近红外光谱技术结合人工神经网络判别普洱茶发酵程度

为了实现对普洱茶发酵程度快速判别,该研究提出了利用近红外光谱结合人工神经网络的方法。普洱茶是中国特有的茶类,发酵是普洱熟茶品质形成的关键工序,目前对于发酵程度的评价主要依赖感官审评,缺乏客观的量化依据。试验以轻度发酵、适度发酵和过度发酵3个不同发酵程度的普洱茶为研究材料。首先对采集得到的原始光谱进行标准归一化(SNV)预处理,利用人工神经网络(ANN)模式识别方法构建普洱茶发酵程度鉴别模型,在模型建立过程中,通过交互验证的方法对模型的最佳主成分因子数(PCs)进行优化。当主成分因子数为9时,ANN模型所得到的结果最佳,模型交互验证识别率和预测识别率分别为98.9%和97.8%。研究结果表明,近...

Full description

Saved in:
Bibliographic Details
Published in农业工程学报 Vol. 29; no. 11; pp. 255 - 260
Main Author 宁井铭 宛晓春 张正竹 毛小文 曾新生
Format Journal Article
LanguageChinese
Published 农业部茶及药用植物安全生产重点开放实验室,安徽农业大学,合肥 230036%勐海茶业有限责任公司,勐海 666200 2013
Subjects
Online AccessGet full text
ISSN1002-6819
DOI10.3969/j.issn.1002-6819.2013.11.033

Cover

More Information
Summary:为了实现对普洱茶发酵程度快速判别,该研究提出了利用近红外光谱结合人工神经网络的方法。普洱茶是中国特有的茶类,发酵是普洱熟茶品质形成的关键工序,目前对于发酵程度的评价主要依赖感官审评,缺乏客观的量化依据。试验以轻度发酵、适度发酵和过度发酵3个不同发酵程度的普洱茶为研究材料。首先对采集得到的原始光谱进行标准归一化(SNV)预处理,利用人工神经网络(ANN)模式识别方法构建普洱茶发酵程度鉴别模型,在模型建立过程中,通过交互验证的方法对模型的最佳主成分因子数(PCs)进行优化。当主成分因子数为9时,ANN模型所得到的结果最佳,模型交互验证识别率和预测识别率分别为98.9%和97.8%。研究结果表明,近红外光谱技术结合模式识别能够实现对普洱茶发酵质量的快速判别,评判结果具有较高的准确性,优于感官审评。
Bibliography:11-2047/S
Ning Jingming, Wan Xiaochun, Zhang Zhengzhu, Mao Xiaowen, Zeng Xinsheng (1. Key Laboratory of Tea and Medicinal Plant and Product Safety, Ministry of Agriculture, A nhui agricultural university Hefei 230036, China; 2. Menghai Tea Co.Ltd, Menghai 666200, China)
In order to get a rapid estimation on the fermentation degree of Pu’er tea in processing, the method of Near Infrared (NIR) spectroscopy combined with Artificial Neural Network (ANN) was first established in this study. Pu’er tea is a special tea that was processed in China only, and was favored by consumers at home and abroad with its bacteriostatic effect and its removal of grease, detoxification and other effects. Fermentation is the most critical process. The degree which is good or bad of fermentation affects the last quality of Pu’er tea directly. Fermentation is high, the beverage color may be red brown, and taste is weak. If fermentation is light, the taste is bitter and astringent, with brown leaves rather than green. Fermentation moder
ISSN:1002-6819
DOI:10.3969/j.issn.1002-6819.2013.11.033