Deep Learning-Based Algorithm for Multi-Type Defects Detection in Solar Cells with Aerial EL Images for Photovoltaic Plants

Tang, Wuqin; Yang, Qiang; Yan, Wenjun

doi:10.32604/cmes.2022.018313

Cited by 9 publications

(6 citation statements)

References 30 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further processing includes perspective correction and possibly image enhancement. To automatically and consistently identify faults and degradation modes in luminescence images, deep-learning methods such as convolutional neural networks (CNN) can be applied [37,92,[95][96][97][98][99][100][101]. The CNNs are trained on thousands of images of various module types, where faults have been marked previously by human experts.…”

Section: Pv Module Conditionsmentioning

confidence: 99%

See 1 more Smart Citation

Outdoor luminescence imaging of field-deployed PV modules

Kunz¹,

Schlipf²,

Fladung³

et al. 2022

Prog. Energy

View full text Add to dashboard Cite

Solar photovoltaic installations have increased exponentially over the last decade and are now at a stage where they provide humanity with the greatest opportunity to mitigate accelerating climate change. For the continued growth and success of photovoltaic energy the reliable inspection of solar power plants is an important requirement. This ensures the installations are of high quality, safe to operate, and produce the maximum possible power for the longest possible plant life. Outdoor luminescence imaging of field-deployed PV modules provides module image data with unparalleled fidelity and is therefore the gold standard for assessing the quality, defect types, and degradation state of field-deployed PV modules. Several luminescence imaging methods have been developed and some of them are already routinely used to inspect solar power plants. The preferred luminescence inspection method to be used depends on the required image resolution, the defect types that need to be identified, cost, inspection throughput, technological readiness, and other factors. Due to the rich and detailed information provided by luminescence imaging measurements and modern image analysis methods, luminescence imaging is becoming an increasingly important tool for PV module quality assurance in PV power plants. Outdoor luminescence imaging can make valuable contributions to the commissioning, operation, and assessment of solar power plants prior to a change of ownership or after severe weather events. Another increasingly important use of these technologies is the cost-effective end-of-life assessment of solar modules to enable a sustainable circular economy.

show abstract

Section: Pv Module Conditionsmentioning

confidence: 99%

“…Inspection systems based on luminescence imaging have an important role to play in performing quality checks of solar power plants due to their ability to detect defects in solar panels with unparalleled accuracy and resolution [36,37]. Figure 1 contrasts the luminescence-based technologies (i.e.…”

Section: Introductionmentioning

confidence: 99%

Outdoor luminescence imaging of field-deployed PV modules

Kunz¹,

Schlipf²,

Fladung³

et al. 2022

Prog. Energy

View full text Add to dashboard Cite

show abstract

“…Several studies have been conducted to improve the performance of solar power systems and use modern systems to benefit from the largest amount of solar energy [17][18][19][20]. The state estimation and prediction for the photovoltaic system are critical as it is very important in avoiding losses due to external influences on the system.…”

Section: Introductionmentioning

confidence: 99%

Automated Classification of Snow-Covered Solar Panel Surfaces Based on Deep Learning Approaches

Al-Dulaimi¹,

Guneser²,

Hameed³

et al. 2023

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

Recently, the demand for renewable energy has increased due to its environmental and economic needs. Solar panels are the mainstay for dealing with solar energy and converting it into another form of usable energy. Solar panels work under suitable climatic conditions that allow the light photons to access the solar cells, as any blocking of sunlight on these cells causes a halt in the panels work and restricts the carry of these photons. Thus, the panels are unable to work under these conditions. A layer of snow forms on the solar panels due to snowfall in areas with low temperatures. Therefore, it causes an insulating layer on solar panels and the inability to produce electrical energy. The detection of snow-covered solar panels is crucial, as it allows us the opportunity to remove snow using some heating techniques more efficiently and restore the photovoltaics system to proper operation. This paper presents five deep learning models, -16, -19, ESNET-18, ESNET-50, and ESNET-101, which are used for the recognition and classification of solar panel images. In this paper, two different cases were applied; the first case is performed on the original dataset without trying any kind of preprocessing, and the second case is extreme climate conditions and simulated by generating motion noise. Furthermore, the dataset was replicated using the upsampling technique in order to handle the unbalancing issue. The conducted dataset is divided into three different categories, namely; all_snow, no_snow, and partial snow. The five models are trained, validated, and tested on this dataset under the same conditions 60% training, 20% validation, and testing 20% for both cases. The accuracy of the models has been compared and verified to distinguish and classify the processed dataset. The accuracy results in the first case show that the compared models -16, -19, ESNET-18, and ESNET-50 give 0.9592, while ESNET-101 gives 0.9694. In the second case, the models outperformed their counterparts in the first case by evaluating performance, where the accuracy results reached 1.00, 0.9545, 0.9888, 1.00. and 1.00 for -16, -19, ESNET-18 and ESNET-50, respectively. Consequently, we conclude that the second case models outperformed their peers.

show abstract

“…Recently, the technology of electroluminescence (EL) imaging has been introduced to the PV industry for visualizing the failures and assessing the quality of solar cells, which has drawn considerable attention from scholars [3]. In the reported literatures, the existing methods are roughly classified into two types: labor-intensive methods and model-based methods [4].…”

Section: Introductionmentioning

confidence: 99%

An intelligent defect detection method in solar cells via IDATLGAN

Pang

2023

3rd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2023)

View full text Add to dashboard Cite

Intelligent defect detection is a key section of the PDCA comprehensive quality management in the solar cells production. deep learning-based models for its powerful capacity of extracting features has successfully applied to defect detection tasks. Nevertheless, the deep learning-based models is susceptible to these problems such as insufficient labelled data and class imbalance, which deteriorates the performance of the deep models. What's worse, the new unknown defects without labels in the target domain tend to be recognized as the unknown defects in the source domain. To solve these problems, a novel method named IDATLGAN is proposed. Experimental results show that the proposed model outperforms the DCNN model in feature extraction ability and fulfil the transfer tasks even when faced with new unknown defects without labels.

show abstract

Deep Learning-Based Algorithm for Multi-Type Defects Detection in Solar Cells with Aerial EL Images for Photovoltaic Plants

Cited by 9 publications

References 30 publications

Outdoor luminescence imaging of field-deployed PV modules

Outdoor luminescence imaging of field-deployed PV modules

Automated Classification of Snow-Covered Solar Panel Surfaces Based on Deep Learning Approaches

An intelligent defect detection method in solar cells via IDATLGAN

Contact Info

Product

Resources

About