Water Management in Proton Exchange Membrane Fuel Cell Based on Actor Critic Learning Control

Due to the complexity of modeling water management system and difficulties of online measuring humidity inside the PEM fuel cell stack, the actor critic learning controller is proposed by using the available measurements which are stack voltage and the difference of stack voltage between current sample time and last sample time. In this method approximation of value function is based on least squares temporal-difference, and approximations of actor model and process model are based on local linear regression. Simulation results show that actor critic learning control can maintain water balance inside the fuel cell stack and achieve the maximum the stack voltage under the different operating conditions.

[1]  Aimy Bazylak,et al.  Liquid water visualization in PEM fuel cells: A review , 2009 .

[2]  Jérôme Dillet,et al.  Local potential evolutions during proton exchange membrane fuel cell operation with dead-ended anode – Part II: Aging mitigation strategies based on water management and nitrogen crossover , 2017 .

[3]  Shohji Tsushima,et al.  Measurement of liquid water content in cathode gas diffusion electrode of polymer electrolyte fuel cell , 2010 .

[4]  Fernando Tadeo,et al.  Model-free control based on reinforcement learning for a wastewater treatment problem , 2011, Appl. Soft Comput..

[5]  Shohji Tsushima,et al.  In-situ visualization of liquid water in an operating PEMFC by soft X-ray radiography , 2010 .

[6]  Mark W. Verbrugge,et al.  A Mathematical Model of the Solid‐Polymer‐Electrolyte Fuel Cell , 1992 .

[7]  Wei-Mon Yan,et al.  Effective schemes to control the dynamic behavior of the water transport in the membrane of PEM fuel cell , 2005 .

[8]  Alfredo Iranzo,et al.  Validation of cell voltage and water content in a PEM (polymer electrolyte membrane) fuel cell model using neutron imaging for different operating conditions , 2016 .

[9]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[10]  Sirivatch Shimpalee,et al.  Prediction of transient response for a 25-cm2 PEM fuel cell , 2007 .

[11]  Omar Imine,et al.  Simulation of species transport and water management in PEM fuel cells , 2011 .

[12]  Cheng-Ching Yu,et al.  Operation-relevant modeling of an experimental proton exchange membrane fuel cell , 2007 .

[13]  T. Springer,et al.  Polymer Electrolyte Fuel Cell Model , 1991 .

[14]  Thirumalachari Sundararajan,et al.  The effect of flow distributors on the liquid water distribution and performance of a PEM fuel cell , 2012 .

[15]  Murat Arcak,et al.  An algorithm for estimation of membrane water content in PEM fuel cells , 2006 .