Chromatographic processes are typically used for the separation and purification of products across different industries. They are described by periodic operating profiles that can make their monitoring and online optimization a challenging task. This is further exacerbated by the complexities of the mathematical formulations, comprising nonlinear partial differential and algebraic equations (PDAEs).
In response to these challenges, recent advances in data-driven modeling are a promising alternative, paving the way to fit-for-purpose models of reduced computational cost. Surrogate models have been shown to reduce computational complexity, while retaining good predictive accuracy. In their AIChE Journal article, “Assessment of data-driven modeling approaches for chromatographic separation processes,” Foteini Michalopoulou and Maria Papathanasiou (Imperial College London) explore the development and application of artificial neural network (ANN)-based surrogate models for the continuous, multicolumn countercurrent solvent gradient purification (MCSGP) process. MCSGP is commonly used for the purification of biopharmaceuticals, such as monoclonal antibodies, where a high degree of precision is required to separate valuable...
Would you like to access the complete CEP Article?
No problem. You just have to complete the following steps.
You have completed 0 of 2 steps.
-
Log in
You must be logged in to view this content. Log in now.
-
AIChE Membership
You must be an AIChE member to view this article. Join now.
Copyright Permissions
Would you like to reuse content from CEP Magazine? It’s easy to request permission to reuse content. Simply click here to connect instantly to licensing services, where you can choose from a list of options regarding how you would like to reuse the desired content and complete the transaction.