Real-time determination of optimal switching times for a H2 production process with CO2 capture using Gaussian Process Regression models

Luca Zanella, Marcella Porru (Corresponding author), Giulio Bottegal, Fausto Gallucci, Martin van Sint Annaland, Leyla Özkan

Research output: Contribution to journalConference articleAcademicpeer-review

Abstract

This work presents a systematic methodology to determine in real-time the optimal durations of the three stages of a new Ca-Cu looping process for H2 production with integrated CO2 capture. Economic and quality criteria are proposed to determine the appropriate time to switch between the stages. These criteria rely on the time-profiles of some key variables, such as product concentrations. Given the delayed nature of hardware sensor measurements, the real-time determination of such variables is based on soft-sensors. For this purpose, Gaussian Process Regression models are employed. The predictive capabilities of these models are tested on several datasets, yielding reliable predictions in most of the cases. The values of the optimal switching times computed with the proposed method differ from the actual values by 4 %, at most.

Original languageEnglish
Pages (from-to)1219-1224
Number of pages6
JournalComputer Aided Chemical Engineering
Volume46
DOIs
Publication statusPublished - 25 Jul 2019
Event29th European Symposium on Computer Aided Process Engineering (ESCAPE 29) - Evoluon, Eindhoven, Netherlands
Duration: 16 Jun 201919 Jun 2019
Conference number: 29

Fingerprint

Sensors
Switches
Hardware
Economics

Keywords

  • CO capture
  • gaussian process regression models
  • machine learning
  • process intensification
  • process monitoring

Cite this

@article{03ebb84939c74cea90f9607dbb319fef,
title = "Real-time determination of optimal switching times for a H2 production process with CO2 capture using Gaussian Process Regression models",
abstract = "This work presents a systematic methodology to determine in real-time the optimal durations of the three stages of a new Ca-Cu looping process for H2 production with integrated CO2 capture. Economic and quality criteria are proposed to determine the appropriate time to switch between the stages. These criteria rely on the time-profiles of some key variables, such as product concentrations. Given the delayed nature of hardware sensor measurements, the real-time determination of such variables is based on soft-sensors. For this purpose, Gaussian Process Regression models are employed. The predictive capabilities of these models are tested on several datasets, yielding reliable predictions in most of the cases. The values of the optimal switching times computed with the proposed method differ from the actual values by 4 {\%}, at most.",
keywords = "CO capture, gaussian process regression models, machine learning, process intensification, process monitoring",
author = "Luca Zanella and Marcella Porru and Giulio Bottegal and Fausto Gallucci and {van Sint Annaland}, Martin and Leyla {\"O}zkan",
year = "2019",
month = "7",
day = "25",
doi = "10.1016/B978-0-12-818634-3.50204-6",
language = "English",
volume = "46",
pages = "1219--1224",
journal = "Computer Aided Chemical Engineering",
issn = "1570-7946",
publisher = "Elsevier",

}

TY - JOUR

T1 - Real-time determination of optimal switching times for a H2 production process with CO2 capture using Gaussian Process Regression models

AU - Zanella, Luca

AU - Porru, Marcella

AU - Bottegal, Giulio

AU - Gallucci, Fausto

AU - van Sint Annaland, Martin

AU - Özkan, Leyla

PY - 2019/7/25

Y1 - 2019/7/25

N2 - This work presents a systematic methodology to determine in real-time the optimal durations of the three stages of a new Ca-Cu looping process for H2 production with integrated CO2 capture. Economic and quality criteria are proposed to determine the appropriate time to switch between the stages. These criteria rely on the time-profiles of some key variables, such as product concentrations. Given the delayed nature of hardware sensor measurements, the real-time determination of such variables is based on soft-sensors. For this purpose, Gaussian Process Regression models are employed. The predictive capabilities of these models are tested on several datasets, yielding reliable predictions in most of the cases. The values of the optimal switching times computed with the proposed method differ from the actual values by 4 %, at most.

AB - This work presents a systematic methodology to determine in real-time the optimal durations of the three stages of a new Ca-Cu looping process for H2 production with integrated CO2 capture. Economic and quality criteria are proposed to determine the appropriate time to switch between the stages. These criteria rely on the time-profiles of some key variables, such as product concentrations. Given the delayed nature of hardware sensor measurements, the real-time determination of such variables is based on soft-sensors. For this purpose, Gaussian Process Regression models are employed. The predictive capabilities of these models are tested on several datasets, yielding reliable predictions in most of the cases. The values of the optimal switching times computed with the proposed method differ from the actual values by 4 %, at most.

KW - CO capture

KW - gaussian process regression models

KW - machine learning

KW - process intensification

KW - process monitoring

UR - http://www.scopus.com/inward/record.url?scp=85069720602&partnerID=8YFLogxK

U2 - 10.1016/B978-0-12-818634-3.50204-6

DO - 10.1016/B978-0-12-818634-3.50204-6

M3 - Conference article

AN - SCOPUS:85069720602

VL - 46

SP - 1219

EP - 1224

JO - Computer Aided Chemical Engineering

JF - Computer Aided Chemical Engineering

SN - 1570-7946

ER -