Fuel-cell parameter estimation based on improved gorilla troops technique.

Area of Science:

• Energy Systems Engineering
• Computational Intelligence
• Electrochemical Engineering

Background:

• Accurate parameter extraction for proton exchange membrane fuel cells (PEMFCs) is crucial for reliable current/voltage (I/V) curve prediction.
• Existing optimization techniques can struggle with local minima and inefficient search space exploration in PEMFC modeling.

Purpose of the Study:

• To propose and validate an advanced version of the improved gorilla troops technique (IGTT) for precise PEMFC parameter estimation.
• To enhance the exploitation phase and prevent local minima entrapment in optimization algorithms for PEMFC models.

Main Methods:

• Developed an improved gorilla troops technique (IGTT) incorporating a Tangent Flight Strategy (TFS) for parameter extraction.
• Applied and evaluated IGTT on BCS 500W and Modular SR-12 PEMFC stacks under varying temperature and pressure conditions.
• Compared IGTT performance against Supply Demand Optimization (SDO), Flying Foxes Optimizer (FFO), Red Fox Optimizer (RFO), original GTT, Grey Wolf Algorithm (GWA), and Particle Swarm Optimization (PSO) on benchmark functions and PEMFC models.

Main Results:

• The proposed IGTT significantly outperformed original GTT, GWA, and PSO on 2017 CEC benchmark functions.
• IGTT achieved highly competitive and minimal Sum of Squared Errors (SSE) values of 0.0117 for BCS 500W and 0.000142 for SR-12 PEMFC stacks.
• IGTT demonstrated superior performance over GTT, SDO, FFO, and RFO in achieving the lowest SSE and standard deviation (STD) for PEMFC parameter identification.

Conclusions:

• The IGTT is a robust and effective metaheuristic algorithm for accurate PEMFC parameter extraction.
• The enhanced optimization strategy of IGTT provides superior convergence and accuracy compared to existing methods.
• This work offers a viable and highly competitive framework for advancing PEMFC modeling and performance analysis.