.png){kind=icon}
.png){kind=icon}
Return
Efficient data-driven modeling and multi-objective optimization of batch crystallization processes using integrated neural network
.png){kind=icon}
PRE
AI
B
刘
M
Y
J
Z
R
DOI：10.1016/j.jprocont.2026.103721.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• INN-based modeling maps the nonlinear relationship between primary operating conditions and 2-D crystal size distribution. • Efficient DoE via sensitivity analysis yields informative INN modeling data while minimizing experiment numbers. • Three MOO programs optimize operating conditions to balance product yield, CSD concentration, and crystal aspect ratio (AR). • A comprehensive loss function related to product CSD prediction errors optimizes the INN model hyperparameters. • L-glutamic acid experiments validate enhanced MOO and reduce modeling experiments by about 50% compared to traditional DoE.
Keywords:
Integrated Neural Network
Batch Crystallization
Multi-Objective Optimization
Crystal Size Distribution
Experimental Design
Journal
IF:
3.9
Papers:
3.4K
Citations:
7.3K
Organization
Cited Papers