Photovoltaic cell defect classification using convolutional neural network and support vector machine

Ahmad, Ashfaq; Jin, Yi; Zhu, Changan; Javed, Iqra; Maqsood, Asim; Akram, Muhammad Waqar

doi:10.1049/iet-rpg.2019.1342

Cited by 37 publications

(11 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, a recent study 24 developed a method for automatically detecting PV module defects in electroluminescence images, using a light convolutional neural network architecture to identify defects in EL images, achieving 93.02% accuracy on the solar cell dataset. Additionally, the classi cations of solar cell defects are based on two machine learning approaches proposed by 25 utilizing features extraction-based support vector machines (SVMs) and convolutional neural networks (CNNs). Using suitable hyperparameters, algorithm optimizers, and loss functions, they have achieved 91.58% accuracy in cell detection classi cation.…”

Section: Known Asmentioning

confidence: 99%

DSMP-CNN: Dual Spin Max Pooling Convolutional Neural Network for Solar Cell Crack Detection

Hassan

Dhimish

2023

Preprint

View full text Add to dashboard Cite

This paper presents a solar cell crack detection system for use in photovoltaic (PV) assembly units. The system utilizes four different Convolutional Neural Network (CNN) architectures with varying validation accuracy to detect cracks, microcracks, Potential Induced Degradations (PIDs), and shaded areas. The system examines the electroluminescence (EL) image of a solar cell and determines its acceptance or rejection status based on the presence and size of the crack. The proposed system was tested on various solar cells and achieved a high degree of accuracy, with an acceptance rate of up to 99.5%. The system was validated with thermal testing using real-world cases, such as shaded areas and microcracks, which were accurately predicted by the system. The results show that the proposed system is a valuable tool for evaluating the condition of PV cells and can lead to improved efficiency. The study also shows that the proposed CNN model outperforms previous studies and can have significant implications for the PV industry by reducing the number of defective cells and improving the overall efficiency of PV assembly units.

show abstract

Section: Known Asmentioning

confidence: 99%

DSMP-CNN: Dual Spin Max Pooling Convolutional Neural Network for Solar Cell Crack Detection

Hassan

Dhimish

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Ahmad et al [8] develop a CNN-inspired architecture for fault detection with EL extract samples of the PV cell surface. The authors report a respectable accuracy of 91.58%.…”

Section: Literature Reviewmentioning

confidence: 99%

PV-CrackNet Architecture for Filter Induced Augmentation and Micro-Cracks Detection within a Photovoltaic Manufacturing Facility

2022

View full text Add to dashboard Cite

Photovoltaic cell manufacturing is a rigorous process involving many stages where the cell surface is exposed to external pressure and temperature differentials. This provides fertile ground for micro-cracks to develop on the cell surface. At present, domain experts carry out a manual inspection of the cell surface to judge if any micro-cracks are present. This research looks to overcome the issue of cell data scarcity through the proposed filter-induced augmentations, thus providing developers with an effective, cost-free mechanism for generating representative data samples. Due to the abstract nature of the cell surfaces, the proposed augmentation strategy is effective in generating representative samples for better generalization. Furthermore, a custom architecture is developed that is computationally lightweight compared to state-of-the-art architectures, containing only 7.01 million learnable parameters while achieving an F1-score of 97%.

show abstract

“…[21][22][23][24][25][26][27][28][29][30][31][32] In terms of pure defect classification without segmentation determining if there is a defect, e.g., a microcrack or a finger interruption, many CNN approaches using EL and IR images of cells and modules are proposed. [33][34][35][36][37][38][39][40][41][42][43][44] To address the problem of a limited amount of data, a method based on generative adversarial networks (GANs) is demonstrated, which enables improvement of prediction results through artificially created EL images. [44] Both segmentation and classification approaches vary strongly in terms of the CNN architecture, dataset, data processing, and defect sought, so the quality of the predictions can only be compared to a limited extent.…”

Section: Related Workmentioning

confidence: 99%

Learning an Empirical Digital Twin from Measurement Images for a Comprehensive Quality Inspection of Solar Cells

Kunze

Rein

Hemsendorf³

et al. 2021

Solar RRL

View full text Add to dashboard Cite

Measurement images of solar cells contain information about their material‐ and process‐related quality beyond current–voltage characteristics. This information is currently only partially used because most algorithms look for human‐defined image features or defects. Herein, a purely data‐driven method is proposed to derive the essential image information in terms of the electrical quality within a comprehensive and meaningful representation. This representation is denoted as the empirical digital twin of the cell. Using it, solar cells can be classified according to their defects visible in the measurement images. For this purpose, a human‐in‐the‐loop approach to efficiently develop a classification scheme is presented. Therefore, a convolutional neural network combining various measurement data of a sample by correlating them with quality parameters is designed. The digital twin is an intermediate representation of the network capturing the quality‐relevant defect signatures from the images. Human experts can analyze this representation space to identify defect clusters that relate to different process errors, such as finger interruptions and shunts. How the representations are usable to derive sorting criteria for quality inspection is shown. Finally, how the empirical digital twin and the sorting scheme can be used for segmenting the defects without additional label effort is demonstrated.

show abstract

Photovoltaic cell defect classification using convolutional neural network and support vector machine

Cited by 37 publications

References 35 publications

DSMP-CNN: Dual Spin Max Pooling Convolutional Neural Network for Solar Cell Crack Detection

DSMP-CNN: Dual Spin Max Pooling Convolutional Neural Network for Solar Cell Crack Detection

PV-CrackNet Architecture for Filter Induced Augmentation and Micro-Cracks Detection within a Photovoltaic Manufacturing Facility

Learning an Empirical Digital Twin from Measurement Images for a Comprehensive Quality Inspection of Solar Cells

Contact Info

Product

Resources

About