Physics-informed neural networks to solve lumped kinetic model for chromatography process
Journal of Chromatography A · 2023-10 · 1708 · 464346
DOI: 10.1016/j.chroma.2023.464346 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Chromatography A, 2023-10. Verfasst von Si-Yuan Tang und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Chemical and Biological Engineering, Zhejiang University, Hangzhou 310058, China; Manufacturing Science and Technology, Global Manufacturi…. Hauptthemen laut MEDLINE: Neural Networks, Computer, Chromatography. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China.
Abstract (Originalsprache)
Numerical method is widely used for solving the mechanistic models of chromatography process, but it is time-consuming and hard to response in real-time. Physics-informed neural network (PINN) as an emerging technology combines the structure of neural network with physics laws, and is getting noticed for solving physics problems with a balanced accuracy and calculation speed. In this research, a proof-of-concept study was carried out to apply PINN to chromatography process simulation. The PINN model structure was designed for the lumped kinetic model (LKM) with all LKM parameters. The PINN structure, training data and model complexity were optimized, and an optimal mode was obtained by adopting an in-series structure with a nonuniform training data set focusing on the breakthrough transition region. A PINN for LKM (LKM-PINN) consisting of four neural networks, 12 layers and 606 neurons was then used for the simulation of breakthrough curves of chromatography processes. The LKM parameters were estimated with two breakthrough curves and used to infer the breakthrough curves at different residence times, loading concentrations and column sizes. The results were comparable to that obtained with numerical methods. With the same raw data and constraints, the average fitting error for LKM-PINN model was 0.075, which was 0.081 for numerical method. With the same initial guess, the LKM-PINN model took 160 s to complete the fitting, while the numerical method took 7 to 72 min, depending on the fitting settings. The fitting speed of LKM-PINN model was further improved to 30 s with random initial guess. Thus, the LKM-PINN model developed in this study is capable to be applied to real-time simulation for digital twin.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Chemical and Biological Engineering, Zhejiang University, Hangzhou 310058, China; Manufacturing Science and Technology, Global Manufacturing, WuXi Biologics, Wuxi 214000, China.
- Manufacturing Science and Technology, Global Manufacturing, WuXi Biologics, Wuxi 214000, China.
- College of Chemical and Biological Engineering, Zhejiang University, Hangzhou 310058, China.
- College of Chemical and Biological Engineering, Zhejiang University, Hangzhou 310058, China. Electronic address: lindq@zju.edu.cn.
Förderung
- National Natural Science Foundation of China
- National Key Research and Development Program of China
Zitieren
APA
Tang, S. Y., Yuan, Y. H., Chen, Y. C., Yao, S. J., Wang, Y., & Lin, D. Q. (2023). Physics-informed neural networks to solve lumped kinetic model for chromatography process. Journal of Chromatography A, 1708, 464346. https://doi.org/10.1016/j.chroma.2023.464346
Vancouver
Tang SY, Yuan YH, Chen YC, Yao SJ, Wang Y, Lin DQ. Physics-informed neural networks to solve lumped kinetic model for chromatography process. Journal of Chromatography A. 2023;1708:464346. doi:10.1016/j.chroma.2023.464346
BibTeX
@article{Tang2023,
author = {Tang, Si-Yuan and Yuan, Yun-Hao and Chen, Yu-Cheng and Yao, Shan-Jing and Wang, Ying and Lin, Dong-Qiang},
title = {Physics-informed neural networks to solve lumped kinetic model for chromatography process},
journal = {Journal of Chromatography A},
year = {2023},
volume = {1708},
pages = {464346},
doi = {10.1016/j.chroma.2023.464346}
}
EUVIMED