Chalak Qazani, Mohamad Reza, Ghasemi, Mostafa, and Asadi, Houshyar (2024) Optimizing microbial fuel cells with multiple-objectives PSO and type-2 fuzzy neural networks. Fuel, 372. 132090.

Preview

PDF (Published Version) - Published Version Available under License Creative Commons Attribution Non-commercial. Download (7MB) | Preview

Abstract

A microbial fuel cell is a novel method for simultaneous wastewater treatment and electricity production using microorganisms as biocatalysts. This study aims to develop an efficient surrogate model to predict microbial fuel cell performance based on varying input parameters, which include glucose (1–9 g/L), yeast extract (1–5 g/L), and aeration rate (0–110 ml/min). The output parameters of interest are chemical oxygen demand (COD) removal, coulombic efficiency, and power production. A type-2 fuzzy neural network (T2FNN) is employed to train the model for accurate predictions of these outputs. In the second phase, the trained model is integrated with multi-objective particle swarm optimization (PSO) to identify the optimal Pareto front solutions that maximize COD removal, coulombic efficiency, and power output. The optimal solutions are validated experimentally, demonstrating a marginal error of 9.50 % between the predicted and observed values. Specifically, the optimized microbial fuel cell achieved a COD removal efficiency with a margin error of 7.41 %, a coulombic efficiency margin error of 18.65 %, and a power generation margin error of 2.45 %. Compared to similar studies, the proposed methodology shows significant improvements, highlighting its effectiveness in enhancing microbial fuel cell performance for bioelectricity production and wastewater treatment. On average, the optimal parameters identified using this method result in notable improvements in COD removal, coulombic efficiency, and power production compared to a full factorial experimental study.

Item ID:	86703
Item Type:	Article (Research - C1)
ISSN:	1873-7153
Keywords:	Microbial fuel cell, Clean energy, Type-2 fuzzy neural network, Multiple-objective optimisation, Particle swarm optimisation
Copyright Information:	© 2024 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC license (http://creativecommons.org/licenses/by- nc/4.0/).
Date Deposited:	28 Aug 2025 01:00
FoR Codes:	40 ENGINEERING > 4004 Chemical engineering > 400410 Wastewater treatment processes @ 50% 46 INFORMATION AND COMPUTING SCIENCES > 4602 Artificial intelligence > 460203 Evolutionary computation @ 25% 46 INFORMATION AND COMPUTING SCIENCES > 4611 Machine learning > 461199 Machine learning not elsewhere classified @ 25%
SEO Codes:	28 EXPANDING KNOWLEDGE > 2801 Expanding knowledge > 280110 Expanding knowledge in engineering @ 60% 28 EXPANDING KNOWLEDGE > 2801 Expanding knowledge > 280115 Expanding knowledge in the information and computing sciences @ 40%
Downloads:	Total: 1 Last 12 Months: 1
	More Statistics