[HTML][HTML] Formulating data-driven surrogate models for process optimization

R Misener, L Biegler - Computers & Chemical Engineering, 2023 - Elsevier
Recent developments in data science and machine learning have inspired a new wave of
research into data-driven modeling for mathematical optimization of process applications …

[HTML][HTML] Hybrid analytical surrogate-based process optimization via Bayesian symbolic regression

S Jog, D Vázquez, LF Santos, JA Caballero… - Computers & Chemical …, 2024 - Elsevier
Modular chemical process simulators are widespread in chemical industries to design and
optimize production processes with sufficient accuracy. However, convergence issues and …

Branch-and-Model: a derivative-free global optimization algorithm

K Ma, LM Rios, A Bhosekar, NV Sahinidis… - Computational …, 2023 - Springer
This paper presents a novel derivative-free global optimization algorithm Branch-and-Model
(BAM). The BAM algorithm partitions the search domain dynamically, builds surrogate …

Efficient trust region filter modeling strategies for computationally expensive black-box optimization

R Liang, Y Han, H Hu, B Chen, Z Yuan… - Computers & Chemical …, 2024 - Elsevier
The study and application of contemporary optimization techniques considerably enhance
the efficiency of chemical research and manufacturing. With the dynamic progression of …

[HTML][HTML] Data-efficient surrogate modeling of thermodynamic equilibria using Sobolev training, data augmentation and adaptive sampling

J Winz, S Engell - Chemical Engineering Science, 2024 - Elsevier
Modern thermodynamic models, such as the PC-SAFT equation of state, are very accurate
but also computationally intensive, which limits their applicability to process design …

Data‐driven integrated design of solvents and extractive distillation processes

Z Wang, T Zhou, K Sundmacher - AIChE Journal, 2023 - Wiley Online Library
As property and process models with many variables need to be considered, integrated
computer‐aided molecular and process design (CAMPD) problems are computationally …

Efficient constraint learning for data-driven active distribution network operation

G Chen, H Zhang, Y Song - IEEE Transactions on Power …, 2023 - ieeexplore.ieee.org
Scheduling flexible sources to promote the integration of renewable generation is one
fundamental problem for operating active distribution networks (ADNs). However, existing …

Physics-informed neural networks with hard linear equality constraints

H Chen, GEC Flores, C Li - Computers & Chemical Engineering, 2024 - Elsevier
Surrogate modeling is used to replace computationally expensive simulations. Neural
networks have been widely applied as surrogate models that enable efficient evaluations …

Design and 4E analysis of heat pump-assisted extractive distillation processes with preconcentration for recovering ethyl-acetate and ethanol from wastewater

T Wu, C Wang, J Liu, Y Zhuang, J Du - Chemical Engineering Research …, 2024 - Elsevier
The separation of ternary azeotropes with a high content of one component using extractive
distillation is energy intensive, and the introduction of preconcentration can significantly …

Zonewise surrogate-based optimization of box-constrained systems

SV Srinivas, IA Karimi - Computers & Chemical Engineering, 2024 - Elsevier
Complex physical or numerical systems may exhibit distinct behaviors in various zones of
their design spaces. We present an algorithm that uses multiple cluster-based surrogates for …