Research On Fault Diagnosis Method Of The Air Management System In Fuel Cell Engine

Compared with the traditional internal combustion engine,hydrogen fuel cell engine has outstanding advantages.Fuel cell engine has many advantages,such as no pollution and low noise,and is considered as one of the new energy sources with the greatest potential for future development and the most environmental protection.In the proton exchange membrane fuel cell engine system,the air management system is mainly to provide sufficient clean air to the fuel cell engine reactor to meet the needs of the electrochemical reaction of the fuel cell engine.The failure of the air management system will cause the reactor to fail to carry out the electrochemical reaction normally,leading to the decrease of the reaction rate of the fuel cell reactor,resulting in a fault state,and even damage to the reactor.It is of great significance to study the fault diagnosis method of fuel cell engine air management system for ensuring the normal operation of fuel cell engine and improving the reliability and stability of fuel cell engine during operation.In this paper,the working principle,typical fault mechanism and fault diagnosis method of proton exchange membrane fuel cell engine air management system are studied systematically.The main research contents are as follows:(1)Through the research and analysis of related literature of fuel cell engine,the composition and working principle of fuel cell engine air management system are analyzed,and the fault characteristics of fuel cell engine and typical fault mechanism of air management system are deeply studied.(2)The model construction method of fuel cell engine air management system is studied.Based on AMESIM(Advanced Modeling Environment for performing Simulation of engineering systems),the fault diagnosis model of fuel cell engine air management system is established.The operating conditions of fuel cell engine were set according to the working conditions specified by NEDC and a step power requirement,and the simulation test was carried out.The error of the simulation results was less than 10% compared with the test results,which verified the accuracy of the established model.(3)Based on the air management system model,typical faults and fault diagnosis methods of the air management system were studied.By setting faults on the model and extracting fault characteristics,a fault diagnosis method of the fuel cell air management system based on BP neural network was proposed.The simulation experiment data of Gaussian noise was added to the simulation data to verify the model diagnosis effect.This paper provides a fault diagnosis method for fuel cell engine air management system.