二元混合气体识别中传感器阵列优化方法研究  

Optimization of Sensor Array in Identification of Binary Gas Mixtures

作　　者：张双岩[1] 余隽[1] 唐祯安[1] 魏广芬[2] 陈毅[1] 申宁[1] 

机构地区：[1]大连理工大学电信学院电子系,辽宁大连116023 [2]山东工商学院信息与电子工程学院,山东烟台264005

出　　处：《仪表技术与传感器》2010年第7期80-83,共4页Instrument Technique and Sensor

基　　金：国家高技术研究发展计划项目(2006AA040102;2006AA040106)

摘　　要：用于混合气体识别的电子鼻系统中,气体传感器阵列直接决定了识别效果、算法复杂性和硬件成本。为了研究阵列优化方法,以甲烷和乙烯二元混合气体为识别对象,将方差分析法和主成分分析法相结合用于气体传感器阵列的筛选优化,对比了优化前和优化后的传感器阵列对二元混合气体的识别效果。该阵列优化方法能够最大限度地简化传感器阵列,优化后的传感器阵列在保持识别精度的同时,传感器数量更少、软硬件成本降低、网络收敛速度更快。Gas sensor array is the base of electrical nose which determines the recognition results,the algorithm complexity and the cost of hardware.Optimization of sensor array was studied.Taken the binary gas mixture of methane and ethylene as the identify object,variance analysis and principal component analysis were combined to select the optimized sensor array,and the identification effect of the pre-optimized array and the optimized array was compared.With this sensor array optimization method,the optimized array occupies less gas sensor in the array,reduces the hardware and algorithms costs,and improves the network convergence speed,meanwhile,it has the similar gas identification properties as the original large sensor array.

关 键 词：方差分析 主成分分析(PCA) BP神经网络 混合气体识别 传感器阵列 

分 类 号：TP212.9[自动化与计算机技术—检测技术与自动化装置]