A Grid-Structured Model of Tubular Reactors

Katsiaryna Haitsiukevich, Samuli Bergman, Cesar de Araujo Filho, Francesco Corona, Alexander Ilin

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

48 Downloads (Pure)

Abstract

We propose a grid-like computational model of tubular reactors. The architecture is inspired by the computations performed by solvers of partial differential equations which describe the dynamics of the chemical process inside a tubular reactor. The proposed model may be entirely based on the known form of the partial differential equations or it may contain generic machine learning components such as multi-layer perceptrons. We show that the proposed model can be trained using limited amounts of data to describe the state of a fixed-bed catalytic reactor. The trained model can reconstruct unmeasured states such as the catalyst activity using the measurements of inlet concentrations and temperatures along the reactor.
Original languageEnglish
Title of host publication2021 IEEE 19th International Conference on Industrial Informatics (INDIN)
PublisherIEEE
Number of pages5
ISBN (Electronic)978-1-7281-4395-8
DOIs
Publication statusPublished - 21 Jul 2021
MoE publication typeA4 Article in a conference publication
EventIEEE International Conference on Industrial Informatics - Palma de Mallorca, Spain, Palma de Mallorca, Spain
Duration: 21 Jul 202123 Jul 2021
https://2021.ieee-indin.org/

Conference

ConferenceIEEE International Conference on Industrial Informatics
Abbreviated titleINDIN
Country/TerritorySpain
CityPalma de Mallorca
Period21/07/202123/07/2021
Internet address

Keywords

  • Catalyst Sctivity
  • Deep learning
  • Fixed-Red Catalytic Reactor
  • Multi-Layer Perceptron
  • Soft Sensor
  • Tubular Reactor
  • Temperature Measurement
  • Computational Modeling
  • Partial Differential Equations
  • Catalysts
  • Mathematical Models
  • Data Models

Fingerprint

Dive into the research topics of 'A Grid-Structured Model of Tubular Reactors'. Together they form a unique fingerprint.

Cite this