New approach for solar tracking systems based on computer vision, low cost hardware and deep learning

Carballo, Jose A.; Bonilla, Javier; Berenguel, Manuel; Fernández-Reche, Jesús; García, G. Martınez

doi:10.1016/j.renene.2018.08.101

Cited by 57 publications

(24 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Various studies have recommended and demonstrated successfully the use of pre-trained network models. 31–37 In the present study, the feature extraction properties of several renowned CNN architectures like VGG 16, 18 GoogLeNet, 38 AlexNet, 17 and ResNet50 20 were evaluated with the help of machine learning classifiers. A brief description of the CNN models considered are described in this section.…”

Section: Machine Learning Based Three Phase Approach For Fault Detection In Aerial Imagesmentioning

confidence: 99%

A combined approach of convolutional neural networks and machine learning for visual fault classification in photovoltaic modules

Venkatesh

Sugumaran

2021

Proceedings of the Institution of Mechanical Engineers, Part O:

View full text Add to dashboard Cite

Fault diagnosis plays a significant role in enhancing the useful lifetime, power output, and reliability of photovoltaic modules (PVM). Visual faults such as burn marks, delamination, discoloration, glass breakage, and snail trails make detection of faults difficult under harsh environmental conditions. Various researchers have made several attempts to identify visual faults in a PVM. However, much of the previous studies were centered on the identification and analysis of limited number of faults. This article presents the use of a deep convolutional neural network (CNN) to extract image features and perform an effective classification of faults by machine learning (ML) algorithms. In contrast to the present-day work, five different fault conditions were considered in the study. The proposed solution consists of three phases, to effectively analyze various PVM defects. First, the module images are acquired using unmanned aerial vehicles (UAVs) and data augmentation is performed to generate a uniform dataset. Afterward, a pre-trained deep CNN is adopted for image feature extraction. Finally, the extracted image features are classified with the help of various ML classifiers. The final results show the effectiveness of pre-trained deep CNN and accurate performance of ML classifiers. The best-in-class ML classifier for multiple fault classification is suggested based on the performance comparison.

show abstract

Section: Machine Learning Based Three Phase Approach For Fault Detection In Aerial Imagesmentioning

confidence: 99%

A combined approach of convolutional neural networks and machine learning for visual fault classification in photovoltaic modules

Venkatesh

Sugumaran

2021

Proceedings of the Institution of Mechanical Engineers, Part O:

View full text Add to dashboard Cite

show abstract

“…The proposed system captures reflections from the target and uses image processing to detect and extract solar angles based on BP neural networks. Carballo et al [55] developed a low-cost machine vision solar tracking system that can be used for Using the same concept, Berenguel et al [50] proposed a model to correct the calculation and installation of the solar position. The model is based on the use of a charge-device camera to capture images of the reflected beams from each field heliostat to the target to be used for offset correction.…”

Section: Review Of Tracking Systems For Crsmentioning

confidence: 99%

“…The proposed system captures reflections from the target and uses image processing to detect and extract solar angles based on BP neural networks. Carballo et al [55] developed a low-cost machine vision solar tracking system that can be used for any type of solar system. The proposed system calculates the Sun vector, the target vector of the receiver and the aiming point vector on a camera plane below the receiver tower.…”

Section: Review Of Tracking Systems For Crsmentioning

confidence: 99%

Pilot Low-Cost Concentrating Solar Power Systems Deployment in Sub-Saharan Africa: A Case Study of Implementation Challenges

et al. 2020

View full text Add to dashboard Cite

Electricity is one of the most crucial resources that drives any given nation’s growth and development. The latest Sustainable Development Goals report indicates Africa still has a high deficit in electricity generation. Concentrating solar power seems to be a potential option to fill the deficit. That is because most of the components of concentrating solar power plants are readily available on the African market at affordable prices, and there are qualified local persons to build the plants. Pilot micro-concentrating solar power plants have been implemented in Sub-Saharan Africa and have shown promising results that could be expanded and leveraged for large-scale electricity generation. An assessment of a pilot concentrating solar power plant in the sub-region noticed one noteworthy obstacle that is the failure of the tracking system to reduce the operating energy cost of running the tracking control system and improve the multifaceted heliostat focusing behavior. This paper highlights the energy situation and the current development in concentrating solar power technology research in Africa. The paper also presents a comprehensive review of the state-of-the-art solar tracking systems for central receiver systems to illustrate the current direction of research regarding the design of low-cost tracking systems in terms of computational complexity, energy consumption, and heliostat alignment accuracy.

show abstract

“…Bobot telur ayam diperoleh dari perhitungan luasan hasil segmentasi telur ayam yang dihasilkan. Disisi lain, pencitraan nyala lampu dapat dianalogikan dengan pencitraan sinar matahari [7,10,11]. Keduanya menggunakan thresholding untuk mendapatkan citra sinar matahari.…”

Section: Pendahuluanunclassified

Digital Imaging Light Energy Saving Lamp Based On A Single Board Computer

Bangsawan¹,

Hanafi²,

Suryana³

2020

RESTI

View full text Add to dashboard Cite

Computer Vision (CV) is an interdisciplinary scientific field that discusses how computers can gain a high-level understanding of digital images or video. A system has been created that is capable of detecting a compact fluoresence lamp (CFL) light. However, in previous research there is no justification that the lamp is only a part that can glow on the lamp alone and has not been done in multi-lamp testing. This study aims to compare the lamp segmentation when it goes OFF and ON so that it could be justified the accuracy of this system and does multi-lamp testing. The method used is an experiment with collecting data by direct observation of the results of the system made. The system consists of a single board computer and a common webcam. The result is the difference between the lamp segmentation when it goes OFF and ON is small with the appropriate threshold setting. So that lamp light imaging had been made could function with good reability.

show abstract

New approach for solar tracking systems based on computer vision, low cost hardware and deep learning

Cited by 57 publications

References 22 publications

A combined approach of convolutional neural networks and machine learning for visual fault classification in photovoltaic modules

A combined approach of convolutional neural networks and machine learning for visual fault classification in photovoltaic modules

Pilot Low-Cost Concentrating Solar Power Systems Deployment in Sub-Saharan Africa: A Case Study of Implementation Challenges

Digital Imaging Light Energy Saving Lamp Based On A Single Board Computer

Contact Info

Product

Resources

About