Scholarlink

This chapter presents a knowledge-driven framework for enhancing maintenance management in complex fusion facilities, with a specific focus on the IFMIF-DONES project. The approach leverages semantic technologies, including a domain-specific OWL ontology and graph databases, to address the limitations of traditional maintenance methods. We detail the practical application of this framework, from ontology development and system architecture to rule-based reasoning using SPARQL. The chapter demonstrates how this semantic approach facilitates data integration, enhances decision traceability, and enables adaptive maintenance planning through practical use cases. The performance of the ontology is demonstrated using SPARQL, highlighting its effectiveness in querying and reasoning over complex maintenance data. This work underscores the value of semantic technologies in creating more intelligent, transparent, and efficient maintenance systems for safety–critical environments.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Knowledge Engineering for Fusion Systems: Ontological Integration and Semantic Reasoning in Practice

  • 章节

  • 发表日期：

    2026年

查看全文
  • Mohammed Anouar Amzert,
  • Antonio Sanchez Membrieves,
  • Juan Fernández Salas,
  • Manuel Chiachio Ruano

摘要

This chapter presents a knowledge-driven framework for enhancing maintenance management in complex fusion facilities, with a specific focus on the IFMIF-DONES project. The approach leverages semantic technologies, including a domain-specific OWL ontology and graph databases, to address the limitations of traditional maintenance methods. We detail the practical application of this framework, from ontology development and system architecture to rule-based reasoning using SPARQL. The chapter demonstrates how this semantic approach facilitates data integration, enhances decision traceability, and enables adaptive maintenance planning through practical use cases. The performance of the ontology is demonstrated using SPARQL, highlighting its effectiveness in querying and reasoning over complex maintenance data. This work underscores the value of semantic technologies in creating more intelligent, transparent, and efficient maintenance systems for safety–critical environments.