AI-assisted Cell-Level Fault Detection and Localization in Solar PV Electroluminescence Images

Ahan, M. R.; Nambi, Akshay; Ganu, Tanuja; Nahata, Dhananjay; Kalyanaraman, Shivkumar

doi:10.1145/3485730.3493455

Cited by 6 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With their development of an End‐to‐End Fault Detection System, Ahan et al (2021), who discussed the intersection of AI and solar panel fault detection, made significant progress. Using Electroluminescence (EL) Imaging, they detected and localized issues with solar panels, thereby enhancing performance and reducing warranty and service costs.…”

Section: Applications Of Artificial Intelligence In Solar and Wind En...mentioning

confidence: 99%

“…In solar energy systems, machine learning algorithms enhance solar panel performance, increase energy forecasting, and optimize energy storage systems. For instance, machine-learning techniques have been used to detect and localize solar panel faults, drastically reducing the time required to identify and rectify faulty cells (Ahan et al, 2021). In addition, machine learning-based solar energy forecasting systems have demonstrated high accuracy (Partheeban et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning and the renewable energy revolution: Exploring solar and wind energy solutions for a sustainable future including innovations in energy storage

Bin Abu Sofian,

Lim,

Siti Halimatul Munawaroh

et al. 2024

Sustainable Development

View full text Add to dashboard Cite

This article evaluates the present global condition of solar and wind energy adoption and explores their benefits and limitations in meeting energy needs. It examines the historical and evolutionary growth of solar and wind energy, global trends in the usage of renewable energy, and upcoming technologies, including floating solar and vertical‐axis wind turbines. The importance of smart grid technology and energy storage alternatives for enhancing the effectiveness and dependability of renewable energy is explored. In addition, the role of Electric Vehicles (EVs) in a modern smart grid has been assessed. Furthermore, the economic benefits, and most recent technological developments of solar and wind energy and their environmental and social ramifications. The potential of solar and wind energy to meet the increasing global energy demand and the problems and opportunities facing the renewable energy industry have shown excellent promise. Machine learning applications for solar and wind energy generation are vital for sustainable energy production. Machine learning can help in design, optimization, cost reduction, and, most importantly, in improving the efficacy of solar and wind energy, including advancing energy storage. This assessment is a crucial resource for policymakers, industry leaders, and researchers who aim to make the world cleaner and more sustainable. Ultimately, this review has shown the great potential of solar and wind energy in meeting global energy demands and sustainable goals.

show abstract

Section: Applications Of Artificial Intelligence In Solar and Wind En...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Machine learning and the renewable energy revolution: Exploring solar and wind energy solutions for a sustainable future including innovations in energy storage

Bin Abu Sofian,

Lim,

Siti Halimatul Munawaroh

et al. 2024

Sustainable Development

View full text Add to dashboard Cite

show abstract

“…As demonstrated for silicon PV, ex situ deployment of these methods in combination with imaging techniques enables monitoring and quantification of the current operational status of fully processed solar cells during operation in the field. [37][38][39][40][41][42][43][44][45] The key ingredient for unlocking large-scale and thus economically viable production of PSCs is the upscaling of the thin-film formation process to large areas using scalable deposition techniques. To this end, the entangled phases of film formation, i.e., drying, nucleation, and crystal growth, must be carefully monitored and controlled to obtain high-quality optoelectronic thin films.…”

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Process Insights into Perovskite Thin‐Film Photovoltaics from Machine Learning with In Situ Luminescence Data

et al. 2023

View full text Add to dashboard Cite

technology demonstrates outstanding power conversion efficiencies (PCEs), exceeding 25%. [3] Despite numerous favorable optoelectronic properties of perovskite semiconductors, four key challenges remain and delay the successful commercialization of perovskite solar cells (PSCs): 1) the long-term stability, 2) the toxicity of the contained lead, 3) upscaling to large-areas, and 4) unlocking cost-effective, reliable large-scale production (high throughput and high yield). [2,4] Traditional efforts in material science and device engineering in the field are based on countless trialand-error experiments. However, these approaches for material discovery, process development, characterization, full device evaluation, and stability testing are often complicated, expensive, laborious, and time-consuming given the large experimental parameter space. [5] These drawbacks motivate the implementation of autonomous experimentation methods and data-driven techniques like machine learning (ML). [6,7] In an increasing number of research fields, ML methods are employed to identify yet undiscovered correlations and to provide insights into fundamental working principles. Besides pattern extraction, ML can be utilized to make classifications or predictions and to uncover new insights into the studied data. For this reason, ML algorithms are successfully adopted to an increasing number of applications in materials science, [8][9][10][11] encompassing,

show abstract

An improved hybrid solar cell defect detection approach using Generative Adversarial Networks and weighted classification

Yusuf Demirci,

Beşli,

Gümüşçü

2024

Expert Systems with Applications

View full text Add to dashboard Cite

AI-assisted Cell-Level Fault Detection and Localization in Solar PV Electroluminescence Images

Cited by 6 publications

References 15 publications

Machine learning and the renewable energy revolution: Exploring solar and wind energy solutions for a sustainable future including innovations in energy storage

Machine learning and the renewable energy revolution: Exploring solar and wind energy solutions for a sustainable future including innovations in energy storage

Process Insights into Perovskite Thin‐Film Photovoltaics from Machine Learning with In Situ Luminescence Data

An improved hybrid solar cell defect detection approach using Generative Adversarial Networks and weighted classification

Contact Info

Product

Resources

About