Parameter extraction of fuel cells using hybrid interior search algorithm

Abstract

Summary Precise modelling of fuel cells is very important for understanding their functioning. In this work, an application of hybrid interior search algorithm (HISA) is proposed to extract the parameters of fuel cells for their electromechanical equations based on nonlinear current‐voltage characteristics. Proposed hybridised algorithm has been developed using evolutionary mutation and crossover operators so as to enhance the modelling capability of interior search algorithm (ISA). To assess the modelling performance of HISA, parameter extraction of two types of fuel cell models, namely, proton exchange membrane fuel cell (PEMFC) and solid oxide fuel cell (SOFC) have been considered. Modelling performance of HISA, assessed using mean squared error between computed and experimental data, is found to be superior to ISA and several other recently reported prominent optimisation methods. Based on the presented intensive simulation investigations, it is concluded that HISA improves the performance of the basic ISA in terms of fitter solutions, robustness, and convergence rate and therefore offers a promising optimisation technique for parameter extraction of fuel cells.

Observations on the Parameter Estimation Problem of Polymer Electrolyte Membrane Fuel Cell Polarization Curves

“…This is important in order to stress the performance of the novel optimization algorithm in different types of problems and to allow others to repeat the results. In many studies, the authors have also decided to implement several different optimizers or variants in order to establish a fair comparison of results; references with at least three different algorithms are as follows: , , , , , . However, it should be kept in mind that the fine‐tuning of the optimization methods will also have an effect on the results, especially in terms of computational performance.…”

“…In contrast, some of the reviewed studies fail to take this into consideration, and even compare the objective function values gained with different parameter sets (i.e., model structures), parameter search space, and even with different objective functions. Some of the most recent studies have noticed the missing tabulated data sets and have presented the data used [9,13,36,53,[64][65][66]. Also, the effect of the measurement errors is covered in [56,59,62], where a noise component was added to the data.…”

Control‐oriented estimation of the exchange current density in PEM fuel cells via stochastic filtering

“…The NARMAX models were introduced as an extension of the classical linear auto-regressive models. 36,37 The general NARMAX structure, Equation (10), is composed of a vector of regressors of the outputs y(t), inputs u(t) and estimation error e(t), a vector of constant coefficients Θ, and a nonlinear function F(Á). The parameters n a , n b and n c define the order of delay of the output, input and error regressors respectively.…”

Parameters determination of proton exchange membrane fuel cell stack electrical model by employing the hybrid water cycle moth‐flame optimization algorithm

“…Past the last some decades, several the writing has ventured to implement various heuristic methods to determine the parameters of PEMFCs 9‐30 . Based on those works, we can notice that the results obtained to solve the problem of identifying FC parameters using meta‐heuristic methods are competitive in terms of performance and reliability.…”