Micro-crack detection of multicrystalline solar cells featuring shape analysis and support vector machines

Anwar, Said Amirul; Abdullah, Mohd Zaid

doi:10.1109/iccsce.2012.6487131

Cited by 21 publications

(13 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To overcome these limitations, this study proposes a machine learning (ML) based approach to extract the defect parameters from lifetime curves. ML-based methods are already used at the PV system level, for example for fault detection 23,24 or to identify cracks in modules using luminescence imaging techniques [25][26][27][28] . ML has also been used in non-Si applications to find relevant material parameters for fabrication of CIGS solar cells 29 , multijunction solar cells 30 , organic solar cells 31 , or perovskite solar cells 32 .…”

Section: Introductionmentioning

confidence: 99%

Extracting bulk defect parameters in silicon wafers using machine learning models

et al. 2020

View full text Add to dashboard Cite

The performance of high-efficiency silicon solar cells is limited by the presence of bulk defects. Identification of these defects has the potential to improve cell performance and reliability. The impact of bulk defects on minority carrier lifetime is commonly measured using temperature- and injection-dependent lifetime spectroscopy and the defect parameters, such as its energy level and capture cross-section ratio, are usually extracted by fitting the Shockley-Read-Hall equation. We propose an alternative extraction approach by using machine learning trained on more than a million simulated lifetime curves, achieving coefficient of determinations between the true and predicted values of the defect parameters above 99%. In particular, random forest regressors, show that defect energy levels can be predicted with a high precision of ±0.02 eV, 87% of the time. The traditional approach of fitting to the Shockley-Read-Hall equation usually yields two sets of defect parameters, one in each half bandgap. The machine learning model is trained to predict the half bandgap location of the energy level, and successfully overcome the traditional approach’s limitation. The proposed approach is validated using experimental measurements, where the machine learning predicts defect energy level and capture cross-section ratio within the uncertainty range of the traditional fitting method. The successful application of machine learning in the context of bulk defect parameter extraction paves the way to more complex data-driven physical models which have the potential to overcome the limitation of traditional approaches and can be applied to other materials such as perovskite and thin film.

show abstract

Section: Introductionmentioning

confidence: 99%

Extracting bulk defect parameters in silicon wafers using machine learning models

et al. 2020

View full text Add to dashboard Cite

show abstract

“…To evaluate the classification capability of the proposed method against our existing shape analysis method [11], a dataset as shown in Table I was used. The polycrystalline solar cell samples in the dataset consist of randomly selected pieces directly off a production line to mirror an actual production run.…”

Section: Resultsmentioning

confidence: 99%

Solar Cell Micro-Crack Detection Using Localised Texture Analysis

Teo¹,

Abdullah²

2018

JOIG

Self Cite

View full text Add to dashboard Cite

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

show abstract

“…Most work on locating and identifying structures of interest revolves around cracks in crystalline silicon solar modules. Tsai, Chang, and Chao [8], Anwar and Abdullah [9,10] used a pipeline consisting of an anisotropic diffusion and certain shape analysis algorithms to localise cracks in EL images.…”

Section: A Image Analysis In Pvmentioning

confidence: 99%

Encoder-decoder semantic segmentation models for electroluminescence images of thin-film photovoltaic modules

Sovetkin¹,

Achterberg²,

Weber³

et al. 2020

Preprint

View full text Add to dashboard Cite

We consider a series of image segmentation methods based on the deep neural networks in order to perform semantic segmentation of electroluminescence (EL) images of thin-film modules. We utilize the encoder-decoder deep neural network architecture. The framework is general such that it can easily be extended to other types of images (e.g. thermography) or solar cell technologies (e.g. crystalline silicon modules). The networks are trained and tested on a sample of images from a database with 6000 EL images of Copper Indium Gallium Diselenide (CIGS) thin film modules. We selected two types of features to extract, shunts and so called "droplets". The latter feature is often observed in the set of images. Several models are tested using various combinations of encoder-decoder layers, and a procedure is proposed to select the best model. We show exemplary results with the best selected model. Furthermore, we applied the best model to the full set of 6000 images and demonstrate that the automated segmentation of EL images can reveal many subtle features which cannot be inferred from studying a small sample of images. We believe these features can contribute to process optimization and quality control.

show abstract

Micro-crack detection of multicrystalline solar cells featuring shape analysis and support vector machines

Cited by 21 publications

References 14 publications

Extracting bulk defect parameters in silicon wafers using machine learning models

Extracting bulk defect parameters in silicon wafers using machine learning models

Solar Cell Micro-Crack Detection Using Localised Texture Analysis

Encoder-decoder semantic segmentation models for electroluminescence images of thin-film photovoltaic modules

Contact Info

Product

Resources

About