An intelligent system of catalyst layer deposition for proton exchange membrane fuel cell

Abstract

Reliability and durability are two main factors influencing fuel cell commercialization. The membrane electrode assembly (MEA) is the key component of the proton exchange membrane (or polymer electrolyte membrane) (PEM) fuel cell. The performance of MEA is primarily impacted by the structure of the catalytic layer. Various methods for coating catalyst material onto the membrane and the gas diffusion layer (GDL) have been surveyed. Various parameters to be controlled to optimize the catalytic layer characteristics have been discussed. There is no direct mathematical model available correlating the two most important quality factors, the thickness and evenness, and the machine control parameters, traveling speed of the spraying nozzle and the distance between two paths. High‐level intelligent control architecture for the auto‐spray process is proposed in this paper to automatically generate the appropriate spray trajectory and speed in real‐time for the low‐level controller to achieve a homogeneous catalyst layer coating (evenness and thickness). The method proposed in this paper provides a non computational high‐level linguistic control without use of an explicit mathematical model while the coupling dynamics exist.