Combining prior knowledge with data-driven modeling of a batch distillation column including start-up

P.F. van Lith, Pascal F. van Lith, Bernardus H.L. Betlem, B. Roffel

Research output: Contribution to journalArticleAcademicpeer-review

19 Citations (Scopus)

Abstract

This paper presents the development of a simple model which describes the product quality and production over time of an experimental batch distillation column, including start-up. The model structure is based on a simple physical framework, which is augmented with fuzzy logic. This provides a way to use prior knowledge about the dynamics, which have a general validity, while additional information about the specific column behavior is derived from measured process data. The model framework is applicable for a wide range of columns operating under a certain control policy. The model framework for the particular column under study makes a priori assumptions about the specific behavior superfluous. In addition, a detailed description of the internal dynamics is not required, which reduces modeling effort. Three different hybrid model structures are compared; the model that uses the available sources of information most effectively can be used to simulate production including part of the start-up by applying constant quality control.
Original languageUndefined
Pages (from-to)1021-1030
Number of pages10
JournalComputers & chemical engineering
Volume27
Issue number7
DOIs
Publication statusPublished - 2003

Keywords

  • IR-61382
  • METIS-214748

Cite this

@article{ff6f325a4b804c26a428dff28749ad12,
title = "Combining prior knowledge with data-driven modeling of a batch distillation column including start-up",
abstract = "This paper presents the development of a simple model which describes the product quality and production over time of an experimental batch distillation column, including start-up. The model structure is based on a simple physical framework, which is augmented with fuzzy logic. This provides a way to use prior knowledge about the dynamics, which have a general validity, while additional information about the specific column behavior is derived from measured process data. The model framework is applicable for a wide range of columns operating under a certain control policy. The model framework for the particular column under study makes a priori assumptions about the specific behavior superfluous. In addition, a detailed description of the internal dynamics is not required, which reduces modeling effort. Three different hybrid model structures are compared; the model that uses the available sources of information most effectively can be used to simulate production including part of the start-up by applying constant quality control.",
keywords = "IR-61382, METIS-214748",
author = "{van Lith}, P.F. and {van Lith}, {Pascal F.} and Betlem, {Bernardus H.L.} and B. Roffel",
year = "2003",
doi = "10.1016/S0098-1354(03)00067-X",
language = "Undefined",
volume = "27",
pages = "1021--1030",
journal = "Computers & chemical engineering",
issn = "0098-1354",
publisher = "Elsevier",
number = "7",

}

Combining prior knowledge with data-driven modeling of a batch distillation column including start-up. / van Lith, P.F.; van Lith, Pascal F.; Betlem, Bernardus H.L.; Roffel, B.

In: Computers & chemical engineering, Vol. 27, No. 7, 2003, p. 1021-1030.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Combining prior knowledge with data-driven modeling of a batch distillation column including start-up

AU - van Lith, P.F.

AU - van Lith, Pascal F.

AU - Betlem, Bernardus H.L.

AU - Roffel, B.

PY - 2003

Y1 - 2003

N2 - This paper presents the development of a simple model which describes the product quality and production over time of an experimental batch distillation column, including start-up. The model structure is based on a simple physical framework, which is augmented with fuzzy logic. This provides a way to use prior knowledge about the dynamics, which have a general validity, while additional information about the specific column behavior is derived from measured process data. The model framework is applicable for a wide range of columns operating under a certain control policy. The model framework for the particular column under study makes a priori assumptions about the specific behavior superfluous. In addition, a detailed description of the internal dynamics is not required, which reduces modeling effort. Three different hybrid model structures are compared; the model that uses the available sources of information most effectively can be used to simulate production including part of the start-up by applying constant quality control.

AB - This paper presents the development of a simple model which describes the product quality and production over time of an experimental batch distillation column, including start-up. The model structure is based on a simple physical framework, which is augmented with fuzzy logic. This provides a way to use prior knowledge about the dynamics, which have a general validity, while additional information about the specific column behavior is derived from measured process data. The model framework is applicable for a wide range of columns operating under a certain control policy. The model framework for the particular column under study makes a priori assumptions about the specific behavior superfluous. In addition, a detailed description of the internal dynamics is not required, which reduces modeling effort. Three different hybrid model structures are compared; the model that uses the available sources of information most effectively can be used to simulate production including part of the start-up by applying constant quality control.

KW - IR-61382

KW - METIS-214748

U2 - 10.1016/S0098-1354(03)00067-X

DO - 10.1016/S0098-1354(03)00067-X

M3 - Article

VL - 27

SP - 1021

EP - 1030

JO - Computers & chemical engineering

JF - Computers & chemical engineering

SN - 0098-1354

IS - 7

ER -