Global Organization
The deep learning method also has been widely used in photovoltaic module defect detection 10. To reduce the detection network complexity, Akram et al. 11 proposed a light convolution neural network based on a visual geometry group network for detecting photovoltaic cell cracking defects.
Improving detection speed is the focus of the one-stage method, while the two-stage method emphasizes detection accuracy. In the practical detection of photovoltaic module defects, we should consider not only the detection speed but also the detection accuracy. The VarifocalNet is an anchor-free detection method and has higher detection accuracy 5.
Moreover, to generalize the PV cell defect detection methods, this paper divide them into (i) imaging-based techniques, (ii) rapid visual inspection methods, and (iii) I–V curve measurements, which are the most powerful diagnostic tools for field-level testing.
Recently, convolutional neural network (CNN) based automatic detection methods for PV cell defects using EL images have attracted much attention. However, existing methods struggle to achieve a good balance between detection accuracy and efficiency. To address this issue, we propose a novel method for efficient PV cell defect detection.
The work presented in this paper predominantly covers widely used imaging-based techniques for PV module defect detection, and it excludes unique methods, such as electrical techniques based on statistical and signals processing, reflectometry-based, and machine learning-based techniques.
The VarifocalNet is an anchor-free detection method and has higher detection accuracy 5. To further improve both the detection accuracy and speed for detecting photovoltaic module defects, a detection method of photovoltaic module defects in EL images with faster detection speed and higher accuracy is proposed based on VarifocalNet.
through the use of electrical current by connecting the solar cell in forward bias mode. This technique is very attractive, because it can be used not only with small solar cell sizes but …
Zhang et al. 8 introduced a photovoltaic cell defect detection method leveraging the YOLOV7 model, which is designed for rapid detection. They enhanced the model''s feature …
Defects of solar panels can easily cause electrical accidents. The YOLO v5 algorithm is improved to make up for the low detection efficiency of the traditional defect …
Recently, convolutional neural network (CNN) based automatic detection methods for PV cell defects using EL images have attracted much attention. However, existing …
LBIC can potentially yield comprehensive diagnoses for structural and process-based solar cell defects. Unlike EBIC, this method flows photogenerated current in solar cells …
Abstract: A solar cell defect detection method with an improved YOLO v5 algorithm is proposed for the characteristics of the complex solar cell image background, …
Moreover, to generalize the PV cell defect detection methods, this paper divide them into (i) imaging-based techniques, (ii) rapid visual inspection methods, and (iii) I–V curve …
A single solar cell produces approximately 2 watts of power, and by connecting multiple cells in an array, a solar module is formed which generates hundreds of kilowatts of power.
LBIC can potentially yield comprehensive diagnoses for structural and process-based solar cell defects. Unlike EBIC, this method flows photogenerated current in solar cells …
This paper focuses exclusively on deep learning methods for defect recognition. CNN modules, ... El Yanboiy et al. 7 implemented real-time solar cell defect detection using …
Defect identification is very complicated due to complex background interference. Therefore, we propose a deep learning model that combines the C2f module of the YOLOv8 backbone with …
Studies of detecting the defects of solar cells using a deep learning approach. …
A solar cell defect detection method with an improved YOLO v5 algorithm is proposed for the characteristics of the complex solar cell image background, variable defect morphology, and …
The ablation study demonstrates that our CCT and PSA modules enhance the detection accuracy of YOLOv8 in photovoltaic cell anomaly detection tasks.
Similar and indeterminate defect detection of solar cell surface with heterogeneous texture and complex background is a challenge of solar cell manufacturing. …
Moreover, to generalize the PV cell defect detection methods, this paper divide them into (i) imaging-based techniques, (ii) rapid visual inspection methods, and (iii) I–V curve …
Traditional solar cell defect detection methods usually use Fourier image reconstruction, filtering, clustering, and so on. The defect detection task of solar cells is …
In the defective photovoltaic module detection accuracy, our improved VarifocalNet method has the highest detection accuracy, followed by the improved Faster R-CNN method and the original...
Studies of detecting the defects of solar cells using a deep learning approach. …
Abstract: Traditional vision methods for solar cell defect detection have problems such as low accuracy and few types of detection, so this paper proposes an optimized YOLOv5 model for …
In the defective photovoltaic module detection accuracy, our improved VarifocalNet method has the highest detection accuracy, followed by the improved Faster R …