自适应蚁群优化算法的近红外光谱特征波长选择方法

为提高近红外光谱预测模型的精度和适用性,同时简化模型,提出了自适应蚁群优化偏最小二乘法优选特征波长的方法,建立不同产地苹果可溶性固形物含量混合分析模型。收集山东、陕西和新疆的富士苹果,采集3800~14000 cm"1范围的近红外光谱,并对其重要品质指标可溶性固形物含量进行测定。利用蚁群算法启发式全局搜索的特点,结合蒙特卡罗轮盘赌随机选择机制,优选苹果可溶性固形物含量的近红外光谱特征波长,然后用偏最小二乘法建立分析模型。与全光谱偏最小二乘模型和遗传偏最小二乘模型相比,蚁群优化算法选择的波长数最少,模型预测能力最强,预测的相关系数R和预测均方根误差RMSEP分别为0.9708和0.5144。研究结果表明,自适应蚁群优化算法可以有效选择近红外光谱特征波长,提高模型的稳健性和适用性。     

基于粒子群算法的波长选择方法用于苹果酸度的近红外光谱分析

采用便携式近红外光谱分析仪,对苹果样品进行扫描获得光谱数据,运用偏最小二乘法结合基于粒子群算法的波长选择方法对苹果试验数据进行多元统计分析,建立数学模型,利用该模型对苹果酸度进行了预测。对于基于粒子群算法和全谱偏最小二乘方法,校正集样品的酸度预测值和实测值之间的相关系数分别为0.9880和0.9553,校正均方根误差分别为0.0197和0.0388;预测集样品的酸度预测值和实测值之间的相关系数分别为0.9833和0.9596,预测均方根误差分别为0.0193和0.0304。与全谱偏最小二乘法相比,基于粒子群算法的偏最小二乘法,不仅较大地减少波长变量而降低计算量,而且也较大地提高了模型性能而增强了模型预测的准确性。该方法可建立较好的定量分析模型,能广泛应用于现场或野外苹果酸度的快速分析。     

独立分量分析预处理法提高苹果糖度模型预测精度研究

为了提高苹果近红外光谱糖度预测模型精度,利用独立分量分析方法(ICA)对苹果近红外光谱进行了预处理,并且建立了糖度的偏最小二乘(PLS)预测模型。结果表明,独立分量分析不但能分离出噪声信号,而且所分离出来的光谱信号也比原始光谱信号光滑。在预处理后的最佳PLS糖度模型校正时的相关系数rc和标准偏差SEC分别为0.9549和0.3361,用于预测时的相关系数rp和标准偏差SEP分别为0.9071和0.4355。与普通的平均处理法的PLS模型相比,其精度有所提高,且模型更加简洁。     

多模型共识偏最小二乘法用于近红外光谱定量分析

将多模型共识偏最小二乘法用于近红外光谱定量分析。利用随机抽取的训练子集建立一系列偏最小二乘模型,选取其中性能较好的部分模型作为成员模型,用这些成员模型来预测未知样品。将该方法用于一组生物样本的近红外光谱与样品中人血清白蛋白、γ-球蛋白以及葡萄糖含量之间的建模研究,并与单模型偏最小二乘法了进行比较。结果 PLS对独立测试集中三种组分进行50次重复预测的平均RMSEP分别为0.1066,0.0853和0.1338,RMSEP的标准偏差分别为0.0174,0.0144和0.0416;而本方法重复预测的平均RMSEP分别为0.0715,0.0750和0.0781,RMSEP的标准偏差分别为0.0033,0.2729×10-4和0.0025。     

icPL-ANN近红外光谱分析方法在航空燃料中的应用研究

以航空燃料的闪点预测为例,针对数据分布分散不连续,与光谱信息的线性关联偏弱的情况,提出一种将波段间隔组合与线性-人工神经网络(icPLANN)相结合的近红外光谱定量分析方法。该方法利用分段建模考核进行波段优选,最大程度地提取了有效信息,并结合PL-ANN方法建立了近红外光谱定量分析模型。最终把预测结果与间隔组合偏最小二乘法(icPLS)的实验结果进行了对比。结果表明,间隔组合PL-ANN模型的校正标准偏差(SEC)为0.75,预测标准偏差(SEP)为0.86,而间隔组合偏最小二乘法SEC为1.48,SEP为1.08,因此前一种方法的预测精度更高,预测决定系数(Rp2)能达到0.8971。可见,针对分散不连续数据与近红外光谱的复共线性影响预测模型准确度和稳定性的问题,间隔组合PL-ANN方法是一种有效的近红外光谱定量方法。     

近红外光谱法对头孢氨苄粉末药品的非破坏定量分析

采用近红外漫反射光谱法对头孢氨苄粉末药品中主要成分头孢氨苄进行快速、无损定量分析.采用偏最小二乘法建立近红外光谱信息与待测组分含量间的最佳数学校正模型.对3种光谱(SNV光谱、一阶导数、二阶导光谱)的预测结果进行了比较,讨论了光谱的预处理方法和主成分数对偏最小二乘法定量预测能力的影响,并对预测集样品进行预测.     

支持向量回归建立成品汽油通用近红外校正模型的研究

针对目前采用偏最小二乘法建立成品汽油分析模型存在的问题,采用近几年新兴的支持向量回归方法建立了多种汽油标号通用的校正模型,其预测能力优于对应的偏最小二乘法,对汽油研究法辛烷值、烯烃和芳烃的预测标准偏差分别为0.37、1.28%和1.38%,可应用于实际的汽油管道自动调合近红外光谱在线分析.     

最小二乘支持向量机结合红外光谱法测定润滑油酸值

在润滑油酸值进行红外光谱法测定中,采用最小二乘支持向量机(LS-SVM)建立了酸值的定量预测模型。用Kennard-Stone方法将30个样本划分为训练集(24个样本)和验证集(6个样本),进行定量预测,并与偏最小二乘法和径向基函数神经网络所建模型的预测进行比较。结果表明:LS-SVM所建模型的预测标准偏差(SEP)最小,仅为0.002;预测值的相对误差为1.3%~5.3%。由此认为LS-SVM所建模型的训练和预测结果均优于其余两种方法所建模型。对5个未知样品的分析结果表明:LS-SVM模型的预测值与化学法实测值之间的相对误差(1.2%~3.1%)也较少。     

组合偏最小二乘回归方法在近红外光谱定量分析中的应用

针对近红外光谱数据局部效应显著,变量个数多,彼此间常存在严重的复共线性,并多与样品组分含量呈非线性关系,构建一种组合非线性偏最小二乘回归(E-S-QPLSR)方法。它采用无重复采样技术(subag-ging),从训练样本中生成若干子样,然后每个子样通过二次多项式偏最小二乘回归(QPLSR),建立其子模型,并实现对训练样本因变量的定量预测,再将它们交由线性PLS算法用于计算各子模型的组合权系数。将该法应用于80个玉米样品的水组分含量与其近红外光谱的定量关系建模,效果良好,显示出很强的学习能力,所建模型的预报性能也优于其它方法。     

无信息变量消除法变量筛选优化烟草中总氮和总糖的定量模型

应用近红外光谱技术对烟草常规化学成分中总氮和总糖进行了测定。无信息变量消除(UVE)剔除光谱矩阵中没有有效信息的数据点,并用偏最小二乘方法(PLS)建立总氮和总糖的定量分析模型,外部检验对模型效果进行了评价。总氮定量模型校正集的决定系数R2为93.35%,标准偏差SEC为0.10;外部检验集的决定系数R2为94.09%,标准偏差SEP为0.11,相对标准偏差RSD为6.12%;总糖的定量模型校正集的决定系数R2为98.20%,标准偏差SEC为0.95;外部检验集样品的决定系数R2为98.01%,标准偏差SEP为0.78,相对标准偏差RSD为2.93%。结果表明:采用UVE建立的总氮与总糖的模型优于用全谱建立的模型,UVE提高了PLS模型的预测能力。     

Characterization of a Stable Adaptive Calibration Model Using Near-Infrared Spectroscopy and Partial Least Squares with a Kalman Filter

The calibration model of near-infrared (NIR) spectra established using the Kalman filter-partial least square (partial least squares combined with a Kalman filter) method can be adapted to outdated equipment, environmental changes, external samples, and other applications. However, the variance of the measurement noise estimation for NIR spectrum measurements cannot be easily obtained using Kalman filter-partial least squares; therefore, the variance in the measurement noise is often assumed to be zero for the Kalman filter-partial least square calibration model, which affects the stability of the model. In this study, the measured input and output data were used effectively, and the gamma test method for estimating the measurement noise variance was used to improve the stability of the Kalman filter-partial least square calibration model. First, an accurate estimation of the measurement noise variance was obtained, and accurate modeling was then performed using Kalman filter-partial least squares. Finally, 600 abandoned drilling fluid samples were used to confirm the validity of the proposed method. The Kalman filter-partial least square and gamma test-Kalman filter-partial least square methods are compared. Testing of external samples 401–600 demonstrated that the stability of the Kalman filter-partial least square model decreased. The root mean square error of the prediction of the Kalman filter-partial least square model was 27.135, which was worse than that of the gamma test-Kalman filter-partial least square model (20.307). The validation results show that the proposed method has better stability in tracking the evolution of the NIR spectrometer’s measurement state.     

激光诱导击穿光谱检测青菜中镉元素的多变量筛选研究

利用激光诱导击穿光谱(LIBS)技术与常规化学分析方法获取28个浓度梯度含Cd元素的青菜样品的LIBS谱线信息以及Cd含量信息.对获取的光谱信息结合标准归一化处理(SNV)、一阶导数(FD)、二阶导数(SD)、中心化处理(Center)作为偏最小二乘法(PLS)模型的优选方法;再根据4种预处理方法的预测结果选取最佳方法,同时将该方法作为间隔偏最小二乘法(iPLS)与联合区间间隔偏最小二乘法(SiPLS)优选青菜LIBS谱线的最佳波长区间.结果表明:通过SiPLS优选的特征波长区间分别为214.72 ～ 215.82 nm,215.88～ 216.97 nm,225.08 ～ 226.35 nm,并且经过中心化预处理后建立的验证模型效果最好,结果显示交叉验证均方根误差(RMSECV)为1.487,验证均方根误差(RMSEP)为1.094,相关系数(R)为0.9942,平均相对误差(ARE)为11.60％.研究结果表明,所选优化方法适合青菜中重金属Cd元素的LIBS校正模型的建立,且具有较好的预测效果.     

基于导数光谱融合建模的红外光谱定量分析方法

设计了基于奇摄动技术的导数光谱估计器并提出基于不同阶次导数光谱空间的融合建模定量分析方法。方法充分利用导数光谱信息空间、区间最小二乘法和融合建模的优点,挖掘光谱深层次信息进行融合建模。分别利用麦汁浓度范围4.23~18.76° P (柏拉图度)的啤酒红外光谱公共数据集和配制的浓度为0.04%~5%范围的葡萄糖溶液实测光谱数据集进行定量分析方法的对比实验。实验结果表明,融合建模定量分析方法能获得最小的预测均方根误差(RMSEP),其值分别为0.121和0.087,能够准确地进行定量分析。与其它建模方法相比较,基于导数光谱的融合建模方法所建立的预测模型具有明显优越的性能。     

光谱滤波法提高激光诱导击穿光谱对蔬菜中元素Pb的检测精度

激光诱导击穿光谱(Laser induced breakdown spectroscopy, LIBS)原始光谱中包含较多噪声信号, 为探究不同滤波方法对LIBS光谱预处理的影响, 本研究以实验室Pb污染处理的蔬菜为研究对象, 采集波长范围在400.45~410.98 nm的LIBS谱线信息, 分别利用相邻平均(Adjacent averaging)、Savitzky-Golay(S-G)滤波器、快速傅里叶变换(Fast Fourier transformation, FFT)对采集的LIBS光谱进行平滑、去噪, 并结合偏最小二乘法(PLS)定量分析模型对光谱处理效果进行评价.结果表明, S-G平滑效果最优, 当S-G滤波器窗口宽度为15, 拟合阶次为3时, PLS定量模型效果最佳, 其验证集均方根误差(RMSEP)为0.26、平均相对误差(ARE)为3.7%.结果表明, 选择适合的滤波方法有助于提高LIBS光谱质量以及检测模型的精度.     

Chemometric detection of acetaminophen in pharmaceuticals by infrared spectroscopy combined with pattern recognition techniques: comparison of attenuated total reflectance-FTIR and Raman spectroscopy

This paper presents and discusses the building of discriminant models from attenuated total reflectance (ATR)-FTIR and Raman spectra that were constructed to detect the presence of acetaminophen in over-the-counter pharmaceutical formulations. The datasets, containing 11 spectra of pure substances and 21 spectra of various formulations, were processed by partial least squares (PLS) discriminant analysis. The models found in the present study coped greatly with the discrimination, and their quality parameters were acceptable. A root mean square error of cross-validation was in the 0.14-0.35 range, while a root mean square error of prediction was in the 0.20-0.56 range. It was found that standard normal variate preprocessing had a negligible influence on the quality of ATR-FTIR; in the Raman case, it lowered the prediction error by 2. The influence of variable selection with the uninformative variable elimination by PLS method was studied, and no further model improvement was found.     

Determination of Basic Nitrogen in Residues of Crude Oil Distillation Using ATR-FTIR and Chemometric Methods

A method for basic nitrogen determination in residues of crude oil distillation using infrared spectroscopy and chemometrics algorithms was developed. Interval partial least squares, synergy interval partial least squares, and backward interval partial least squares were evaluated for calibration model construction. The samples were divided into a calibration and prediction set containing 40 and 15 samples, respectively. The first derivative with a Savitzky-Golay filter and the mean centered data showed the best results and were used in all calibration models. The backward interval partial least squares algorithm with spectra divided in 60 intervals and combinations of 4 intervals (1407 to 1372; 1117 to 1082; 971 to 936; 914 to 879 cm^?1) showed the best root mean square error of prediction of 0.016 wt%. This calibration model displayed a suitable correlation coefficient between reference and predicted values.     

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.     

Determination of Nitrogen in Rapeseed by Fourier Transform Infrared Photoacoustic Spectroscopy and Independent Component Analysis

Fourier-transform mid-infrared photoacoustic spectroscopy was utilized for rapid and nondestructive determination of nitrogen in rapeseeds. Rapeseed spectra were characterized by independent component analysis for quantitative calibration. A calibration model was built by using independent components as the input for partial least squares. Compared to full-spectrum partial least squares, the combined model achieved higher prediction accuracy with a residual predictive deviation of 2.06. Moreover, a genetic algorithm coupled with partial least squares was adopted to optimize the independent components for partial least square modeling and provide a further refined model with the highest residual predictive deviation of 2.12. A t-test verified a high congruence between results obtained by calibration models and the reference Kjeldahl method. This study demonstrated the promise of Fourier-transform mid-infrared photoacoustic spectroscopy for the determination of nitrogen in rapeseeds and the applicability of independent components for multivariate calibration.     

近红外光谱法测定端羟基环氧乙烷-四氢呋喃共聚醚的羟值

提出了用近红外光谱测定端羟基环氧乙烷-四氢呋喃共聚醚(PET)的羟值,结合主成分回归和偏最小二乘法建立了PET羟值与其近红外光谱之间的关联模型。结果表明,近红外光谱法与化学分析法的测定结果一致;近红外光谱法测定PET羟值的相对误差在5%以内;利用遗传算法选择部分波长建立校正可以降低模型的预测误差。     

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.