[HTML][HTML] A review and perspective on hybrid modeling methodologies

AM Schweidtmann, D Zhang, M von Stosch - Digital Chemical Engineering, 2024‏ - Elsevier
The term hybrid modeling refers to the combination of parametric models (typically derived
from knowledge about the system) and nonparametric models (typically deduced from data) …

Hybrid modeling in bioprocess dynamics: Structural variabilities, implementation strategies, and practical challenges

B Mahanty - Biotechnology and Bioengineering, 2023‏ - Wiley Online Library
Hybrid modeling, with an appropriate blend of the mechanistic and data‐driven framework,
is increasingly being adopted in bioprocess modeling, model‐based experimental design …

Exploring the potential of time-series transformers for process modeling and control in chemical systems: an inevitable paradigm shift?

N Sitapure, JSI Kwon - Chemical Engineering Research and Design, 2023‏ - Elsevier
The last two years have seen groundbreaking advances in natural language processing
(NLP) with the advent of applications like ChatGPT, Codex, and ChatSonic. This revolution …

CrystalGPT: Enhancing system-to-system transferability in crystallization prediction and control using time-series-transformers

N Sitapure, JSI Kwon - Computers & Chemical Engineering, 2023‏ - Elsevier
For prediction and real-time control tasks, machine-learning (ML)-based digital twins are
frequently employed. However, while these models are typically accurate, they are custom …

Deep hybrid model‐based predictive control with guarantees on domain of applicability

MSF Bangi, JSI Kwon - AIChE Journal, 2023‏ - Wiley Online Library
A hybrid model integrates a first‐principles model with a data‐driven model which predicts
certain unknown dynamics of the process, resulting in higher accuracy than first‐principles …

Introducing hybrid modeling with time-series-transformers: A comparative study of series and parallel approach in batch crystallization

N Sitapure, J Sang-Il Kwon - Industrial & Engineering Chemistry …, 2023‏ - ACS Publications
Given the hesitance surrounding the direct implementation of black-box tools due to safety
and operational concerns, fully data-driven deep-neural-network (DNN)-based digital twins …

[HTML][HTML] Physics-informed machine learning for MPC: Application to a batch crystallization process

G Wu, WTG Yion, KLNQ Dang, Z Wu - Chemical Engineering Research …, 2023‏ - Elsevier
This work presents a framework for develo** physics-informed recurrent neural network
(PIRNN) models and PIRNN-based predictive control schemes for batch crystallization …

Achieving optimal paper properties: A layered multiscale kMC and LSTM-ANN-based control approach for kraft pul**

P Shah, HK Choi, JSI Kwon - Processes, 2023‏ - mdpi.com
The growing demand for various types of paper highlights the importance of optimizing the
kraft pul** process to achieve desired paper properties. This work proposes a novel …

Physics-informed online machine learning and predictive control of nonlinear processes with parameter uncertainty

Y Zheng, Z Wu - Industrial & Engineering Chemistry Research, 2023‏ - ACS Publications
In this work, we present a physics-informed recurrent neural network (PIRNN)-based
modeling approach for nonlinear dynamic systems with parameter uncertainty. Physics …

Predictive control of reactor network model using machine learning for hydrogen-rich gas and biochar poly-generation by biomass waste gasification in supercritical …

C Wang, C Hu, Y Zheng, H **, Z Wu - Energy, 2023‏ - Elsevier
Supercritical water gasification (SCWG) technology can convert biomass into hydrogen rich
gas and biochar. Fluidized bed reactor is promising for the industrialization of this …