摘要:
为了更有效合理地解决煤矿工作面中低氧问题,以神东某煤矿工作面监测数据为样本, 考虑监测物理参数之间的相互影响关系,借助主成分分析法对广义回归神经网络(GRNN)进行 改进,构建工作面氧气浓度预测模型,编制改进的GRNN模型程序。 将预测氧气浓度结果与实测 数据对比,证明改进后的GRNN模型具有良好的拟合准确度和泛化能力,比改进前GRNN模型和 BP神经网络模型更适合于煤矿工作面低氧问题的预测;利用改进的GRNN模型分析了工作面 进、回风压力及进风温度对工作面及回风平巷氧浓度的影响,为矿井工作面低氧预测及工作面低 氧防治技术提供了参考。
Abstract:
Inordertosolvetheproblemofworkingfacehypoxiaincoalminemoreeffectivelyandreasonably,animprovedgeneralneuralnetwork(GRNN)modelforpredictionofoxygenconcentrationin coalminewasconstructed,bytakingthemonitoringdataofaworkingfaceinShendongassamplesand consideringtheinteractionrelationshipbetweenphysicalparameters,basedonprincipalcomponentanalysis.Comparingthepredictedoxygenconcentrationresultswiththemeasureddata,itprovesthatthe improvedGRNN model has good fitting accuracy and generalization ability.By using the improved GRNNmodel,theoriginalGRNNmodelandBPneuralnetworkmodelrespectivelyinthecomparative analysisofhypoxiaproblems,itfoundthattheimprovedGRNNmodelhasbettereffectsandismore suitableforthepredictionofhypoxiaproblemsincoalmineface.Theinfluenceofinletairpressure, outletairpressureandinletairtemperatureontheoxygenconcentrationwereanalyzedbytheimproved GRNNmodel.ThisimprovedGRNNmodelcangiveareferencetohypoxiapredictionandhypoxiacontroltechnologyoftheworkingface.
点击查看大图
下载: