Browse by author
Lookup NU author(s): Zi Ang, Dr Wai Lok Woo
Full text for this publication is not currently held within this repository. Alternative links are provided below where available.
© 2017 IEEE. 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.
Author(s): Ang ZYA, Woo WL, Mesbahi E
Publication type: Conference Proceedings (inc. Abstract)
Publication status: Published
Conference Name: Proceedings of 2017 International Conference on Green Energy and Applications, ICGEA 2017
Year of Conference: 2017
Pages: 80-84
Online publication date: 11/05/2017
Acceptance date: 02/04/2016
Publisher: Institute of Electrical and Electronics Engineers Inc.
URL: https://doi.org/10.1109/ICGEA.2017.7925459
DOI: 10.1109/ICGEA.2017.7925459
Library holdings: Search Newcastle University Library for this item
ISBN: 9781538639856