本文選題：FTIR + 人工神經(jīng)網(wǎng)絡(luò)　； 參考：《光譜學(xué)與光譜分析》2017年03期

【摘要】：隨著餐飲業(yè)的發(fā)展,餐飲煙氣已經(jīng)成為某些城市三大空氣污染源之一。由于餐飲煙氣對(duì)人體健康威脅很大,近年來對(duì)餐飲煙氣的研究愈來愈熱。餐飲煙氣中包含有大量食用油加熱過程中裂解而產(chǎn)生的不飽和烴類,危害著人類健康。不同食用油裂解出來的成分以及含量有所不同,通過構(gòu)建一定的分類識(shí)別數(shù)學(xué)模型,從而實(shí)現(xiàn)對(duì)食用油分類識(shí)別。采用自主研發(fā)的傅里葉變換紅外光譜儀,采集了不同食用油油煙煙氣紅外光譜數(shù)據(jù)。同時(shí)構(gòu)建了主成分分析(PCA)分別結(jié)合概率神經(jīng)網(wǎng)絡(luò)(PNN)以及誤差反向傳播人工神經(jīng)網(wǎng)絡(luò)(BPANN)的分類識(shí)別算法。將兩種分類識(shí)別算法對(duì)不同食用油油煙煙氣的傅里葉變換紅外光譜數(shù)據(jù)進(jìn)行分析。通過樣本數(shù)據(jù)對(duì)數(shù)學(xué)模型進(jìn)行訓(xùn)練,將訓(xùn)練好的數(shù)學(xué)模型對(duì)未知光譜數(shù)據(jù)進(jìn)行分析,來確定產(chǎn)生油煙煙氣的食用油種類。實(shí)驗(yàn)結(jié)果表明,兩種算法都能對(duì)不同的油煙種類進(jìn)行較好地分類識(shí)別。在全波段識(shí)別時(shí),識(shí)別率分別達(dá)到90.25%和97.0%。通過對(duì)煙氣光譜數(shù)據(jù)的吸收波段進(jìn)行分析,提取大氣窗口并且具有較強(qiáng)可揮發(fā)性有機(jī)物(VOCs)吸收特征的波段(1 300~700 cm~(-1)以及3 000~2 600 cm~(-1));將吸光度數(shù)據(jù)分成兩個(gè)分離的吸收波段,兩種算法在3 000 2 600 cm~(-1)波段都有較好的識(shí)別效果,PCA-PNN算法識(shí)別率為90.25%,PCA-BPANN算法識(shí)別率為92.25%�？梢�,兩種人工神經(jīng)網(wǎng)絡(luò)算法都能有效對(duì)食用油煙種類進(jìn)行識(shí)別。
[Abstract]:With the development of catering industry, fume has become one of the three air pollution sources in some cities. Because the fume of food and beverage is a great threat to human health, the research on the fume of food and beverage is becoming more and more hot in recent years. There are a lot of unsaturated hydrocarbons produced by cooking oil pyrolysis in the fume of food and beverage, which is harmful to human health. The components and contents of different edible oils are different. A certain mathematical model of classification and recognition is constructed to realize the classification and recognition of edible oils. Fourier transform infrared spectrometer (FTIR) was developed to collect infrared spectrum data of different cooking oil fumes. At the same time, the classification and recognition algorithms of principal component analysis (PCA) combined with probabilistic neural network (PNNN) and error back-propagation artificial neural network (BPANN) are constructed. The Fourier transform infrared spectral data of different cooking oil fumes were analyzed by two classification recognition algorithms. The mathematical model is trained by sample data, and the unknown spectral data are analyzed by the trained mathematical model to determine the type of cooking oil that produces fume. The experimental results show that the two algorithms can be used to classify and identify different types of oil fumes. The recognition rates are 90.25% and 97.0% respectively. By analyzing the absorption bands of smoke spectral data, we extracted the atmospheric window and have a strong absorption characteristic of volatile organic compounds (VOCs) (1 300 ~ 700 cm ~ (-1) and 3 000 ~ (2 600) cm ~ (-1) ~ (-1). The absorbance data are divided into two separate absorption bands. The recognition rate of PCA-PNN algorithm is 90.25 and the recognition rate of PCA-BPANN algorithm is 92.25. Therefore, the two artificial neural network algorithms can effectively identify the types of cooking oil smoke.
【作者單位】： 中國(guó)科學(xué)院安徽光學(xué)精密機(jī)械研究所中國(guó)科學(xué)院環(huán)境光學(xué)與技術(shù)重點(diǎn)實(shí)驗(yàn)室;中國(guó)科學(xué)技術(shù)大學(xué);
【基金】：中國(guó)科學(xué)院戰(zhàn)略性先導(dǎo)科技專項(xiàng)(XDB05050300);中國(guó)科學(xué)院戰(zhàn)略性先導(dǎo)科技專項(xiàng)(XDB05040500) 國(guó)家重大科學(xué)儀器設(shè)備開發(fā)專項(xiàng)(2013YQ22064302) 工業(yè)區(qū)VOCs排放通量遙測(cè)方法研究項(xiàng)目(41405029)資助
【分類號(hào)】：X831;O657.33

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 侯晉,陳國(guó)松,王鎮(zhèn)浦;人工神經(jīng)網(wǎng)絡(luò)的發(fā)展及在多元校正中的應(yīng)用[J];分析科學(xué)學(xué)報(bào);2001年01期

2 趙欣;人工神經(jīng)網(wǎng)絡(luò)應(yīng)用于大氣規(guī)劃的可能性[J];邯鄲職業(yè)技術(shù)學(xué)院學(xué)報(bào);2002年04期

3 賴靜;王清;孫東立;;人工神經(jīng)網(wǎng)絡(luò)在材料研究中的應(yīng)用[J];材料工程;2006年S1期

4 石幸利;;人工神經(jīng)網(wǎng)絡(luò)的發(fā)展及其應(yīng)用[J];重慶科技學(xué)院學(xué)報(bào);2006年02期

5 石樂明;周家駒;劉信安;孫敦明;許志宏;;人工神經(jīng)網(wǎng)絡(luò)用于化學(xué)雜交劑的構(gòu)效關(guān)系研究[J];化學(xué)通報(bào);1992年06期

6 龔小一，鄧勃，羅國(guó)安;前向人工神經(jīng)網(wǎng)絡(luò)的生成系統(tǒng)[J];計(jì)算機(jī)與應(yīng)用化學(xué);1996年04期

7 公源;;基于人工神經(jīng)網(wǎng)絡(luò)的汽車噴涂配比優(yōu)化研究與應(yīng)用[J];鍛壓裝備與制造技術(shù);2014年01期

8 王艷斌,袁洪福,陸婉珍,齊洪祥,殷宗玲;人工神經(jīng)網(wǎng)絡(luò)用于近紅外光譜測(cè)定柴油閃點(diǎn)[J];分析化學(xué);2000年09期

9 胡海峰,馬杰,馬玉書,王仁安;減壓渣油評(píng)價(jià)中的人工神經(jīng)網(wǎng)絡(luò)分析方法[J];計(jì)算機(jī)與應(yīng)用化學(xué);2000年03期

10 高志明,關(guān)巖,于洪梅,吳秀紅,李井會(huì);人工神經(jīng)網(wǎng)絡(luò)在化學(xué)中的應(yīng)用進(jìn)展[J];鞍山鋼鐵學(xué)院學(xué)報(bào);2000年03期

相關(guān)會(huì)議論文 前10條

1 吳兵;;一種具有語義分布的自構(gòu)造的新人工神經(jīng)網(wǎng)絡(luò)系統(tǒng)及其應(yīng)用[A];1999年中國(guó)神經(jīng)網(wǎng)絡(luò)與信號(hào)處理學(xué)術(shù)會(huì)議論文集[C];1999年

2 劉R，

本文編號(hào)：2018909