Machine learning analysis on performance of naturally-sensitized solar cells

Maddah, Hisham A.

doi:10.1016/j.optmat.2022.112343

Cited by 8 publications

(4 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Arooj and Wang demonstrated a valuable attempt to optimize the sensitizers used in DSSC fabrication and report an efficiency of 17.30% by ML [259]. By understanding the characteristics of natural sensitized Maddah investigated to enhance the performance of DSSCs through ML [260]. Wen et al illustrated a quantitative structure-property relationship model by combining MLand computational quantum chemistry for exploring various organic dyes capable of being integrated in organic DSSCs [261].…”

Section: Machine Learning (Ml) In Dsscsmentioning

confidence: 99%

Recent advances in the development of flexible dye-sensitized solar cells: fabrication, challenges and applications-a review

Dawo¹,

Chaturvedi²

2023

Flex. Print. Electron.

View full text Add to dashboard Cite

Flexible dye-sensitized solar cells (FDSSCs) show a huge potential for stretchable electronics and portable power sources due to their lightweight, handy, flexibility, cost-effective, and easy processing. This paper introduces basic operating principles and design opportunities for maximum efficiencies for FDSSCs. Flexible polymers or metal substrates, enabling cost reduction due to large volume production with roll to roll manufacturing technique. DSSCs achieved a PCE of 14.30 % on rigid conductive substrates, 10.28 % on flexible metal substrates, and 8 % on plastic substrates. A brief distinction has been made on different substrates, preparation of charge transfers materials, coating and printing techniques and processing methods for enhancing the performance of FDSSCs. We also highlight issues pertaining to progress in the stability of devices and the commercialisation of FDSCs technologies will be explained.

show abstract

Section: Machine Learning (Ml) In Dsscsmentioning

confidence: 99%

Recent advances in the development of flexible dye-sensitized solar cells: fabrication, challenges and applications-a review

Dawo¹,

Chaturvedi²

2023

Flex. Print. Electron.

View full text Add to dashboard Cite

show abstract

“…Leaf nodes represent the possible outcomes from which conclusions can be deducted [38]. A decision tree algorithm uses an iterative process, a greedy search, in which the data splitting into partitions is undertaken by minimizing the sum of squared deviations from the mean in the two separate partitions [29]. There are different types of decision tree algorithms, including popular ones such as iterative dichotomiser 3 (ID3), a later iteration of ID3 (C4.5), and classification and regression trees (CART) [29].…”

Section: Decision Tree Regressionmentioning

confidence: 99%

“…Conclusions can be deducted based on the categorized responses that are represented in the leaf nodes. The root node of the tree is the parent node of all existing nodes, where each link represents a decision, and each leaf represents an outcome [29]. A random forest (RF) algorithm is an extension of the bagging method, which assembles decision trees which are uncorrelated [30].…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Analysis on the Performance of Dye-Sensitized Solar Cell—Thermoelectric Generator Hybrid System

Varga

Racz

2022

Energies

View full text Add to dashboard Cite

In cases where a dye-sensitized solar cell (DSSC) is exposed to light, thermal energy accumulates inside the device, reducing the maximum power output. Utilizing this energy via the Seebeck effect can convert thermal energy into electrical current. Similar systems have been designed and built by other researchers, but associated tests were undertaken in laboratory environments using simulated sunlight and not outdoor conditions with methods that belong to conventional data analysis and simulation methods. In this study four machine learning techniques were analyzed: decision tree regression (DTR), random forest regression (RFR), K-nearest neighbors regression (K-NNR), and artificial neural network (ANN). DTR algorithm has the least errors and the most R2, indicating it as the most accurate method. The DSSC-TEG hybrid system was extrapolated based on the results of the DTR and taking the worst-case scenario (node-6). The main question is how many thermoelectric generators (TEGs) are needed for an inverter to operate a hydraulic pump to circulate water, and how much area is required for that number of TEGs. Considering the average value of the electric voltage of the TEG belonging to node-6, 60,741 pieces of TEGs would be needed, which means about 98 m2 to circulate water.

show abstract

“…[18][19][20][21] The application of ML in the DSSC field has also been explored in recent years. [22][23][24][25][26] For instance, Xu et al adopted an artificial neural network to forecast absorption maxima for organic dyes in DSSCs based on a collection of 70 organic dyes with diverse structures. 27 In a similar vein, Venkatraman et al utilized supervised machine learning to ascertain whether dye adsorption on titania would induce changes in its absorption characteristics.…”

Section: Introductionmentioning

confidence: 99%

Deep-learning-assisted photovoltaic performance prediction of sensitizers in dye-sensitized solar cells

Zhang,

Fu,

Zhang

et al. 2024

New J. Chem.

View full text Add to dashboard Cite

show abstract

Machine learning analysis on performance of naturally-sensitized solar cells

Cited by 8 publications

References 60 publications

Recent advances in the development of flexible dye-sensitized solar cells: fabrication, challenges and applications-a review

Recent advances in the development of flexible dye-sensitized solar cells: fabrication, challenges and applications-a review

Machine Learning Analysis on the Performance of Dye-Sensitized Solar Cell—Thermoelectric Generator Hybrid System

Deep-learning-assisted photovoltaic performance prediction of sensitizers in dye-sensitized solar cells

Contact Info

Product

Resources

About