Efficient estimation of proton exchange membrane fuel cells parameters using a hybrid swarm intelligent algorithm

Area of Science:

• * Energy Systems Engineering
• * Computational Intelligence
• * Electrochemical Engineering

Background:

• * Accurate parameter identification is crucial for optimizing proton exchange membrane fuel cell (PEMFC) performance.
• * Nature-inspired optimization algorithms are increasingly applied to complex engineering problems.
• * Existing methods for PEMFC parameter identification face challenges in accuracy and convergence speed.

Purpose of the Study:

• * To introduce a novel hybrid optimization algorithm, the Gray Particle Cuckoo (GPC), for PEMFC parameter identification.
• * To evaluate the GPC algorithm's effectiveness on various commercial PEMFC models.
• * To compare the GPC algorithm's performance against other metaheuristic algorithms.

Main Methods:

• * Development of the hybrid Gray Particle Cuckoo (GPC) algorithm, integrating Grey Wolf Optimizer (GWO), Particle Swarm Optimization (PSO), and Cuckoo Search (CS).
• * Fitness function defined as the sum of squared errors (SSE) between estimated and actual cell voltages.
• * Validation using four commercial PEMFC stacks (BCS500-W, Ballard Mark V, Temasek, NedStack PS6) under varying conditions and benchmark datasets (CEC 2019).

Main Results:

• * The GPC algorithm achieved the lowest SSE values across all tested PEMFC models, demonstrating superior accuracy.
• * Performance metrics including MSE, IAE, MBE, MAE, and RMSE confirmed the GPC algorithm's optimal solution quality and faster convergence.
• * Statistical tests validated the GPC algorithm's efficacy and robustness compared to other metaheuristic algorithms.

Conclusions:

• * The proposed hybrid GPC algorithm is a highly effective tool for accurate parameter identification in PEMFCs.
• * The GPC algorithm offers significant advantages in solution quality and convergence speed over existing optimization techniques.
• * This research provides a robust method for advancing PEMFC modeling and performance optimization.