基于离散傅立叶变换的支持向量机光谱定量分析法

研究了火电厂电煤煤粉的近红外光谱特征,提取了前3个主成分和前6个离散傅立叶变换(DFT)系数,结合主成分得分、马氏距离和偏最小二乘(PLS)交互验证方法剔除异常样本,并建立偏最小二乘回归(PLSR)、栅格支持向量机回归(G-SVR)、遗传算法支持向量机回归(GA-SVR)和粒子群算法支持向量机回归(PSO-SVR)等定量分析模型。结果表明,利用DFT系数作为PSO-SVR模型的输入变量,当其进化代数为300,种群规模为20,模型参数c1、c2为1.5,1.7时,性能最优,其中校正集相关系数(RC)为0.990,测试集相关系数(RP)为0.954,定标标准差(SEC)为0.366,测试标准差(SEP)为0.128。该方法准确可靠,已成功应用于近红外在线电煤发热量监测系统,并可推广用于其它较为复杂的近红外在线分析系统。     

人工神经网络用于近红外光谱预测汽油辛烷值

本文对BP人工神经网络(ANN)方法在汽油的辛烷值与其近红外光谱光谱吸光度的关系之间进行关联预报方面进行了研究。采用35个汽油实际样本数据,建立了利用汽油的近红外光谱光谱吸光度预测汽油辛烷值的BP人工神经网络模型。对所有辛烷值的计算结果与实测值进行了比较,得到的预测值与实测值计算误差小于1.55%。     

基于PLS-红外光谱的汽油辛烷值测定方法研究

辛烷值是反映汽油抗爆性的重要指标,现有的辛烷值测试方法具有分析周期长、测试成本高等缺点。本文以红外光谱法结合偏最小二乘法(PLS)建立了汽油辛烷值快速测定方法。实验采集了113个汽油样品的光谱数据,以研究法辛烷值(RON)测得的实际辛烷值为参数,建立了预测汽油辛烷值的PLS模型。结果表明:20个预测集的相关系数Rp~2为1.0184,预测均方根误差RMSEP为0.4639。说明此方法对汽油辛烷值具有较好的预测效果,且操作简单、分析速度快,具有一定的可行性。     

近红外光谱-径向基神经网络在异烟肼片无损定量分析中的应用

应用异烟肼片粉末的近红外漫反射光谱数据分别结合偏最小二乘法(PLS)和径向基神经网络(RBFNN)建立定量分析模型,并用所建模型对预测集样品进行了预测,结果表明:应用RBFNN所建立的定量分析模型优于PLS模型,相关系数(r)值由0.99593提高到0.99734,交互验证均方根误差(RMSECV)值由0.00523下降到0.00423,预测均方根误差(RMSEP)值由0.00614下降到0.00501。     

烟草组分的近红外光谱和支持向量机分析

测定了120个产自福建、安徽和云南烟草样品的近红外光谱. 在利用支持向量机(SVM)技术建立其定量、定性分析模型之前, 用小波变换技术对光谱变量进行了有效的压缩, 然后采用径向基核函数建立了75个烟草样品的分类模型, 同时建立了总糖、还原糖、烟碱和总氮4个组分的定量分析模型, 并利用45个烟草样品对模型进行了检验. 仿真实验表明, 建立的SVM分类模型分类准确率达到100%, 而4个组分的定量分析模型的预测决定系数(R2)、预测均方差(RMSEP)和平均相对误差(RME)3个指标值显示其模型泛化能力非常强, 预测效果良好, 可见这是一种有效的近红外光谱的建模分析方法.     

基于主成分分析和小波神经网络的近红外多组分建模研究

将小麦叶片原始光谱经过预处理后,采用主成分分析(PCA)对数据进行降维,取前3个主成分输入小波神经网络,建立了基于主成分分析和小波神经网络的近红外多组分预测模型(WNN);进一步研究了小波基函数个数的选取(WNN隐层节点数)对小波神经网络模型性能的影响,并将WNN模型与偏最小二乘法(PLS)和传统的反向传播神经网络(BPNN)模型进行了比较.结果表明,所建立的WNN模型能用于同时预测小麦叶片全氮和可溶性总糖两种组分含量,其预测均方根误差(RMSEP)分别为0.101%和0.089%,预测相关系数(R)分别为0.980和0.967.另外,在收敛速度和预测精度上,WNN模型明显优于BPNN和PLS模型,从而为将小波神经网络用于近红外光谱的多组分定量分析奠定了基础.     

应用光谱技术无损检测油菜叶片中乙酰乳酸合成酶

应用可见/近红外光谱技术实现了油菜叶片中乙酰乳酸合成酶(ALS)的快速无损检测.对99个油菜样本进行光谱扫描,经过平滑、变量标准化、一阶求导等预处理后,应用偏最小二乘法(PLS)建立了ALS的预测模型.同时提取有效特征变量,作为反向传输人工神经网络(BPNN)和最小二乘-支持向量机(LS-SVM)的输入值,并建立相应的模型.用66个样本建模,33个样本验证.结果表明,LS-SVM模型能够获得最优的预测结果,预测集样本的相关系数(r)、预测标准差(RMSEP)和偏差(Bias)分别为0.998、 0.715和0.079,获得了满意的预测精度.结果表明,应用可见/近红外光谱技术结合LS-SVM检测油菜中乙酰乳酸合成酶是可行的,并能获得满意的预测精度,为进一步应用光谱技术进行油菜生长状况的大田监测奠定了基础.     

近红外光谱法测定30%TBP/正十二烷中硝酸含量

核燃料后处理工艺控制分析中,有机相中硝酸含量是一项重要的控制参数。通过研究TBP/正十二烷介质中硝酸的近红外光谱,将有机相样品的傅立叶变换近红外光谱与偏最小二乘回归法相结合,建立了含铀后处理有机相样品中硝酸浓度的测量方法。建立的定量校正模型的最佳校正标准偏差(RMSEC)、预测标准偏差(RMSEP)以及相关系数(r)分别为0.011,0.014,0.999。方法检出限为0.05 mol/L,测量结果的相对标准偏差不大于4%(n=6)。采用近红外分析法与滴定法对模拟样品进行测量,对测量结果进行t检验,结果表明两种方法的测定结果无显著性差异。所建方法无需样品预处理,可直接测量,分析速度快,结果准确,具有一定的实用性。     

基于近红外光谱技术的亚麻纤维化学成分含量快速测定

在推进亚麻纤维的纺纱及其产业化生产过程中,快速、准确的定量分析纤维的化学成分是重要趋势。该研究利用近红外光谱技术分析亚麻纤维化学成分,以化学分析法测定值为对照,采用偏最小二乘法(PLS)建立亚麻纤维化学成分的近红外模型,从而实现了其化学成分的高效、快速定量分析。结果表明,建立的亚麻纤维纤维素、半纤维素、木质素和果胶近红外模型的校正相关系数(R_C)与验证相关系数(R_(CV))均在0.9以上,校正均方根误差(RMSEC)小于预测均方根误差(RMSEP)且均小于1。外部验证和双尾t检验表明模型预测结果较为准确,预测值与化学分析法得到的实测值无显著性差异,故该模型可用于相关化学成分含量的快速预测。     

傅立叶变换近红外光谱法测定腐乳中总酸、蛋白质和水分

应用傅立叶变换近红外光谱技术,建立了腐乳中总酸、蛋白质和水分的分析模型。测定32份腐乳的近红外光谱数据,得到原始光谱信息,通过光谱预处理方法消除原始光谱噪声,最后采用偏最小二乘法建立回归方程。最终得到总酸、蛋白质和水分近红外光谱分析模型的决定系数(R2)依次为99.37%、99.70%、99.73%,交叉验证均方根差(RMSECV)依次为0.00871、0.11、0.0714。用该模型对11个未知腐乳样品进行外部验证,其总酸、蛋白质和水分外部验证的决定系数(R2)依次为98.74%、99.38%、99.48%,预测标准偏差(RMSEP)依次为0.00862、0.113、0.0683。内部交叉验证和外部验证均证明,近红外定量分析有较高的准确度,能满足腐乳生产中总酸、蛋白质和水分的检测精度要求。     

Combined wavelet transform-artificial neural network use in tablet active content determination by near-infrared spectroscopy

The pharmaceutical industry faces increasing regulatory pressure to optimize quality control. Content uniformity is a basic release test for solid dosage forms. To accelerate test throughput and comply with the Food and Drug Administration's process analytical technology initiative, attention is increasingly turning to nondestructive spectroscopic techniques, notably near-infrared (NIR) spectroscopy (NIRS). However, validation of NIRS using requisite linearity and standard error of prediction (SEP) criteria remains a challenge. This study applied wavelet transformation of the NIR spectra of a commercial tablet to build a model using conventional partial least squares (PLS) regression and an artificial neural network (ANN). Wavelet coefficients in the PLS and ANN models reduced SEP by up to 60% compared to PLS models using mathematical spectra pretreatment. ANN modeling yielded high-linearity calibration and a correlation coefficient exceeding 0.996.     

Quantitative Analysis of Berberine in Processed Coptis by Near-Infrared Diffuse Reflectance Spectroscopy

The near-infrared（NIR） diffuse reflectance spectroscopy was used to study the content of Berberine in the processed Coptis. The allocated proportions of Coptis to ginger, yellow liquor or Evodia rutaecarpa changed according to the results of orthogonal design as well as the temperature. For as withdrawing the full and effective information from the spectral data as possible, the spectral data was preprocessed through first derivative and multiplicative scatter correetion（MSC） according to the optimization results of different preprocessing methods. Firstly, the model was established by partial least squares（PLS）; the coefficient of determination（R2） of the prediction was 0.839, the root mean squared error of prediction（RMSEP） was 0.1422, and the mean relative error（RME） was 0.0276. Secondly, for reducing the dimension and removing noise, the spectral variables were highly effectively compressed via the wavelet transformation（WT） technology and the Haar wavelet was selected to decompose the spectral signals. After the wavelet coefficients from WT were input into the artificial neural network（ANN） instead of the spectra signal, the quantitative analysis model of Berberine in processed Coptis was established. The R^2 of the model was 0.9153, the RMSEP was 0.0444, and the RME was 0.0091. The values of appraisal index, namely R^2, RMSECV, and RME, indicate that the generalization ability and prediction precision of ANN are superior to those of PLS. The overall results show that NIR spectroscopy combined with ANN can be efficiently utilized for the rapid and accurate analysis of routine chemical compositions in Coptis. Accordingly, the result can provide technical support for the further analysis of Berberine and other components in processed Coptis. Simultaneously, the research can also offer the foundation of quantitative analysis of other NIR application.     

Determination of α-linolenic acid and linoleic acid in edible oils using near-infrared spectroscopy improved by wavelet transform and uninformative variable elimination

This paper proposes an analytical method for simultaneous near-infrared (NIR) spectrometric determination of α-linolenic and linoleic acid in eight types of edible vegetable oils and their blending. For this purpose, a combination of spectral wavelength selection by wavelet transform (WT) and elimination of uninformative variables (UVE) was proposed to obtain simple partial least square (PLS) models based on a small subset of wavelengths. WT was firstly utilized to compress full NIR spectra which contain 1413 redundant variables, and 42 wavelet approximate coefficients were obtained. UVE was then carried out to further select the informative variables. Finally, 27 and 19 wavelet approximate coefficients were selected by UVE for α-linolenic and linoleic acid, respectively. The selected variables were used as inputs of PLS model. Due to original spectra were compressed, and irrelevant variables were eliminated, more parsimonious and efficient model based on WT-UVE was obtained compared with the conventional PLS model with full spectra data. The coefficient of determination (r²) and root mean square error prediction set (RMSEP) for prediction set were 0.9345 and 0.0123 for α-linolenic acid prediction by WT-UVE-PLS model. The r² and RMSEP were 0.9054, 0.0437 for linoleic acid prediction. The good performance showed a potential application using WT-UVE to select NIR effective variables. WT-UVE can both speed up the calculation and improve the predicted results. The results indicated that it was feasible to fast determine α-linolenic acid and linoleic acid content in edible oils using NIR spectroscopy.     

Modeling and prediction of activity coefficient ratio of electrolytes in aqueous electrolyte solution containing amino acids using artificial neural network

Modeling and prediction of activity coefficients of electrolytes and biomolecules is a key to developing the separation and purification processes of biomolecules. In this paper the systems containing amino acids or peptide + water + one electrolyte (NaCl, KCl, NaBr, KBr) are modeled by different types of neural networks and an artificial neural network (ANN) is designed that can predict the mean ionic activity coefficient ratio of electrolytes in presence and in absence of amino acid in different mixtures better than the common polynomial equations proposed for this kind of predictions. It was found that the designed ANN which is a multi-layer perceptron (MLP) type network can be better trained than other types of neural network.The root mean square deviation (RMSD) of the designed neural network in prediction of the mean ionic activity coefficient ratio of electrolytes is less than 0.005 and proves the effectiveness of the ANN in correlation and prediction of activity coefficients in the studied mixtures.     

Application of artificial neural network to determination of active principle ingredient in pharmaceutical quality control based on near infrared spectroscopy

In the construction of a neural network, most attentions have been paid to the selection of the architecture, the selection of the learning parameters and the network validation while the selection of input variables shared little. This study focused on the selection of input variables by various data pre-treatment for constructing ANN models. The results showed that the validation results differed from each other when different data-pretreatment methods combined with near-infrared spectroscopy (NIRS) to build a model using artificial neural network (ANN) for quality control of paracetamol in coldrex. And wavelet coefficients after orthogonal signal correction (OSC) in the ANN models reduced RMSEP by up to 77% compared to ANN models using derivatives combined with PCA pretreatment. The selection of input variables has potent to improve the calibration ability of ANN, and the model can be used for pressure reduction of quality control in the pharmaceutical industry.     

基于近红外光谱的食用植物油中反式脂肪酸含量快速定量检测及模型优化研究

利用近红外光谱技术对食用植物油中反式脂肪酸(Trans fatty acids,TFA)含量进行快速定量检测,并通过波段选择、预处理方法、变量筛选及建模方法对TFA含量预测模型进行优化.采用AntarisⅡ傅里叶变换近红外光谱仪在4000~10000 cm-1光谱范围采集98个食用植物油样本的近红外透射光谱,然后采用气相色谱法测定TFA的真实含量.首先,对样本原始光谱进行波段、预处理方法优选;在此基础上,采用竞争自适应重加权法(Competitive adaptive reweighted sampling,CARS)筛选TFA相关的重要变量,最后应用主成分回归、偏最小二乘和最小二乘支持向量机方法分别建立食用植物油中TFA含量的预测模型.研究结果表明,近红外光谱技术检测食用植物油中的TFA含量是可行的,优化后的最佳预测模型的校正集和预测集R2分别为0.992和0.989,RMSEC和RMSEP分别为0.071%和0.075%.最佳预测模型所用的变量仅26个,占全波段变量的0.854%.此外,与全波段偏最小二乘预测模型相比,其预测集R2由0.904上升为0.989,RMSEP由0.230%下降为0.075%.由此表明,模型优化非常必要,CARS能有效筛选TFA相关的重要变量,极大减少建模变量数,从而简化预测模型,并较大提高预测模型的精度和稳定性.     

Prediction of CO2 Solubility in Polymers by Radial Basis Function Artificial Neural Network Based on Chaotic Self-adaptive Particle Swarm Optimization and Fuzzy Clustering Method

To replace costly and time-consuming experimentation in laboratory, a novel solubility prediction model based on chaos theory, self-adaptive particle swarm optimization （PSO）, fuzzy c-means clustering method, and radial ba- sis function artificial neural network （RBF ANN） is proposed to predict CO2 solubility in polymers, hereafter called CSPSO-FC RBF ANN. The premature convergence problem is overcome by modifying the conventional PSO using chaos theory and self-adaptive inertia weight factor. Fuzzy c-means clustering method is used to tune the hidden centers and radial basis function spreads. The modified PSO algorithm is employed to optimize the RBF ANN connection weights. Then, the proposed CSPSO-FC RBF ANN is used to investigate solubility of CO2 in polystyrene （PS）, polypropylene （PP）, poly（butylene succinate） （PBS） and poly（butylene succinate-co-adipate） （PBSA）, respec- tively. Results indicate that CSPSO-FC RBF ANN is an effective method for gas solubility in polymers. In addition, compared with conventional RBF ANN and PSO ANN, CSPSO-FC RBF ANN shows better performance. The values of average relative deviation （ARD）, squared correlation coefficient （R2） and standard deviation （SD） are 0.1071, 0.9973 and 0.0108, respectively. Statistical data demonstrate that CSPSO-FC RBF ANN has excellent prediction capability and high-accuracy, and the correlation between prediction values and experimental data is good.     

土壤总氮近红外光谱分析的波段优选

利用移动窗口偏最小二乘( MWPLS)和Savitzky-Golay(SG)平滑方法优选土壤总氮的近红外(NIR)光谱分析模型.从全部97个土壤样品中随机选出35个样品作为检验集;基于偏最小二乘交叉检验预测偏差(PLSPB),将余下62个样品划分为具有相似性的建模定标集(37个样品)、建模预测集(25个样品).最优波段为1692～2138 nm,SG平滑的导数阶数(OD)、多项式次数(DP)、平滑点数(NSP)分别为0,6,69,PLS因子数为11,建模预测均方根偏差(M-RMSEP)、建模预测相关系数(M-Rp)分别为0.015％,0.931,检验预测均方根偏差(V-RM-SEP)、检验预测相关系数(V-RP)分别为0.018％,0.882.其结果可为设计专用NIR仪器提供有价值的参考.