OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

Improvement of online adaptation knowledge acquisition and reuse in case-based reasoning: Application to process engineering design

Roldan Reyes, Eduardo and Negny, Stéphane and Cortes Robles, Guillermo and Le Lann, Jean-Marc Improvement of online adaptation knowledge acquisition and reuse in case-based reasoning: Application to process engineering design. (2015) Engineering Applications of Artificial Intelligence, 41. 1-16. ISSN 0952-1976

[img]
Preview
(Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
1MB

Official URL: https://doi.org/10.1016/j.engappai.2015.01.015

Abstract

Despite various publications in the area during the last few years, the adaptation step is still a crucial phase for a relevant and reasonable Case Based Reasoning system. Furthermore, the online acquisition of the new adaptation knowledge is of particular interest as it enables the progressive improvement of the system while reducing the knowledge engineering effort without constraints for the expert. Therefore this paper presents a new interactive method for adaptation knowledge elicitation, acquisition and reuse, thanks to a modification of the traditional CBR cycle. Moreover to improve adaptation knowledge reuse, a test procedure is also implemented to help the user in the adaptation step and its diagnosis during adaptation failure. A study on the quality and usefulness of the new knowledge acquired is also driven. As our Knowledge Based Systems (KBS) is more focused on preliminary design, and more particularly in the field of process engineering, we need to unify in the same method two types of knowledge: contextual and general. To realize this, this article proposes the integration of the Constraint Satisfaction Problem (based on general knowledge) approach into the Case Based Reasoning (based on contextual knowledge) process to improve the case representation and the adaptation of past experiences. To highlight its capability, the proposed approach is illustrated through a case study dedicated to the design of an industrial mixing device.

Item Type:Article
HAL Id:hal-01879760
Audience (journal):International peer-reviewed journal
Uncontrolled Keywords:
Institution:French research institutions > Centre National de la Recherche Scientifique - CNRS (FRANCE)
Université de Toulouse > Institut National Polytechnique de Toulouse - INPT (FRANCE)
Université de Toulouse > Université Toulouse III - Paul Sabatier - UPS (FRANCE)
Other partners > Instituto Tecnologico de Orizaba (MEXICO)
Laboratory name:
Statistics:download
Deposited By: Loetitia MOYA
Deposited On:24 Sep 2018 09:56

Repository Staff Only: item control page