Research And Application Of Case-based Reasoning On Event Ontology About Coal Mine Safety

In our country, the coal resources are still occupying a large proportion in the primary energy structure. The demand of coal resources in our country is still high. As the largest coal producer and consumer country of the world, the number of deaths due to coal mine accidents is 3 times the level of other country. It indicated that the treatment of coal mine safety accidents in our country still have a lot of problems. At the time of the accident, there would be expanded accidents or secondary accidents because of lack of timely, scientific emergency processing decision. In this paper, the event ontology model will be used to represent the coal mine safety incident. When the accident happened, it would supply a timely solution what will reduce the loss of incident to decision-maker through case-based reasoning.Firstly, this paper introduces the concept of event ontology, ontology and ontology languages, the definition of event ontology and the relationships among events. The relationship between description logic and ontology languages is introduced, and the basic Tableau algorithm for ontology detection is also introduced. To case based reasoning, the general description, the related technologies and application is discussed.Secondly, in this paper a lot of research has focused on related technologies of event ontology. Through analysis the lack of other case representation models in coal mine safety event, the oriented event ontology case representation model is proposed. And according to the characteristics of coal mine safety event, the component of event and the relationship between events, we use ontology development tool ‘protégé’ to construct event ontology model of coal-mine accident, and define the data properties and object properties. The event ontology is detected to make sure whether the event ontology has a conflict.Again, case retrieval and case similarity measure are the core part of the case-based reasoning technology. This paper also has a research on the two aspects and puts forward the improvement of case retrieval method and similarity calculation method according to the characteristics of coal mine safety accidents.Finally, the above research results have been applied to coal mine safety event ontology. We design and implement a case-based reasoning system of coal mine safety event ontology, select a mine accident to demonstrate the case-based reasoning process. Finally, the similarity calculation method proposed in this paper is compared with vector space model similarity measure to verify the validity and accuracy of the similarity calculation method by experiments.