.png){kind=icon}
.png){kind=icon}
Return
Physics-Informed Neural Networks to Solve the Equilibrium Dispersive Model: Digital-Twin Application
.png){kind=icon}
PRE
AI
M
F
DOI：10.1016/j.jtice.2026.106888.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• PINN solves the HPLC EDM with high accuracy and fast computation. • It outperforms CADET for chromatographic concentration profile prediction. • Robust prediction is achieved across varied HPLC operating conditions. • In-series multi-network PINN captures breakthrough dynamics effectively. • Training with 200 data points gives accurate predictions for diverse conditions.
Keywords:
Physics-Informed Neural Networks
Equilibrium Dispersive Model
High-Performance Liquid Chromatography
Surrogate modeling
Digital twin
Journal
IF:
6.3
Papers:
6.3K
Citations:
2.1W
Organization
No organization information available
Cited Papers