Search Results (7)

To address the challenges posed by complex backgrounds and the low occurrence in photovoltaic cell images captured by industrial sensors, we propose a novel defect detection method: MRA-YOLOv8. First, a multi-branch coordinate attention network (MBCANet) is introduced into the backbone. The coordinate attention network (CANet) is incorporated to mitigate the noise impact of background information on the detection task, and multiple branches are employed to enhance the model’s feature extraction capability. Second, we integrate a multi-path feature extraction module, ResBlock, into the neck. This module provides finer-grained multi-scale features, improving feature extraction from complex backgrounds and enhancing the model’s robustness. Finally, we implement alpha-minimum point distance-based IoU (AMPDIoU) to the head. This loss function enhances the accuracy and robustness of small object detection by integrating minimum point distance-based IoU (MPDIoU) and Alpha-IoU methods. The results demonstrate that MRA-YOLOv8 outperforms other mainstream methods in detection performance. On the photovoltaic electroluminescence anomaly detection (PVEL-AD) dataset, the proposed method achieves a mAP₅₀ of 91.7%, representing an improvement of 3.1% over YOLOv8 and 16.1% over detection transformer (DETR). On the SPDI dataset, our method achieves a mAP₅₀ of 69.3%, showing a 2.1% improvement over YOLOv8 and a 6.6% improvement over DETR. The proposed MRA-YOLOv8 also exhibits great deployment potential. It can be effectively integrated with drone-based inspection systems, allowing for efficient and accurate PV plant inspections. Moreover, to tackle the issue of data imbalance, we propose generating synthetic defect data via generative adversarial networks (GANs), which can supplement the limited defect samples and improve the model’s generalization ability. Full article

Considering the defect detection issues in electroluminescence (EL) of photovoltaic (PV) cell systems, lots of factors result in performance degradation, including defect diversity, data imbalance, scale difference, etc. Focal-EIoU loss, an effective defect detection solution for EL, is proposed based on the improved YOLOv5. Firstly, by analyzing the detection background and scale characteristics of EL defects, a binary classification is carried out in the system. Subsequently, a cascade detection network based on YOLOv5 is designed to further extract features from the binary-classified defects. The defect localization and classification are achieved in this way. To address the problem of imbalanced defect samples, a loss function is designed based on EIoU and Focal-F1 Loss. Experimental results are illustrated to show the effectiveness. Compared with the existing CNN-based deep learning approaches, the proposed focal loss calculation-based method can effectively improve the performance of handling sample imbalance. Moreover, in the detection of 12 types of defects, the Yolov5 algorithms can always obtain higher MAP (mean average precision) even with different parameter levels (Yolov5m: 0.791 vs. 0.857, Yolov5l: 0.798 vs. 0.862, Yolov5x: 0.802 vs. 0.867, Yolov5s: 0.793 vs. 0.865). Full article

Photovoltaic (PV) cell defect detection has become a prominent problem in the development of the PV industry; however, the entire industry lacks effective technical means. In this paper, we propose a deep-learning-based defect detection method for photovoltaic cells, which addresses two technical challenges: (1) to propose a method for data enhancement and category weight assignment, which effectively mitigates the impact of the problem of scant data and data imbalance on model performance; (2) to propose a feature fusion method based on ResNet152–Xception. A coordinate attention (CA) mechanism is incorporated into the feature map to enhance the feature extraction capability of the existing model. The proposed model was conducted on two global publicly available PV-defective electroluminescence (EL) image datasets, and using CNN, Vgg16, MobileNetV2, InceptionV3, DenseNet121, ResNet152, Xception and InceptionResNetV2 as comparative benchmarks, it was evaluated that several metrics were significantly improved. In addition, the accuracy reached 96.17% in the binary classification task of identifying the presence or absence of defects and 92.13% in the multiclassification task of identifying different defect types. The numerical experimental results show that the proposed deep-learning-based defect detection method for PV cells can automatically perform efficient and accurate defect detection using EL images. Full article

We fabricated indium gallium nitride (InGaN) red light-emitting diodes (LEDs) with a peak emission wavelength of 649 nm and investigated their electroluminescence (EL) properties. An additional separated peak in the EL spectrum of the red LEDs at 20 mA was observed at 465 nm. This additional peak also exhibits a blue-shift with increasing currents as does the main emission peak. Using high-resolution microscopy, we observed many point-like emission spots in the EL emission images at the currents below 1 mA. However, these emission spots cannot be identified at currents above 5 mA because the red emission from quantum wells (QWs) is much stronger than that emitted by these spots. Finally, we demonstrate that these emission spots are related to the defects generated in red QWs. The measured In content was lower at the vicinity of the defects, which was regarded as the reason for separated short-wavelength emission in red InGaN LEDs. Full article

This article describes the event detection system of the NEXT-White detector, a 5 kg high pressure xenon TPC with electroluminescent amplification, located in the Laboratorio Subterráneo de Canfranc (LSC), Spain. The detector is based on a plane of photomultipliers (PMTs) for energy measurements and a silicon photomultiplier (SiPM) tracking plane for offline topological event filtering. The event detection system, based on the SRS-ATCA data acquisition system developed in the framework of the CERN RD51 collaboration, has been designed to detect multiple events based on online PMT signal energy measurements and a coincidence-detection algorithm. Implemented on FPGA, the system has been successfully running and evolving during NEXT-White operation. The event detection system brings some relevant and new functionalities in the field. A distributed double event processor has been implemented to detect simultaneously two different types of events thus allowing simultaneous calibration and physics runs. This special feature provides constant monitoring of the detector conditions, being especially relevant to the lifetime and geometrical map computations which are needed to correct high-energy physics events. Other features, like primary scintillation event rejection, or a double buffer associated with the type of event being searched, help reduce the unnecessary data throughput thus minimizing dead time and improving trigger efficiency. Full article

For the development and application of GaN-based nanowire structures, it is crucial to understand their fundamental properties. In this work, we provide the nano-scale correlation of the morphological, electrical, and optical properties of GaN/AlGaN nanowire light emitting diodes (LEDs), observed using a combination of spatially and spectrally resolved cathodoluminescence spectroscopy and imaging, electron beam-induced current microscopy, the nano-probe technique, and scanning electron microscopy. To complement the results, the photo- and electro-luminescence were also studied. The interpretation of the experimental data was supported by the results of numerical simulations of the electronic band structure. We characterized two types of nanowire LEDs grown in one process, which exhibit top facets of different shapes and, as we proved, have opposite growth polarities. We show that switching the polarity of nanowires (NWs) from the N- to Ga-face has a significant impact on their optical and electrical properties. In particular, cathodoluminescence studies revealed quantum wells emissions at about 3.5 eV, which were much brighter in Ga-polar NWs than in N-polar NWs. Moreover, the electron beam-induced current mapping proved that the p–n junctions were not active in N-polar NWs. Our results clearly indicate that intentional polarity inversion between the n- and p-type parts of NWs is a potential path towards the development of efficient nanoLED NW structures. Full article

Electroluminescence (EL) is a powerful tool for the qualitative mapping of the electronic properties of solar modules, where electronic and electrical defects are easily detected. However, a direct quantitative prediction of electrical module performance purely based on electroluminescence images has yet to be accomplished. Our novel approach, called “EL power prediction of modules” (ELMO) as presented here, used just two electroluminescence images to predict the electrical loss of mechanically damaged modules when compared to their original (data sheet) power. First, using this method, two EL images taken at different excitation currents were converted into locally resolved (relative) series resistance images. From the known, total applied voltage to the module, we were then able to calculate absolute series resistance values and the real distribution of voltages and currents. Then, we reconstructed the complete current/voltage curve of the damaged module. We experimentally validated and confirmed the simulation model via the characterization of a commercially available photovoltaic module containing 60 multicrystalline silicon cells, which were mechanically damaged by hail. Deviation between the directly measured and predicted current/voltage curve was less than 4.3% at the maximum power point. For multiple modules of the same type, the level of error dropped below 1% by calibrating the simulation. We approximated the ideality factor from a module with a known current/voltage curve and then expand the application to modules of the same type. In addition to yielding series resistance mapping, our new ELMO method was also capable of yielding parallel resistance mapping. We analyzed the electrical properties of a commercially available module, containing 72 monocrystalline high-efficiency back contact solar cells, which suffered from potential induced degradation. For this module, we predicted electrical performance with an accuracy of better than 1% at the maximum power point. Full article