Benchmarking of hydrogen selective membranes: Experimental and modelling approach to compare membrane performance

Precombustion CO2 capture can be feasible with mature palladium-based membranes in modules. Before moving on to demonstration, benchmarking of membranes is a crucial step in their introduction. The strategy presented here, consisting of matching results from experiments and model development, will be a valuable tool in benchmarking membrane performance. Using experiments with pure hydrogen feed and no sweep, the permeation of hydrogen through the metallic palladium layer was accurately fitted with a standard permeation equation (1) with Q and n as regressed parameters. The pressure drop in the membrane support was included but was found to be small (14 kPa). Hydrogen-nitrogen separation experiments without sweep gas could be predicted by a 2D laminar flow convection and diffusion model. Thus, convective and diffusive transport of hydrogen and inert in the modules was successfully accounted for by the module model. Experiments with nitrogen sweep gas have shown significant resistances in the membrane support. These were predicted by the dusty gas model to be both a small pressure drop and a rather large mole fraction gradient in the support layer, the latter being far more important than the former. The derived model allows to quantify, as a function of operating conditions, the intrinsic and external mass transfer resistances. In order to make the final step toward full use of the model in benchmarking of membranes the model is currently be extended to incorporate the effect of inhibition of syngas components. The final model will be used to run selected cases and the results will be validated with hydrogen permeation results from experiments in syngas. The model will also be used for predicting membrane performance at commercial scale.