Performance prediction of hybrid thermoelectric generator with high accuracy using artificial neural networks

Journal article

Authors/Editors

Strategic Research Themes

No matching items found.

Publication Details

Author list: Angeline A.A., Asirvatham L.G., Hemanth D.J., Jayakumar J., Wongwises S.

Publisher: Elsevier Ltd

Publication year: 2019

Volume number: 33

Start page: 53

End page: 60

Number of pages: 8

ISSN: 2213-1388

eISSN: 2213-1388

URL: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85063293508&doi=10.1016%2fj.seta.2019.02.008&partnerID=40&md5=71c415437965912a2e6ebc67735e3435

Languages: English-Great Britain (EN-GB)

View in Web of Science | View on publisher site | View citing articles in Web of Science

Abstract

This paper presents the application of Artificial Neural Networks for the simulation of the performance parameters of a hybrid thermoelectric generator, using the artificial neural networks tool in the MATLAB software under various temperature, load and series condition. The simulated parameters (till an input heater temperature of about 250 °C) are compared with experimental results and the average error between the experimental approach and ANN based approach for all the parameter values is less than 3%. This low error value shows that the experiments need not be repeated for input temperatures above 250 °C which is quite complex. Hence, the effect of temperature gradient on the hybrid thermoelectric generator performance upto 350 °C of the hot side temperature with a single module and “N” no. of series connection have been estimated using ANN methodology. Experimental results suggest the necessity for ANN based approaches for hybrid TEG applications. © 2019

Keywords

Figure of merit