介绍了红外二氧化碳传感机理,提出了一种新型空间双光束测量结构,并基于RBF 神经网络建立了传感器数学模型。为了提高传感器动态特性,设计了动态补偿滤波器,研制成功一种新型高性能传感器。实验结果表明,上述技术有效地提高了传感器的精度、实时性及可靠性。关　键　词: 　　红外; 　二氧化碳传感器; 　数学模型; 　RBF 神经网络; 　动态补偿滤波器Abstract : The principle of sensing of carbon dioxide using IR radiation is int roduced and a novel double2beam optical st ructure is presented in the paper. Based on the good abilities of RBF network such as nonlinear mapping , learning and generalizing , the mathematic model of IR carbon dioxide sen2 sor is established. A dynamic compensation filter is designed to improve the dynamic characteristic of IR carbon dioxide sensor. A novel IR carbon dioxide sensor with high performance is made. The ex2 perimental result s show that the above key techniques prompt the accuracy , real2time and reliability of IR carbon dioxide sensor efficiently.Key words : 　　IR ; 　Carbon dioxide sensor ; 　Mathematic model ; 　RBF neural network ; 　 Dynamic compensation filter