Prediction and analysis of energy generation from thermoelectric energy generator with operating environmental parameters

Ang, Zi Yang Adrian, Woo, Wai Lok and Mesbahi, Ehsan (2017) Prediction and analysis of energy generation from thermoelectric energy generator with operating environmental parameters. In: 2017 International Conference on Green Energy and Applications (ICGEA). IEEE, pp. 80-84. ISBN 978-1-5386-3986-3

Full text not available from this repository.

Abstract

This paper presents an integrated artificial neural network (ANN) approach for the design and prediction of energy generated from a thermoelectric generator (TEG) under the influence of the operating environmental parameters. The unique ANN model can predict the output voltage generated as well as ensuring the reliability of the output. Deriving of individual input parameter can also be obtained from the learned network when given a required output voltage together with sensitivity analysis for the identification of key input parameters that have strong influence in the output value generated by the TEG were also incorporated in the model, making it an efficient tool for the design and conceptualisation of a TEG. This proposed approach is particularly useful when TEG users are faced with limited resources for achieving their required output power. The developed ANN model shows the mean square error (MSE) of 0.0008 in modelling an experimental dataset consisting of 4096 data. The predicted results obtained from the optimized ANN model are also verified with the testing of experimental data and a good agreement is obtained with errors of +/- 0.15.

Item Type:	Book Section
Uncontrolled Keywords:	energy harvesting, thermoelectricity, renewable energy, artificial neural network
Subjects:	G900 Others in Mathematical and Computing Sciences
Department:	Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User:	Becky Skoyles
Date Deposited:	03 Apr 2019 12:20
Last Modified:	10 Oct 2019 20:46
URI:	http://nrl.northumbria.ac.uk/id/eprint/38722

Downloads