Research On Related Retrieval Technology Based The Aerospace Ontology

The knowledge base in the aerospace domain is becoming huge and complicated, so it is a quite challenging task to correctly find the required knowledge in the massive knowledge base. It is very meaningful to improve the abilities of information and knowledge search especially for the aerospace enterprise. Hence, how to help designers to search information more efficiently is the key point in aerospace information retrieval system. However, the present retrieval systems primarily use two techniques including classic keyword-based full text search and SQL-like class retrieval. The former is not able to promise the precision. And the latter could not satisfy aerospace designers since it requires their in-depth understanding of the system.Based on the project in cooperation with china academy of launch vehicle technology cooperative project: "Knowledge Management Research to Support complex product development", we studied the method of ontology modeling and ontology-based search, and the aerospace knowledge management system is developed to show the validity of the proposed method.We introduce the relevant theory of ontology and information retrieval technology including the concept, characteristics, description language and analysis of ontology. Information retrieval technology is introduced including the basic concepts, basic processes, models and evaluation indicators of information retrieval.Then the method of modeling aerospace ontology is presented. The scope of aerospace ontology, terms and relationships between terms in the aerospace domain are determined. Then Aerospace ontology is described by OWL language. Finally the methods of evaluation and integration for aerospace ontology are presented.The methods of associated terms'retrieval, rule-based term's retrieval and aerospace ontology-based information retrieval are presented. The related terms are searched through parsing owl files by Jena. Meanwhile SWRL rules could be loaded to meet further the needs of the user. Based on the traditional information retrieval model, the aerospace ontology-based information retrieval model is presented. The comparison on the tests and the principles for two models show that the aerospace ontology-based information retrieval method is superior to the traditional information retrieval method.At last, the knowledge-based knowledge retrieval system in the aerospace field is designed and developed on the basis of the proposed method. Firstly the system frame, including system development platform, system structure and function module are designed, and then the main function modules including ontology base module, knowledge representation module, knowledge search module, knowledge acquisition module and knowledge base module are developed. Finally the example of system operation is introduced.