發(fā)布時(shí)間：2018-09-07 17:10

【摘要】：為了實(shí)現(xiàn)對(duì)小麥品質(zhì)參數(shù)的快速檢測(cè),本文提出了基于近紅外光譜結(jié)合定量算法建立數(shù)學(xué)模型,以全國(guó)各地的160份小麥顆粒和小麥面粉為對(duì)象,采集其漫反射吸收光譜,并以國(guó)標(biāo)法檢測(cè)得到小麥的蛋白質(zhì)含量、水分值和面筋值作為參考值,將所得樣品均勻劃分成訓(xùn)練集和驗(yàn)證集,對(duì)所建模型進(jìn)行定標(biāo)驗(yàn)證,并使用最佳模型檢測(cè)小麥其它成分,具體研究?jī)?nèi)容和結(jié)果如下:1、以BP神經(jīng)網(wǎng)絡(luò)為基礎(chǔ),結(jié)合不同的優(yōu)化算法建立數(shù)學(xué)模型通過(guò)神經(jīng)網(wǎng)絡(luò)定量分析方法,結(jié)合小波算法、去趨勢(shì)算法、一階導(dǎo)數(shù)算法、主成分分析法等預(yù)處理算法,對(duì)得到的小麥蛋白質(zhì)光譜數(shù)據(jù)進(jìn)行預(yù)處理,結(jié)果表明:神經(jīng)網(wǎng)絡(luò)通過(guò)主成分分析和去趨勢(shì)算法得到的結(jié)果最佳R值高達(dá)0.98,RMSEP為0.26%,其他數(shù)學(xué)模型線性結(jié)果較佳,R值在0.95到0.98之間,RMSEP在0.26%到0.30%之間。2、以偏最小二乘回歸PLSR為基礎(chǔ),結(jié)合不同的優(yōu)化算法建立數(shù)學(xué)模型通過(guò)偏最小二乘法定量分析方法,結(jié)合小波算法,一階導(dǎo)數(shù),二階導(dǎo)數(shù),去趨勢(shì)算法建立數(shù)學(xué)模型,采用交叉驗(yàn)證留一法取得最佳主成分個(gè)數(shù)。對(duì)小麥蛋白質(zhì)光譜數(shù)據(jù)進(jìn)行處理,結(jié)果比較,數(shù)據(jù)經(jīng)過(guò)交叉驗(yàn)證留一法結(jié)合小波變換對(duì)光譜數(shù)據(jù)進(jìn)行預(yù)處理,得到的結(jié)果最佳R值為0.92,RMSPCV為1.71%,而其他數(shù)學(xué)模型線性效果一般。3、比較分析上述兩個(gè)模型通過(guò)兩個(gè)數(shù)學(xué)模型進(jìn)行分析比較得出,神經(jīng)網(wǎng)絡(luò)的預(yù)測(cè)能力明顯高于偏最小二乘法,不管是R還是RMSEP的數(shù)值大小都說(shuō)明神經(jīng)網(wǎng)絡(luò)更適合處理非線性的問(wèn)題。4、基于BP神經(jīng)網(wǎng)絡(luò)模型,對(duì)小麥水分和面筋含量的檢測(cè)使用已有的神經(jīng)網(wǎng)絡(luò)數(shù)學(xué)模型對(duì)小麥的水分和面筋值含量進(jìn)行檢測(cè),通過(guò)分析比較,面粉面筋在BP-ANN結(jié)合Detrended優(yōu)化算法下,得到的分析結(jié)果最佳,其中R值高達(dá)0.98,RMSEP值僅為0.24%,而小麥水分在BPP-ANN結(jié)合小波變換的算法下得到的結(jié)果最佳,其中R為0.96,RMSEP值為0.31%。
[Abstract]:In order to detect wheat quality parameters quickly, a mathematical model based on near infrared spectroscopy (NIR) combined with quantitative algorithm is proposed. 160 wheat grains and wheat flour from all over the country are taken as objects, and their diffuse reflectance absorption spectra are collected. The protein content, water value and gluten value of wheat were measured by national standard method as reference values. The samples were divided into training set and verification set, the model was calibrated and the best model was used to detect the other components of wheat. The specific research contents and results are as follows: 1. Based on BP neural network, mathematical model is established by combining different optimization algorithms. Quantitative analysis method of neural network, wavelet algorithm, trend removal algorithm, first-order derivative algorithm are used. Pretreatment algorithms such as principal component analysis (PCA) were used to preprocess the wheat protein spectral data. The results show that the optimum R value of neural network obtained by principal component analysis and de-trend algorithm is as high as 0.26, and that of other mathematical models is 0.95 to 0.98. The optimum R value of neural network is 0.26% to 0.30%, which is based on partial least square regression (PLSR). Combined with different optimization algorithms, mathematical models were established by partial least square quantitative analysis method, wavelet algorithm, first derivative, second order derivative, de-trend algorithm. The best number of principal components is obtained by using cross validation method. The spectral data of wheat protein were processed. The results showed that the data were preprocessed by cross validation and wavelet transform. The optimum R value is 0.92g RMSPCV (1.71V), while the linear effect of other mathematical models is normal. The comparison and analysis of the above two models show that the prediction ability of the neural network is obviously higher than that of the partial least square method. The magnitude of either R or RMSEP indicates that neural networks are more suitable for dealing with nonlinear problems. 4, based on the BP neural network model, The existing neural network mathematical model was used to detect the water content and gluten content of wheat. Through the analysis and comparison, the results of wheat flour gluten analysis under BP-ANN and Detrended optimization algorithm were the best. Among them, the R value was as high as 0.98g RMSEP was only 0.24, while the wheat moisture content was the best under the BPP-ANN and wavelet transform algorithm, where R was 0.96rMSEP = 0.31.
【學(xué)位授予單位】：中國(guó)計(jì)量學(xué)院
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類(lèi)號(hào)】：S512.1;TN219

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 張保軍,樊虎玲;環(huán)境條件對(duì)小麥蛋白質(zhì)的影響研究進(jìn)展[J];水土保持研究;2002年02期

2 V.A.Johnson;劉淑芬;陸維忠;;小麥蛋白質(zhì)育種的進(jìn)展與展望[J];麥類(lèi)作物學(xué)報(bào);1984年06期

3 林素蘭;;春小麥蛋白質(zhì)和賴氨酸與產(chǎn)量及其構(gòu)成因素的相關(guān)分析[J];遼寧農(nóng)業(yè)科學(xué);1988年01期

4 陸恒;;小麥蛋白質(zhì)及其制品[J];糧食與飼料工業(yè);1988年03期

5 王世敬;;加拿大小麥蛋白質(zhì)研究現(xiàn)狀[J];寧夏農(nóng)林科技;1989年04期

6 紀(jì)建海;崔志軍;;小麥蛋白質(zhì)、面粉特性與面條品質(zhì)的探討[J];糧食科技與經(jīng)濟(jì);2011年01期

7 黎永獻(xiàn);黃前美;王光慈;;大米和小麥蛋白質(zhì)的快速測(cè)定[J];西南農(nóng)學(xué)院學(xué)報(bào);1985年01期

8 張京;;小麥蛋白質(zhì)基因資源的開(kāi)發(fā)和利用[J];種子世界;1986年04期

9 王世敬;加拿大小麥蛋白質(zhì)研究的現(xiàn)狀和成就[J];寧夏農(nóng)學(xué)院學(xué)報(bào);1989年02期

10 殷允春;張麗娟;杜金哲;;氮肥運(yùn)籌對(duì)小麥蛋白質(zhì)及濕面筋含量的影響[J];青島農(nóng)業(yè)大學(xué)學(xué)報(bào)(自然科學(xué)版);2008年04期

相關(guān)重要報(bào)紙文章 前1條

1 ;小麥蛋白質(zhì)可能誘發(fā)幼兒糖尿病[N];北京科技報(bào);2003年

相關(guān)博士學(xué)位論文 前1條

1 張其斌;小麥蛋白質(zhì)的流變行為和力學(xué)性能研究[D];浙江大學(xué);2008年

相關(guān)碩士學(xué)位論文 前5條

1 王錚;化學(xué)改性對(duì)小麥蛋白質(zhì)塑料結(jié)構(gòu)與性能的影響[D];浙江大學(xué);2007年

2 溫亮;小麥蛋白質(zhì)近紅外模型的建立及特異種質(zhì)資源篩選與分析[D];華中農(nóng)業(yè)大學(xué);2009年

3 侯東麗;谷氨酰胺轉(zhuǎn)胺酶對(duì)小麥蛋白質(zhì)和淀粉催化研究[D];西北農(nóng)林科技大學(xué);2011年

4 賴立群;基于近紅外光譜的小麥品質(zhì)參數(shù)快速檢測(cè)[D];中國(guó)計(jì)量學(xué)院;2015年

5 田士林;多小穗小麥蛋白質(zhì)及相關(guān)農(nóng)藝性狀研究[D];西北農(nóng)林科技大學(xué);2008年

，

本文編號(hào)：2228888