本文選題：近紅外光譜　切入點(diǎn)：模型更新　出處：《光譜學(xué)與光譜分析》2017年11期

【摘要】：近紅外光譜是一種快速、無損的定量分析工具。為了提高黃酒關(guān)鍵參數(shù)的檢測水平,采用近紅外光譜法進(jìn)行定量分析。檢測過程中,由于受環(huán)境波動(dòng)、儀器老化、原料變化等因素的影響,基于舊樣品所建的模型的精確度逐漸下降。為保持模型的預(yù)測精度,引入遞歸偏最小二乘(recursive partial least square,RPLS)對(duì)模型進(jìn)行更新。以往此方法多使用全譜信息擴(kuò)充建模集并進(jìn)行遞歸計(jì)算,光譜的變量多,且包含環(huán)境影響等干擾信息,更新計(jì)算量大,且精度的提升效果不明顯。考慮到黃酒生產(chǎn)過程中特征波段變化小的特性,提出了一種基于特征波段的黃酒近紅外光譜檢測模型遞歸更新方法。先采用相關(guān)系數(shù)法提取特征波段建立低維模型,在采集到新樣品理化值后,再利用其特征波段光譜信息,使用遞歸偏最小二乘對(duì)低維模型進(jìn)行更新。此方法被應(yīng)用于黃酒總酸的近紅外檢測模型更新。模型評(píng)價(jià)使用相關(guān)系數(shù)r,預(yù)測標(biāo)準(zhǔn)偏差RMSEP和預(yù)測相對(duì)分析誤差RPD三個(gè)指標(biāo)。結(jié)果表明:采用本方法后,模型穩(wěn)定性顯著優(yōu)化,計(jì)算效率有所提升,模型預(yù)測效果良好,三個(gè)評(píng)價(jià)指標(biāo)分別達(dá)到0.965 7,0.184 3和3.736 2,較全譜PRLS時(shí)分別提高3%,24%和31%,在實(shí)際應(yīng)用中有一定的參考價(jià)值。
[Abstract]:Near-infrared spectroscopy (NIR) is a rapid and non-destructive tool for quantitative analysis. In order to improve the detection level of key parameters of yellow rice wine, the near-infrared spectroscopy is used for quantitative analysis. The accuracy of the model based on the old sample has gradually declined due to the influence of factors such as the change of raw material. In order to maintain the prediction accuracy of the model, The recursive partial least square (RPLS) is introduced to update the model. In the past, the whole spectrum information is used to expand the modeling set and calculate recursively. The spectral variables are many, and the disturbance information such as environmental impact is included. And the effect of raising precision is not obvious. Considering the small change of characteristic band in rice wine production, In this paper, a recursive updating method of near infrared spectrum detection model of yellow rice wine based on feature band is proposed. Firstly, the correlation coefficient method is used to extract the feature band to establish a low dimensional model. After the new physical and chemical values of the sample are collected, the spectral information of the characteristic band is then used. This method is used to update the low-dimensional model by recursive partial least squares. This method has been applied to the near infrared detection model updating of total acid in rice wine. The model evaluation uses correlation coefficient r, prediction standard deviation (RMSEP) and prediction relative analysis error (RPD). The results show that, after using this method, The stability of the model is significantly optimized, the calculation efficiency is improved, and the prediction effect of the model is good. The three evaluation indexes are 0.965 0.1843 and 3.736 2, respectively, which are 34% and 31% higher than those of the full-spectrum PRLS, respectively. It has certain reference value in practical application.
【作者單位】： 江南大學(xué)輕工過程先進(jìn)控制教育部重點(diǎn)實(shí)驗(yàn)室;
【基金】：國家自然科學(xué)基金項(xiàng)目(61573169) 流程工業(yè)綜合自動(dòng)化國家重點(diǎn)實(shí)驗(yàn)室開放課題基金項(xiàng)目(PAL-N201502) 中央高校基本科研業(yè)務(wù)費(fèi)專項(xiàng)資金項(xiàng)目(JUSRP51407B)資助
【分類號(hào)】：O657.33;TS262.4

【相似文獻(xiàn)】

相關(guān)期刊論文 前8條

1 葉芙蓉;陳細(xì)丹;;高效液相色譜法測定黃酒中的糖類[J];釀酒;2012年05期

2 林曉婕;魏巍;何志剛;林曉姿;;離子排斥色譜法測定黃酒中的13種有機(jī)酸[J];色譜;2014年03期

3 陳乃東;胡平;羅志強(qiáng);馬莉;李望遠(yuǎn);;黃酒及其酸敗組分的高效毛細(xì)管電泳檢測方法的研究[J];食品工業(yè)科技;2014年08期

4 薛磊;呂進(jìn);施秧;屠海云;劉輝軍;;基于近紅外光譜的黃酒風(fēng)格判別方法[J];食品科學(xué);2014年08期

5 呂芬;黃偉雄;余勝兵;李少霞;龍朝陽;;廣東黃酒中氨基甲酸乙酯的監(jiān)測與控制分析[J];中國衛(wèi)生檢驗(yàn)雜志;2014年15期

6 朱潘煒;周建弟;劉東紅;;不同年份成品黃酒對(duì)照GC-MS指紋圖譜的建立[J];中國食品學(xué)報(bào);2012年01期

7 陳乃東;陳乃富;王慶紅;楊輝;;黃酒成分HPLC分析[J];安徽農(nóng)學(xué)通報(bào)(上半月刊);2012年13期

8 陳軍;;HPLC法同時(shí)測定黃酒中4種非法食品添加劑[J];化學(xué)分析計(jì)量;2014年03期

相關(guān)碩士學(xué)位論文 前3條

1 蔣巧勇;黃酒總糖的近紅外光譜檢測模型優(yōu)化研究[D];中國計(jì)量學(xué)院;2015年

2 戴鑫;基于氣相色譜—質(zhì)譜的黃酒香氣分析和酒齡、產(chǎn)地鑒別[D];上海應(yīng)用技術(shù)學(xué)院;2014年

3 薛磊;黃酒品質(zhì)近紅外光譜模型優(yōu)化研究[D];中國計(jì)量學(xué)院;2014年

，

本文編號(hào)：1690817