OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

Enhancing predictive maintenance architecture process by using ontology-enabled Case-Based Reasoning

Montero-Jiménez, Juan José and Vingerhoeds, Rob A. and Grabot, Bernard Enhancing predictive maintenance architecture process by using ontology-enabled Case-Based Reasoning. (2021) In: 2021 IEEE International Symposium on Systems Engineering, 13 September 2021 - 13 October 2021 (Virtual event, Austria).

[img]
Preview
(Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
864kB

Official URL: https://doi.org/10.1109/ISSE51541.2021.9582535

Abstract

A common milestone in systems architecture development is the logical architecture. It provides a detailed overview of the system components and their interfaces but keeps the architecture as generic as possible, meaning that no component is bound to a specific technology. Subsequently, the architect searches for physical/informational components to fulfill the logical architecture and can apply structured creativity to look for innovative solutions. This search can turn out to be a difficult and long-lasting task depending on the system complexity. Too many options may be available to fulfill the logical system components and not always the most suitable ones are identified. This problem is for instance encountered in the design of new predictive maintenance systems, especially when selecting the components to carry out the diagnostics and prognostics. The current study proposes to support the choice of suitable components combining case-based reasoning and ontologies. A domain ontology has been developed as a terminology framework to support the case base, case structure and similarity measures for a casebased reasoning Decision Support System (DSS). The DSS uses attributes of the new problem to solve and suggests the most similar cases from past experiences. The retrieved solutions can be adapted to develop a new predictive maintenance architecture. The decision support system has been tested with data coming from proved predictive maintenance solutions documented in scientific publications.

Item Type:Conference or Workshop Item (Paper)
HAL Id:hal-03514100
Audience (conference):International conference proceedings
Uncontrolled Keywords:
Institution:Université de Toulouse > Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)
Université de Toulouse > Institut Supérieur de l'Aéronautique et de l'Espace - ISAE-SUPAERO (FRANCE)
Other partners > Instituto Tecnológico de Costa Rica - Cartago (COSTA RICA)
Laboratory name:
Statistics:download
Deposited On:06 Jan 2022 09:33

Repository Staff Only: item control page