Fuzzy ontologies for retrieval of industrial knowledge

Information and knowledge are critical resources in operating and maintaining industrial process plants. The basis for the required knowledge repository is created at the design stage and extended after the hand-over of design data with modifications, maintenance histories and operational experiences. It is in the common interest of plant owners, engineering contractors and equipment and material suppliers to manage, communicate and utilise the information over the whole life-cycle of the plant. Our goal was to better “mobilise” knowledge stored in heterogeneous databases to users with various backgrounds, geographical locations and situations. The working hypothesis of the research was that fuzzy mathematics combined with domain-specific data models, in other words, fuzzy ontologies, would help manage the uncertainty in finding information that matches the user’s needs. In this way, this paper places itself in the domain of knowledge management. The main goals of the report are to give practical examples of fuzzy ontology in an industrial context, show how such ontologies can be developed, to test the functionality of the applied formalisms and tools, demonstrate the feasibility of fuzzy ontology in searching information from a knowledge base, and describe the next development tasks. ISBN 978-951-38-7494-0 (URL: http://www.vtt.fi/publications/index.jsp) Series title and ISSN Project number VTT Working Papers 1459-7683 (URL: http://www.vtt.fi/publications/index.jsp) Date Language Pages November 2010 English 54 p. + app. 2 p. Name of project Commissioned by Tekes, Metso Automation, Kemira, Rautaruukki, UPM