.png){kind=icon}
.png){kind=icon}
Return
Digital design of crystallization processes using statistical machine learning
.png){kind=icon}
PRE
AI
Y
Y
N
C
Y
C
Z
DOI：10.1016/j.compchemeng.2025.109518.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This study presents a generic statistical machine learning (ML)-driven modeling workflow for designing crystallization processes, serving as a practical alternative in situations where traditional mechanistic population-balance modeling approaches are impractical. Key highlights of the proposed workflow include synthetic data augmentation to reduce dependency on extensive experimental datasets; the incorporation of active learning strategies to iteratively suggest experimental conditions and refine experimental datasets; and the successful deployment of ML models within the Quality-by-Digital-Design (QbDD) framework. The effectiveness of the proposed approach is demonstrated through two case studies: (1) an in-silico study involving an agrochemical compound, and (2) an experimental case study with an industrial pharmaceutical compound. ML models trained in these scenarios achieved prediction errors below 10% when predicting critical quality attributes (CQAs). These models subsequently enabled deterministic and probabilistic design space analyses, followed by model-based process optimization, and were confirmed through experimental validation. While the approaches are exemplified using crystallization processes, it provides a generic and systematic framework for the ML model, development applicable to reactions and other complex process systems.
Journal
C
IF:
3.9
Papers:
8.1K
Citations:
1.7W
Organization
Cited Papers