Optimizing Solid Oxide Fuel Cell Performance Using Advanced Meta-Heuristic Algorithms
This study investigates the effects of varying operating parameters on Solid Oxide Fuel Cell (SOFC) performance through a series of experiments and simulations. The background of this research is rooted in the need for enhanced SOFC efficiency and reliability, which are critical for sustainable ener...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Bilijipub publisher
2024-06-01
|
| Series: | Advances in Engineering and Intelligence Systems |
| Subjects: | |
| Online Access: | https://aeis.bilijipub.com/article_199137_7831158fc81e317685e03298a75a1d81.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This study investigates the effects of varying operating parameters on Solid Oxide Fuel Cell (SOFC) performance through a series of experiments and simulations. The background of this research is rooted in the need for enhanced SOFC efficiency and reliability, which are critical for sustainable energy solutions. Our approach utilizes a Radial Basis Function (RBF) neural network trained with experimental data encompassing five input parameters: oxygen concentration, operating temperature, instrumentation, electrolyte thickness, and electrical current, with the goal of optimizing the single output parameter of power. The main novelty of this work lies in the application of six meta-heuristic algorithms for optimizing the weights and biases of the trained RBF network. These include the Angle of Attack Optimization (AOA), Particle Swarm Optimization with Grey Wolf Optimizer (PSOGWO), Particle Swarm Optimization (PSO), Grey Wolf Optimizer (GWO), Moth Flame Optimization (MFO), and Multi-Verse Optimizer (MVO). The models are evaluated against a comprehensive set of performance metrics: Root Mean Square Error (RMSE), Mean Squared Error (MSE), coefficient of determination (R²), correlation coefficient (R), Mean Absolute Error (MAE), Relative Absolute Error (RAE), Squared Error (SE), Mean Absolute Percentage Error (MAPE), and Normalized Mean Squared Error (NMSE). Our results indicate that the AOA method outperforms other algorithms, showing the highest accuracy and robust behavior across various data sets. Specifically, AOA achieved the highest values for R and R² (0.966 and 0.932, respectively) and the lowest values for RMSE, MSE, MAE, RAE, SE, MAPE, and NMSE (0.074, 0.005, 0.054, 0.242, 22.542, 0.711, and 0.482, respectively). These findings suggest that the AOA method not only offers superior performance but also exhibits the highest convergence among the tested optimization models. This research confirms the potential of advanced optimization techniques in improving the operational parameters of SOFCs, setting the stage for future advancements in fuel cell technologies. |
|---|---|
| ISSN: | 2821-0263 |