基于BP网络的气敏传感器阵列测试分析  

Test and analysis of BP network-based gas sensor arrays

作　　者：周东祥[1] 宋委远[1] 王鹤[1] 周新民[1] 

机构地区：[1]华中科技大学电子科学与技术系,湖北武汉430074

出　　处：《华中科技大学学报（自然科学版）》2007年第4期51-53,共3页Journal of Huazhong University of Science and Technology(Natural Science Edition)

基　　金：武汉市科技局重大攻关项目(20041003068-02)

摘　　要：将BP人工神经网络应用于气敏传感器阵列测试系统中,对测试系统进行了详细的论述.用改进BP算法对不同浓度的目标混合气体进行了定性及定量分析,并以图表形式输出结果.研究表明,网络经过多次训练及测试后,基本上克服了半导体传感器因存在“交叉敏感性”而影响输出的缺点,提高了测试准确度,总体性能较好.The analysis and application of back-propagation （BP） artificial neural network for the gas sensor array test system is presented, and the parts of the test system are proposed. With the improved back-propagation algorithm, the quantitative and qualitative analysis results for the multi-gas in different concentration were obtained with graph and table. The experiment indicates that the disadvantage of ＂across sensitivity＂ is avoided with the BP network training and testing, the result can meet the required precision, which shows that the combination of gas sensor array and artificial neural network can complete the test of the quantitative and qu＇alitative analysis for the multi-gas.

关 键 词：BP网络 气敏传感器阵列 测试分析 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]