A Bayesian optimization approach for data-driven Petlyuk distillation column
Authors:
- Antonio Flores-TlacuahuacAFAntonio Flores-Tlacuahuac
- Alexander Panales-PérezAPAlexander Panales-Pérez
- Luis Fabián Fuentes-CortésLFLuis Fabián Fuentes-Cortés
Open Access
- 1 July 2025
- conference paper
- Published by The CACHE Foundation, Inc. in Systems and Control Transactions
- Vol. 4, 1029-1034
Abstract
Recently, the focus on increasing process efficiency to reduce energy consumption has driven the adoption of alternative systems, such as Petlyuk distillation columns. It has been proven that, when compared to conventional distillation columns, these systems offer significant energy and cost savings. From an economic standpoint, achieving high-purity products alone does not ensure the feasibility of a process. Instead, balancing the trade-off between product purity and cost necessitates multi-objective optimization. While conventional optimization methods are effective, novel strategies like Bayesian optimization offer distinct advantages for handling complex systems. Bayesian optimization requires no explicit mathematical model and can efficiently optimize even when starting from a single initial point. However, as a black-box method, it demands a detailed analysis of hyperparameters, such as the acquisition function and the number of initial points, to ensure optimal performance. This work presents a case study of a Petlyuk distillation column, focusing on the influence of key hyperparameters in Bayesian optimization. Additionally, the role of uncertainty in the optimization process is explored, as it is a critical factor in real-world applications. By simulating uncertainty, this study provides insights into its impact on the optimization process.Keywords
This publication has 9 references indexed in Scilit:
- A stochastic data-driven Bayesian optimization approach for intensified ethanol–water separation systemsChemical Engineering and Processing - Process Intensification, 2024
- A Literature Review and Critical Analysis of Metaheuristics Recently DevelopedArchives of Computational Methods in Engineering, 2023
- An inherently safer development approach for thermally coupled distillation sequences: Application in hazardous chemical separationProcess Safety and Environmental Protection, 2022
- Good practices for Bayesian optimization of high dimensional structured spacesApplied AI Letters, 2021
- Investigating the impact of data normalization on classification performanceApplied Soft Computing, 2020
- High-dimensional Bayesian optimization using low-dimensional feature spacesMachine Learning, 2020
- Optimum design of Petlyuk and divided-wall distillation systems using a shortcut modelChemical Engineering Research and Design, 2010
- Pareto front of ideal Petlyuk sequences using a multiobjective genetic algorithm with constraintsComputers & Chemical Engineering, 2009
- Retrofitting conventional column systems to dividing-Wall ColumnsChemical Engineering Research and Design, 2009