An event-triggered and dimension learning scheme WOA for PEMFC modeling and parameter identification

Aiming at the high dimension and complexity of parameters identification problem, a whale optimization algorithm based on event-triggered and dimension learning scheme (EDWOA) is presented, which is specifically designed for the proton exchange membrane fuel cell (PEMFC) model. Drawing inspiration f...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Energy (Oxford) Ročník 305; s. 132352
Hlavní autori: Sun, Zhe, Wang, Yiwen, Xie, Xiangpeng, Yang, Qiming, Bi, Yunrui, Sun, Zhixin
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 01.10.2024
Predmet:
algorithms
energy
fuel cells
Improved whale optimization algorithm
Parameter identification
Proton exchange membrane fuel cell
Improved whale optimization algorithm
Parameter identification
Proton exchange membrane fuel cell
ISSN:0360-5442
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Aiming at the high dimension and complexity of parameters identification problem, a whale optimization algorithm based on event-triggered and dimension learning scheme (EDWOA) is presented, which is specifically designed for the proton exchange membrane fuel cell (PEMFC) model. Drawing inspiration from group optimization strategies, a novel dimensional learning method is introduced to enhance the dynamic search capabilities of the algorithm. To assess the efficacy of the proposed algorithm, benchmark function testing was conducted, and its fitness surpassed common heuristic algorithms on over 15 objective functions. The results clearly indicate that the EDWOA algorithm outperforms its counterparts in terms of global search performance. Its ability to navigate complex search spaces sets it apart from other algorithms. Finally, the proposed EDWOA algorithm is successfully applied to parameter identification in the PEMFC model. Through a comparative analysis with existing research findings, it was found that the identified PEMFC model exhibited a notable enhancement in fitness, ranging from 0.02 to 0.93. This underscores the effectiveness of the EDWOA algorithm in improving the performance and dynamic output of PEMFC models. •An improved whale optimization algorithm based on event-triggered strategy and dimension learning mechanism is proposed.•Through benchmark function testing, the EDWOA algorithm demonstrates superior search performance compared to other variants and commonly used heuristic algorithms.•The proposed EDWOA algorithm is successfully applied to identify the PEMFC semi-empirical model parameters.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0360-5442
DOI:10.1016/j.energy.2024.132352