第8卷第2期 智能系统学报 Vol.8 No.2 2013年4月 CAAI Transactions on Intelligent Systems Apr.2013 D0I:10.3969/i.issn.16734785.201209026 网络出版t地址：htp://www.cnki.net/kcma/detail/23.1538.TP.20130326.0906.003.html 自适应概率神经网络及其在白酒电子鼻中的应用 周红标，张宇林，丁友威，刘佳佳2 (1.淮阴工学院电子与电气工程学院，江苏淮安223003；2.南京师范大学电气与自动化工程学院，江苏南京210042) 摘要：为了探索电子鼻对白酒品质鉴别的可能性，利用自制的新型无线白酒电子鼻对洋河海之蓝、今世缘省接待、 安徽迎驾大曲和牛栏山陈酿进行了分析.对所采集的数据进行平滑处理后提取稳态响应值和斜率值，利用主成分分 析对特征向量进行降维处理，并将获得的前2个主元得分作为概率神经网络识别模型的输入参量.针对传统概率神 经网络平滑因子σ单一易导致分类错误的缺陷，利用差异演化算法优化σ参数集，建立了自适应概率神经网络识别 模型.实验结果表明，DE-PNN相比BP-PWNN、PSO-PNN和SVM等，识别精度更高，抗噪性能更好，同时也证明了电子 鼻能有效地检出不同品牌的白酒。 关键词：差异演化算法；自适应概率神经网络；电子鼻；白酒识别 中图分类号：TP183:1TS262.3文献标志码：A文章编号：16734785(2013)02-017706 Application of adaptive probabilistic neural network in Chinese liquor E-Nose ZHOU Hongbiao',ZHANG Yulin',DING Youwei',LIU Jiajia2 (1.Faculty of Electronic and Electrical Engineering,Huaiyin Institute of Technology,Huai'an 223003,China;2.School of Electrical and Automation Engineering,Nanjing Normal University,Nanjing 210042,China) Abstract:In order to explore the possibility of hard liquor quality recognition by an electronic nose,the Chinese liquor of Yanghe Haizhilan,Jinshiyuan Shengjiedai,Anhui Yingjiadaqu,and Niulanshan Chenniang were analyzed by using self-made new wireless electronic nose for recognition of hard liquor quality.Firstly,the steady-state re- sponse and slope values were extracted after smoothing the collected data.Secondly,principal component analysis PCA was used to reduce the dimension of the eigenvector,and the obtained first two principal components scores were then used as the input parameters of the probabilistic neural network recognition model.Next,the aim was to overcome defect of traditional probabilistic neural network smoothing factor which would cause classification error easily.The method of adaptive probabilistic neural network identification model was presented,utilizing differential evolution algorithm to optimize the set of parameters.The results show that differential evolution-probabilistic neural network obtained a high recognition accuracy and noise immunity compared to back propagation,particle swarm op- timization-probabilistic neural network and support vector machine.The experiment also proved that the electronic nose can effectively detect different liquor brands in China. Keywords:differential evolution algorithm;adaptive probabilistic neural network;electronic nose;hard liquor quality recognition 白酒电子鼻最主要的应用场合是对白酒生产过别.目前，白酒品质识别主要是使用电子鼻对不同品 程进行质量监控，以保证白酒的品质，其核心要 牌、不同酒精度和不同香型的白酒进行识别23]，期 求就是要实现基于计算机技术的白酒品质智能鉴 望能够通过气味数据的处理将它们区分开来.传感 器所测量的信号与被测量的气体之间并没有直接对 收稿日期：201209-12.网络出版日期：201303-26. 基金项目：国家自然科学基金资助项目(61203056)：准安市科技公共 应关系，因而需要通过模式识别算法对其进行处理. 服务平台资助项目(HAP201107). 目前，电子鼻数据分析中的模式识别算法主要 通信作者：周红标.E-mail:bihb@163.com