Research On Modeling And Optimal Control Of PEMFC Fuel Cell System

Energy security and environmental protection are two key issues in today’s human society.Proton Exchange Membrane Fuel Cell(PEMFC)is a low-temperature fuel cell.Because of its high energy density,simple structure,and zero emissions,it has huge development potential and application prospects.PEMFC system is a nonlinear,multivariable,multi input and output complex system,and its control objectives are safety,stability and efficient operation.The research of PEMFC mainly focuses on the establishment of models and the control of subsystems,which is very important for improving the power generation efficiency and prolonging the service life of fuel cells.At present,the domestic related research is still in the laboratory stage,especially in the aspect of control,there are still many problems to be solved.This paper studies the modeling and optimal control of the PEMFC system.The main contents are as follows:(1)Introduced the research background of PEMFC,including its production,characteristics and development.The research status of PEMFC system modeling and optimization control is analyzed,and the research focus of this paper is put forward.(2)Under certain assumptions,based on PEMFC’s electrochemical properties,gas thermodynamic properties,mass conservation law,etc.,a PEMFC stack model and a air supply system model are established.It provides a certain theoretical basis for the subsequent establishment of the stack model based on the improved BP neural network and PEMFC system control design.(3)Due to the complex relationship between the output characteristics of the PEMFC stack and the operating parameters,a PEMFC stack model based on the BP neural network is established.The Bayesian regularization algorithm is used to improve the BP neural network,which better solves the over-fitting problem of high training accuracy and low prediction accuracy in the traditional BP neural network.The simulation verified that the trained stack model has certain advantages in accuracy and stability.Even in the case of a reduced number of training samples,good generalization ability and high stability can be maintained.(4)Aiming at the soft output characteristics of PEMFC,the DC/DC system of PEMFC was built.The working conditions and control rules of dual sources DC/DC containing fuel cell and battery were analyzed.A dual outer loop control strategy based on fuel cell voltage and battery voltage was adopted.The dual outer loop control structure realizes that when the battery terminal voltage is too high or the fuel cell output current is too large,the output current of the fuel cell is limited.It avoids overcharging of the battery and overdischarging of the fuel cell,and improves the safety and reliability of the system.And the effectiveness of the proposed method is verified by simulation.(5)Considering that the power consumption of the air compressor in the PEMFC system is the largest proportion of all auxiliary equipment.The perturbation and observation(P&O)and DC/DC energy management linkage method is adopted to control the air compressor terminal voltage to maintain the system near the maximum efficiency point.It shortens the time required to search for the maximum system efficiency point,effectively avoids the oxygen excess ratio that may be out of control when the load power changes,and simulation verifies the correctness of the control method.