Process performance maps for membrane-based CO2 separation using artificial neural networks

Membrane-based gas separation processes are currently being implemented at different scales for several industrial applications. The optimal design of such processes, which is key importance their large-scale commercial deployment, has been extensively studied through parametric analyses and optimisation procedures. Nevertheless, the applicability methodologies generally limited by large computational time effort they require. In this work, surrogate models based on artificial neural networks developed to circumvent lengthy a one-stage two-stage cascade membrane-based process. 200 ms, model generates Pareto front that describes trade-off between process specific electricity consumption productivity given input data, i.e., membrane material properties, feed composition target. Whereas applicable any binary mixture, here its features illustrated creating performance maps post-combustion CO2 capture. Such provide valuable insights on: (i) attainable regions in term recovery purity, (ii) impact material, target fronts operating conditions.