Exergy analysis and optimisation of a two-stage solar thermoelectric generator with tapered legs

Eke, Mkpamdi; Maduabuchi, Chika; Lamba, Ravita; Njoku, Howard O.; Ma, Xiaoli; Gurevich, Yuri; Tyagi, Shoobhangi; Ekechukwu, O. V.; Ejiogu, E.C.; Eneh, Chibuoke

doi:10.1504/ijex.2022.122309

Cited by 16 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Polynomial expressions describing the effects of temperature on the semiconductor properties are available from reference [47]. Furthermore, the properties of other materials used to model the stand-alone and incorporated systems can be easily obtained from our previous work [48][49][50][51][52][53][54]. The photovoltaic-thermoelectric coupling equations, the numerical model verification, and the deep neural network equations are provided and well explained in the Supplementary Material accompanying this work.…”

Section: Methodsmentioning

confidence: 99%

Machine Learning Performance Prediction of a Solar Photovoltaic-Thermoelectric System with Various Crystalline Silicon Cell Types

Alghamdi

Maduabuchi

Albaker

et al. 2023

International Journal of Energy Research

View full text Add to dashboard Cite

Since the solar photovoltaic-thermoelectric (PV-TE) is an upcoming technology, the current literature on PV-TEs have failed to thoroughly investigate the effects of different solar cell types on the PV-TE’s performance. Such parametric study becomes necessary since the properties of the solar cell, characterized by the cell temperature coefficient and reference efficiency, determine the overall performance of the PV-TE. Further, the design information obtained from numerical solvers is minimal due to the high time and computational energy required to optimize the photovoltaic-thermoelectric (PV-TE) performance. This problem severely affects the ease with which useful design information can be drawn from current methods to design high-performance PVs. Additionally, to reduce the complexity of the existing numerical model, the previous models have introduced some principal assumptions that have significantly affected the accuracy of the numerical results. Finally, the numerical model has neglected several real-life operating conditions since they increase the model complexity. For the first time, deep neural networks are proposed to predict the photovoltaic-thermoelectric performance designed with 3 different crystalline solar cells as a perfect replacement for the inefficient numerical methods used to analyze the hybrid system. After that, the data generated by the numerical solver is fed to an optimum 3-layer deep neural network with 20 neurons per layer to forecast the hybrid system’s performance efficiently. The training of the neural network is governed by Bayesian regularization and the performance of the model is evaluated using the mean squared error, coefficient of determination, and training time. Results show that the deep neural network accurately learned the results that took the conventional numerical solver 1,600 mins to generate in just 12 min and 27 s, making the proposed network 128.51 times faster than the traditional numerical method. Furthermore, the accuracy of the network is demonstrated by the low mean squared error of 3.34 × 10 − 8 and high training and testing regression of 100% and 99.98%, respectively.

show abstract

Section: Methodsmentioning

confidence: 99%

Machine Learning Performance Prediction of a Solar Photovoltaic-Thermoelectric System with Various Crystalline Silicon Cell Types

Alghamdi

Maduabuchi

Albaker

et al. 2023

International Journal of Energy Research

View full text Add to dashboard Cite

show abstract

A synergistic approach to optimizing the performance of a concentrating solar segmented variable area leg thermoelectric generator using numerical methods and neural networks

Alghamdi,

Maduabuchi,

Albaker

et al. 2024

J Therm Anal Calorim

View full text Add to dashboard Cite

This study presents an optimized design for segmented variable area leg thermoelectric modules using finite element methods and Bayesian regularized neural networks. We explored the impact of geometry and thermal parameters on module performance using ANSYS software, identifying optimal parameters for power output and efficiency. Key findings revealed the higher influence of geometric parameters and confirmed the advantages of segmented thermoelectric generators for high-temperature applications like concentrated solar systems. With this optimization, power output and efficiency of the module increased by 875% and 165%, respectively, under 25 Suns. To refine the optimization process, a Bayesian regularized neural network was utilized, proving effective in predicting module performance with a low mean squared error and high coefficient of determination. This research provides important insights into high-performance thermoelectric modules for sustainable energy applications, demonstrating the significant role of advanced computational methods in energy solutions.

show abstract

Energy and exergy analyses and optimizations for two-stage TEC driven by two-stage TEG with Thomson effect

Chen,

Ge,

Feng

et al. 2023

Sci. China Technol. Sci.

View full text Add to dashboard Cite

Exergy analysis and optimisation of a two-stage solar thermoelectric generator with tapered legs

Cited by 16 publications

References 0 publications

Machine Learning Performance Prediction of a Solar Photovoltaic-Thermoelectric System with Various Crystalline Silicon Cell Types

Machine Learning Performance Prediction of a Solar Photovoltaic-Thermoelectric System with Various Crystalline Silicon Cell Types

A synergistic approach to optimizing the performance of a concentrating solar segmented variable area leg thermoelectric generator using numerical methods and neural networks

Energy and exergy analyses and optimizations for two-stage TEC driven by two-stage TEG with Thomson effect

Contact Info

Product

Resources

About