Automatic Micro-Crack Detection of Polycrystalline Solar Cells in Industrial Scene

Fan, Tao; Sun, Tao; Xie, Xiaorong; Hu, Liu; Na, Zhixiong

doi:10.1109/access.2022.3145980

Cited by 9 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, the average accuracy reached 99.23% by using transfer learning method to train the model. Fan et al [ 5 ], aiming at the micro-crack defect target of polycrystalline silicon solar cells, proposed a detection method that enhanced the micro-crack defect feature through image preprocessing and used ResNet50 network as the backbone network to extract the defect feature. Through testing the industrial micro-crack defect dataset, it was found that the detection accuracy rate of this method could reach 98.29%.…”

Section: Introductionmentioning

confidence: 99%

Research on multi-defects classification detection method for solar cells based on deep learning

Li,

Zhang,

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Solar cells are playing a significant role in aerospace equipment. 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). Corresponding to different types of defects, the deep learning model with different optimization methods and a classification detection method based on multi-models fusion are proposed in the paper. In the proposed model, in order to solve the mismatch problem between the default anchor boxes size of YOLOv5s model and the extreme scale of the battery mismatch defect label boxes, the K-means algorithm was adopted to re-cluster the dedicated anchor boxes for the mismatch defect label boxes. In order to improve the comprehensive detection accuracy of YOLOv5s model for the general defects, the YOLOv5s model was also improved by the methods of image preprocessing, anchor box improving and detection head replacing. In order to ensure the recognition accuracy and improve the detection speed for easy-detecting defects, the lightweight classification network MobileNetV2 was also used to classify the cells with glass-upside-down defects. The experimental results show that the proposed optimization model and classification detection method can significantly improve the defect detection precision. Respectively, the detection precision for mismatch, bubble, glass-crack and cell-crack defects are up to 95.64%, 91.8%, 93.1% and 98.0%. By using lightweight model to train the glass-upside-down defect dataset, the average classification accuracy reaches 100% and the detection speed reaches 13.29 frames per second. The comparison experiments show that the proposed model has a great improvement in detection accuracy compared with the original model, and the defect detection speed of lightweight classification network is improved more obviously, which confirms the effectiveness of the proposed optimization model and the multi-defect classification detection method for solar cells defect detection.

show abstract

Section: Introductionmentioning

confidence: 99%

Research on multi-defects classification detection method for solar cells based on deep learning

Li,

Zhang,

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Yu et al [ 12 ] proposed a different crack detection method based on image by using deep convolutional neural network and Enhanced Chicken Swarm Algorithm (ECSA), and conducted comparative experiments with other crack detection methods on a variety of concrete crack samples. Fan et al [ 13 ] proposed a microcrack detection method based on ResNet to detect microcracks on polycrystalline solar cells, which effectively improved the accuracy of detecting solar-cell defects. In 2021, on the basis of the U-Net [ 14 ] model, Li et al [ 15 ] used asymmetric convolution to enhance the feature representation and feature extraction capability of the convolution layer, and effectively improved the problem of insufficient feature utilization of the U-Net model.…”

Section: Introductionmentioning

confidence: 99%

Research on Ground Object Classification Method of High Resolution Remote-Sensing Images Based on Improved DeeplabV3+

Wang

et al. 2022

Sensors

View full text Add to dashboard Cite

Ground-object classification using remote-sensing images of high resolution is widely used in land planning, ecological monitoring, and resource protection. Traditional image segmentation technology has poor effect on complex scenes in high-resolution remote-sensing images. In the field of deep learning, some deep neural networks are being applied to high-resolution remote-sensing image segmentation. The DeeplabV3+ network is a deep neural network based on encoder-decoder architecture, which is commonly used to segment images with high precision. However, the segmentation accuracy of high-resolution remote-sensing images is poor, the number of network parameters is large, and the cost of training network is high. Therefore, this paper improves the DeeplabV3+ network. Firstly, MobileNetV2 network was used as the backbone feature-extraction network, and an attention-mechanism module was added after the feature-extraction module and the ASPP module to introduce focal loss balance. Our design has the following advantages: it enhances the ability of network to extract image features; it reduces network training costs; and it achieves better semantic segmentation accuracy. Experiments on high-resolution remote-sensing image datasets show that the mIou of the proposed method on WHDLD datasets is 64.76%, 4.24% higher than traditional DeeplabV3+ network mIou, and the mIou on CCF BDCI datasets is 64.58%. This is 5.35% higher than traditional DeeplabV3+ network mIou and outperforms traditional DeeplabV3+, U-NET, PSP-NET and MACU-net networks.

show abstract

“…Tang et al [ 29 ] proposed an evolutionary algorithm which combines traditional image processing techniques, deep learning, migration learning and deep clustering; this fine-tuned model can detect new defects with high accuracy. Fan et al [ 30 ] proposed a migration learning and ResNet-based microcrack detection method, which combines feature fusion and incorporates a self-attention mechanism to aggregate low-level features and deep semantic strong features to significantly improve defect detection.…”

Section: Introductionmentioning

confidence: 99%

Deep-Learning-Based Automatic Detection of Photovoltaic Cell Defects in Electroluminescence Images

Wang

Sun

et al. 2022

Sensors

View full text Add to dashboard Cite

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.

show abstract

Automatic Micro-Crack Detection of Polycrystalline Solar Cells in Industrial Scene

Cited by 9 publications

References 28 publications

Research on multi-defects classification detection method for solar cells based on deep learning

Research on multi-defects classification detection method for solar cells based on deep learning

Research on Ground Object Classification Method of High Resolution Remote-Sensing Images Based on Improved DeeplabV3+

Deep-Learning-Based Automatic Detection of Photovoltaic Cell Defects in Electroluminescence Images

Contact Info

Product

Resources

About