电子鼻漂移阈值构建及其白酒鉴别应用.docxVIP

电子鼻漂移阈值构建及其白酒鉴别应用 殷勇葛飞于慧春 河南科技大学食品与生物工程学院 摘要： 电了鼻漂移是气敏传感器的固有行为，用空载数据揭示漂移现象更具有一般性。 为了有效去除电子鼻漂移，提出了一种基于空载条件下与小波包分解的漂移去 除方法。对电子鼻空载数据进行小波包分解，获得小波包分解的逼近系数集;在 对其进行离散度分析之后，构建了空载条件下的一种阈值函数。在此阈值函数基 础上，扩展成为样本（有载）条件下的去漂移阈值函数，进而发展成有载样本 的漂移剔除方法。为了检验该方法的有效性及实用性，将其应用于4种白酒的鉴 别中。对4种白酒电子鼻数据按测试吋间顺序生成训练集和测试集，线性的 Fisher判别分析（FDA）结果表明，训练集、测试集数据处理前后的鉴别正确率 均得到了提高，最低提高值为23. 65%O这表明此方法能够提升电子鼻的检测能 力。同时，为了进一步检验该漂移去除方法的性能，采用非线性的BP神经网络 进行鉴别分析，结果显示:训练集的鉴别正确率从处理前的65. 5%提高到处理后 的100. 0%,处理后的测试集鉴别正确率也达到了 97. 5%。这不仅说明了 4种白酒 的鉴别属较复杂的非线性分类问题，还充分说明了该漂移去除方法的有效性。 关键词： 白酒;电子鼻;漂移;空载分析;小波包分解;鉴别分析; 作者简介：殷勇（1966-），男，教授，博士生导师，主要从事农产品、食品品 质检测技术研究，E-mai 1: yinyong@haust. edu. cn 收稿日期：2017-05-24 基金：国家自然科学基金项目 A Construeting Method of Threshold function for Electronic Nose Drift and Its Application in Identification of White Spirit Yin Yong Ge Fei Yu Huichun College of Food Bioengineering, Henan University of Science and Technology; Abstract： The drift i s the inhere nt behavior of gas sen sor, so it is more gen erality to reveal drift phenomena with no_load data. In order to remove the drift effectively, in the no-load condition, a drift removal method based on wavelet packet decomposition is proposed. Firstly, wavelet packet decomposition was employed to decompose the no-load data of the E~nose, and the approximation coefficient set of wavelet packet decomposition could be obtained. After the di serete analysis of the approximation coefficient set was carried out, a threshold function based on no-load data of the E~nose was constructed. Then, the drift threshold function based on the sample data (loaded data) was obtained by extending the threshold function based on no-load data; furthermore, a drift elimination method for sample data was given. To test the effectiveness and practicability of the above method, it was applied to identify 4 kinds of white spirit samples using the E-nose. The E-nose data of the 4 kinds of samples were divided into training set and test set according to the test time sequen