kth.sePublications
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
Enhancing the Precision of a Hydraulic Robotic Arm
KTH, School of Industrial Engineering and Management (ITM), Engineering Design, Mechatronics and Embedded Control Systems.
KTH, School of Industrial Engineering and Management (ITM), Engineering Design, Mechatronics and Embedded Control Systems.
2024 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Förbättring av Precisionen hos en Hydraulisk Robotarm (Swedish)
Abstract [en]

This thesis explored the use of a Gated Recurrent Unit (GRU) based neural network, used as a feedforward controller in the electro-hydraulic driven robotic arm of DeLavals Voluntary Milking System (VMS). The research focused on developing a GRU-based feedforward controller and comparing its performance to the existing controller of the VMS in terms of velocity tracking accuracy, as the non-linear dynamics of the electro-hydraulic actuators pose a challenge for traditional methods of system modelling. The network was trained on data collected from the robotic arm’s movements, enabling it to learn the complex relationship between desired velocities and the corresponding outputs. This trained network was implemented as a feedforward controller, directly generating actuator commands to achieve the desired velocity trajectory. The performance comparison utilises Mean Squared Error (MSE) to evaluate the tracking accuracy of both controllers. The results demonstrate that the GRU-based feedforward controller significantly outperforms the existing controller, achieving a 53% lower MSE value. These results further signify the potential of GRU neural networks for improved control of robotic manipulators with complex dynamics.

Abstract [sv]

Denna avhandling undersökte användningen av ett GRU-baserat neuralt nätverk, som används som en feedforward-kontroller i robotarmen på DeLavals VMS-maskin, med elektrohydrauliska ställdon. Forskningen fokuserade på att utveckla en GRU-baserad feedforward-kontroller och jämföra dess prestanda med den befintliga kontrollern för VMS:en när det gäller hastighetsspårningsnoggrannhet, eftersom den icke-linjära dynamiken hos de elektrohydrauliska ställdonen utgör en utmaning för traditionella metoder för systemmodellering. Nätverket tränades på data som samlats in från robotarmens rörelser, vilket gjorde det möjligt för den att lära sig det komplexa förhållandet mellan önskade hastigheter och motsvarande utsignaler. Det tränade nätverket implementerades som en feedforward-kontroller som genererar ställdonskommandon för att uppnå den önskade hastighetsbanan. Prestandajämförelsen använder MSE för att utvärdera spårningsnoggrannheten hos båda kontrollerna. Resultaten visar att den GRU-baserade feedforward-kontrollern är betydligt bättre än den befintliga kontrollern och uppnår ett 53% lägre MSE-värde. Dessa resultat visar ytterligare på potentialen hos GRU neurala nätverk för förbättrad styrning av robotmanipulatorer med komplex dynamik.

Place, publisher, year, edition, pages
2024. , p. 40
Series
TRITA-ITM-EX ; 2024:443
Keywords [en]
Neural network, Recurrent neural network, Feedforward control, Hydraulic actuator
Keywords [sv]
Neuralt nätverk, Återkommande neuralt nätverk, Feedforward-reglering, Hydrauliskt ställdon
National Category
Mechanical Engineering
Identifiers
URN: urn:nbn:se:kth:diva-362121OAI: oai:DiVA.org:kth-362121DiVA, id: diva2:1950567
External cooperation
Delaval International AB
Subject / course
Mechatronics
Educational program
Degree of Master
Presentation
2024-07-09, 00:00
Supervisors
Examiners
Available from: 2025-04-08 Created: 2025-04-08 Last updated: 2025-04-08Bibliographically approved

Open Access in DiVA

fulltext(1983 kB)26 downloads
File information
File name FULLTEXT01.pdfFile size 1983 kBChecksum SHA-512
1fd584072aa3cf38a1cf799c00361cb04f22531d7eb1163c2eaba1211797501d602c452d3ffa71a2eedb55f70e565f146a94ccba839be63fbafae75ffa8398dd
Type fulltextMimetype application/pdf

By organisation
Mechatronics and Embedded Control Systems
Mechanical Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 26 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: 376 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