TY - JOUR
T1 - Numerical investigation of micro solid oxide fuel cell performance in combination with artificial intelligence approach
AU - Taleghani, Parastoo
AU - Ghassemi, Majid
AU - Chizari, Mahmoud
N1 - © 2024 The Authors. Published by Elsevier Ltd. This is an open access article distributed under the Creative Commons Attribution License, to view a copy of the license, see: https://creativecommons.org/licenses/by/4.0/
PY - 2024/12/30
Y1 - 2024/12/30
N2 - The current study presents a multiphysics numerical model for a micro-planar proton-conducting solid oxide fuel cell (H-SOFC). The numerical model considered an anode-supported H-SOFC with direct internal reforming (DIR) of methane. The model solves coupled nonlinear equations, including continuity, momentum, mass transfer, chemical and electrochemical reactions, and energy equations. Furthermore, The numerical model results are used in artificial intelligence (AI) models, the K-nearest neighbour (KNN) and, artificial neural network (ANN), to predict the current density and power density of the H-SOFC. The results show that increasing the air-to-fuel (A/F) ratio decreases the current density and overall cell power. In particular, improvements in power and current density observed in H-SOFC when the A/F ratio is set to 0.5, resulting in a respective increase of 2 % and 7 % compared to the initial state at A/F = 1. With an error rate of less than 1 % and an R-score of around 99 %, the ANN model shows good agreement with the numerical results.
AB - The current study presents a multiphysics numerical model for a micro-planar proton-conducting solid oxide fuel cell (H-SOFC). The numerical model considered an anode-supported H-SOFC with direct internal reforming (DIR) of methane. The model solves coupled nonlinear equations, including continuity, momentum, mass transfer, chemical and electrochemical reactions, and energy equations. Furthermore, The numerical model results are used in artificial intelligence (AI) models, the K-nearest neighbour (KNN) and, artificial neural network (ANN), to predict the current density and power density of the H-SOFC. The results show that increasing the air-to-fuel (A/F) ratio decreases the current density and overall cell power. In particular, improvements in power and current density observed in H-SOFC when the A/F ratio is set to 0.5, resulting in a respective increase of 2 % and 7 % compared to the initial state at A/F = 1. With an error rate of less than 1 % and an R-score of around 99 %, the ANN model shows good agreement with the numerical results.
KW - Artificial intelligence
KW - Artificial neural network
KW - Micro solid oxide fuel cell
KW - Numerical model
KW - Proton-conducting electrolyte
UR - http://www.scopus.com/inward/record.url?scp=85211223607&partnerID=8YFLogxK
U2 - 10.1016/j.heliyon.2024.e40996
DO - 10.1016/j.heliyon.2024.e40996
M3 - Article
SN - 2405-8440
VL - 10
SP - 1
EP - 17
JO - Heliyon
JF - Heliyon
IS - 24
M1 - e40996
ER -