liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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
Large Language Model-Driven Simulations for System of Systems Analysis in Firefighting Aircraft Conceptual Design
Linköping University, Faculty of Science & Engineering. Linköping University, Department of Management and Engineering, Fluid and Mechatronic Systems.ORCID iD: 0000-0002-2322-2402
Linköping University, Department of Management and Engineering, Fluid and Mechatronic Systems. Linköping University, Faculty of Science & Engineering. Design Methodology, Saab Aeronautics, Sweden.ORCID iD: 0000-0002-1301-7931
Institute of Aircraft Design and Lightweight Structure (IFL), Technische Universität Braunschweig, Germany.
Linköping University, Department of Management and Engineering, Fluid and Mechatronic Systems. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0002-2315-0680
2024 (English)Conference paper, Oral presentation only (Other academic)
Sustainable development
Climate Improvements
Abstract [en]

Conceptual design of aircraft tailored for a specific role requires a holistic view to account for requirements atdifferent levels, from systems to sub-systems and their components. This is the case with aircraft designedfor firefighting, where they collaborate and communicate with other systems towards a common goal. Thiscollaborative and holistic perspective is what a System of System (SoS) analysis tries to achieve. To conduct aSoS analysis, the use of Agent-Based Modelling and Simulations (ABMSs) is widely adopted. A crucial aspectof this approach is the ability to capture emergent behaviours that arise from collaborative systems, whichare represented in the Agent-Based Simulation (ABS) by agents whose actions are traditionally governed bydecision trees. The present study introduces a novel methodology using ABMS where a Large Language Model(LLM) plays the role of a human in the loop. The purpose is to represent the decision-making of an IncidentCommander (IC) by allowing a LLM to play this role within a wildfire situation. The IC will follow operationalguidelines and guide the agents’ behaviour in order to provide them with more degrees of freedom and removethe constraints associated with traditional behaviour trees. This approach not only aids in simulating realisticoperational scenarios but also generates valuable insights for Aircraft Conceptual Design (ACD), enabling thederivation of specific design requirements based on simulation outcomes.

Place, publisher, year, edition, pages
2024.
Keywords [en]
Aircraft Conceptual Design, System of Systems Analysis, Wildfire Management, Agent-Based Modelling, Large Language Models
National Category
Aerospace Engineering
Identifiers
URN: urn:nbn:se:liu:diva-207781OAI: oai:DiVA.org:liu-207781DiVA, id: diva2:1900328
Conference
34th Congress of the International Council of the Aeronautical Sciences, Italy, September 9-13, 2024
Available from: 2024-09-23 Created: 2024-09-23 Last updated: 2024-10-18Bibliographically approved

Open Access in DiVA

No full text in DiVA

Authority records

Lovaco, JorgeMunjulury, Raghu ChaitanyaKrus, Petter

Search in DiVA

By author/editor
Lovaco, JorgeMunjulury, Raghu ChaitanyaKrus, Petter
By organisation
Faculty of Science & EngineeringFluid and Mechatronic Systems
Aerospace Engineering

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 138 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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