基于神经网络的矿用红外瓦斯传感器检测模型的研究  

Research of Detection Model of Mine-used Infrared Gas Sensor Based on Neural Network

作　　者：张丽[1] 王汝琳[1] 王瑛[1] 贺玉凯[1] 

机构地区：[1]中国矿业大学(北京)机电与信息工程学院,北京100083

出　　处：《工矿自动化》2009年第8期18-21,共4页Journal Of Mine Automation

基　　金：国家自然科学基金重点项目(50534060)

摘　　要：文章简要介绍了瓦斯红外检测原理,指出了传统吸收型模型的不足,基于RBF神经网络的非线性逼近能力建立了一种红外瓦斯传感器检测模型,给出了RBF神经网络的组织,并对RBF神经网络进行了训练,得到了红外瓦斯传感器检测模型的RBF神经网络结构。实验结果表明,该模型误差小、精度高,可满足煤矿井下应用的需要。The paper briefly introduced the principle of gas infrared detection and pointed out existing problems of traditional absorption model.It established a detection model of infrared gas sensor based on nonlinear approximation capability of RBF neural network,gave the structure of the RBF neural network,and trained the RBF neural network,then obtained RBF neural network structure of the detection model of infrared gas sensor.The experiment results showed that the model has small error and high accurate,which can meet the requirements of mine application.

关 键 词：煤矿 红外瓦斯传感器 非线性 RBF神经网络 

分 类 号：TD712[矿业工程—矿井通风与安全]