Classification of Hotspots in Photovoltaic Modules with Deep Learning Methods

Abstract

Solar energy systems are increasing their capacity in the energy industry day by day by operating with higher efficiency in parallel with technological developments. The functional operation of photovoltaic (PV) module contributes greatly to the optimal performance of these systems. On the other hand, detection and classification of faults occurring in PV modules are of vital importance in the operation and maintenance of solar energy systems. In this study, the classification of hotspots, which is one of the most common faults in Photovoltaic (PV) modules, is carried out by deep learning methods. First, data augmentation is applied to the images in the training dataset to improve the classification performance. Then, pre-trained deep learning models namely AlexNet, GoogLeNet, ShuffleNet, SqueezeNet, ResNet-50, and MobileNet-v2 are compared on the same test dataset. According to the obtained experimental results, AlexNet has the best performance with an accuracy value of 98.65%, while ResNet-50 provides the worst result with 94.59%.

Keywords

• Classification
• Deep Learning
• Hotspot
• Photovoltaic Module

References

1. Korkmaz D, Acikgoz H, Yildiz C. A Novel Short-Term Photovoltaic Power Forecasting Approach based on Deep Convolutional Neural Network. Int J Green Energy 2021:1–15.
2. Korkmaz D, Acikgoz H. An efficient fault classification method in solar photovoltaic modules using transfer learning and multi-scale convolutional neural network. Eng Appl Artif Intell 2022;113:104959.
3. 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.
4. 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.
5. Wang Q, Paynabar K, Pacella M. Online automatic anomaly detection for photovoltaic systems using thermography imaging and low rank matrix decomposition. J Qual Technol 2021;0:1–14.
6. 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.
7. Ali MU, Saleem S, Masood H, Kallu KD, Masud M, Alvi MJ, et al. Early hotspot detection in photovoltaic modules using color image descriptors: An infrared thermography study. Int J Energy Res 2022;46:774–85.
8. Rahaman SA, Urmee T, Parlevliet DA. PV system defects identification using Remotely Piloted Aircraft (RPA) based infrared (IR) imaging: A review. Sol Energy 2020;206:579–95.

9. Cipriani G, D’Amico A, Guarino S, Manno D, Traverso M, Di Dio V. Convolutional neural network for dust and hotspot classification in PV modules. Energies 2020;13.
10. Dhimish M. Defining the best-fit machine learning classifier to early diagnose photovoltaic solar cells hot-spots. Case Stud Therm Eng 2021;25:100980.
11. 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.
12. Manno D, Cipriani G, Ciulla G, Di Dio V, Guarino S, Lo Brano V. Deep learning strategies for automatic fault diagnosis in photovoltaic systems by thermographic images. Energy Convers Manag 2021;241:114315.
13. Kirsten Vidal de Oliveira A, Aghaei M, Rüther R. Aerial infrared thermography for low-cost and fast fault detection in utility-scale PV power plants. Sol Energy 2020;211:712–24.
14. Matthew M, Edward O, Vadhavkar N. Infrared Solar Module Dataset for Anomaly Detection. Int Conf Learn Represent. Published online 2020;1-5.
15. Krizhevsky, A, Sutskever, I, Hinton, GE. Imagenet classification with deep convolutional neural networks. In Proceedings of the 25th International Conference on Neural Information Processing Systems. 2012;1097-1105.
16. Zhang X, Zhou X, Lin M, Sun J. ShuffleNet: An extremely efficient convolutional neural network for mobile devices. Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. 2018;6848-6856.
17. Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K. Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <0.5 mb model size. arXiv preprint arXiv:1602.07360, 2016.
18. He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. 2016;770-778.
19. Szegedy C, Liu W, Jia Y, et al. Going deeper with convolutions. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. 2015;1-9.
20. Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC. MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. 2018;4510-4520.