Abstract
As carriers of green energy, proton exchange membrane fuel cells (PEMFCs) and photovoltaic (PV) cells are complex and nonlinear multivariate systems. For simulation analysis, optimization control, efficacy prediction, and fault diagnosis, it is crucial to rapidly and accurately establish reliability modules and extract parameters from the system modules. This study employed three types of particle swarm optimization (PSO) algorithms to find the optimal parameters of two energy models by minimizing the sum squared errors (SSE) and roots mean squared errors (RMSE). The three algorithms are inertia weight PSO, constriction PSO, and momentum PSO. The obtained calculation results of these three algorithms were compared with those obtained using algorithms from other relevant studies. This study revealed that the use of momentum PSO enables rapid convergence (under 30 convergence times) and the most accurate modeling and yields the most stable parameter extraction (SSE of PEMFC is 2.0656, RMSE of PV cells is 8.839 · 10−4). In summary, momentum PSO is the algorithm that is most suitable for system parameter identification with multiple dimensions and complex modules.
Highlights
Since the start of the Industrial Revolution, humans began to replace animals with vehicles and ships as their primary means of transportation
The operating data of NedStackPS6 system can be found in Reference [31], which consists of 65 cells
Three advanced particle swarm optimization (PSO) algorithms were adopted to improve upon the search efficiency of the original PSO and the accuracy of the optimal solution
Summary
Since the start of the Industrial Revolution, humans began to replace animals with vehicles and ships as their primary means of transportation. It is unable to analyze certain system parameters and can only represents the variable relationship between input and output—and poses a hindrance to the design of an optimal system Another method is semiempirical modeling, a mathematical model based on the PEMFC reaction mechanism [6,7,8]: studies have indicated that these mathematical models constructed by deriving experiment results are highly stable and efficient. Some swarm optimization algorithms that have been employed to estimate PV cell parameters include particle swarm optimization (PSO) [27], artificial bee colony [28], and whale optimization algorithms [29] Such algorithms typically yield more satisfactory estimation results than deterministic methods. After 30 independent runs, the algorithm are compared in terms of the fitness values
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have