牛乳清粉摻偽羊乳粉的近紅外光譜法快速無(wú)損檢測(cè)
發(fā)布時(shí)間：2018-10-23 08:41
【摘要】：為快速無(wú)損檢測(cè)摻偽羊乳粉中牛乳清粉的含量,采用近紅外光譜法(NIR)結(jié)合ν-支持向量回歸(ν-SVR)檢測(cè)197個(gè)摻偽牛乳清粉的羊乳粉,并與偏最小二乘法(PLS)對(duì)比,光譜經(jīng)平滑、標(biāo)準(zhǔn)變量變換及導(dǎo)數(shù)預(yù)處理。隨機(jī)選取132個(gè)樣本作為校正集建立模型,其余65個(gè)樣本作為測(cè)試集,評(píng)估模型性能。結(jié)果顯示:校正集最優(yōu)模型為標(biāo)準(zhǔn)變量變換、Savitzky-Golay平滑和二階導(dǎo)預(yù)處理ν-SVR模型,其交叉驗(yàn)證誤差均方根(RMSECV)為0.586,交叉驗(yàn)證相關(guān)系數(shù)(RCV)達(dá)到0.9947。預(yù)測(cè)集驗(yàn)證結(jié)果ν-SVR法比PLS法更優(yōu),ν-SVR模型預(yù)測(cè)值與真實(shí)值R達(dá)到0.9958,RMSEP為0.526。試驗(yàn)結(jié)果表明NIR結(jié)合ν-SVR模型可用于摻偽羊乳粉中牛乳清粉的快速無(wú)損檢測(cè),而且操作簡(jiǎn)便,可為實(shí)際應(yīng)用提供參考。
[Abstract]:In order to detect the content of bovine whey powder in adulterated sheep milk powder quickly, 197 sheep whey powder adulterated with false bovine whey powder were detected by near infrared spectroscopy (NIR) combined with 謂 -support vector regression (SVR), and compared with partial least square method (PLS), the spectrum was smooth. Standard variable transformation and derivative preprocessing. 132 samples were selected randomly as calibration set to establish the model, and the other 65 samples were selected as test sets to evaluate the performance of the model. The results show that the optimal model of calibration set is standard variable transformation, Savitzky-Golay smoothing and second-order derivative preprocessing v-SVR model. The root-mean-square (RMSECV) of cross-validation error is 0.586, and the correlation coefficient (RCV) of cross-validation is 0.9947. The prediction set verifies that the SVR method is better than the PLS method, and the predicted value and the real value R of the 謂 SVR model are 0.9958 and 0.526 respectively. The experimental results show that NIR combined with v-SVR model can be used for fast nondestructive detection of bovine whey powder in adulterated sheep milk powder, and it is easy to operate and can be used as a reference for practical application.
【作者單位】： 北京食品營(yíng)養(yǎng)與人類(lèi)健康高精尖創(chuàng)新中心/食品添加劑與配料北京高校工程研究中心北京工商大學(xué);吉林省食品檢驗(yàn)所;
【分類(lèi)號(hào)】：O657.33;TS252.7
，
本文編號(hào)：2288727
[Abstract]:In order to detect the content of bovine whey powder in adulterated sheep milk powder quickly, 197 sheep whey powder adulterated with false bovine whey powder were detected by near infrared spectroscopy (NIR) combined with 謂 -support vector regression (SVR), and compared with partial least square method (PLS), the spectrum was smooth. Standard variable transformation and derivative preprocessing. 132 samples were selected randomly as calibration set to establish the model, and the other 65 samples were selected as test sets to evaluate the performance of the model. The results show that the optimal model of calibration set is standard variable transformation, Savitzky-Golay smoothing and second-order derivative preprocessing v-SVR model. The root-mean-square (RMSECV) of cross-validation error is 0.586, and the correlation coefficient (RCV) of cross-validation is 0.9947. The prediction set verifies that the SVR method is better than the PLS method, and the predicted value and the real value R of the 謂 SVR model are 0.9958 and 0.526 respectively. The experimental results show that NIR combined with v-SVR model can be used for fast nondestructive detection of bovine whey powder in adulterated sheep milk powder, and it is easy to operate and can be used as a reference for practical application.
【作者單位】： 北京食品營(yíng)養(yǎng)與人類(lèi)健康高精尖創(chuàng)新中心/食品添加劑與配料北京高校工程研究中心北京工商大學(xué);吉林省食品檢驗(yàn)所;
【分類(lèi)號(hào)】：O657.33;TS252.7
，
本文編號(hào)：2288727
本文鏈接：http://sikaile.net/kejilunwen/huaxue/2288727.html
最近更新
教材專(zhuān)著
