Modeling And Multi-objective Optimization Of Fuel Cell System Based On Meta-heuristic Algorithm

With limited fossil energy reserves,large energy demand and deteriorating environmental problems,people pay more and more attention to the development and utilization of alternative clean energy.Hydrogen energy is regarded as the energy with the most development potential in the 21 st century due to its high energy density and green and low carbon characteristics.Under the current "two-carbon" background,it is of great significance to develop technologies for efficient and comprehensive utilization of hydrogen energy.As an efficient hydrogen energy conversion device,proton exchange membrane fuel cells have been widely used in various fields such as transportation,portable power supply,and stationary power generation.Optimizing the fuel cell system to make it operate under suitable working conditions will help to improve the efficiency of hydrogen energy utilization.In this paper,the proton exchange membrane fuel cell system is taken as the research object,and the related researches on fuel cell system modeling and multi-objective optimization are carried out.The main research work of this paper is as follows:The structure and working principle of the proton exchange membrane fuel cell were analyzed,and the lumped parameter model of the fuel cell system was established based on the internal electrode reaction of the cell.The parameters are used as the input of the model,and the polarization curve of the simulation output of the model is obtained,which is compared with the measured data of the specific fuel cell.In order to improve the accuracy of the proton exchange membrane fuel cell model,an improved meta-heuristic algorithm is considered to optimize the identification of the model parameters.Firstly,the principle of traditional meta-heuristic algorithms such as genetic algorithm GA,differential evolution algorithm DE,particle swarm algorithm PSO,etc.are analyzed.On this basis,the gray wolf optimization algorithm GWO is selected as the object of algorithm optimization to balance the optimization algorithm Aiming at the ability of global exploration and local convergence,an improved IGWO algorithm based on parameters is proposed.The performance of the proposed algorithm is tested based on8 benchmark functions,and the test results verify the effectiveness and superiority of the improved gray wolf optimization algorithm IGWO.Based on the proposed IGWO algorithm,the parameters of the proton exchange membrane fuel cell model are estimated,and the optimization objective function is to minimize the sum of the squares of errors between the fuel cell model data and the measured data.Based on two fuel cell examples—a 250 W fuel cell stack and Ballard Mark V fuel cell stack to verify the model after parameter optimization and identification,the results show that the optimized fuel cell model has high accuracy,and the polarization curve output by the model simulation has a high degree of agreement with the experimental data points.Based on the proton exchange membrane fuel cell model after parameter optimization and identification,the energy efficiency and output power model of the fuel cell system is established.Sensitivity analysis of the operating parameters of the fuel cell system is carried out using statistical methods such as orthogonal experimental design and variance analysis,and the operating parameters that have the most significant impact on system performance are determined as decision variables for multi-objective optimization.Taking the maximum energy efficiency and maximum output power of the fuel cell system as the optimization objective function,the improved multi-objective gray wolf optimization algorithm MOGWO is used to optimize the efficiency and power of the fuel cell system,and a set of Pareto optimal solutions are obtained.According to a certain compromise principle to calculate the optimal operating point of the fuel cell and the corresponding optimal operating parameters.The output power of the optimal operating point of the fuel cell is290.36 W,and the energy efficiency is 33.02%,which is 14.13% and 18.27% higher than the output power and energy efficiency of the system before multi-objective optimization,respectively.