Study on Recognition of the True or False Red Wine Based on Visible-Near Infrared Spectroscopy

郭海霞; 王涛; 刘洋; 吴海云; 左月明; 宋海燕; 贺晋瑜

doi:doi:10.3964/j.issn.1000-0593(2011)12-3269-04

光谱学与光谱分析, 2011, 31 (12): 3269, 网络出版: 2012-01-05

Study on Recognition of the True or False Red Wine Based on Visible-Near Infrared Spectroscopy

论文大纲

郭海霞 ^1,*王涛 ¹刘洋 ¹吴海云 ¹左月明 ¹宋海燕 ¹贺晋瑜 ²

作者单位

¹ 山西农业大学工学院, 山西太谷030801

² 山西省农业科学院果树研究所, 山西太谷030815

葡萄酒可见-近红外光谱 BP神经网络真伪鉴别 Red wine Visible-near infrared spectroscopy BP neural network Ture or false Recognition

摘要

研究收集了不同品牌的90个葡萄酒样品，为了消除各光谱基线不同带来的影响，对所有光谱曲线都进行了一阶求导，以一阶导数谱线作为有效数据，通过独立主成分（PC）分析可知，前两个主成分的贡献率达到80%以上，主成分聚类使得真伪葡萄酒样品明显分为两类; 以前四个主成分作为BP神经网络的输入建立了一个三层人工神经网络的识别模型，该模型对葡萄酒样品的预测识别率达到100%。研究表明，可见-近红外透射光谱结合主成分分析建立的BP神经网络模型能为快速、无损鉴别葡萄酒真伪提供一种准确可靠的新方法。

Abstract

This study selected 90 samples from different brands of red wine. In order to eliminate the impact of spectral curve’s baseline, the first derivatives of all of spectral curves were calculated and the principal component analysis was carried out on the first derivative spectra. The result showed that the contribution rate of the first two principal components was over 80 percent. By the first two principal components, all the red wine samples were obviously divided into two classes. Furthermore a 3-layer artificial neural network predictive model was built with the first four principal components as input variables and 100 percent correct prediction rate was gained. The research showed that the visible-near infrared spectroscopy combined with principal component analysis provides an accurate and reliable new method to rapidly and nondestructively recognize the true or false red wines.

参考文献

[1] ZHU Ji-yi, WANG Zhen-hai（朱济义，王振海）. China Standardization（中国标准化）， 2001, 1(2): 23.

[2] WANG Hua, ZHAO Xian-hua, LIU Jing， et al（王华，赵现化，刘晶，等）. Scientia Agricultura Sinica（中国农业科学）， 2010, 43(15): 3204.

[3] WU Yu-tao（武玉涛）. Journal of Handan Polytechnic College（邯郸职业技术学院学报）， 2009, 22(3): 38.

[4] DU Xue-chun, ZHU Xiao-kai（杜学春, 朱孝凯）. Technology Wind（科技风）， 2009, (20): 190.

[5] ZOU Xiao-bo, ZHAO Jie-wen（邹小波，赵杰文）. Acta Optica Sinica(光学学报)， 2007, 27(7): 1316.

[6] LIU Yan-de, CHEN Xing-miao, OUYANG Ai-guo（刘燕德，陈兴苗，欧阳爱国）. Acta Optica Sinica(光学学报)， 2008, 28(3): 478.

[7] LIN Xin, NIU Zhi-you, LIU Mei-ying, et al（林新，牛智有，刘梅英，等）. Journal of Huazhong Agricultural University（华中农业大学学报), 2009, 28(4): 487.

[8] A Lita, XU Xiu-ting, SONG Juan-juan, et al（阿力塔，徐秀廷，宋娟娟，等）. Journal of Instrumental Analysis（分析测试学报）， 2009, 28(2): 177.

[9] ZOU Ping, WANG Shao-yan, ZHANG Zhi-qiang, et al（邹萍，王绍艳，张志强，等）. Journal of Instrumental Analysis（分析测试学报）， 2007, 26(1): 120.

[10] XIU Lian-cun, ZHENG Zhi-zhong, YU Zheng-kui, et al（修连存，郑志忠，俞正奎，等）. Acta Geologica Sinica（地质学报), 2007, 81(11): 1584.

[11] CHU Xiao-li, YUAN Hong-fu, LU Wan-zhen(褚小立，袁洪福，陆婉珍). Progress in Chemistry(化学进展)， 2004, 16（4）: 528.

[12] ZHOU Zi-li, ZHANG Yi-fang, HE Yong, et al（周子立，张怡芳，何勇，等）. Software Engineer(软件工程师)， 2010, (5): 53.

郭海霞, 王涛, 刘洋, 吴海云, 左月明, 宋海燕, 贺晋瑜. Study on Recognition of the True or False Red Wine Based on Visible-Near Infrared Spectroscopy[J]. 光谱学与光谱分析, 2011, 31(12): 3269. GUO Hai-xia, WANG Tao, LIU Yang, WU Hai-yun, ZUO Yue-ming, SONG Hai-yan, HE Jin-yu. Study on Recognition of the True or False Red Wine Based on Visible-Near Infrared Spectroscopy[J]. Spectroscopy and Spectral Analysis, 2011, 31(12): 3269.

Study on Recognition of the True or False Red Wine Based on Visible-Near Infrared Spectroscopy

关于本站 Cookie 的使用提示

全站搜索

Study on Recognition of the True or False Red Wine Based on Visible-Near Infrared Spectroscopy

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索