本文選題：濃香型白酒　切入點(diǎn)：三維熒光光譜　出處：《光譜學(xué)與光譜分析》2016年04期

【摘要】：提出一種利用三維熒光光譜技術(shù)鑒別不同品牌濃香型白酒的方法。運(yùn)用FLS920熒光光譜儀測(cè)量了七個(gè)不同品牌濃香型白酒的三維熒光光譜,不同品牌濃香型白酒的熒光光譜特征相似,僅憑熒光特征參數(shù)較難區(qū)分。采用求偏導(dǎo)和小波壓縮相結(jié)合的數(shù)據(jù)預(yù)處理方法,求解光譜數(shù)據(jù)中每一激發(fā)波長(zhǎng)下,熒光強(qiáng)度對(duì)發(fā)射波長(zhǎng)的一階和二階偏導(dǎo)數(shù),選取db7緊支撐正交小波對(duì)數(shù)據(jù)進(jìn)行壓縮,選擇4尺度分解后的近似系數(shù)作為新的數(shù)據(jù)矩陣,然后做主成分分析(PCA)。將提取的主成分作為支持向量機(jī)(SVM)的輸入,并利用Kfold交叉驗(yàn)證的方法尋找支持向量機(jī)的最優(yōu)參數(shù)c和γ,建立不同品牌白酒的分類(lèi)鑒別模型。從每個(gè)品牌白酒中隨機(jī)選取14個(gè)樣本,共98個(gè)樣本組成訓(xùn)練集,其余的42個(gè)樣本組成預(yù)測(cè)集。分別比較了數(shù)據(jù)不求偏導(dǎo),對(duì)數(shù)據(jù)求一階偏導(dǎo)和二階偏導(dǎo)的預(yù)處理后對(duì)鑒別模型的影響。結(jié)果表明:三維熒光光譜經(jīng)過(guò)二階偏導(dǎo)的預(yù)處理后,結(jié)合主成分分析和支持向量機(jī)能很好地實(shí)現(xiàn)不同品牌濃香型白酒的分類(lèi)鑒別,模型的準(zhǔn)確率為98.98%,預(yù)測(cè)集的準(zhǔn)確率為100%。該方法具有簡(jiǎn)單,快速,成本低的優(yōu)點(diǎn),可為中國(guó)白酒的檢測(cè)和鑒別技術(shù)的發(fā)展提供幫助。
[Abstract]:A method of identification of three-dimensional fluorescence spectroscopy of different brands of liquor. By using FLS920 fluorescence spectrometer three-dimensional fluorescence spectra of seven different brands of liquor were measured, fluorescence spectral characteristics of different brands of liquor are similar, only by fluorescence characteristic parameters is difficult to distinguish. By using the method of data preprocessing and partial derivative the combination of wavelet compression, for spectral data of each excitation wavelength, the fluorescence intensity of the emission wavelength of one order and two order partial derivative, selecting DB7 compactly supported orthogonal wavelet to compress the data, select the approximate coefficient 4 scale decomposition as a new data matrix, then principal component analysis (PCA). The extraction of principal components as support vector machine (SVM) input, and using the method of Kfold cross validation to find the optimal parameters of support vector machine C and gamma, identification and classification of the establishment of different brand of liquor Model. From each brand of liquor were randomly selected from 14 samples, a total of 98 samples consisting of the training set and the remaining 42 samples composed of prediction set. Compared the data for partial derivatives, for impact on identification model of first-order partial derivative and two order partial derivatives of the pretreatment of the data. The results showed that: three dimensional fluorescence spectra after two order partial derivatives of the pretreatment, combined with principal component analysis and support vector machine can realize the identification and classification of different brands of liquor, the accuracy of the model is 98.98%, the accuracy rate of the prediction set is 100%. the method is simple, rapid, low cost, can help to develop for the detection and identification technology Chinese liquor.

【作者單位】： 江南大學(xué)理學(xué)院;
【基金】：國(guó)家自然科學(xué)基金項(xiàng)目(61378037)資助
【分類(lèi)號(hào)】：O657.34;TS261.7

【相似文獻(xiàn)】

中國(guó)期刊全文數(shù)據(jù)庫(kù) 前1條

1 袁瀚;易彬;沈才萍;;應(yīng)用GC-MS對(duì)兩種原糧釀造的濃香型白酒揮發(fā)性化合物的分析[J];釀酒科技;2014年03期

，

本文編號(hào)：1716475