Research of Solar Cell Surface Defect Detection System Based on Machine Vision

Feng, Mei Lin; Zhou, Xian; Yu, Jianguo

doi:10.4028/www.scientific.net/amr.718-720.532

Cited by 6 publications

(3 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wang Y et al [7] proposed a weighted fusion filtering algorithm that combines Gaussian filtering and mean filtering, which can both protect the local edge features of the image and reduce the image noise well to meet the requirements of high-definition images for subsequent image processing.Akram et al [8] Proposed image filtering, color quantization and edge detection solar panel infrared image processing scheme, to achieve the infrared image of serious and minor defects in the region of edge localization.…”

Section: Image Processingmentioning

confidence: 99%

Research Progress on Deep Learning Based Defect Detection Technology for Solar Panels

Wang,

Guo,

et al. 2024

EAI Endorsed Trans Energy Web

View full text Add to dashboard Cite

INTRODUCTION: Based on machine vision technology to carry out photovoltaic panel defect detection technology research to solve the photovoltaic panel production line automation online defect detection and localization problems. OBJECTIVES: The goal is to improve the accuracy of defect detection on PV cell production lines, increase the speed of defect detection to meet real-time monitoring needs, and improve production efficiency. METHODS: In this paper, three detection methods such as image processing based detection, traditional machine learning based detection and deep learning algorithm based detection are discussed and compared and analyzed respectively. Finally, it is concluded that deep learning based detection methods are more effective in comparison. Then, further analysis and simulation experiments are done by several deep learning based detection algorithms. RESULTS: The experimental results show that the YOLOv8 algorithm has the highest precision rate and maintains good results in terms of recall and mAP values. The detection speed is all less than other algorithms, 10.6ms. CONCLUSION: The inspection model based on yolov8 algorithm has the highest comprehensive performance and is the most suitable algorithmic model for detecting defects in solar panels in production lines.

show abstract

Section: Image Processingmentioning

confidence: 99%

Research Progress on Deep Learning Based Defect Detection Technology for Solar Panels

Wang,

Guo,

et al. 2024

EAI Endorsed Trans Energy Web

View full text Add to dashboard Cite

show abstract

“…However, segmentation errors may still occur with keyboards exhibiting significant rotation [8] . Addressing the difficulty of detecting bridging, solder skipping, and insufficient solder defects in soldering, Liang designed a Bayesian Cbayes-LeNet neural network for defect recognition in fused high-quality solder joint images, improving detection accuracy [9] . For defect detection in PCB solder points, Zhao proposed a multi-IOP Publishing doi:10.1088/1742-6596/2787/1/012038 2 feature SVM multi-classification algorithm, demonstrating significant advantages in detection accuracy and performance [10] .…”

Section: Introductionmentioning

confidence: 99%

Keycap character detection model based on target classification

Xiong,

Zhu,

Wang

2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The production process of keycaps may result in surface character defects. The existing keycap character defect detection technology has low efficiency and accuracy, hindering the automation of keycap manufacturing. Addressing the challenge of extracting the entire keyboard from illuminated regions, this paper proposes a method using image feature points for template matching to extract the region of interest. Subsequently, leveraging prior knowledge, the paper addresses character segmentation and extraction on the keyboard. For character detection, the paper preprocesses images and classifies them by using an S-VGG network, yielding corresponding labels.

show abstract

“…Wujie Zhang proposed a machine vision method combined with Hoof transform to detect cracks on solar cell [2]. Meilin Feng developed a detection system on the bubble, scratch, and other defect detection [4]. However, because of the complex texture on polysilicon solar cell, these monocrystalline silicon inspection methods are not suitable for polysilicon solar cell inspection, as they don't cover all kinds of the defects shown in Fig.…”

Section: Introductionmentioning

confidence: 99%

Polycrystalline Silicon Wafer Surface Color Defect Inspection Based on Machine Vision

Wang

Miao

et al. 2014

AMM

View full text Add to dashboard Cite

As non-uniform color and complex texture exist on the polycrystalline silicon solar cell, manual surface inspection adopted by most domestic factories suffers from low efficiency and poor repetitive detection ability. To overcome the shortcomings of manual inspection, based on machine vision and SVM, an automatic silicon wafer surface defect detection and classification system has been developed in this paper: through feature extraction of color images and defect areas, a series of wafer classifiers are trained and used to separate the defective products from qualified ones. Experiments on samples and actual application in the enterprise show that the system has achieved high accuracy and fast run-time performance, indicating that machine vision is an effective and promising method for polycrystalline silicon solar cell inspection.

show abstract

Research of Solar Cell Surface Defect Detection System Based on Machine Vision

Cited by 6 publications

References 1 publication

Research Progress on Deep Learning Based Defect Detection Technology for Solar Panels

Research Progress on Deep Learning Based Defect Detection Technology for Solar Panels

Keycap character detection model based on target classification

Polycrystalline Silicon Wafer Surface Color Defect Inspection Based on Machine Vision

Contact Info

Product

Resources

About