.png){kind=icon}
.png){kind=icon}
Return
Optimizing proton exchange membrane fuel cell parameter identification using enhanced hummingbird algorithm
.png){kind=icon}
PRE
AI
DOI：10.1016/j.ijhydene.2024.09.211.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Fuel cells (FCs) have attracted significant interest due to their versatile applications, but modeling their nonlinear behavior is challenging. This research proposes an Enhanced Artificial Hummingbird Algorithm (EAHA) to identify the seven unknown parameters of proton exchange membrane fuel cell (PEMFC) stacks using their experimental data. The goal is to accurately predict the current/voltage (I/V) curves by minimizing a cost function defined as the sum of squared differences between measured data points and model estimates. The EAHA combines several territorial foraging techniques with a linear regulation mechanism. Its performance is compared to the conventional Artificial Hummingbird Algorithm (AHA) using three common PEMFC modules. Additionally, a comparative analysis is performed against previously published methods and newly developed optimizers like Particle Swarm Optimizer (PSO), Grasshopper Optimization Algorithm (GOA), Atom Search Optimization (ASO), Grey Wolf Optimizer (GWO), and parental algorithm i.e., Artificial Hummingbird Algorithm (AHA). The findings showcase the proposed approach's efficacy relative to existing methods and state-of-the-art optimizers. The two models are taken for the checking of reliability and performance of the PEMFC. The results are also compared with the Non-Parametric tests and it is concluded that the proposed algorithm is far better than the rest of the compared algorithms in both the models.
Keywords:
Proton exchange membrane fuel cell
Optimization
Hydrogen
Enhanced algorithm
Sum of square error
Benchmark test function
Non-parametric test
Journal
IF:
8.3
Papers:
5.4W
Citations:
23.1W
Organization
View more organizations