近红外光谱技术结合支持向量回归法测定烯草酮的含量

采用近红外光谱(NIR)技术结合支持向量回归法(SVR)建立了烯草酮乳油的定量分析方法。通过添加烯草酮原药、烯草酮助剂到二甲苯溶剂来配制不同浓度的校正集,采用SVR法建立了烯草酮的定量分析模型,模型的决定系数(R2)、校正集均方根误差(RMSEC)、检验集均方根误差(RMSEV)、预测集均方根误差(RMSEP)分别为1.0000、0.0260、0.0569和0.0550。结果表明,近红外光谱技术结合支持向量回归法可以准确地定量分析乳油中烯草酮的含量,方法简单、快捷,在农药质量检测中具有实际应用价值。     

煤中全水分及灰分的近红外测试方法研究

为了快速、无损检测煤质中的全水分和灰分,采集了120个精煤样品的近红外漫反射光谱,对微分光谱进行分析,利用偏最小二乘回归(PLSR)算法结合不同光谱预处理方法建立基于马氏距离剔除异常样品后的定量数学模型,分析预测值与真实值的相关性,并对最优预处理下的模型残差进行讨论。结果表明:经过多元散射校正处理后建立的全水分模型效果最优,相关系数达到0.982 12,校正集均方根误差为0.013,预测集均方根误差为0.017。经过5点平滑预处理后建立的灰分模型效果最佳,相关系数达到0.947 47,校正集均方根误差为0.058,预测集均方根误差为0.052,2项指标的残差波动均匀,模型的稳定性和预测能力较强。     

运用近红外光谱分析煤质硫含量

为了研究煤质的硫含量,采集了120个煤粉样品的近红外漫反射光谱,建立了偏最小二乘回归结合不同光谱预处理方法的定量数学模型,并与工业检测结果进行对比。结果表明:采用5点平滑处理后的模型效果最佳,相关系数达到0.89695,校正集均方根误差(RMSEC)和预测集均方根误差(RMSEP)分别为0.0406和0.0423,结果表明模型具有较高的相关性、稳定性和预测能力。     

基于DMD哈达玛变换近红外光谱仪的汽油辛烷值检测

应用近红外光谱分析检测技术建立一种汽油研究法辛烷值的快速定量分析方法。收集来自不同地区共100个汽油样品,应用化学计量学方法建立近红外光谱原始数据信息与研究法辛烷值之间的定量分析模型,结果表明:对原始光谱进行归一化处理后,采用偏最小二乘回归建立数学模型,其校正集与预测集相关系数分别为0.9300和0.9322,校正集均方根误差与预测集均方根误差分别为0.6700和0.6577,表明模型准确可靠,可应用于汽油辛烷值的快速检测。     

近红外光谱法检测氨纶中残存DMAC溶剂含量

以丙酮为溶剂,将氨纶中的残存溶剂N,N'-二甲基乙酰胺(DMAC)进行超声萃取,采用近红外光谱技术,结合偏最小二乘法,建立DMAC定量校正模型,测定氨纶中残存DMAC溶剂含量。结果表明:采用交叉验证得到了DMAC质量分数的线性范围为0~1.79%,1.79%~9.44%,模型的相关系数(R~2)分别为0.999 96,0.999 64,校正集的交叉验证均方根误差分别为0.004 11,0.041 34,预测集的均方根误差分别为0.003 95,0.032 30,方法的加标回收率为86.58%~100.87%,相对标准偏差为0.25%~0.95%。     

PCR和PLSR在煤质全水分检测中的比较研究

为了快速、无损的检测出煤质内部的全水分含量，研究采集了200个焦煤样品的近红外光谱，采用马氏距离和学生式残差相结合的方法剔除了异常样品，并对其进行了一阶微分、二阶微分、15点平滑、多元散射校正(MSC)和标准归一化处理(SNV)光谱预处理，采用主成分回归(PCR)和偏最小二乘回归(PLSR)对煤样进行建模分析。试验结果表明：经SNV预处理后的PCR模型最佳，校正集和交叉验证集相关系数分别为0.903和0.874,均方根误差分别为0.089和0.132;经15点平滑处理后的PLSR模型最佳，校正集和交叉验证集相关系数分别为0.974和0.887,均方根误差分别为0.038和0.043。PLSR模型相比PCR模型更具有代表性，模型稳定性和预测能力更强。     

近红外光谱法快速检测腐竹中硼砂的含量

选取市售腐竹作为研究对象，采集样品的近红外光谱，用国标分光光度法测定样品中硼砂的含量作为标准值，结合偏最小二乘法，建立了腐竹中硼砂含量的近红外光谱快速检测模型。结果表明，采用二阶导数谱，在7 150.75～5 924.25 cm^-1光谱区间，经多元散射校正、五点平滑处理建立的模型为较优模型。该模型的校正集线性相关系数(R_c)值为0.994 1,校正集均方根偏差(RMSEC)值为0.050 8,验证集线性相关系数(R_p)值为0.980 6,验证集均方根偏差(RMSEP)值为0.114,主因子数(factors)为10,相对分析误差(RPD)为5.1。模型有较好的稳定性，外部验证结果准确，可以用于腐竹中硼砂含量的快速检测。     

一种改进的支持向量回归的混凝土强度预测方法

混凝土抗压强度是影响建筑质量的主要因素,根据一些主要参数事先预测其强度可作为现场施工的参考。以支持向量回归(SVR)为理论基础,提出一种基于马氏距离的加权型SVR(MWSVR)的人工智能算法对混凝土强度进行预测。不同于将训练样本统一看待的传统方法,该算法根据训练集和测试集自变量的距离来决定训练样本在求解SVR模型中的重要性,距离测试集近的训练样本权重更大,赋予其更高的惩罚因子,从而得到更优的回归超平面。通过与决策树、随机森林、BP神经网络、RBF神经网络和传统SVR方法的比较研究,发现该算法具有更低的均方根误差。     

人造革基布纤维含量近红外光谱法专属定量分析模型的建立

研究了近红外光谱法在人造革基布纤维含量定量分析中的应用。通过分析样品近红外光谱的主成分,选择校正和验证样品集,选用偏最小二乘法(PLS),建立人造革基布纤维含量专属定量分析模型。结果表明:在9 017.5~4 396.9 cm~(-1)的波数范围内,选用9个主成分数建立了专属定量分析模型,模型的校正均方根误差(RMSEC)为0.678、相关系数(R_c~2)为0.999 5;预测均方根误差(RMSEP)为0.705、相关系数(R_v~2)为0.998 9,残差范围为-1.5~1.4;专属定量分析模型具有较好的预测准确性和方法重复性,可实现人造革基布纤维含量的快速测定。     

乳油型农药中多种禁止使用农药成分的同时检测

[目的]建立气相色谱法对乳油型农药制剂中多种禁止使用农药成分分析的方法.[方法]样品采用丙酮稀释,经大口径毛细管分离,气相色谱FID检测,双柱定性,内标法定量检测.[结果]6种乳油型农药中添加回收率在91.4％～105.6％之间,相对标准偏差为0.53％～3.75％.[结论]该方法可以高效、准确的对多种禁止使用农药成分同时检测.     

The prediction of clay contents in oil shale using DRIFTS and TGA data facilitated by multivariate calibration

The prediction of clay content in oil shale is important for the optimisation of oil shale processing conditions and process feasibility. The multivariate calibration technique of partial least squares regression (PLSR) was implemented in order to predict clay content in oil shale samples taken from the Stuart oil shale deposit, Queensland, Australia. The calibration data used were the diffuse reflectance infrared Fourier transformed spectroscopy (DRIFTS) spectra of 34 oil shale samples. DRIFTS data from another set of 20 oil shale samples were used for model validation. The data pre-processing includes the use of derivatives facilitated by the Savitsky-Golay nine-points’ method. A four components model was constructed and it showed a root mean square error of calibration (RMSEC) of 4.79% and a root mean square error of prediction (RMSEP) of 4.35%. TGA data sets were also used to construct a calibration model, which produced less accurate results than DRIFTS. DRIFTS, when combined with multivariate calibration, provided an accurate in situ method of evaluating clay content in oil shale. Clay content measured using XRD was used as a reference.     

近红外光谱法快速测定高含量精制甘油中的甘油含量

采用偏最小二乘法(PLS)建立了快速测定高含量精制甘油中甘油含量的近红外光谱校正模型,该模型主因子数为4,相关系数(R2)为99.12%,校正标准偏差(RMSECV)为0.027;以预测集对模型进行验证,结果表明,R2为99.17%,预测标准偏差(RMSEP)为0.023,对同一样品预测值的相对标准偏差(RSD)为0.04%。     

超高效液相色谱法测定陈皮、蒲公英根中2种氨基甲酸酯类农药残留

[目的]建立了带荧光检测器和柱后衍生系统的超高效液相色谱仪同时检测陈皮和蒲公英根中灭多威、克百威及其代谢物3-羟基克百威的方法。[方法]试样经QuEChERS方法进行前处理,经柱后衍生后,超高效液相色谱仪-荧光检测器测定,外标法定量。[结果]3种分析物的质量浓度范围在0.01~0.2 mg/L内,线性良好,回收率在84.80%~106.30%之间,变异系数不大于11%,最低定量限为0.01 mg/kg。[结论]该方法简单、稳定且灵敏度高,可用于中药材中农药残留的检测。     

Rapid Determination of Free Fatty Acid in Extra Virgin Olive Oil by Raman Spectroscopy and Multivariate Analysis

We introduce a visible Raman spectroscopic method for determining the free fatty acid (FFA) content of extra virgin olive oil with the aid of multivariate analysis. Oleic acid was used to increase the FFA content in extra virgin olive oil up to 0.80% in order to extend the calibration span. For calibration purposes, titration was carried out to determine the concentration of FFA for the investigated oil samples. As calibration model for the FFA content (FFA%), a partial least squares (PLS) regression was applied. The accuracy of the Raman calibration model was estimated using the root mean square error (RMSE) of calibration and validation and the correlation coefficient (R ²) between actual and predicted values. The calibration curve of actual FFA% obtained by titration versus predicted values based on Raman spectra was established for different spectral regions. The spectral window (945–1600 cm⁻¹), which includes carotenoid bands, was found to be a useful fingerprint region being statistically significant for the prediction of the FFA%. High R ² and small RMSE values for calibration and validation could be obtained, respectively.     

50％溴螨·炔螨特乳油的气相色谱分析

[目的]建立一种同时分析溴螨酯和炔螨特的气相色谱法.[方法]采用气相色谱法,以邻苯二甲酸二辛酯为内标物,使用DM-5毛细管柱和氢火焰离子化检测器,对溴螨·炔螨特乳油进行分离和定量分析.[结果]溴螨酯、炔螨特的线性相关系数为0.9969、0.997 5;平均回收率100.07％、100.12％;标准偏差为0.075、0.104;变异系数为0.3％、0.4％.[结论]方法操作简单、快速、准确,适用于溴螨·炔螨特乳油样品的定性和定量分析.     

丙草胺原药的高效液相色谱分析

[目的]建立一种测定丙草胺原药含量的高效液相色谱分析方法。[方法]采用反相高效液相色谱法,使用Inertsil CN-3色谱柱,以乙腈-水为流动相,在230 nm下进行定量分析。[结果]丙草胺质量浓度在800~2400 mg/L时,线性相关系数为0.9996,标准偏差为0.26,变异系数为0.27%,平均回收率为100.23%。[结论]该方法简单,准确,分离效果好,可满足丙草胺原药的定量分析。     

禾谷镰孢菌对杀菌剂戊唑醇敏感基线的建立

[目的]研究禾谷镰孢菌(Fusarium graminearum)对三唑类杀菌剂戊唑醇的敏感性,以期为该病的综合治理提供科学依据.[方法]采用菌丝生长速率法测定菌株对戊唑醇的敏感性.[结果]从河北、河南、山东省等主要地区采集和分离获得130个菌株,对戊唑醇的EC50值分布范围为0.0072～0.2880 mg/L,平均值为(0.1130±0.0570)mg/L,菌株对戊唑醇的敏感性频率分布呈单峰曲线,平均EC50值可作为菌株对戊唑醇的敏感性基线.[结论]该敏感基线可以作为田间禾谷镰孢菌对戊唑醇抗药性监测敏感性变化的参考.     

基于SVR的开关柜局部放电估计模型的研究

构建了一种基于支持向量回归机(SVR)的开关柜局部放电估计模型,利用开关柜局部放电在线监测系统所测得的超声波和高频脉冲电流数据对SVR模型进行训练,并验证其准确度。Matlab仿真结果为:训练集的均方差为0.015 2,决定系数为0.890,测试集的均方差为0.026 5,决定系数为0.849。该模型有效地对开关柜局部放电量做出了估计,为开关柜出现局部放电提供预警支持。     

Real-time monitoring of drug concentration in a continuous powder mixing process using NIR spectroscopy

A non-destructive NIR spectroscopic method was used to acquire on-line spectra of a continuous mixing process, and evaluate the performance of this novel system. Partial least squares (PLS) calibration models were developed and used for real-time determination of active ingredient concentration on the blends produced with a continuous mixer. The NIR method was developed for concentrations ranging from 0 to 15% (w/w) of acetaminophen (APAP), the active pharmaceutical ingredient used in the experiments. The calibration model's overall accuracy was 0.41% (w/w), and estimated through the root mean square error of cross validation (RMSECV) for samples predicted using leave-class-out cross validation. In this cross validation, each concentration was defined as a class, and when a sample of a specific concentration was predicted all samples of that concentration were left out of the calibration model. The precision of the calibration model was also estimated at various concentration levels, to facilitate the differentiation between the variation in drug concentration due to the analytical method's measurement uncertainty and the variation in the drug distribution throughout the powder blend. The results obtained are very promising since in three of the five powder mixes, the variation in the drug concentration in the powder blends was similar to that of the analytical method indicating a high degree of blend homogeneity