Research On Ontology Construction Of Gas Explosion Accident And Semantic Reasoning

Semantic Web technology provides a method for the unified description and processing of complex information,which widely used in biomedical,building automation.Semantic reasoning technology can infer information from existing data and obtain implicit information that plays an important role in semantic research.In this paper,semantic ontology construction and reasoning are introduced into the field of mine safety.This not only provides a unified knowledge description system for the field of mine safety,but also enables the extension of exisiting information.It provides technical support for mine safety early warning.Based on the mine accident danger source theory and the gas explosion accident tree analysis method,a gas explosion accident ontology containing the mine danger source ontology and gas explosion accident tree ontology is constructed.By designing the custom rules of Jena,the reasoning from the root danger source to the status danger source is realized.At the same time,according to the gas explosion accident tree ontology,the calculation of the top event probability is completed.The experimental results show that the constructed mine danger source ontology can realize the correct reasoning,and calculate the probability of top event based on gas explosion accident tree ontology.This preliminarly verifies the effectiveness of using OWL ontology to predict gas explosion accidents.Apart from this,we found that the reasoning efficiency is gradually declining with the increase of the amount of ontology and rule data,which provides the direction of the next research.With the rapid growth of semantic data,traditional single-machine reasoning systems can not satisfy effective inference calculations,and exisiting parallel reasoning algorithms also have obvious shortcomings in inference performance.Based on the ontology reasoning research in the field of mine safety,and with the background of large-scale semantic data processing,this paper proposed an algorithm,named as parallel reasoning for OWL semantic rules based on Spark(PROS).The algorithm includes three major optimizations as follows.Firstly,by analyzing the mutual dependencies,the OWL Horst rules are divided into four classes.Secondly,locally optimal strategies are designed for the four classes of rules,which furtherly improves the reasoning efficiency.Thirdly,carefully analyzing the dependencies of the four classes of rules,we take the Sameas rules into iteration so as to boost reasoning ability of PROS.Applying PROS algorithm to gas explosion accident ontology reasoning,and reasoning time is significantly reduced.The experimentalresults indicate that the proposed PROS outperforms in reasoning integrity and stability compared to existing parallel reasoning algorithms.Meanwhile the PROS greatly reduces the reasoning time compared to single-node implementation and shows good expansibility.