Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Benefits of Using Intelligent Control Systems in Comparison to Classical Methods for Temperature Control in a Greenhouse
KTH, School of Electrical Engineering and Computer Science (EECS).
KTH, School of Electrical Engineering and Computer Science (EECS).
2019 (English)Independent thesis Basic level (degree of Bachelor), 10 credits / 15 HE creditsStudent thesisAlternative title
Fördelarna av intelligenta kontrollsystem i jämförelse med klassiska metoder för temperaturkontroll i växthus (Swedish)
Abstract [en]

In the last decades, intelligent control systems have rapidly replaced classical methods to solve problems in many spheres of science and technology. The purpose of this study is to demonstrate the benefits of intelligent control systems in comparison to the classical methods in a low-scale benchmarking problem. The problem chosen in this study is temperature control in a green house. The intelligent control methods of neural network and fuzzy logic have been simulated. These simulations are used to compare with the simulations of classical methodologies such as PID and open loop controllers. Results from the tests on these simulations show that intelligent control methods have better overall performance with better accuracy and a smaller temperature variance. Additionally, neural networks have the benefit of independence from models and does not require extensive knowledge of the problem field. The classical methods are on the other hand easier to implement and do not require a complex selection of training data.

Abstract [sv]

Under de senaste decennierna har intelligenta kontrollsystem snabbt ersatt klassiska metoder för att lösa många problem inom vetenskap och teknik. Syftet med denna studie är att visa fördelarna med intelligenta kontrollsystem i jämförelse med de klassiska metoderna i ett lågskaligt benchmarkingproblem. Problemet som valts i denna studie är temperaturkontroll i ett växthus. Bland de intelligenta kontrollmetoderna har neuralt nätverk och suddig logik valts ut för att skapa simuleringar av intelligenta kontrollsystem. Dessa simuleringar jämfördes sedan med simuleringarna av de klassiska metoderna såsom PID och öppen slingkontroller. Resultat från testen på dessa simuleringar visar att intelligenta kontrollmetoder har bättre noggrannhet och mindre temperaturvariation. Dessutom har neuralt nätverk fördelen av att vara oberoende från modeller och kräver inte omfattande kunskaper om problemsområdet. De klassiska metoderna är å andra sidan enklare att implementera samt kräver inte ett komplext urval av träningsdata.

Place, publisher, year, edition, pages
2019. , p. 35
Series
TRITA-EECS-EX ; 2019:352
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-259702OAI: oai:DiVA.org:kth-259702DiVA, id: diva2:1353095
Supervisors
Examiners
Available from: 2019-09-24 Created: 2019-09-20 Last updated: 2019-09-24Bibliographically approved

Open Access in DiVA

fulltext(1037 kB)4 downloads
File information
File name FULLTEXT01.pdfFile size 1037 kBChecksum SHA-512
b0c4b1f7bd8d358692a695335ce58670d0e669773b5e951b8d0dfee571daad445a8cb62488d83b5c659d388a6fad9b8d413b960a5cb62d719bb0570d334469f3
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 4 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 17 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf