLO algorithms are an effective method for detecting hotspot defects in solar panels. This study highlights the importance of using object detection algorithms to make solar energy plants more efficient. Additionally, it can be considered as a guiding and contributing study to the literature, providing insights for future research.
References
- Yilmaz F, Ozturk M, Selbas R. Investigation of the thermodynamic analysis of solar Energy-Based multi-generation plant for sustainable multi-generation. Sustainable Energy Technologies and Assessments, 2022; 53: 102461.
- International Energy Agency (IEA). CO2 Emissions in 2022. IEA, Paris, France. https://www.iea.org/reports/co2-emissions-in-2022 (Erişim tarihi: Mayıs 2023)
- International Energy Agency (IEA). Renewables 2022: Analysis and Forecast to 2027. IEA, Paris, France. https://www.iea.org/reports/renewables-2022 (Erişim tarihi: Mayıs 2023)
- Taşkin O. Kusurlu güneş panelinde (PV) verimlerin ölçülmesi. Uludağ Üniversitesi Mühendislik Fakültesi Dergisi, 2019; 24(1): 289-298.
- Açıkgöz H. Korkmaz D. Elektrolüminesans görüntülerde arızalı fotovoltaik panel hücrelerin evrişimli sinir ağı ile otomatik sınıflandırılması. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 2022; 34(2): 589-600.
- Dhimish M. Defining the best-fit machine learning classifier to early diagnose photovoltaic solar cells hot-spots. Case Studies in Thermal Engineering. 2021; 25, 100980.
- Ali M. U. Khan H. F. Masud M. Kallu K. D. Zafar A. A machine learning framework to identify the hotspot in photovoltaic module using infrared thermography. Solar Energy. 2020; 208: 643-651.
- Goudelis G. Lazaridis P. I. Dhimish M. A review of models for photovoltaic crack and hotspot prediction. Energies. 2022; 15(12): 4303.
- Mustafa R. J. Gomaa M. R. Al-Dhaifallah M. Rezk H. Environmental impacts on the performance of solar photovoltaic systems. Sustainability. 2020; 12(2): 608.
- Niazi K. A. K. Akhtar W. Khan H. A. Yang Y. Athar S. Hotspot diagnosis for solar photovoltaic modules using a Naive Bayes classifier. Solar Energy. 2019; 190, 34-43.
- Chen J. Li Y. Ling Q. (2020, August). Hot-Spot Detection for Thermographic Images of Solar Panels. In 2020 Chinese Control and Decision Conference (CCDC); 22-24 August 2020; Hefei, China: IEEE pp. 4651-4655.
- Prajapati N. Raj, A. Aiyar R. Paraye M. Detection and Identification of faults in a PV Module using CNN-based Algorithm. International Conference for Emerging Technology (INCET); 27-29 May 2022; Belgaum, India: IEEE pp. 1-5.
- Afifah A. N. N. Suyuti A. (2020, December). Hotspot detection in photovoltaic module using Otsu thresholding method. In 2020 IEEE International Conference on Communication, Networks and Satellite (Comnetsat); 17-18 December 2020; Batam, Indonesia: IEEE. pp. 408-412.
- Cipriani G. Boscaino V. Di Dio V. Cardona F. Zizzo G. Di Caro S. (2019, June). Application of thermographic techniques for the detection of failures on photovoltaic modules. In 2019 IEEE international conference on environment and electrical; 11-14 June 2019; Genova, Italy: IEEE. pp. 1-5
- Ren Y. Yu Y. Li J. Zhang W. Design of photovoltaic hotspot detection system based on deep learning. The 2020 3rd International Conference on Computer Information Science and Artificial Intelligence (CISAI); 25-27 September 2020; Inner Mongolia, China: In Journal of Physics: Conference Series 1693(1) pp. 012075)
- Ali M. U. Saleem S. Masood H. Kallu K. D. Masud M. Alvi M. J. Zafar A. Early hotspot detection in photovoltaic modules using color image descriptors: An infrared thermography study. International Journal of Energy Research. 2022;46(2):774-785.
- Sun T. Xing H. Cao S. Zhang Y. Fan S. Liu P. A novel detection method for hot spots of photovoltaic (PV) panels using improved anchors and prediction heads of YOLOv5 network. Energy Reports 2022; 8: 1219-1229
- Sevi M. Aydın İ. Akın E. YOLOv5 ile Topluluk Öğrenmesine Dayalı Olarak Ray Yüzeyindeki Kusurların Tespiti. Demiryolu Mühendisliği 2023; 17: 115-132.
- Kıvrak O. Gürbüz M.Z. Performance Comparison of YOLOv3, YOLOv4 and YOLOv5 algorithms: A Case Study for Poultry Recognition. Avrupa Bilim ve Teknoloji Dergisi 2022; 38: 392-397.
- Ağdaş M.T. Gülseçen Ş. Güvenlik Kameralarında Otomatik Silah ve Bıçak Tespit Sistemi: Karşılaştırmalı YOLO Modelleri. Avrupa Bilim ve Teknoloji Dergisi 2022; 41: 16-22.
- Chen Z. Wu R. Lin Y. Li C. Chen S. Yuan Z. Zou X. (2022). Plant disease recognition model based on improved YOLOv5. Agronomy 2022; 12(2): 365
- Azizah A. N. Fatichah C. Tajweed-YOLO: Object Detection Method for Tajweed by Applying HSV Color Model Augmentation on Mushaf Images. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) 2023; 7(2); 236-245.
- Wei, J., & Qu, Y. (2023). Lightweight improvement of YOLOv6 algorithm for small target detection. https://www.researchsquare.com/article/rs-2687469/v1 (Erişim Tarihi: Mayıs 2023).
- Dewi C. Chen A. P. S. Christanto H. J. Deep Learning for Highly Accurate Hand Recognition Based on Yolov7 Model. Big Data and Cognitive Computing 2023; 7(1): 53.
- Tang F. Yang F. Tian X. Long-Distance Person Detection Based on YOLOv7. Electronics 2023; 12(6); 1502.
- Chen J. Ma B. Ji C. Zhang J. Feng Q. Liu X. Li Y. Apple inflorescence recognition of phenology stage in complex background based on improved YOLOv7. Computers and Electronics in Agriculture 2023; 211: 108048.
- Cao L. Zheng X. Fang, L. The Semantic Segmentation of Standing Tree Images Based on the YOLOv7 Deep Learning Algorithm. Electronics 2023; 12(4); 929.
- Terven J. Cordova-Esparza D. A comprehensive review of YOLO: From YOLOv1 to YOLOv8 and beyond. arXiv preprint arXiv 2023;2304.00501.
- Aboah A. Wang B. Bagci U. Adu-Gyamfi Y. Real-time multi-class helmet violation detection using few-shot data sampling technique and yolov8. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition; 17-24 June 2023; Vancouver, BC, Canada: IEEE pp. 5349-5357.
- Zhao H. Jin J. Liu Y. Guo Y. Shen Y. FSDF: A high-performance fire detection framework. Expert Systems with Applications 2024; 238: 121665.
Details
| Primary Language | Turkish |
|---|---|
| Subjects | Deep Learning |
| Journal Section | MBD |
| Authors | |
| Publication Date | March 28, 2024 |
| Submission Date | June 21, 2023 |
| Published in Issue | Year 2024 Volume: 36 Issue: 1 |
