SEARCH FOR SIMILAR TECHNICAL SOLUTIONS BY OBJECT ABSTRACTION USING AN ONTOLOGY
DS 68-6: Proceedings of the 18th International Conference on Engineering Design (ICED 11), Impacting Society through Engineering Design, Vol. 6: Design Information and Knowledge, Lyngby/Copenhagen, Denmark, 15.-19.08.2011
Editor: Culley, S.J.; Hicks, B.J.; McAloone, T.C.; Howard, T.J. & Chen, W.
Author: Kohn, Andreas; Lindemann, Udo
Section: Design Information and Knowledge Management
The search for existing solutions in mechanical engineering is a key-factor for successful product development. By reusing existing solutions, the amount of work and costs within the product development process can be reduced. However, not only exact matches for a required solution are helpful, but also the suggestion of similar solutions could often meet the requirements and bring benefit. Therefore, the presented research aims at improving the process of retrieving existing solutions similar to a user query. This is achieved by developing an abstraction level in form of a shape classification for the objects handled in a technical solution. An ontology is used for modeling the required concepts and providing the necessary relations to shape classification. Semantic similarity measures are applied for calculating the similarity of technical solutions and the user query according to the information modeled in the ontology. With the help of a developed prototype that uses the ontology as knowledge repository for annotating and searching solution documents, the presented approach is applied and evaluated in the field of automation industry.