Nandy, A.
, Hartwell, A.
and Morris, K.
(2026),
Utilizing Pre-trained Language Models to Support Circular Design Decision-Making, Proceedings of the ASME 2025 International Mechanical Engineering Congress and Exposition, Memphis, TN, US, [online], https://doi.org/10.1115/IMECE2025-167017, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=960056
(Accessed February 28, 2026)
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
Secure .gov websites use HTTPS
A lock (
) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.
Utilizing Pre-trained Language Models to Support Circular Design Decision-Making
Published
Author(s)
, ,
Abstract
Circular practices (e.g., extending product/component life and recovering end-of-life products) can divert products from waste streams, creating alternative material sources and resilient production systems. Recently developed design guidelines and principles can ensure that circularity is planned into a product design. However, when expertise on circularity is lacking, determining which of the numerous guidelines to prioritize and implement is challenging, especially for complex product assemblies. This study evaluates an approach to support the selection of relevant circular design principles for different product types, leveraging advances in natural language processing and semantic understanding. Several pre-trained language models are evaluated for their performance in ranking the circular design principles most relevant to two sets of consumer electronic products in comparison to human-determined ratings. The approach can reduce barriers to practically implementing circular product design principles, but results indicate that alignment with human decision-making is sensitive to model choices and product representation.Proceedings Title
Proceedings of the ASME 2025 International Mechanical Engineering Congress and Exposition
Volume
Volume 2: Advanced Manufacturing
Conference Dates
November 16-20, 2025
Conference Location
Memphis, TN, US
Pub Type
Conferences
Download Paper
Keywords
product design, circular economy, circular product design, semantic search, large language models (LLMs)
Citation
Issues
If you have any questions about this publication or are having problems accessing it, please contact [email protected].
Created February 23, 2026, Updated February 27, 2026