oru.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Evolutionary computation based system decomposition with neural networks
Ilmenau University of Technology, Ilmenau, Germany. (Neuroinformatics and Cognitive Robotics Lab)
Örebro universitet, Institutionen för naturvetenskap och teknik. (Mobile Robotics and Olfaction Lab)
Ilmenau University of Technology, Ilmenau, Germany. (Neuroinformatics and Cognitive Robotics Lab)
Ilmenau University of Technology, Ilmenau, Germany. (Neuroinformatics and Cognitive Robotics Lab)
2013 (engelsk)Inngår i: ESANN 2013 proceedings, European Symposium on Artificial Neural Networks, Computational Intelligenceand Machine Learning, Louvain-La-Neuve: ESANN , 2013, s. 191-196Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

We present an evolutionary approach to divide a complex control system into smaller sub-systems with the help of neural networks.Thereto, measured channels are partitioned into several disjunct sets, rep-resenting possible sub-problems, while the networks are used to assessthe quality of the resulting decomposition. We show that this approach iswell suited to calculate correct decompositions of complex control systems.Furthermore, the obtained neural networks are used to predict importantprocess factors with considerable better approximation quality than mono-lithic approaches that have to deal with all input channels in parallel.

sted, utgiver, år, opplag, sider
Louvain-La-Neuve: ESANN , 2013. s. 191-196
Emneord [en]
neural nets, evolutionary algorithm, system decomposition
HSV kategori
Forskningsprogram
Datavetenskap; Reglerteknik
Identifikatorer
URN: urn:nbn:se:oru:diva-30519ISBN: 9782874190810 (tryckt)OAI: oai:DiVA.org:oru-30519DiVA, id: diva2:644383
Konferanse
European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN) 2013
Tilgjengelig fra: 2013-08-30 Laget: 2013-08-30 Sist oppdatert: 2018-05-21bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

http://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2013-58.pdf

Personposter BETA

Schaffernicht, Erik

Søk i DiVA

Av forfatter/redaktør
Schaffernicht, Erik
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

isbn
urn-nbn

Altmetric

isbn
urn-nbn
Totalt: 8797 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf