Optimal parameters estimation of the PEMFC using a balanced version of Water Strider Algorithm

Recently, much attention was paid to the application of renewable energy in environmental issues. Meanwhile, the fuel cell industry, which is considered an environmentally friendly industry, is one of the important components of this project. They are in fact devices for the direct conversion of che...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Energy reports 2021-11, Vol.7, p.6876-6886
Hauptverfasser: Syah, Rahmad, Isola, Lawal Adedoyin, Guerrero, John William Grimaldo, Suksatan, Wanich, Sunarsi, Denok, Elveny, Marischa, Alkaim, Ayad F., Thangavelu, Lakshmi, Aravindhan, Surendar
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Recently, much attention was paid to the application of renewable energy in environmental issues. Meanwhile, the fuel cell industry, which is considered an environmentally friendly industry, is one of the important components of this project. They are in fact devices for the direct conversion of chemical energy into electrical energy by an electrochemical reaction without the need for any mechanical parts. In this study, it is attempted to model one of their important types, called proton exchange membrane fuel cells, so that it can be used in predicting the behavior of the fuel cell and examining various parameters affecting the performance of the cell. The main idea is to optimal parameters estimation for the proton exchange membrane fuel cells by minimizing the total Squared Error value between the empirical output voltage and the approximated output voltage. For giving better results in terms of accuracy and reliability, a new design of a metaheuristic called the balanced Water Strider Algorithm is utilized. The results of the suggested method are finally validated by comparison with several latest optimizers applied on a practical test case. After running all of the optimizers 30 times independently, the proposed method with minimum absolute error equals 3.4831e−4 shows the best results toward the others.
ISSN:2352-4847
2352-4847
DOI:10.1016/j.egyr.2021.10.057