应用PLS及BP神经网络定量分析汽油中甲缩醛含量

建立了采用中红外方法测定汽油中甲缩醛含量的方法。通过实验室配比一定体积分数的甲缩醛-汽油混合物作为研究的基础数据,利用傅里叶红外光谱仪测定不同比例甲缩醛-汽油混合物的谱图,分别建立偏最小二乘法(PLS)和BP神经网络的中红外谱图分析的校正模型。其中偏最小二乘法甲缩醛定量模型的相关系数R2为0.975 3,预测均方根误差(RMSEP)为0.121;BP神经网络法甲缩醛定量模型的相关系数R2为0.974 2,预测均方根误差(RMSEP)为0.132。该方法是一种操作简便、快速可靠的分析甲缩醛含量的方法。     

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%。     

拉曼光谱用于CHO细胞培养液多指标快速分析

为了快速分析中国仓鼠卵巢(CHO)细胞培养液,在CHO细胞培养过程中取样,离线分析获得葡萄糖浓度、乳酸浓度、谷氨酸浓度、谷氨酰胺浓度、活细胞密度、总细胞密度、细胞活度和单克隆抗体表达量等指标的参考值,采集细胞培养液上清的拉曼光谱,以偏最小二乘(PLS)法建立拉曼光谱与各指标的多元校正模型。各模型均具有合理的主成分数、较高的决定系数(R~2)、较低的校正误差均方根(RMSEC)和预测误差均方根(RMSEP),且RMSEC与RMSEP相差不大,模型具有较好的预测性能。结果表明,该方法可望用于CHO细胞培养过程多指标离线快速检测,也为该生产过程在线实时监测和反馈控制的实现提供了研究基础。     

流化床制粒过程颗粒水分预测研究

对流化床进行工程化改造,安装近红外光谱仪,对制粒过程中的颗粒水分含量进行光谱采集。采用偏最小二乘法(PLS)、粒子群-核岭回归(PSO-KRR)和随机森林-偏最小二乘法(RF-PLS)建立回归模型,对不同的算法的预测精度进行了研究。结果表明,PLS模型预测集均方根误差(RMSE)为0.218 0,相关系数R为0.971 7;PSO-KRR模型预测集RMSE为0.215 4,R为0.973 8;RF-PLS模型预测集RMSE为0.205 9,R为0.973 3。其中RF-PLS模型的预测效果最好。     

近红外光谱技术应用于中草药口服液在线质量控制的化学计量学建模

以一种中草药口服液中多糖含量、可溶性固形物含量及pH为对象,利用近红外光谱技术对其进行实时在线检测,重点研究了化学计量学建模方法。建模过程采用了一种系统工程的方法,综合考虑了光谱预处理、特征波段选择、数据选择和分组、近红外原始光谱和化学分析参考值的误差分析,并把工具箱集成在一起。还考察了光谱采集的重复性、采样点取样条件,并对实验室测定的参考值进行了重复性及测量误差的考察。通过对比最终选择的是偏最小二乘法(PLS)结合遗传算法自动选波段。除此之外,以模型的交叉验证均方根误差(RMSECV)、预测均方根误差(RMSEP)、质量指标化学参考值与预测值间的相对误差为指标筛选最佳建模参数。建模结果显示,多糖模型预测值与化学参考值间的相对误差可控制在10%内,可溶性固形物误差在5%内,pH误差在4%内。生产使用表明,所建立的模型可有效应用于在线、快速对质量指标做出准确的预测。     

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。     

近红外光谱技术结合支持向量回归法测定非法对硫磷的含量

[目的]采用近红外光谱(NIR)技术结合支持向量回归法(SVR)建立乳油中非法对硫磷的定量分析方法.[方法]通过向1.8％阿维菌素乳油中加入对硫磷原药和二甲苯溶剂来配制不同质量分数的校正集,采用SVR法建立非法对硫磷的定量分析模型.[结果]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0.9994、0.4377、0.5065、0.7482.[结论]该法可以定量测定乳油中非法对硫磷的含量.     

近红外光谱法测定HMX中α-HMX杂质晶型的含量

为了快速检测HMX中杂质晶型α-HMX的含量,在制备建模样品的基础上,利用近红外光谱技术,采用偏最小二乘法建立了HMX光谱与其α-HMX杂质晶型含量的计算模型。讨论了建模样品的代表性、模型光谱范围的选择及模型的优化过程。结果表明,模型具有广泛代表性,最佳光谱范围为6 476~6 446cm-1和4 602~4 424cm-1,交互验证决定系数(R2)为0.996,参考值交互验证残差均方根(RMSECV)为0.20%;外部验证的残差均方根(RMSEP)为0.27%;该法误差均小于0.13%,标准偏差为0.1%;近红外光谱法操作简单、快速、无损、绿色环保,可用于HMX中α-HMX杂质晶型含量的检测。     

基于二维相关近红外光谱技术测定辅料十二烷基硫酸钠

为了测定缬沙坦和辅料十二烷基硫酸钠共存样品中辅料的含量,配制成含有十二烷基硫酸钠含量为0.30%~5.88%的缬沙坦样品共35个。以十二烷基硫酸钠浓度为外扰,分别研究了十二烷基硫酸钠和缬沙坦共存样品的二维相关近红外光谱特征,分别选择随浓度变化大的区间4119~4216 cm-1、4235~4273 cm-1、4312~4351 cm-1、4484~4676 cm-1、5732~5828 cm-1、8132~8323 cm-1为光谱的建模区间,利用偏最小二乘方法建立定量预测模型。结果表明:模型的交叉验证决定系数为0.8670,交叉验证均方根误差(RMSECV)为0.804,预测均方根误差(RMSEP)为0.775,对未知样品集预测结果的平均相对误差为0.25%,这表明二维相关近红外光谱技术选择的波段建立的定量模型具有较好的预测效果。     

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。     

复合PLS模型在近红外光谱分析煤炭中的应用

为了更好地确定偏最小二乘法模型的主成分数,提出一种传统偏最小二乘法和多主成分数偏最小二乘法相结合构建复合偏最小二乘模型的方法。给出了预测时两种样品相似度的计算方式:直接距离法和性质得分距离法。分别采用复合偏最小二乘法和传统偏最小二乘法对煤炭的全硫、灰分、热值和碳含量进行建模预测,比较传统偏最小二乘法和多主成分数偏最小二乘法建模过程中的相关系数和交互验证均方根误差,采用复合偏最小二乘模型对验证集样品预测时,计算了不同相似度计算方式下不同样品间距离算法的预测均方根误差,并同传统偏最小二乘法预测均方根的误差进行比较,结果表明:复合偏最小二乘法建模比传统偏最小二乘法建模有更强的适应性,能够提高预测的准确性。     

Fourier Transform Near Infrared Spectroscopy as a Quality Control Tool for the Analysis of Lecithin and By-Products During Soybean Oil Processing

Fourier transform near infrared (FT-NIR) spectroscopy was used to analyze multiple measurement parameters in lecithin production samples and soybean oil refining by-products. For lecithin, partial least squares (PLS) calibration models were developed for acetone insolubles, acid value and moisture and leave-one-out cross validation of the calibration models yielded root mean square error of cross validation (RMSECV) values of 0.37%, 0.59 (mg KOH/g) and 0.050%, respectively. An independent test set consisting of 40% of the lecithin production samples were predicted from the PLS calibration models and a root mean square error of prediction (RMSEP) of 0.41%, 0.53 (mg KOH/g) and 0.056% were obtained for acetone insolubles, acid value and moisture, respectively. Comparison of FT-NIR predictions and corresponding reference method values of 10 lecithin samples using a two-tailed t test showed no significant difference at the p = 0.05 level. A set of 51 samples of soybean oil refining by-products, including acidulated soapstock, fatty acids and black oil, were used for developing PLS calibration models for measuring acid value, moisture and iodine value and leave-one-out cross validations for each model gave values for RMSECV of 6.59 (mg KOH/g), 0.046% and 0.42 (mg I₂/g), respectively. Overall, the results of this study demonstrate the suitability of FT-NIR spectroscopy for the routine analysis of lecithin production samples and soybean oil refining by-products for quality control purposes.     

傅里叶变换近红外光谱法快速测定聚氯乙烯的K值

研究了傅里叶变换近红外光谱技术快速测定聚氯乙烯K值的分析方法。采用漫反射方式和偏最小二乘法 (PLS),建立了聚氯乙烯K值定量分析数学模型,其决定系数(R2)和均方差(RMSECV)分别为97．96％和0．362。实验结果表明:近红外分析法和实验室标准分析方法测定结果基本一致。本方法重复性好,具有快速、操作简单、无污染等诸多优点。     

Application of MIA for a QSAR Study of Inhibitory Activity of DHP Derivatives and Design of New Compounds Using WT and GA for Pixel Processing

A quantitative structure-activity relationship (QSAR) modeling was carried out for the prediction of inhibitory activity of dihydropyridine (DHP) derivatives known as calcium channel blocker (CCB) drugs. Partial least squares (PLS) algorithm was used for prediction of inhibitory activity of calcium channel antagonists as a function of the bidimensional images. In the present study, it is investigated that the effect of pixel selection by application of genetic algorithms (GAs) for PLS model, because of the GAs is very useful in the variable selection in modeling. Pre-processing methods such as wavelet transform (WT) were also used to enhance the predictive power of multivariate calibration methods. The subset of pixels, which resulted in the low prediction error, was selected by GA. To evaluate the models applied in this study (PLS, GA-PLS and WT-GA-PLS), the inhibitory activities of several compounds, not included in the modeling procedure, were predicted. The results of models showed high prediction ability with root mean square error of prediction (RMSEP) of 0.51, 0.39 and 0.17 for PLS, GA-PLS and WT-GA-PLS, respectively. The WT-GA-PLS method was employed to predict the inhibitory activity of the new antagonists.     

Simultaneous determination of molecular weight and crystallinity of recycled HDPE by infrared spectroscopy and multivariate calibration

An attempt of correlating molecular weight (M_n) of recycled high‐density polyethylene (HDPE) as measured by size‐exclusion chromatography (SEC) with diffuse reflectance near and mid‐infrared spectroscopy (NIR/MIR) was made by means of multivariate calibration. The spectral data obtained was also used to extract information about the degree of crystallinity of the recycled resin. Differential scanning calorimetry (DSC) was used as the reference method. Partial least‐squares (PLS) calibration was performed on the MIR and NIR spectral data for prediction of M_n. Four PC factors described fully the PLS models. The root‐mean‐square error of prediction (RMSEP) obtained with MIR data was 360, whereas a RMSEP of 470 was achieved when calibration was carried out on the diffuse reflectance NIR data. A PLS calibration for prediction of degree of crystallinity was performed on the NIR data in the 1100–1900‐nm region, but the ability of prediction of this model was poor. However a PLS calibration in the region 2000–2500 nm yield better results. Four PC factors explained the most of the variance in the spectra and the RMSEP was 0.4 wt %. © 2002 Wiley Periodicals, Inc. J Appl Polym Sci 85: 321–327, 2002     

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。     

基于振动信号分析法的催化剂积炭量测量模型

基于催化剂固体颗粒运动碰撞反应器壁面产生振动信号的机理,借助平滑消噪及偏最小二乘（PLS）回归等多元数据处理手段,结合振动信号的功率谱分析,建立了在一定表观气速下测量结焦催化剂积炭量的PLS回归模型。实验室冷模研究表明,在表观气速为0.06～0.12 m·s^-1的范围内,模型所得催化剂积炭量预测值与真实值的相关系数均在0.893以上,而预测均方根误差(RMSEP)均在0.51以下,具有较高的精度。由此,获得了一种便捷灵敏、安全环保的非侵入式结焦催化剂积炭量测量技术,能够实现反应器内结焦催化剂积炭量的实时在线检测与监控。