Using DSMs in Functionally Driven Explorative Design Experiments – an Automation Approach

Panarotto, Massimo; Kipouros, Timoleon; Brahma, Arindam; Isaksson, Ola; Tholin, Oskar Strandh; Clarkson, P. John

doi:10.35199/dsm2022.08

Cited by 3 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…spatial, energy, information, material) can be automatically populated in Design Structure Matrix (DSM) representation. However, no example can be found in cases where multiple system architectures are explored and analysed at the same time (e.g., Suh et al, 2010;Panarotto et al, 2022). Another area which has recently been tackled by LLM-focused research has been CAD and geometry information (e.g., Meltzer et al, 2024).…”

Section: Current Applications Of Llms In Design Activitiesmentioning

confidence: 99%

Large language models in complex system design

Gomez,

Krus,

Panarotto

et al. 2024

Proc. Des. Soc.

View full text Add to dashboard Cite

This paper investigates the use of Large Language Models (LLMs) in engineering complex systems, demonstrating how they can support designers on detail design phases. Two aerospace cases, a system architecture definition and a CAD model generation activities are studied. The research reveals LLMs' challenges and opportunities to support designers, and future research areas to further improve their application in engineering tasks. It emphasizes the new paradigm of LLMs support compared to traditional Machine Learning techniques, as they can successfully perform tasks with just a few examples.

show abstract

Section: Current Applications Of Llms In Design Activitiesmentioning

confidence: 99%

Large language models in complex system design

Gomez,

Krus,

Panarotto

et al. 2024

Proc. Des. Soc.

View full text Add to dashboard Cite

show abstract

“…The tool also provides an opportunity to extract these instances and the dependencies in them as DSMs. The details of the tool and the DSM extraction method can be found in Panarotto et al (2022).…”

Section: Industrial Casementioning

confidence: 99%

Function Driven Assessment of Manufacturing Risks in Concept Generation Stages

et al. 2023

Self Cite

View full text Add to dashboard Cite

Decisions made in the concept generation phase have a significant effect on the product. While product- related risks typically can be considered in the early stages of design, risks such as supply chain and manufacturing methods are rarely easy to account for in early phases. This is because the currently available methods require mature data, which may not be available during concept generation. In this paper, we propose an approach to address this. First, the product and the non-product (manufacturing and/or supply chain) attributes are modelled using the enhanced function means (EF-M) modelling method. The EF-M method provides the opportunity to model alternative solutions-set for functions. Dependencies are then mapped within the product and the manufacturing models, and also in between them. An automatic combinatorial method of concept generation is employed where each generated instance is a design concept-manufacturing method pair. A risk propagation algorithm is then used to assess the risks of all the generated alternatives.

show abstract

“…This example is inspired by a project conducted in collaboration with a manufacturer of aero-engine components (Panarotto et al, 2022). The main research problem identified by the company was to evaluate supplier readiness in highly integrated aero-engine components.…”

Section: Second Example: Evaluating Supplier Readiness In Highly Inte...mentioning

confidence: 99%

Problem decomposition: the key to Agile sprints in Design Research

2023

DS 126: Proceedings of the 25th International DSM Conference (DSM 2023)

View full text Add to dashboard Cite

In design research, parallelization and anticipation of tasks are crucial to having an effective impact on industry and society. In practice, however, parallelization and anticipation are difficult due to high inter-dependency among research problems and design supports. This paper proposes a framework to use the Design Structure Matrix combined with Axiomatic Design to isolate research problems and their design supports. This modular independence is an important building block to plan for quick and parallel agile design research "sprints". The application of the approach is illustrated through two practical examples. The results highlight the importance to control a limited number of interfaces to work "agile" in design research without wasteful rework.

show abstract

Using DSMs in Functionally Driven Explorative Design Experiments – an Automation Approach

Cited by 3 publications

References 18 publications

Large language models in complex system design

Large language models in complex system design

Function Driven Assessment of Manufacturing Risks in Concept Generation Stages

Problem decomposition: the key to Agile sprints in Design Research

Contact Info

Product

Resources

About