Solar Cell Micro-Crack Detection Using Localised Texture Analysis

Abstract

A novel method to classify micro-cracks in Photoluminescence (PL) images of polycrystalline solar cells is proposed. Micro-cracks in PL images are difficult distinguish as they're easily confused with noises that are present which may share the same size and shape features. Instead of relying on shape analysis to classify micro-cracks, the proposed method takes advantage of the patterns that are present at the end points of micro-cracks. Textural features are extracted via grey level co-occurrence matrix at the end points and then used as feature vectors in a SVM classifier. The proposed method is compared against existing shape analysis method and a preliminary experimental result has shown a significant improvement in sensitivity, specificity and accuracy.  Index Terms-solar cell, photoluminescence, micro-crack Teow Wee Teo graduated from University of Bradford, UK with a first-class honours B.Sc. degree from the Department of Computing and Mathematics in 2007 before joining TTVision Technologies Sdn. Bhd. as a R&D Engineer. His research focuses on machine vision applications in the photovoltaic industry with particular interests on machine learning, infrared imaging and luminescence technologies. As present, he is also a Ph.D. candidate under the supervision of Professor Dr Mohd Zaid Bin Abdullah at Universiti Sains Malaysia. Mohd Zaid graduated from Universiti Sains Malaysia (USM) with a B. App. Sc. degree in Electronic in 1986 before joining Hitachi Semiconductor (Malaysia) as a Test Engineer. In 1989 he commenced an M.Sc. in

Fundamental study related to the development of modular solar panel for improved durability and repairability

“…They showed (see Figure 18) that a single hail can devastate the PV site and render it useless for energy production. Furthermore, the field engineers elaborated that it is possible to have PV panel that suffer no visual cracks owing to hail impact, but they might have micro-cracks that can lower the efficiency of the PV panel [27][28][29][30]. These micro-cracks only become visible in an EL image as shown in Figure 19.…”

“…2 with 50% system damage FIGURE 17 Payback period for comparison scenario no. 2 with 90% system damage have PV panel that suffer no visual cracks owing to hail impact, but they might have micro-cracks that can lower the efficiency of the PV panel [27][28][29][30]. These micro-cracks only become visible in an EL image as shown in Figure 19.…”

Saliency-based fabric defect detection network with feature pyramid learning and refinement

“…In the textile industry, the quality and price of all textile products are almost dependent on the efficiency and effectiveness of the automatic defect detection. In addition, the detection of surface defects is particularly important in other industries, such as the solar cell micro-crack detection [1] and electronic wafer surface detection [2]. However, traditional manual fabric defect detection is usually accompanied by inattention, fatigue, time-consuming and other problems, which may lead to low accuracy and slow speed.…”

Surface defect sample generation method based on GAN

“…Defect detection methods are important to guarantee the product quality 1,2 . In recent years, deep learning has been continuously applied in surface defect detection.…”