基于电子鼻技术的茶叶贮藏时间检测方法  

Detection Method for Storage Time of Tea Based on Electronic Nose Technology

作　　者：杨春兰[1] 薛大为[1] 

机构地区：[1]蚌埠学院电子与电气工程系,安徽蚌埠233030

出　　处：《兰州文理学院学报（自然科学版）》2016年第5期51-54,共4页Journal of Lanzhou University of Arts and Science(Natural Sciences)

基　　金：安徽省高等学校省级自然科学研究项目(KJ2013Z195);安徽省高等学校优秀青年人才基金项目(2012SQRL218)

摘　　要：为了寻求不同贮藏时间下茶叶品质的检测方法,以黄山毛峰茶为研究对象,利用电子鼻对7个不同贮藏时间下的干茶叶进行检测.根据电子鼻传感器阵列响应特点选取了特征变量,以特征变量为自变量,以茶叶贮藏时间为因变量,建立了茶叶贮藏时间的BP神经网络预测模型.通过测试样本对模型进行实验分析.结果表明:该模型对于7个不同贮藏时间茶叶样本最大预测误差为42.1天,预测误差超过10天的最大样本数为5个,占总样本数的7.14%.验证了所建立的茶叶贮藏时间BP神经网络预测模型的可行性.In order to seek the detection method of tea quality in different storage time, dry Huangshan Maofeng Tea under 7 different storage time are chosen to be detected by electronic nose. Characteristic variables are chosen according to the response of electronic nose sensors. Then, BP neural network prediction model is built by using characteristic variables as independent variables and storage time as dependent variable. The experimental analysis shows that the maximum prediction errors for tea un- der 7 different storage time are 42.1 days; the maximum sample size with prediction errors exceeding 10 days are 5 samples, 7.14% of total samples. Thus, the feasibility of the prediction model for storage time of tea is verified.

关 键 词：茶叶 电子鼻 贮藏时间 BP神经网络 

分 类 号：TP212.6[自动化与计算机技术—检测技术与自动化装置]