Evaluation of artificial neural network algorithms for predicting the effect of the urine flow rate on the power performance of microbial fuel cells
Evaluation of artificial neural network algorithms for predicting the effect of the urine flow rate on the power performance of microbial fuel cells
Microbial fuel cell (MFC) power performance strongly depends on the biofilm growth, which in turn is affected by the feed flow rate. In this work, an artificial neural network (ANN) approach has been used to simulate the effect of the flow rate on the power output by ceramic MFCs fed with neat human urine. To this aim, three different second-order algorithms were used to train our network and then compared in terms of prediction accuracy and convergence time: Quasi-Newton, Levenberg-Marquardt, and Conjugate Gradient. The results showed that the three training algorithms were able to accurately simulate power production. Amongst all of them, the Levenberg-Marquardt was the one that presented the highest accuracy (R = 95%) and the fastest convergence (7.8 s). These results show that ANNs are useful and reliable tools for predicting energy harvesting from ceramic-MFCs under changeable flow rate conditions, which will facilitate the practical deployment of this technology.
Artificial neural networks, Bioenergy, Flow rate, Microbial fuel cells, Modelling, Urine
de Ramón-Fernández, A.
14074e84-50b3-4276-a24e-856ba59e2729
Salar-García, M. J.
f727455c-3d80-4901-88f7-63b70eadcfe6
Ruiz Fernández, D.
9bb9c015-c82a-428b-acdc-6aa97beb2253
Greenman, J.
eb3d9b82-7cac-4442-9301-f34884ae4a16
Ieropoulos, I. A.
6c580270-3e08-430a-9f49-7fbe869daf13
15 December 2020
de Ramón-Fernández, A.
14074e84-50b3-4276-a24e-856ba59e2729
Salar-García, M. J.
f727455c-3d80-4901-88f7-63b70eadcfe6
Ruiz Fernández, D.
9bb9c015-c82a-428b-acdc-6aa97beb2253
Greenman, J.
eb3d9b82-7cac-4442-9301-f34884ae4a16
Ieropoulos, I. A.
6c580270-3e08-430a-9f49-7fbe869daf13
de Ramón-Fernández, A., Salar-García, M. J., Ruiz Fernández, D., Greenman, J. and Ieropoulos, I. A.
(2020)
Evaluation of artificial neural network algorithms for predicting the effect of the urine flow rate on the power performance of microbial fuel cells.
Energy, 213, [118806].
(doi:10.1016/j.energy.2020.118806).
Abstract
Microbial fuel cell (MFC) power performance strongly depends on the biofilm growth, which in turn is affected by the feed flow rate. In this work, an artificial neural network (ANN) approach has been used to simulate the effect of the flow rate on the power output by ceramic MFCs fed with neat human urine. To this aim, three different second-order algorithms were used to train our network and then compared in terms of prediction accuracy and convergence time: Quasi-Newton, Levenberg-Marquardt, and Conjugate Gradient. The results showed that the three training algorithms were able to accurately simulate power production. Amongst all of them, the Levenberg-Marquardt was the one that presented the highest accuracy (R = 95%) and the fastest convergence (7.8 s). These results show that ANNs are useful and reliable tools for predicting energy harvesting from ceramic-MFCs under changeable flow rate conditions, which will facilitate the practical deployment of this technology.
Text
1-s2.0-S0360544220319137-main
- Version of Record
More information
Published date: 15 December 2020
Additional Information:
Funding Information:
M.J. Salar-Garc?a is supported by Fundaci?n Seneca (Ref. 20372/PD/17) and A. De Ram?n-Fern?ndez by the Spanish Ministry of Economy and Competitiveness (Ref. BES-2015-073611). I. Ieropoulos also thanks the Bill & Melinda Gates Foundation (grant no. INV-006499) for its financial support.
Funding Information:
M.J. Salar-García is supported by Fundación Seneca (Ref. 20372/PD/17) and A. De Ramón-Fernández by the Spanish Ministry of Economy and Competitiveness (Ref. BES-2015-073611). I. Ieropoulos also thanks the Bill & Melinda Gates Foundation (grant no. INV-006499 ) for its financial support.
Publisher Copyright:
© 2020 The Authors
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
Keywords:
Artificial neural networks, Bioenergy, Flow rate, Microbial fuel cells, Modelling, Urine
Identifiers
Local EPrints ID: 454002
URI: http://eprints.soton.ac.uk/id/eprint/454002
ISSN: 0360-5442
PURE UUID: 002e05ac-53b5-48f9-80c5-3062f028237b
Catalogue record
Date deposited: 27 Jan 2022 18:12
Last modified: 18 Mar 2024 04:04
Export record
Altmetrics
Contributors
Author:
A. de Ramón-Fernández
Author:
M. J. Salar-García
Author:
D. Ruiz Fernández
Author:
J. Greenman
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics