Reusable Surrogate Models for Distillation Columns

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bubel, Martin, Seidel, Tobias, Bortz, Michael
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916975745171456
author Bubel, Martin
Seidel, Tobias
Bortz, Michael
author_facet Bubel, Martin
Seidel, Tobias
Bortz, Michael
contents Surrogate modeling is a powerful methodology in chemical process engineering, frequently employed to accelerate optimization tasks where traditional flowsheet simulators are computationally prohibitive. However, the state-of-the-art is dominated by surrogate models trained for a narrow range of fixed chemical systems and operating conditions, limiting their reusability. This work introduces a paradigm shift towards reusable surrogates by developing a single model for distillation columns that generalizes across a vast design space. The key enabler is a novel ML-fueled modelfluid representation which allows for the generation of datasets of more than $1,000,000$ samples. This allows the surrogate to generalize not only over column specifications but also over the entire chemical space of homogeneous ternary vapor-liquid mixtures. We validate the model's accuracy and demonstrate its practical utility in a case study on entrainer distillation, where it successfully screens and ranks candidate entrainers, significantly reducing the computational effort compared to rigorous optimization.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06638
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reusable Surrogate Models for Distillation Columns
Bubel, Martin
Seidel, Tobias
Bortz, Michael
Computational Engineering, Finance, and Science
Surrogate modeling is a powerful methodology in chemical process engineering, frequently employed to accelerate optimization tasks where traditional flowsheet simulators are computationally prohibitive. However, the state-of-the-art is dominated by surrogate models trained for a narrow range of fixed chemical systems and operating conditions, limiting their reusability. This work introduces a paradigm shift towards reusable surrogates by developing a single model for distillation columns that generalizes across a vast design space. The key enabler is a novel ML-fueled modelfluid representation which allows for the generation of datasets of more than $1,000,000$ samples. This allows the surrogate to generalize not only over column specifications but also over the entire chemical space of homogeneous ternary vapor-liquid mixtures. We validate the model's accuracy and demonstrate its practical utility in a case study on entrainer distillation, where it successfully screens and ranks candidate entrainers, significantly reducing the computational effort compared to rigorous optimization.
title Reusable Surrogate Models for Distillation Columns
topic Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2509.06638