Skip to Main content Skip to Navigation
Theses

Proposition d’un assistant intelligent dédié aux règles de conception pour l’industrie manufacturière

Abstract : Thesis title: Proposal of a Context-Aware Cognitive Design Assistant dedicated to design rules for the manufacturing industryDesign rules are an essential interface between professional designers and the expert knowledge they need to perform their task. They guide designers toward better design choices and contribute to the efficiency of the design process. The mastering of these rules is a crucial issue for the manufacturing industry. However, most companies store their design rules in unstructured design manuals. Design rules research in these manuals of several hundred pages, is complex and tedious. Designers have to work on their CAD modeling activity, while spending time and cognitive resources, researching for applicable design rules. In this thesis, we propose the development of a Context-Aware Cognitive Design Assistant (CACDA) dedicated to design rules for the manufacturing industry in order to improve the efficiency of CAD modeling. Unlike a CAD quality software that seeks to identify design errors in the digital model, our assistant takes a proactive, designer-centric approach. The assistant is able to perform design rules recommendations on the fly based on the design context. The designer can select applicable rules without having to spend the time and effort of a research in a design manual. In order to demonstrate the feasibility and relevance of this approach, a technical demonstrator of the assistant has been developed and tested as part of an industrial case study. This work opens up the prospect of a new generation of cognitive assistants for design, based on the capture and analysis of the design context.Keywords: Design rules, CAD, Manufacturing industry, Context-awareness, Cognitive assistant, Graph database
Complete list of metadata

https://pastel.archives-ouvertes.fr/tel-03663859
Contributor : ABES STAR :  Contact
Submitted on : Tuesday, May 10, 2022 - 2:44:14 PM
Last modification on : Wednesday, May 11, 2022 - 3:36:34 AM

File

108621_HUET_2022_archivage.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-03663859, version 1

Citation

Armand Huet. Proposition d’un assistant intelligent dédié aux règles de conception pour l’industrie manufacturière. Biomécanique [physics.med-ph]. HESAM Université, 2022. Français. ⟨NNT : 2022HESAE022⟩. ⟨tel-03663859⟩

Share

Metrics

Record views

56

Files downloads

3