Optimal parameter estimation of proton exchange membrane fuel cells utilizing training-imitation strategy and coronavirus mask protection optimizer

Abstract

The precision of the electrochemical characteristic model for proton exchange membrane fuel cells (PEMFCs) is essential in assessing their performance. Owing to the lack of accurate parameter information for PEMFC, parameter evaluation of PEMFC has become a research hot spot. A novel optimization algorithm, namely training-imitation strategy-assisted coronavirus mask protection optimizer (TISCMPO), is proposed to identify the PEMFC parameters. In TISCMPO, a training-imitation strategy (TIS) is performed to enhance the convergence performance. The sum of squared errors of the estimated voltage and current voltage is selected as the optimization objective in this work. The performance of TISCMPO is verified and compared to various state-of-the-art optimization algorithms using various test cases. Results show that the TISCMPO is more competitive than other optimizers in addressing the engineering problem. Further, the statistical results show that TISCMPO can achieve promising results, which guarantees the reliability and robustness.