Functional decomposition of technical products based on large language models and Monte Carlo tree search
Publikation: Beiträge in Zeitschriften › Konferenzaufsätze in Fachzeitschriften › Forschung › begutachtet
Standard
in: Proceedings of the Design Society, Jahrgang 5, 01.08.2025, S. 1913-1922.
Publikation: Beiträge in Zeitschriften › Konferenzaufsätze in Fachzeitschriften › Forschung › begutachtet
Harvard
APA
Vancouver
Bibtex
}
RIS
TY - JOUR
T1 - Functional decomposition of technical products based on large language models and Monte Carlo tree search
AU - Haddad, Meno Said
AU - Seibel, Arthur
N1 - Publisher Copyright: © The Author(s) 2025.
PY - 2025/8/1
Y1 - 2025/8/1
N2 - Functional decomposition (FD) is essential for simplifying complex systems in engineering design but remains a resource-intensive task reliant on expert knowledge. Despite advances in artificial intelligence, the automation of FD remains underexplored. This study introduces the use of GPT-4o, enhanced with a proposed Monte Carlo tree search for functional decomposition (MCTS-FD) algorithm, to automate FD. The approach is evaluated qualitatively by comparing outputs with those of graduate engineering students and quantitatively by assessing metrics such as structural integrity and semantic accuracy. The results show that GPT-4o, enhanced by MCTS-FD, outperforms smaller models in error rates and graph connectivity, highlighting the potential of large language models to automate FD with human-like accuracy.
AB - Functional decomposition (FD) is essential for simplifying complex systems in engineering design but remains a resource-intensive task reliant on expert knowledge. Despite advances in artificial intelligence, the automation of FD remains underexplored. This study introduces the use of GPT-4o, enhanced with a proposed Monte Carlo tree search for functional decomposition (MCTS-FD) algorithm, to automate FD. The approach is evaluated qualitatively by comparing outputs with those of graduate engineering students and quantitatively by assessing metrics such as structural integrity and semantic accuracy. The results show that GPT-4o, enhanced by MCTS-FD, outperforms smaller models in error rates and graph connectivity, highlighting the potential of large language models to automate FD with human-like accuracy.
KW - conceptual design
KW - functional modelling
KW - large language models
KW - machine learning
KW - Monte Carlo tree search
KW - Engineering
UR - http://www.scopus.com/inward/record.url?scp=105022786068&partnerID=8YFLogxK
U2 - 10.1017/pds.2025.10205
DO - 10.1017/pds.2025.10205
M3 - Conference article in journal
AN - SCOPUS:105022786068
VL - 5
SP - 1913
EP - 1922
JO - Proceedings of the Design Society
JF - Proceedings of the Design Society
SN - 2732-527X
T2 - 25th International Conference on Engineering Design, ICED 2025
Y2 - 11 August 2025 through 14 August 2025
ER -