TY - JOUR
T1 - Finding best operational conditions of PEM fuel cell using adaptive neuro-fuzzy inference system and metaheuristics
AU - Rezk, Hegazy
AU - Wilberforce, Tabbi
AU - Sayed, Enas Taha
AU - Alahmadi, Ahmed N.M.
AU - Olabi, A. G.
N1 - Publisher Copyright:
© 2022
PY - 2022/11
Y1 - 2022/11
N2 - The optimum output power of the proton exchange membrane fuel cell (PEMFC) is dependent on operational conditions such as fuel pressure, oxidant pressure, fuel flow rate, and oxidant flow rate. Therefore, the aim of this paper is to enhance performance of PEMFC by identifying optimal operating parameters of PEMFC. The proposed strategy includes both modelling and optimization stages. An adaptive network-based fuzzy inference system (ANFIS) is utilized in creating the model based on experimental datasets. Whereas, the grey wolf optimizer (GWO) is used to identify the best values of fuel pressure, oxidant pressure, fuel flow rate, and oxidant flow rate corresponding to maximum power PEMFC. The obtained results demonstrated the superiority of the integration between ANIFS based modelling and GWO. Regarding the modelling accuracy, The RMSE values are 0.017 as well as 0.0262 respectively for treating and testing phases. The coefficient of determination values is 0.9921 as well as 0.9622 respectively for treating coupled with testing phases. The optimal parameters are 1.0 bar, 0.8 bar, 117.03 mL/min, 150.0 mL/min respectively fuel pressure, oxidant pressure, fuel flow rate, and oxidant flow rate corresponding to maximum power of PEMFC. Thanks to the integration between ANFIS-based modelling and GWO, the output power of PEMFC has been increased from 0.587 W using experimental work to 0.92 W.
AB - The optimum output power of the proton exchange membrane fuel cell (PEMFC) is dependent on operational conditions such as fuel pressure, oxidant pressure, fuel flow rate, and oxidant flow rate. Therefore, the aim of this paper is to enhance performance of PEMFC by identifying optimal operating parameters of PEMFC. The proposed strategy includes both modelling and optimization stages. An adaptive network-based fuzzy inference system (ANFIS) is utilized in creating the model based on experimental datasets. Whereas, the grey wolf optimizer (GWO) is used to identify the best values of fuel pressure, oxidant pressure, fuel flow rate, and oxidant flow rate corresponding to maximum power PEMFC. The obtained results demonstrated the superiority of the integration between ANIFS based modelling and GWO. Regarding the modelling accuracy, The RMSE values are 0.017 as well as 0.0262 respectively for treating and testing phases. The coefficient of determination values is 0.9921 as well as 0.9622 respectively for treating coupled with testing phases. The optimal parameters are 1.0 bar, 0.8 bar, 117.03 mL/min, 150.0 mL/min respectively fuel pressure, oxidant pressure, fuel flow rate, and oxidant flow rate corresponding to maximum power of PEMFC. Thanks to the integration between ANFIS-based modelling and GWO, the output power of PEMFC has been increased from 0.587 W using experimental work to 0.92 W.
KW - ANFIS modelling
KW - Fuel cells
KW - Grey wolf optimizer
UR - http://www.scopus.com/inward/record.url?scp=85130081157&partnerID=8YFLogxK
U2 - 10.1016/j.egyr.2022.04.061
DO - 10.1016/j.egyr.2022.04.061
M3 - Article
AN - SCOPUS:85130081157
SN - 2352-4847
VL - 8
SP - 6181
EP - 6190
JO - Energy Reports
JF - Energy Reports
ER -
