基于BP网络和D-S证据理论的瓦斯监测系统的研究  

Research of Gas Monitoring System Based on BP Network and D-S Evidence Theory

作　　者：付华[1] 康海潮[1] 梁明广[1] 

机构地区：[1]辽宁工程技术大学电气与控制工程学院,辽宁葫芦岛125105

出　　处：《工矿自动化》2011年第8期159-161,共3页Journal Of Mine Automation

基　　金：国家自然科学基金资助项目(50874059);教育部博士点项目(200801470003);辽宁省优秀人才基金项目(2007R18)

摘　　要：针对目前煤矿采用的瓦斯传感器输出信号具有模糊性、不确定性等问题,提出了一种基于BP网络和D-S证据理论的瓦斯监测系统的设计方案。该系统采用改进的BP算法获取煤矿环境的基本概率分配,采用D-S证据理论对BP网络输出结果进行信息融合,从而对井下瓦斯状态作出判断和决策。实验结果表明,该系统提高了瓦斯监测信息的准确性和决策的快速性。In view of problems of fuzziness and uncertainty of output signal of gas sensor used in coal mine,the paper proposed a design scheme of gas monitoring system based on BP network and D-S evidence theory.The system uses improved BP algorithm to get basic probability assignment of underground environment and uses D-S evidence theory to fusion information of output of BP network,so as to make judgment and decision of underground gas state.The experiment result showed that the system improves accuracy of monitored gas information and rapidity of decision.

关 键 词：瓦斯监测 信息融合 BP网络 D-S证据理论 LMBP算法 

分 类 号：TD712.3[矿业工程—矿井通风与安全]