本文選題：乙醇　切入點(diǎn)：固態(tài)發(fā)酵　出處：《江蘇大學(xué)》2017年碩士論文

【摘要】：為實(shí)現(xiàn)乙醇固態(tài)發(fā)酵過(guò)程的實(shí)時(shí)檢測(cè),本論文開展了基于近紅外光譜技術(shù)的乙醇固態(tài)發(fā)酵過(guò)程參數(shù)的定量檢測(cè)和狀態(tài)的定性判別研究。具體研究工作如下:(1)對(duì)玉米粉生料固態(tài)發(fā)酵乙醇的工藝進(jìn)行了試驗(yàn)研究。開展了玉米粉生料固態(tài)發(fā)酵產(chǎn)乙醇的試驗(yàn),采用理化試驗(yàn)分析方法得到樣品中乙醇和還原糖的含量,并采集樣本的近紅外光譜,為后續(xù)建立固態(tài)發(fā)酵過(guò)程參數(shù)及狀態(tài)檢測(cè)模型提供試驗(yàn)數(shù)據(jù)。(2)探討了乙醇固態(tài)發(fā)酵過(guò)程關(guān)鍵參數(shù)(乙醇和還原糖)的近紅外光譜定量檢測(cè)方法。使用聯(lián)合區(qū)間偏最小二乘法從標(biāo)準(zhǔn)正態(tài)變量變換預(yù)處理后的光譜中選擇關(guān)于參數(shù)乙醇和還原糖含量的最優(yōu)聯(lián)合子區(qū)間;再使用迭代保留信息變量法從最優(yōu)聯(lián)合子區(qū)間中分別篩選出關(guān)于參數(shù)乙醇和還原糖的特征波數(shù)變量,并與傳統(tǒng)方法遺傳算法和競(jìng)爭(zhēng)自適應(yīng)重加權(quán)采樣法進(jìn)行對(duì)比;最后,建立關(guān)于乙醇和還原糖含量的偏最小二乘預(yù)測(cè)模型。試驗(yàn)結(jié)果顯示:迭代保留信息變量方法選擇的關(guān)于參數(shù)乙醇和還原糖含量的特征變量數(shù)分別為45個(gè)和43個(gè);由這些特征波數(shù)變量建立的偏最小二乘模型關(guān)于參數(shù)乙醇含量的測(cè)試集均方根誤差和預(yù)測(cè)相關(guān)系數(shù)分別為0.2485和0.9937,關(guān)于參數(shù)還原糖含量的測(cè)試集均方根誤差和預(yù)測(cè)相關(guān)系數(shù)分別為0.1418和0.9949;迭代保留信息變量方法選擇的特征波數(shù)變量個(gè)數(shù)是最少的,而且由這些特征波數(shù)變量建立的偏最小二乘模型具有最好的預(yù)測(cè)結(jié)果。研究結(jié)果表明,利用近紅外光譜技術(shù)結(jié)合適當(dāng)?shù)幕瘜W(xué)計(jì)量學(xué)方法可以有效對(duì)乙醇固態(tài)發(fā)酵過(guò)程關(guān)鍵參數(shù)進(jìn)行快速檢測(cè)。(3)探討了乙醇固態(tài)發(fā)酵過(guò)程狀態(tài)的近紅外光譜定性檢測(cè)方法。使用聯(lián)合區(qū)間偏最小二乘法從標(biāo)準(zhǔn)正態(tài)變量變換預(yù)處理后的光譜中選擇關(guān)于發(fā)酵狀態(tài)的最優(yōu)聯(lián)合子區(qū)間;再分別使用迭代保留信息變量法、競(jìng)爭(zhēng)自適應(yīng)重加權(quán)采樣法和遺傳算法從最優(yōu)聯(lián)合子區(qū)間中篩選出關(guān)于發(fā)酵過(guò)程狀態(tài)的特征波數(shù)變量;最后,建立發(fā)酵過(guò)程狀態(tài)的主成分分析模型和極限學(xué)習(xí)機(jī)模型。試驗(yàn)結(jié)果顯示:迭代保留信息變量方法篩選的光譜特征波數(shù)變量建立的主成分分析模型前2個(gè)主成分累計(jì)貢獻(xiàn)率為96.0236%,均高于其它主成分分析模型;迭代保留信息變量方法篩選的光譜特征波數(shù)變量建立的極限學(xué)習(xí)機(jī)狀態(tài)識(shí)別模型校正集和測(cè)試集正確率分別為99.8182%和97.2728%,均高于其它極限學(xué)習(xí)機(jī)預(yù)測(cè)模型。研究結(jié)果表明,利用近紅外光譜技術(shù)結(jié)合適當(dāng)?shù)幕瘜W(xué)計(jì)量學(xué)方法可以有效對(duì)乙醇固態(tài)發(fā)酵過(guò)程狀態(tài)進(jìn)行快速識(shí)別。本研究為乙醇固態(tài)發(fā)酵過(guò)程的近紅外光譜在線檢測(cè)提供新的思路,為乙醇固態(tài)發(fā)酵過(guò)程在線檢測(cè)的便攜式近紅外光譜裝備研發(fā)奠定理論和技術(shù)基礎(chǔ)。
[Abstract]:In order to realize the real-time detection of ethanol solid-state fermentation process, In this paper, the quantitative detection of the parameters of ethanol solid-state fermentation process based on near-infrared spectroscopy and the qualitative discrimination of the state were carried out. The specific research work is as follows: 1) the technology of solid state fermentation of ethanol from raw corn meal was tested. The experiment of producing ethanol by solid state fermentation of raw corn meal was carried out. The contents of ethanol and reducing sugar in the samples were obtained by physicochemical analysis, and the near infrared spectra of the samples were collected. The key parameters (ethanol and reducing sugar) of solid-state fermentation process were determined by Near-Infrared Spectroscopy (NIR). The combined interval bias was used to determine the key parameters (ethanol and reducing sugar). The least square method selects the optimal joint subinterval of the parameter ethanol and reducing sugar content from the spectrum of the standard normal variable transformation pretreatment. Then the characteristic wavenumber variables about the parameter ethanol and reducing sugar are screened out from the optimal joint subinterval by iterative preserving information variable method, and compared with the traditional genetic algorithm and the competitive adaptive re-weighted sampling method. Finally, A partial least square prediction model for ethanol and reducing sugar content was established. The experimental results showed that the number of characteristic variables on the content of ethanol and reducing sugar selected by iterative retention information variable method was 45 and 43 respectively. The RMS error and predictive correlation coefficient of the test set for the parameter ethanol content are 0.2485 and 0.9937, respectively, and the RMS error and prediction of the parameter reducing sugar content are 0.2485 and 0.9937 for the partial least squares model based on these characteristic wavenumber variables, respectively. The correlation coefficients are 0.1418 and 0.9949, respectively, and the number of characteristic wavenumber variables selected by iterative preserving information variable method is the least. Moreover, the partial least squares model based on these characteristic wavenumber variables has the best prediction results. Near-infrared spectroscopy (NIR) combined with appropriate chemometrics can be used to detect the key parameters of solid-state ethanol fermentation. Using the joint interval partial least square method to select the optimal joint subinterval about the fermentation state from the spectrum pretreated by the standard normal variable transformation; Then the iterative preserving information variable method, the competitive adaptive re-weighted sampling method and the genetic algorithm are used to screen out the characteristic wavenumber variables about the state of fermentation process from the optimal joint subinterval. The principal component analysis model and ultimate learning machine model of fermentation process were established. The experimental results showed that the first two principal component analysis models were established by the spectral characteristic wavenumber variables screened by iterative retention information variable method. The total contribution rate was 96.0236, which was higher than that of other principal component analysis models. The correct rates of calibration set and test set of state recognition model of LLM are 99.8182% and 97.2728%, respectively, which are higher than those of other prediction models. Near-infrared spectroscopy (NIR) combined with appropriate chemometrics can be used to identify the state of solid-state ethanol fermentation. This study provides a new idea for on-line detection of solid-state ethanol fermentation by near-infrared spectroscopy (NIR). It lays a theoretical and technical foundation for the development of portable near infrared spectrum equipment for the on-line detection of ethanol solid state fermentation process.
【學(xué)位授予單位】：江蘇大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TQ223.122;O657.33

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 胡雪桃;朱瑤迪;鄒小波;申婷婷;陳武;石吉勇;;近紅外光譜技術(shù)快速預(yù)測(cè)鎮(zhèn)江香醋乙醇脫氫酶活性的研究[J];中國(guó)調(diào)味品;2016年02期

2 于霜;劉國(guó)海;夏榮盛;江輝;;基于Adaboost及譜回歸判別分析的近紅外光譜固態(tài)發(fā)酵過(guò)程狀態(tài)識(shí)別[J];光譜學(xué)與光譜分析;2016年01期

3 沈小梅;馬雷;李安軍;劉國(guó)英;湯有宏;;基于近紅外光譜分析技術(shù)對(duì)釀酒原料水份的檢測(cè)方法研究與優(yōu)化[J];食品與發(fā)酵科技;2015年05期

4 張光義;李望良;張聚偉;余劍;汪印;許光文;;固態(tài)厭氧發(fā)酵生產(chǎn)沼氣技術(shù)基礎(chǔ)研發(fā)與工程應(yīng)用進(jìn)展[J];高�；瘜W(xué)工程學(xué)報(bào);2014年01期

5 劉國(guó)海;肖夏宏;江輝;梅從立;丁煜函;;基于BP-Adaboost的近紅外光譜檢測(cè)固態(tài)發(fā)酵過(guò)程pH值[J];江蘇大學(xué)學(xué)報(bào)(自然科學(xué)版);2013年05期

6 劉國(guó)海;江輝;梅從立;;基于dbiPLS-SPA變量篩選的固態(tài)發(fā)酵濕度近紅外光譜檢測(cè)[J];農(nóng)業(yè)工程學(xué)報(bào);2013年S1期

7 段中華;張洪偉;;煤直接制乙醇技術(shù)的應(yīng)用前景分析[J];化工設(shè)計(jì);2013年01期

8 江輝;劉國(guó)海;梅從立;肖夏宏;于霜;丁煜函;;基于OC-SVM和近紅外光譜的秸稈固態(tài)發(fā)酵進(jìn)程監(jiān)測(cè)[J];農(nóng)業(yè)機(jī)械學(xué)報(bào);2012年10期

9 徐洪宇;張京芳;盧春生;侯力璇;;近紅外光譜技術(shù)在釀酒葡萄品質(zhì)檢測(cè)中的應(yīng)用現(xiàn)狀及展望[J];中國(guó)食品學(xué)報(bào);2012年08期

10 劉國(guó)海;江輝;肖夏宏;張東娟;梅從立;丁煜函;;近紅外光譜結(jié)合ELM快速檢測(cè)固態(tài)發(fā)酵過(guò)程參數(shù)pH值[J];光譜學(xué)與光譜分析;2012年04期

相關(guān)碩士學(xué)位論文 前3條

1 黃常毅;近紅外光譜技術(shù)在微生物發(fā)酵過(guò)程中的應(yīng)用研究[D];江南大學(xué);2014年

2 范海濱;近紅外光譜快速檢測(cè)紅曲菌固態(tài)發(fā)酵參數(shù)的研究[D];江南大學(xué);2014年

3 馬文超;玉米生料發(fā)酵酒精的研究[D];江南大學(xué);2005年

，

本文編號(hào)：1667710