【摘要】 本文将动态检测方法应用到电子鼻技术中,采用半导体气敏传感器MQ131、MQ135、MQ138组成阵列,设计了实时的动态检测、数据采集系统,测试了甲苯、乙酸酐、乙醚、丙酮四种气体.并且针对气体在动态检测方式下的气敏机理,提出了一种新的特征提取方法——分段平均微分值法,此方法既能获取动态响应过程的主流特征信息又有效地削弱了浓度的影响.最后,将分段平均微分法结合BP神经网络模式识别技术对不同浓度下的甲苯、乙酸酐、乙醚、丙酮四种气体进行了识别,识别率可达91.67%.更多还原

【Abstract】 In this study,Dynamic detection method was applied to the electronic nose technique,three semiconductor gas sensors MQ131、MQ135、MQ138 were chosen to compose the gas sensor array,and an on-line dynamic detection、data acquisition system was designed to make an identification among toluene、acetic anhydride、aether、acetone.A new method of feature extraction,segmental average differentiation was proposed here,which based on the gas mechanism under the dynamic detection of gas-sensors array,it reveals the main feature during the process of dynamic detection and reduces the influence of gas concentration effectively.At last,by means of the feature extraction method we proposed,and combined with the pattern recognition techniques of BP neural network,toluene、acetic anhydride、aether、acetone in different concentration have been recognized,the recognition rates come to 91.67%.更多还原