Skip to main navigation Skip to search Skip to main content

Indirect training with error backpropagation in gray-box neural model: Application to a chemical process

  • Universidad Andres Bello
  • Universidad de Santiago de Chile

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

6 Scopus citations

Abstract

Gray-box neural models mix differential equations, which act as white boxes, and neural networks, used as black boxes, to complete the phenomenological model. These models have been used in different researches proving their efficacy. The aim of this work is to show the training of the gray-box model through indirect back propagation and Levenberg-Marquardt. The gray-box neural model was tested in the simulation of a chemical process in a continuous stirred tank reactor (CSTR) with 5% noise, responding successfully.

Original languageEnglish
Title of host publicationProceedings - 29th International Conference of the Chilean Computer Science Society, SCCC 2010
PublisherIEEE Computer Society
Pages265-269
Number of pages5
ISBN (Print)9780769544007
DOIs
StatePublished - 2010
Externally publishedYes

Publication series

NameProceedings - International Conference of the Chilean Computer Science Society, SCCC
ISSN (Print)1522-4902

Keywords

  • chemical processes
  • gray-box neural model
  • neural networks
  • time-varying parameters

Fingerprint

Dive into the research topics of 'Indirect training with error backpropagation in gray-box neural model: Application to a chemical process'. Together they form a unique fingerprint.

Cite this