本文選題：近紅外光譜技術(shù) + 蒙特卡羅交叉驗(yàn)證　； 參考：《北方工業(yè)大學(xué)》2017年碩士論文

【摘要】：淀粉品質(zhì)的優(yōu)劣與其水分含量的多少關(guān)系密切。傳統(tǒng)的檢測(cè)技術(shù)雖然能夠達(dá)到預(yù)測(cè)目的,但是常常伴有耗時(shí)長(zhǎng),效率低,準(zhǔn)確性差,破壞待測(cè)樣本等諸多缺點(diǎn)。因此,研究一種快速、方便、準(zhǔn)確、無(wú)損的檢測(cè)方法具有十分重要的意義。本文以淀粉為研究對(duì)象,利用近紅外光譜技術(shù)和化學(xué)計(jì)量學(xué)分析方法,開展淀粉含水量檢測(cè)技術(shù)的研究。先對(duì)所采集的淀粉樣本做了光譜預(yù)處理、提取最佳主成分?jǐn)?shù)、識(shí)別和剔除奇異樣本等前期準(zhǔn)備工作,然后建立定量校正模型,最終實(shí)現(xiàn)了對(duì)淀粉含水量的預(yù)測(cè)。本文運(yùn)用偏最小二乘回歸(Partial Least Squares Regression,PLSR)建立淀粉含水量的預(yù)測(cè)模型,由于建模前期的數(shù)據(jù)準(zhǔn)備工作對(duì)模型的穩(wěn)定性和預(yù)測(cè)能力影響較大,本文的研究重點(diǎn)主要放在建模前的數(shù)據(jù)處理中,包括選擇光譜預(yù)處理方法、提取最佳主成分、識(shí)別與驗(yàn)證校正集中的奇異樣本等工作。論文通過對(duì)比不同預(yù)處理方法下模型的評(píng)價(jià)指標(biāo)的優(yōu)劣,選擇了適合淀粉樣本的標(biāo)準(zhǔn)正態(tài)變量變換(SNV)的光譜預(yù)處理方法;而參與建模的最佳主成分?jǐn)?shù)的確定則利用交互驗(yàn)證均方差方法進(jìn)行選擇。其中,對(duì)奇異樣本的識(shí)別設(shè)計(jì)了一種基于蒙特卡羅交叉驗(yàn)證(Monte Carlo cross validation,MCCV)的檢測(cè)方法,該方法基于蒙特卡羅的概率統(tǒng)計(jì)思想,建立大量的PLSR模型,得到所有校正集樣本的預(yù)測(cè)殘差的均值和方差,做出均值-方差分布圖,把位于高均值或高標(biāo)準(zhǔn)差區(qū)域的樣本暫定為可疑樣本。然后利用三組對(duì)比實(shí)驗(yàn)并結(jié)合t檢驗(yàn)對(duì)識(shí)別出的奇異樣本做驗(yàn)證。對(duì)比實(shí)驗(yàn)分別是:保留可疑樣本建模、剔除可疑樣本建模、隨機(jī)剔除與可疑樣本數(shù)目相同的樣本建模。先記錄各實(shí)驗(yàn)中模型的評(píng)價(jià)指標(biāo),再運(yùn)用t檢驗(yàn)方法對(duì)指標(biāo)間的差異進(jìn)行分析,由t檢驗(yàn)結(jié)果判斷差異是否具有顯著性。若存在顯著性差異,則說明識(shí)別出的可疑樣本是奇異樣本;反之,則說明該可疑樣本是非奇異樣本。本文用蒙特卡羅交叉驗(yàn)證法對(duì)參與建模的100個(gè)淀粉樣本進(jìn)行奇異樣本的識(shí)別和驗(yàn)證,成功篩查出了其中的奇異樣本,證明了該方法的可靠性。然后,用經(jīng)過前期處理的淀粉樣本建立了含水量預(yù)測(cè)模型,并用測(cè)試集樣本對(duì)模型進(jìn)行了驗(yàn)證,通過對(duì)含水量的預(yù)測(cè)值和實(shí)際值的分析,證明了預(yù)測(cè)模型的可行性。故把近紅外光譜技術(shù)應(yīng)用到淀粉含水量預(yù)測(cè)系統(tǒng)的設(shè)計(jì)中。軟件設(shè)計(jì)用到Matlab和SPSS。Matlab調(diào)用Excel表中的數(shù)據(jù),用于分析和建模,并實(shí)現(xiàn)對(duì)仿真結(jié)果的展示;SPSS實(shí)現(xiàn)對(duì)數(shù)據(jù)的統(tǒng)計(jì)和分析。
[Abstract]:The quality of starch is closely related to the amount of water content. Although the traditional testing technology can achieve the purpose of prediction, it is often accompanied by long time, low efficiency, poor accuracy, and many disadvantages. Therefore, it is of great significance to study a rapid, convenient, accurate and nondestructive testing method. Powder is used as the research object, using near infrared spectroscopy and chemometrics analysis to carry out the research on the detection technology of starch moisture content. First, we pretreated the sample starch samples, extracted the best main fraction, identified and eliminated the strange sample preparation work, then established the quantitative correction model, and finally realized the lake. Prediction of the water content of powder. This paper uses partial least squares regression (Partial Least Squares Regression, PLSR) to establish the prediction model of water content in starch. Because the data preparation work in the early stage of modeling has great influence on the stability and prediction ability of the model, the main focus of this paper is to be placed in the data processing before modeling, including the selection of spectrum. Preprocessing method, extracting the best principal component, identifying and validating the singular samples of the calibration center. By comparing the evaluation indexes of the model under different preprocessing methods, the paper selects the standard normal variable transformation (SNV) method suitable for the starch sample, and the optimum main fraction of the model is determined by the method. In this method, a detection method based on Monte Carlo cross validation (MCCV) is designed for the identification of singular samples. The method is based on the probability and statistics idea of Monte Carlo and establishes a large number of PLSR modes, and the mean sum of the predicted residual of all correction set samples is obtained. Variance, make the mean variance distribution map, set the sample in the high mean or high standard deviation region as suspicious sample. Then use three groups of contrast experiments and t test to verify the identified singular samples. Contrast experiments are: retaining suspicious sample modeling, eliminating suspicious sample modeling, random elimination of the number of suspicious samples The same sample model is used to record the evaluation indexes of the models in each experiment, and then the t test method is used to analyze the differences between the indexes. The t test results are used to determine whether the difference is significant. If there is a significant difference, the identified suspicious samples are singular samples, and the inverse, the suspicious sample is a nonsingular sample. The Monte Carlo cross validation method is used to identify and verify the singular samples of 100 starch samples involved in the modeling. The singular samples are successfully screened and the reliability of the method is proved. Then, the prediction model of water content is established with the starch samples treated by the previous period, and the model is verified by the test set sample. After the analysis of the prediction value and actual value of water content, the feasibility of the prediction model is proved. Therefore, the near infrared spectroscopy is applied to the design of the prediction system of starch water content. The software design uses Matlab and SPSS.Matlab to call the data in the Excel table, for analysis and modeling, and to the display of the simulation results; the SPSS realizes the data. Statistics and analysis.

【學(xué)位授予單位】：北方工業(yè)大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TS237;O657.33

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 宋相中;唐果;張錄達(dá);熊艷梅;閔順耕;;近紅外光譜分析中的變量選擇算法研究進(jìn)展[J];光譜學(xué)與光譜分析;2017年04期

2 王旭朝;郝中騏;郭連波;李祥友;曾曉雁;陸永楓;;顯微激光誘導(dǎo)擊穿光譜技術(shù)對(duì)低合金鋼中Mn的定量檢測(cè)[J];光譜學(xué)與光譜分析;2017年04期

3 張伊挺;王翠翠;樊夢(mèng)麗;蔡文生;邵學(xué)廣;;基于便攜式近紅外光譜儀的重金屬離子定量分析研究[J];光譜學(xué)與光譜分析;2016年12期

4 王海霞;所同川;余河水;李正;;基于近紅外光譜技術(shù)的甘草提取過程最優(yōu)建模方法研究[J];中國(guó)中藥雜志;2016年19期

5 李正風(fēng);徐廣晉;王家俊;杜國(guó)榮;蔡文生;邵學(xué)廣;;模型診斷用于近紅外光譜建模校正集中奇異樣本的識(shí)別[J];分析化學(xué);2016年02期

6 林永忠;李麗娜;林添良;;血糖近紅外光譜分析中奇異樣本去除方法研究[J];生物醫(yī)學(xué)工程學(xué)雜志;2015年06期

7 王智宏;劉杰;王婧茹;孫玉洋;于永;林君;;數(shù)據(jù)預(yù)處理方法對(duì)油頁(yè)巖含油率近紅外光譜分析的影響[J];吉林大學(xué)學(xué)報(bào)(工學(xué)版);2013年04期

8 孫曉榮;劉翠玲;吳靜珠;董秀麗;吳勝男;;基于近紅外光譜的淀粉含水量快速檢測(cè)研究[J];食品工業(yè)科技;2011年10期

9 李華;王菊香;郭恒光;陶楊;劉潔;;光譜預(yù)處理方法對(duì)混胺近紅外定量模型影響的研究[J];分析科學(xué)學(xué)報(bào);2010年05期

10 柳艷云;胡昌勤;;近紅外分析中光譜波長(zhǎng)選擇方法進(jìn)展與應(yīng)用[J];藥物分析雜志;2010年05期

相關(guān)博士學(xué)位論文 前1條

1 林志丹;基于可見/近紅外光譜分析的化肥土壤成分速測(cè)模型研究[D];中國(guó)科學(xué)技術(shù)大學(xué);2016年

相關(guān)碩士學(xué)位論文 前9條

1 陳國(guó)權(quán);近紅外光譜技術(shù)在感冒靈顆粒生產(chǎn)過程質(zhì)量控制中的應(yīng)用研究[D];浙江大學(xué);2017年

2 常云彩;常見食用淀粉特性及摻假檢測(cè)方法研究[D];河南工業(yè)大學(xué);2015年

3 韓明;基于近紅外光譜技術(shù)食品檢測(cè)軟件開發(fā)及其應(yīng)用研究[D];電子科技大學(xué);2013年

4 徐彥;近紅外光譜技術(shù)快速檢測(cè)秈稻主要成分及新陳度的研究[D];中南林業(yè)科技大學(xué);2011年

5 張建慧;近紅外光譜分析法在煙草生產(chǎn)中的應(yīng)用研究[D];河南農(nóng)業(yè)大學(xué);2010年

6 楊瓊;近紅外光譜法定量分析及其應(yīng)用研究[D];西南大學(xué);2009年

7 馬蘭;基于近紅外光譜檢測(cè)番茄內(nèi)部品質(zhì)的研究[D];華中農(nóng)業(yè)大學(xué);2008年

8 吳繼明;模型轉(zhuǎn)移技術(shù)在近紅外光譜儀器上的應(yīng)用研究[D];江蘇大學(xué);2007年

9 李冰;近紅外光譜法用于丹參中原兒茶醛含量定量預(yù)測(cè)研究[D];吉林大學(xué);2004年

，

本文編號(hào)：1894654