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,
Photovoltaic cells play a critical role in solar power generation, with defects in these cells significantly impacting energy conversion efficiency. To address challenges in detecting defects of varying scales in solar cells, an enhanced YOLOv5 algorithm is proposed. This algorithm integrates the Convolutional Block Attention Module (CBAM) to improve feature extraction,
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, variable defect morphology, and large-scale differences. First, the deformable convolution is incorporated into the CSP module to achieve an adaptive learning scale and perceptual
In view of the surface defect characteristics in the manufacturing process of solar cells, the common surface defects are divided into three categories, which include difficult-detecting defects (mismatch), general defects (bubble, glass-crack and cell-crack) and easy-detecting defects (glass-upside-down).
This study presents an advanced defect detection approach for solar cells using the YOLOv10 deep learning model. Leveraging a comprehensive dataset of 10,500 solar cell
Traditionally, defect detection in EL images of PV cells has relied on labor-intensive manual inspection, which are not only time-consuming but also prone to human errors and subjectivity (Bartler et al., 2018).Due to the rise of advanced imaging techniques and considerable progress in machine vision and artificial intelligence, innovative solutions have
To address issues of low detection accuracy and high false-positive and false-negative rates in solar cell defect detection, this paper proposes an optimized solar cell electroluminescent (EL) defect detection model based on the YOLOv8 deep learning framework.
In recent years, the solar cells defect detection method based on deep learning has the char-acteristics of high precision, fast speed, and strong robustness, and has achieved certain appli-cation effects.
In this paper, addressing the challenges of low accuracy in detecting small surface defects on solar cells and limited defect categories, a lightweight solar cell detection
Adaptive solar cell defect detection: Since the solar cell has the same area in the series of EL images and the position of defects is unchanged, only a standard C k (with high j k preferably) is selected to perform adaptive defect detection. Each P x,y of this standard C k is firstly detected using the initialized n and p, and P x,y is renamed as D x,y when I x,y satisfies
To address challenges in detecting defects of varying scales in solar cells, an enhanced YOLOv5 algorithm is proposed. This algorithm integrates the Convolutional Block Attention Module (CBAM) to improve feature extraction, incorporates the Bi-directional Feature Pyramid Network (BiFPN) for refined feature fusion, and introduces the FasterNet
We published an automatic computer vision pipeline of identifying solar cell defects. Tools can handle field images with a complex background (e.g., vegetation). Tools can be applied to other kinds of defects with transfer learning. We compared the performance of classification and object detection neural networks.
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 more accurate and comprehensive identification of defects in solar cells. The model firstly integrates five data enhancement methods, namely Mosaic, Mixup, hsv transform, scale transform and flip, to
To address challenges in detecting defects of varying scales in solar cells, an enhanced YOLOv5 algorithm is proposed. This algorithm integrates the Convolutional Block Attention Module
The widespread adoption of solar energy as a sustainable power source hinges on the efficiency and reliability of photovoltaic (PV) cells. These cells, responsible for the conversion of sunlight into electricity, are subject to various internal and external factors that can compromise their performance [] fects within PV cells, ranging from micro-cracks to material
We published an automatic computer vision pipeline of identifying solar cell defects. Tools can handle field images with a complex background (e.g., vegetation). Tools
Tsai D-M et al (2015) Defect detection in multi-crystal solar cells using clustering with uniformity measures. Adv Eng Inform 29(3):419–430. Google Scholar Bartler A et al (2018) Automated detection of solar cell defects with deep learning. In: 2018 26th European signal processing conference (EUSIPCO). IEEE
In this work, we proposed a compact classification framework based on hybrid data augmentation and deep learning models for detection of the defective solar cells.
Solar cell defects are a major reason for PV system efficiency degradation, which causes disturbance or interruption of the generated electric current. In this study, a novel system for
CHEN Yafang,LIAO Fei,HUANY Xinyu,et al.Multi-scale YOLOv5 for solar cell defect detection[J].Optics and Precision Engineering,2023,31(12):1804-1815.
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 more accurate and comprehensive identification of defects in solar cells.
In view of the surface defect characteristics in the manufacturing process of solar cells, the common surface defects are divided into three categories, which include
In recent years, the solar cells defect detection method based on deep learning has the char-acteristics of high precision, fast speed, and strong robustness, and has achieved
Solar cell defects exhibit significant variations and multiple types, with some defect data being difficult to acquire or having small scales, posing challenges in terms of small sample and small target in defect detection for solar cells. In order to address this issue, this paper proposes a multi-step approach for detecting the complex defects of solar cells. First,
This study presents an advanced defect detection approach for solar cells using the YOLOv10 deep learning model. Leveraging a comprehensive dataset of 10,500 solar cell images annotated with 12 distinct defect types, our model integrates Compact Inverted Blocks (CIBs) and Partial Self-Attention (PSA) modules to enhance feature extraction and
In this paper, addressing the challenges of low accuracy in detecting small surface defects on solar cells and limited defect categories, a lightweight solar cell detection model named YOLOPL is proposed. The contributions of this study are as follows: The introduction of YOLOPL, an optimized and improved solar cell defect recognition model
Stoicescu, " Automated Detection of Solar Cell Defects with Deep Learning," in 2018 26th European Signal Processing Conference (EUSIPCO), 2018, pp. 2035–2039.
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 more accurate
Electroluminescence (EL) imaging is a fast, non-destructive and established method for detecting defects in solar modules (Jahn et al., 2018, Bedrich et al., 2018, Fuyuki et al., 2005, Abdelhamid et al., 2014).
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, variable defect morphology, and large-scale differences.
We published an automatic computer vision pipeline of identifying solar cell defects. Tools can handle field images with a complex background (e.g., vegetation). Tools can be applied to other kinds of defects with transfer learning. We compared the performance of classification and object detection neural networks.
After the UNet model predicted module masks, we applied an algorithm combining Hough line detection (OpenCV, 2021a, Duda and Hart, 1972) and corner detection (OpenCV, 2021b, Shi and Tomasi, 1994) from OpenCV (Bradski, 2000) to detect the four corners of the mask. The detected corners are shown in Fig. 2 (b).
Our dataset is composed of 19,228 EL images of interdigitated back contact (IBC) solar modules (16 × 8 cells). Each raw image has a size of 640 × 512 pixels. Our perspective transform tool finds the target module and transforms it into a module image with a size of 600 × 300, as shown in 3.
Defect identification is achieved with a machine learning model (Random Forest, ResNet models and YOLO) trained on 762 manually-labeled EL images of PV modules.
Our team brings unparalleled expertise in the energy storage industry, helping you stay at the forefront of innovation. We ensure your energy solutions align with the latest market developments and advanced technologies.
Gain access to up-to-date information about solar photovoltaic and energy storage markets. Our ongoing analysis allows you to make strategic decisions, fostering growth and long-term success in the renewable energy sector.
We specialize in creating tailored energy storage solutions that are precisely designed for your unique requirements, enhancing the efficiency and performance of solar energy storage and consumption.
Our extensive global network of partners and industry experts enables seamless integration and support for solar photovoltaic and energy storage systems worldwide, facilitating efficient operations across regions.
We are dedicated to providing premium energy storage solutions tailored to your needs.
From start to finish, we ensure that our products deliver unmatched performance and reliability for every customer.