Crystallization remains one of the most widely used operations in pharmaceutical manufacturing, serving as both a purification step and a way to tune critical properties of the solid drug product. Crystal size and shape have major effects on filtration, powder flow, dissolution, tabletability, and overall manufacturability. Yet these attributes are highly sensitive to nonlinear interactions among cooling strategy, supersaturation, seeding, nucleation, and growth. Traditional population balance models (PBMs) simplify this complexity by assuming a single particle dimension (usually the spherical-equivalent diameter) and a fixed shape factor. Although practical, that simplification can overlook the evolution of crystal morphology, which is a key limitation when dealing with rod- or plate-like particles that are common among organic compounds.
In their AIChE Journal article, “2D Population Balance Modeling and ML-Based Multi-Objective Optimization for the Crystallization Process of Resveratrol,” Zoltan K. Nagy (Purdue Univ.) and coworkers demonstrate how two-dimensional PBMs, combined with machine-learning (ML)-accelerated optimization, can provide new insight into the simultaneous evolution of crystal size and...
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.