Automatic Classification of Defective Photovoltaic Module Cells in Electroluminescence Images

Yıl 2022, Cilt: 34 Sayı: 2, 589 - 600, 30.09.2022

Hakan Açıkgöz Deniz Korkmaz

https://doi.org/10.35234/fumbd.1099000

Cited By: 1

Öz

Detection and classification of faults in photovoltaic (PV) module cells have become a very important issue for the efficient and reliable operation of solar power plants. In this study, an efficient convolutional neural network (CNN) model is proposed for fast and accurate detection and classification of faults in PV module cells. The proposed model is developed with SqueezeNet, which has fewer parameters and model size, using the transfer learning approach. In order to improve the training convergence and increase the classification performance, the activation functions of the proposed model are changed and skip connections are added from the fire modules. A dataset obtained from Electroluminescence (EL) images are used in the experiments. Data augmentation techniques are also applied to eliminate the imbalance of class distribution and increase the class samples. The performance of the proposed method is compared with pre-trained CNN architectures such as AlexNet, ShuffleNet, GoogLeNet, and SqueezeNet. In the experimental studies, the accuracy, precision, sensitivity, specificity, and F1-score values of the proposed method are obtained as 91.29%, 84.21%, 89.72%, 92.04%, and 86.88%, respectively. In addition, the proposed method improves the accuracy values of the other methods between 0.99% and 6.29%. When all the obtained results are analyzed, it is observed that the proposed method has a superior performance in the detection of faults in PV module cells.

Anahtar Kelimeler

Photovoltaic Module Cells, Fault Detection, Electroluminescence Imaging, Convolutional Neural Network, Deep Learning

Elektrolüminesans Görüntülerde Arızalı Fotovoltaik Panel Hücrelerin Evrişimli Sinir Ağı ile Otomatik Sınıflandırılması

Öz

Fotovoltaik (FV) panel hücrelerindeki arızaların tespiti ve sınıflandırılması güneş enerjisi santrallerinin verimli ve güvenilir bir şekilde işletilebilmesi için oldukça önemli bir konu haline gelmiştir. Bu çalışmada, FV panel hücrelerindeki arızaların hızlı ve doğru bir şekilde tespit edilmesi ve sınıflandırılması için etkin bir evrişimli sinir ağı (ESA) modeli önerilmiştir. Önerilen model, daha az parametre ve model boyutuna sahip SqueezeNet ile transfer öğrenme yaklaşımı kullanılarak geliştirilmiştir. Eğitim yakınsamasını iyileştirmek ve sınıflandırma başarımını arttırmak için modelin aktivasyon fonksiyonları değiştirilerek ateşleme modüllerinden atlama bağlantıları oluşturulmuştur. Deneylerde, elektrolüminesans (EL) görüntülerden elde edilen bir veri seti kullanılmıştır. Sınıf dağılımının dengesizliğini gidermek ve örnek sayısını arttırmak için veri artırma teknikleri uygulanmıştır. Önerilen yöntemin performansı AlexNet, ShuffleNet, GoogLeNet ve SqueezeNet gibi ön eğitimli ESA mimarileri ile karşılaştırılmıştır. Gerçekleştirilen deneysel çalışmalarda önerilen yöntemin doğruluk, kesinlik, duyarlılık, özgüllük ve F1-skor değerleri sırasıyla %91.29, %84.21, %89.72, %92.04 ve %86.88 olarak elde edilmiştir. Ayrıca, önerilen yöntem diğer yöntemlerin doğruluk ölçütündeki değerlerini %0.99 ile %6.29 arasında iyileştirmiştir. Elde edilen tüm sonuçlar analiz edildiğinde, önerilen yöntemin FV panel hücrelerindeki arızaların tespitinde etkili bir performansa sahip olduğu gözlemlenmiştir.

Anahtar Kelimeler

Fotovoltaik Panel Hücreleri, Arıza Tespiti, Elektrolüminesans Görüntüleme, Evrişimli Sinir Ağları, Derin Öğrenme

Kaynakça

• Korkmaz D. SolarNet: A hybrid reliable model based on convolutional neural network and variational mode decomposition for hourly photovoltaic power forecasting. Appl Energy 2021;300:117410. doi:10.1016/j.apenergy.2021.117410.
• Acikgoz H. A novel approach based on integration of convolutional neural networks and deep feature selection for short-term solar radiation forecasting. Appl Energy 2022;305:117912. doi:10.1016/j.apenergy.2021.117912.
• Li B, Delpha C, Diallo D, Migan-Dubois A. Application of Artificial Neural Networks to photovoltaic fault detection and diagnosis: A review. Renew Sustain Energy Rev 2021;138. doi:10.1016/j.rser.2020.110512.
• Ali MU, Khan HF, Masud M, Kallu KD, Zafar A. A machine learning framework to identify the hotspot in photovoltaic module using infrared thermography. Sol Energy 2020;208:643–51. doi:10.1016/j.solener.2020.08.027.
• Pratt L, Govender D, Klein R. Defect detection and quantification in electroluminescence images of solar PV modules using U-net semantic segmentation. Renew Energy 2021;178:1211–22. doi:10.1016/j.renene.2021.06.086.
• Demirci MY, Beşli N, Gümüşçü A. Efficient deep feature extraction and classification for identifying defective photovoltaic module cells in Electroluminescence images. Expert Syst Appl 2021;175. doi:10.1016/j.eswa.2021.114810.
• Khezri R, Mahmoudi A, Aki H. Optimal planning of solar photovoltaic and battery storage systems for grid-connected residential sector: Review, challenges and new perspectives. Renew Sustain Energy Rev 2022;153:111763. doi:10.1016/j.rser.2021.111763.
• Naveen Venkatesh S, Sugumaran V. Machine vision based fault diagnosis of photovoltaic modules using lazy learning approach. Meas J Int Meas Confed 2022;191:110786. doi:10.1016/j.measurement.2022.110786.
• Deitsch S, Christlein V, Berger S, Buerhop-Lutz C, Maier A, Gallwitz F, et al. Automatic classification of defective photovoltaic module cells in electroluminescence images. Sol Energy 2019;185:455–68. doi:10.1016/j.solener.2019.02.067.
• Otamendi U, Martinez I, Quartulli M, Olaizola IG, Viles E, Cambarau W. Segmentation of cell-level anomalies in electroluminescence images of photovoltaic modules. Sol Energy 2021;220:914–26. doi:10.1016/j.solener.2021.03.058.
• Akram MW, Li G, Jin Y, Chen X, Zhu C, Zhao X, et al. CNN based automatic detection of photovoltaic cell defects in electroluminescence images. Energy 2019;189:116319. doi:10.1016/j.energy.2019.116319.
• Zhao Y, Zhan K, Wang Z, Shen W. Deep learning-based automatic detection of multitype defects in photovoltaic modules and application in real production line. Prog Photovoltaics Res Appl 2021;29:471–84. doi:10.1002/pip.3395.
• Chen H, Zhao H, Han D, Liu K. Accurate and robust crack detection using steerable evidence filtering in electroluminescence images of solar cells. Opt Lasers Eng 2019;118:22–33. doi:10.1016/j.optlaseng.2019.01.016.
• Moradi Sizkouhi A, Aghaei M, Esmailifar SM. A deep convolutional encoder-decoder architecture for autonomous fault detection of PV plants using multi-copters. Sol Energy 2021;223:217–28. doi:10.1016/j.solener.2021.05.029.
• Akram MW, Li G, Jin Y, Chen X, Zhu C, Ahmad A. Automatic detection of photovoltaic module defects in infrared images with isolated and develop-model transfer deep learning. Sol Energy 2020;198:175–86. doi:10.1016/j.solener.2020.01.055.
• Haidari P, Hajiahmad A, Jafari A, Nasiri A. Deep learning-based model for fault classification in solar modules using infrared images. Sustain Energy Technol Assessments 2022;52:102110. doi:10.1016/j.seta.2022.102110.
• Rico Espinosa A, Bressan M, Giraldo LF. Failure signature classification in solar photovoltaic plants using RGB images and convolutional neural networks. Renew Energy 2020;162:249–56. doi:10.1016/j.renene.2020.07.154.
• Su B, Chen H, Liu K, Liu W. RCAG-Net: Residual Channelwise Attention Gate Network for Hot Spot Defect Detection of Photovoltaic Farms. IEEE Trans Instrum Meas 2021;70. doi:10.1109/TIM.2021.3054415.
• Fioresi J, Colvin DJ, Frota R, Gupta R, Li M, Seigneur HP, et al. Automated Defect Detection and Localization in Photovoltaic Cells Using Semantic Segmentation of Electroluminescence Images. IEEE J Photovoltaics 2022;12:53–61. doi:10.1109/JPHOTOV.2021.3131059.
• Su B, Chen H, Zhu Y, Liu W, Liu K. Classification of Manufacturing Defects in Multicrystalline Solar Cells with Novel Feature Descriptor. IEEE Trans Instrum Meas 2019;68:4675–88. doi:10.1109/TIM.2019.2900961.
• Qian X, Li J, Cao J, Wu Y, Wang W. Micro-cracks detection of solar cells surface via combining short-term and long-term deep features. Neural Networks 2020;127:132–40. doi:10.1016/j.neunet.2020.04.012.
• Chen H, Pang Y, Hu Q, Liu K. Solar cell surface defect inspection based on multispectral convolutional neural network. J Intell Manuf 2020;31:453–68. doi:10.1007/s10845-018-1458-z.
• Gallardo-Saavedra S, Hernández-Callejo L, Alonso-García M del C, Santos JD, Morales-Aragonés JI, Alonso-Gómez V, et al. Nondestructive characterization of solar PV cells defects by means of electroluminescence, infrared thermography, I–V curves and visual tests: Experimental study and comparison. Energy 2020;205. doi:10.1016/j.energy.2020.117930.
• Gu J, Wang Z, Kuen J, Ma L, Shahroudy A, Shuai B, et al. Recent advances in convolutional neural networks. Pattern Recognit 2018;77:354–77. doi:10.1016/j.patcog.2017.10.013.
• Deitsch S, Buerhop-Lutz C, Sovetkin E, Steland A, Maier A, Gallwitz F, et al. Segmentation of photovoltaic module cells in uncalibrated electroluminescence images. Mach Vis Appl 2021;32:1–23. doi:10.1007/s00138-021-01191-9.
• Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size. Arxiv 160207360 2016:1–13.
• Ucar F, Korkmaz D. COVIDiagnosis-Net: Deep Bayes-SqueezeNet based diagnosis of the coronavirus disease 2019 (COVID-19) from X-ray images. Med Hypotheses 2020;140:109761. doi:10.1016/j.mehy.2020.109761.
• Alhichri H, Bazi Y, Alajlan N, Jdira B Bin. Helping the visually impaired see via image multi-labeling based on SqueezeNet CNN. Appl Sci 2019;9. doi:10.3390/app9214656.
• Polsinelli M, Cinque L, Placidi G. A light CNN for detecting COVID-19 from CT scans of the chest. Pattern Recognit Lett 2020;140:95–100. doi:10.1016/j.patrec.2020.10.001.
• Yang Z, Yang X, Li M, Li W. Automated garden-insect recognition using improved lightweight convolution network. Inf Process Agric 2022. doi:10.1016/j.inpa.2021.12.006.
• Shorten C, Khoshgoftaar TM. A survey on Image Data Augmentation for Deep Learning. J Big Data 2019;6:1–48. doi:10.1186/s40537-019-0197-0.