In this work we present a framework to generate surrogate models from rigorous process models embedded in a modelling environment or a process simulator. These unit operations (i.e. process flowsheet subsystems) are treated as black-box models to generate data for fitting and deriving the surrogate. Further, the methodology includes the formulation of a superstructure optimization problem and solving it to identify the optimal process flowsheet structure and point of operation from the possible alternatives. The superstructure optimization incorporates selection and interconnection of each surrogate and multi-objective optimization in respect to total annual cost and environmental impact. In this paper we highlight the surrogate building step of the methodology with a rigorous counter-current spray column model and assess the performance of different surrogate modelling methods.
|Conference||13th International Symposium on Process Systems Engineering (PSE 2018)|
|Period||01/07/2018 → 05/07/2018|
|Series||Computer Aided Chemical Engineering|
- Polynomial Chaos Expansion
- Gaussian Process Regression
- Superstructure Generation