Iterative learning control of a PEM fuel cell system during purge processes

摘要

Polymer electrolyte membrane fuel cell systems convert chemical energy from hydrogen into electrical power via a reaction with oxygen. During the chemical reaction diffused nitrogen and water condensate cumulate in the anode volume and influence the chemical reaction. For an efficient chemical reaction purge processes are necessary. The temporary opening of the exhaust valve allows these purge process, which removes the water and nitrogen. For the multiple times executed purge procedure an Iterative Learning Control approach of the anode pressure is used. For this purpose, the nonlinear characteristics of the FC system model are transferred into discrete-time, time-variant, linear state-space models to create learning filters and use in Optimal Iterative Learning Control structure. All experiments were verified on a test bench with a 4.4 kW PEM fuel cell.