Font Size: a A A

Risk Prediction Of Coal Mine Gas Explosion Disaster

Posted on:2018-04-01Degree:MasterType:Thesis
Country:ChinaCandidate:M Z ShanFull Text:PDF
GTID:2321330518992027Subject:Control theory and control engineering
Abstract/Summary:PDF Full Text Request
Coal mining mining belongs to high risk areas,including the dangers of gas explosion is one of the biggest,seriously affected the growth of national economy and social stability.The greater the chance of a gas explosion in a coal mine,the greater the damage to future disasters.How to predict the gas explosion quickly and accurately is a problem that needs to be solved.Based on this,this article made a detailed study of coal mine gas explosion prediction system,through the gas monitoring system combined with pattern recognition theory,put forward the KPCA-FOA-the SVM prediction model,and simulated in the model.Because the supervisory system of coal mine gas explosion has nonlinear,usually used in the control theory,it is difficult to meet the requirements of gas explosion risk prediction system,so this article flies algorithm based on support vector machine(SVM)optimization of the network,the network is applied to the prediction system.In view of coal mine gas explosion caused by many factors,and the influence degree of every factor is different,using kernel principal component analysis to cause explosion index for feature extraction,concise characteristic dimension.Because the parameters of support vector machine forecasting model can affect the convergence and generalization ability of the model,this article uses the drosophila global optimization algorithm,search optimal parameters combination model,so as to improve the accuracy of the prediction system,to improve the reliability of the monitoring system of gas explosion.Through constructing gas explosion prediction model,the monitoring system,real-time analysis of the impact indicators of FOA-SVM model in the simulation analysis is carried out in the monitoring system of gas explosion.The simulation shows that the model can warn the coal mine gas explosion,and the accuracy and reliability are better.Paper research is based on the national natural science fund project(51274118)study,such as pattern recognition,coal mine safety multidisciplinary study on combination of gas explosion in coal mine disasters,has certain theoretical research value and practical significance.
Keywords/Search Tags:gas explosion, kernel principal component analysis, fruit fly optimization algorithm, support vector machine
PDF Full Text Request
Related items