Enhancing Solid Oxide Fuel Cell Efficiency Through Advanced Model Identification Using Differential Evolutionary Mutation Fennec Fox Algorithm
Abstract Fuel cells (FCs) are increasingly attracting attention for their efficient conversion of chemical energy into electricity without the need for combustion. Their high efficiency and versatility make them a promising technology across various applications. Researchers are actively exploring w...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-02-01
|
| Series: | International Journal of Computational Intelligence Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s44196-025-00759-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract Fuel cells (FCs) are increasingly attracting attention for their efficient conversion of chemical energy into electricity without the need for combustion. Their high efficiency and versatility make them a promising technology across various applications. Researchers are actively exploring ways to optimize FC systems to meet specific energy needs. Among the different types of fuel cells, solid oxide fuel cells (SOFCs) stand out as a promising clean energy technology that generates electricity through electrochemical reactions. However, accurately modeling SOFCs, which is essential for reducing design costs, presents a challenge due to their complex and nonlinear characteristics. An ideal model should be adaptable to varying operating pressures and temperatures. This research introduces a novel approach for optimal SOFC model identification using a differential evolutionary mutation Fennec fox algorithm (DEMFFA). A real-world case study demonstrates the superior effectiveness of DEMFFA compared to existing methods. Additionally, a sensitivity analysis evaluates the influence of temperature and pressure on the model, with results indicating that the proposed method achieves higher efficiency than other approaches. The sum of the square error of the proposed algorithm is 1.18E-11 followed by the parent algorithm, Fennec fox algorithm (FFA) (1.24E-09), and some of the compared algorithms. The computational time of the proposed algorithm is 1.001 s, followed by the parent algorithm FFA (1.199 s) and some of the compared algorithms. DEMFFA offers significant potential, enhancing renewable energy, minimizing SOFC's environmental impact, and improving real-world applications like distributed power generation and hydrogen integration. |
|---|---|
| ISSN: | 1875-6883 |