摘要
采用近红外光谱技术建立了一种快速无损的乌龙茶品种识别方法。收集闽南地区不同茶场中铁观音、黄金桂、本山、毛蟹与梅占等5个品种共210份具有代表性的乌龙茶样品，采集近红外光谱数据，选用1100～1300 nm ，1640～2498 nm作为检测波长范围，利用主成分分析法（principal component analysis ， PCA）建立模型，并在实验过程中比较多元散射校正（multiplicative scatter correction ，MSC）与标准正态变量校正（standard normal variate ，SNV）两种数据预处理方法对模型的影响。实验结果表明，多元散射校正对模型的影响优于标准正态变量校正，对校正集的识别准确率达到了96％，对预测集中样品的识别准确率达到了90％。实验结果证明了采用近红外光谱技术可以快速无损识别闽南地区乌龙茶，具有较强的实用价值和推广价值。
The present paper presented a fast and non-destructive method for the discrimination of minnan oolong tea varieties by near-infrared spectroscopy technology .Two hundred ten samples including Tieguanyin ,Huangjingui ,Benshan ,Maoxie and Meizhan were collected in different tea plantations of Minnan .NIR spectra of 1 100~1 300 nm and 1 640~2 498 nm were suc-cessfully obtained .Prediction model was built by principal component analysis （PCA） ,and the effects of multiplicative scatter correction（MSC） and standard normal variate（SNV） on the model were observed and compared .It was indicated that the effect of MSC on the model was superior for the effect of SNV because the classification accuracy of model for the calibration samples reached 96% ,and this number to the prediction samples was about 90% .These results demonstrated that the near-infrared spectroscopy method established could be an efficient and accurate way for the discrimination of minnan oolong teas and would have a strong practical value .
出处
《光谱学与光谱分析》
SCIE
EI
CAS
CSCD
北大核心
2014年第3期656-659,共4页
Spectroscopy and Spectral Analysis
基金
科技部支撑计划产学研项目(2011BAK10B04)
质检公益项目(101010073-2)
国家质检总局科技项目(2013IK147)资助
