A task-decomposed AI-aided approach for generative conceptual design
File(s)
Accepted version
Author(s)
Type
Conference Paper
Abstract
Generative algorithm-based conceptual design has been innovatively applied as an emerging digital design paradigm for early-stage design ideation. With powerful large language models (LLMs), designers can enter an initial prompt as a design requirement to generate using machine reasoning capability descriptive natural language content. The machine-generated output can be used as stimuli to inspire designers during design ideation. However, the lack of transparency and insufficient controllability of LLMs can limit their effectiveness when assisting humans on a generative conceptual design task. This generation process lacks theoretical guidance and a comprehensive understanding of design requirements, which may potentially lead to generated concepts that are mismatched or lack creativity. Inspired by the Function-Behavior-Structure (FBS) model, this paper proposes a task-decomposed AI-aided approach for generative conceptual design. We decompose a conceptual design task into three sub-tasks including functional reasoning, behavioral reasoning, and structural reasoning. Prompt templates and specification signifiers are specified for different steps to guide the LLMs to generate reasonable results, controllably. The output of each step becomes the input of the next, aiding in aggregating gains per step and embedding the selection preferences of human designers at each stage. A conceptual design experiment is conducted, and the results show that the conceptual design ideation with our method are more reasonable and creative in comparison to a baseline.
Date Issued
2023-11-21
Date Acceptance
2023-04-24
Citation
Volume 6: 35th International Conference on Design Theory and Methodology (DTM), 2023, 6, pp.1-11
ISBN
978-0-7918-8734-9
Publisher
American Society of Mechanical Engineers (ASME)
Start Page
1
End Page
11
Journal / Book Title
Volume 6: 35th International Conference on Design Theory and Methodology (DTM)
Volume
6
Copyright Statement
Copyright © 2023 by ASME. This permission is granted for the specific purpose outlined at https://asmedigitalcollection.asme.org/ and does not authorize any further use of the material without proper approval. Sales, downloads, or any other distribution of the ASME paper are not permitted under this permission. For future permission requests, please contact Permissions@asme.org [mailto:Permissions@asme.org].
Source
ASME 2023 International Design Engineering Technical Conferences & Computers and Information in Engineering Conference (IDETC/CIE2023)
Publication Status
Published
Start Date
2023-08-20
Finish Date
2023-08-23
Coverage Spatial
Boston, Massachusetts, USA
Date Publish Online
2023-11-21