近红外光谱法检测奶粉中三聚氰胺的方法探讨

目的建立近红外光谱法快速鉴别奶粉中三聚氰胺的掺假。方法应用奶粉的脂肪、蛋白质、水分、乳糖和灰分5个理化指标建立奶粉的近红外鉴别模型。应用Spectrum软件的PLS1算法对样品进行计算,并对待鉴别奶粉进行定量分析。结果本方法能有效识别三聚氰胺质量比在0.05%~0.08%的掺假奶粉,但不能准确识别有何种掺杂物;对0.1%以上的掺假奶粉能正确识别出掺假物是三聚氰胺。对样品的脂肪、蛋白质、水份、乳糖和灰分5项理化指标进行定量分析的实际值与样品在模型中的计算值相对误差在10%以内。结论该方法快速、有效,可适用于奶粉三聚氰胺掺假的快速筛选和掺假鉴别。     

近红外光谱法检测奶粉掺假

目的建立近红外光谱法结合Adulterant Screen算法快速鉴别奶粉中大豆蛋白和尿素掺假的方法。方法采用近红外光谱仪获得奶粉未知样的光谱曲线,再用Adulterant Screen算法以及全数据库奶粉分类模型和既定类型的掺假物模型对曲线主要成分和掺假成分进行分析。结果该方法对一定浓度大豆蛋白和尿素掺假奶粉样可以实现掺假鉴别,大豆蛋白和尿素掺假奶粉样的掺假判别限分别为0.3 g/100g和0.2 g/100g,掺假物正确识别限分别为0.5 g/100g和0.8 g/100g。结论利用近红外光谱法结合Adulterant Screen算法可以快速鉴别奶粉中大豆蛋白和尿素的掺假。     

Short-wave near-infrared spectroscopy of milk powder for brand identification and component analysis

The aim of the present paper was to provide new insight into the short-wave near-infrared (NIR) spectroscopic analysis of milk powder. Near-infrared spectra in the 800- to 1,025-nm region of 350 samples were analyzed to determine the brands and quality of milk powders. Brand identification was done by a least squares support vector machine (LS-SVM) model coupled with fast fixed-point independent component analysis (ICA). The correct answer rate of the ICA-LS-SVM model reached as high as 98%, which was better than that of the LS-SVM (95%). Contents of fat, protein, and carbohydrate were determined by the LS-SVM and ICA-LS-SVM models. Both processes offered good determination performance for analyzing the main components in milk powder based on short-wave NIR spectra. The coefficients of determination for prediction and root mean square error of prediction of ICA-LS-SVM were 0.983, 0.231, and 0.982, and 0.161, 0.980, and 0.410, respectively, for the 3 components. However, there were less than 10 input variables in the ICA-LS-SVM model compared with 225 in the LS-SVM model. Thus, the processing time was much shorter and the model was simpler. The results presented in this paper demonstrate that the short-wave NIR region is promising for fast and reliable determination of the brand and main components in milk powder.     

大米蛋白粉多组分含量近红外光谱快速检测

大米蛋白粉中蛋白质、脂肪和水分的含量是其品质评定的重要指标,应用近红外光谱方法检测大米蛋白粉多组分含量.采集244份大米蛋白粉样品光谱数据,经小波变换处理后建立极限学习机模型(ELM),并采用自适应算法对极限学习机的参数进行优化,提高了模型的精度和稳定性.结果 显示,大米蛋白粉中蛋白质、脂肪和水分的预测集决定系数(R2...     

近红外光谱技术结合宽度学习系统识别国外奶粉产地

目的 利用近红外光谱技术对国外奶粉进行产地识别。方法 采集荷兰、新西兰、澳大利亚、德国、法国、英国和爱尔兰7个国家55个奶粉样品的近红外光谱,经过数据预处理、主成分分析降低数据维度和特征筛选,构建基于宽度学习系统（Broad Learning System,BLS）的奶粉产地快速识别模型。结果 采用多元散射校正加Savitzky-Golay滤波的预处理效果最好,与未做预处理相比,准确率提高14.55 %,主成分特征数大于38,识别效果最稳定,实验中还研究BLS主要参数对识别准确率的影响,可以指导参数选择。对荷兰、新西兰、澳大利亚和欧洲其它产地4类产地识别,测试准确率达到100.0 %,对样本做7类产地识别,准确率达到81.18 %。相同条件下,与支持向量机方法对比,4类产地识别,BLS方法准确率比支持向量机方法高9.10 %,7类产地识别,两者准确率相同。结论 本文提出的基于BLS的方法可以较好实现国外奶粉产地识别,为奶粉产地快速识别提供了新思路。     

发酵乳酸度近红外光谱快速检测方法的研究

利用近红外光谱技术对发酵乳酸度进行快速分析检测。采用电位滴定仪法测定71批次含活乳酸菌发酵乳样品的酸度实测值,并同时扫描得到近红外光谱数据。以校正集均方根误差(RMSEC)、预测集均方根误差(RMSEP)、交互验证均方根误差(RMSECV)及其相关系数R_c、R_p、R_cv为评价指标建立最优的酸度定量模型。利用模型对10批次含活乳酸菌发酵乳样品的酸度进行预测。结果表明,优化后的模型,其RMSEC、RMSEP、RMSECV及其相关系数R_c、R_p、R_cv分别为3.27、4.39、4.84,0.946 2、0.922 5、0.877 8。经外部验证后,该模型酸度预测值和实测值的最大相对误差为6.76%,满足不超过10%的要求。说明模型具有良好的预测性能,可用于发酵乳中酸度的快速检测。     

可见/近红外漫反射光谱无损检测甜柿果实硬度

该研究的目的是建立可见/近红外漫反射光谱无损检测甜柿果实硬度的数学模型,评价可见/近红外漫反射光谱无损检测甜柿果实硬度的应用价值。果实硬度采用果皮脆性、果皮强度和果肉平均硬度作为评价指标。在可见/近红外光谱区域(400～2 500 nm),采用改进偏最小二乘法,对比分析了不同导数处理、不同散射及标准化处理的甜柿果实硬度定标模型。结果表明,对于果皮强度和果皮脆性,采用最小偏二乘法、一阶导数处理和标准多元离散校正处理建立的定标模型预测效果较好,RP2分别为0.858和0.862,SEP分别为0.094和0.157,RPD分别为2.47和2.63。对于果肉平均硬度,采用改进偏最小二乘法、一阶导数处理和标准正常化和去散射处理建立的定标模型预测效果较好,RP2为0.82,SEP为0.063,RPD为2.35。因此,可见/近红外漫反射光谱无损检测技术可用于甜柿果实硬度的无损检测。     

Infrared spectroscopy technique for the nondestructive measurement of fat content in milk powder

The aim of this study was to investigate the potential of the infrared spectroscopy technique for nondestructive measurement of fat content in milk powder. Fat is an important component of milk powder. It is very important to be able to detect the fat content in milk powder using a rapid and nondestructive method. Near and mid infrared spectroscopy techniques were used to achieve this purpose. Least-squares support vector machine (LS-SVM) was applied to developing the fat-content prediction model based on the infrared spectral transmission values. The results based on LS-SVM were better than those of back-propagation artificial neural networks. The determination coefficient for prediction of the results predicted by the LS-SVM model was 0.9796 and the root mean square error was 0.836708. It was concluded that infrared spectroscopy technique could quantify the fat content in milk powder rapidly and nondestructively. The process is simple and easy to operate. Moreover, the prediction results were compared between near infrared and mid infrared spectral data. The results showed that the performances of model with both mid infrared and near infrared spectral data were a little worse than that of the whole infrared spectral data. The results could be beneficial for designing a simple and nondestructive spectral sensor for the quantification of fat content in milk powder.     

红提葡萄V_C含量的可见/近红外检测模型

为了建立红提葡萄VC含量的可见/近红外漫反射光谱检测模型,并评价其应用价值,应用不同的化学计量学建模方法和光谱预处理方法,在不同特征波长区间内建立定标模型,讨论建模效果,并通过预测集样品验证最优模型的精度。结果显示:在全光谱范围内,应用改进偏最小二乘法(MPLS)结合一阶导数、5点平滑、加权多元离散校正(WMSC)处理得到的定标模型效果最优,交互验证标准差SECV为0.054 3,定标决定系数R2cv为0.920 2,预测决定系数R2p为0.931 8,预测标准差SEP为0.050 0,残差平方和PRESS为0.188 0,预测相对分析误差RPD为3.640 0。故应用可见/近红外漫反射技术对红提葡萄果实VC含量进行快速无损检测是可行的,模型稳定且精度较高。     

Monitoring quality loss of pasteurized skim milk using visible and short wavelength near-infrared spectroscopy and multivariate analysis

Visible and short wavelength near-infrared diffuse reflectance spectroscopy (600 to 1,100 nm) was evaluated as a technique for detecting and monitoring spoilage of pasteurized skim milk at 3 storage temperatures (6, 21, and 37°C) over 3 to 30 h (control, t = 0 h; n = 3). Spectra, total aerobic plate count, and pH were obtained, with a total of 60 spectra acquired per sample. Multivariate statistical procedures, including principal component analysis, soft independent modeling of class analogy, and partial least squares calibration models were developed for predicting the degree of milk spoilage. Principal component analysis showed apparent clustering and segregation of milk samples that were stored at different time intervals. Milk samples that were stored for 30 h or less at different temperatures were noticeably separated from control and distinctly clustered. Soft independent modeling of class analogy analysis could correctly classify 88 to 93% of spectra of incubated samples from control at 30 h. A partial least squares model with 5 latent variables correlating spectral features with bacterial counts and pH yielded a correlation coefficient (R = 0.99 and 0.99) and a standard error of prediction (0.34 log₁₀ cfu/mL and 0.031 pH unit), respectively. It may be feasible to use short wavelength near-infrared spectroscopy to detect and monitor milk spoilage rapidly and noninvasively by correlating changes in spectral features with the level of bacterial proliferation and milk spoilage.     

基于近红外光谱和SSA-ELM的苹果糖度预测

目的：剔除近红外光谱存在大量冗余信息以及提高苹果糖度预测模型的精度,建立快速无损检测苹果糖度的方法。方法：提出一种基于小波包变换的特征波长筛选和樽海鞘算法改进极限学习机的苹果糖度预测模型。针对苹果光谱数据具有维度高而复杂的特点,对光谱数据进行降维处理,分别对比全波段和偏最小二乘法、连续投影法和小波包变换等筛选特征波长的结果,确定苹果光谱特征波长筛选方法;针对极限学习机（extreme learning machine,ELM）,模型性能受其初始权值和隐含层偏置选择的影响,运用樽海鞘群算法进行ELM模型的初始权值和隐含层偏置优化,提出一种基于樽海鞘算法改进极限学习机的苹果糖度预测模型。结果：与遗传算法（genetic algorithm,GA）改进ELM（GA-ELM）、粒子群算法改进ELM（PSO-ELM）和ELM相比,基于SSA-ELM的苹果糖度预测模型的预测精度最高。结论：通过智能算法优化ELM模型的参数可以有效提高ELM模型的苹果糖度预测精度。     

应用傅立叶变换近红外光谱检测婴幼儿配方奶粉中的乳糖含量

利用傅立叶变换近红外光谱（FT-NIR）技术结合偏最小二乘法（PLS）对婴幼儿配方奶粉中的乳糖进行快速检测分析。搜集 94个不同产地、不同品牌的婴幼儿配方奶粉中乳糖的实验室数据,并采集婴幼儿配方奶粉的近红外光谱图,选择最优的光谱预处理方法,优化、验证和建立模型,并预测6个未知品牌的婴幼儿配方奶粉样品的乳糖含量。结果表明,不同阶段的婴幼儿配方奶粉有非常相似 的近红外特征图谱,图谱处理后的方差为95.423 5%,该模型测定的乳糖值与高效液相色谱（HPLC）法测定的乳糖值之间的平均相对误 差均≤0.67%,相对标准偏差（RSD）均≤0.88%,均符合误差范围。该方法可以无损、快速、高效地测定婴幼儿配方奶粉中的乳糖含量。     

Characterising variances of milk powder and instrumentation for the development of a non-targeted,Raman spectroscopy and chemometrics detection method for the evaluation of authenticity

There is a need to develop rapid tools to screen milk products for economically motivated adulteration. An understanding of the physiochemical variability within skim milk powder (SMP) and non-fat dry milk (NFDM) is the key to establishing the natural differences of these commodities prior to the development of non-targeted detection methods. This study explored the sources of variance in 71 commercial SMP and NFDM samples using Raman spectroscopy and principal component analysis (PCA) and characterised the largest number of commercial milk powders acquired from a broad number of international manufacturers. Spectral pre-processing using a gap-segment derivative transformation (gap size = 5, segment width = 9, fourth derivative) in combination with sample normalisation was necessary to reduce the fluorescence background of the milk powder samples. PC scores plots revealed no clear trends for various parameters, including day of analysis, powder type, supplier and processing temperatures, while the largest variance was due to irreproducibility in sample positioning. Significant chemical sources of variances were explained by using the spectral features in the PC loadings plots where four samples from the same manufacturer were determined to likely contain an additional component or lactose anomers, and one additional sample was identified as an outlier and likely containing an adulterant or differing quality components. The variance study discussed herein with this large, diverse set of milk powders holds promise for future use as a non-targeted screening method that could be applied to commercial milk powders.     

基于可见/近红外光谱技术的腐坏猪肉检测控制系统设计

目的 设计腐坏猪肉的快速、无损检测控制系统。方法 通过研究可见/近红外光谱技术, 根据其在应用过程中的使用特点并结合实际情况的需求, 设计检测系统的总体方案。结果 设计检测系统方案, 包括检测对象、检测指标, 设计控制系统的结构、功能和工作流程。结论 光纤探头距离样品高度为10 cm, 单个样品检测时间控制在5 s内, 使用DSP作为控制核心, 用于检测猪肉是否腐败。     

Fast determination of boiling time of yardlong bean using visible and near infrared spectroscopy and chemometrics

The performance of visible and near infrared (Vis-NIR) spectroscopy as a rapid and non-destructive technique to determine the boiling time of yardlong beans was investigated. Vis-NIR spectra of beans boiled for 0, 30 to 300 s were measured. Robust least-squares support vector machines (R-LS-SVM) with RBF kernel obtained the best result. Partial least square based variable elimination (VE_PLS) and robust least square-support vector machines based variable elimination (VE_R-LS-SVM) were used for variable selections. Four most important variables at 409, 614, 880, and 984 nm were selected. After the variable selection, 90% of the variables were eliminated and the model’s residual predictive deviation (RPD) only decreased 10% compared to that of the model without the variable elimination. The results showed that the Vis-NIR spectra can be used to determine the boiling time of yardlong beans during the boiling process.     

Elman网络近红外光谱技术同时测定鲜乳中三种主成分含量

采用Elman神经网络(反馈神经网络,Recurrent Network)结合近红外光谱技术建立鲜乳中的脂肪、蛋白质、乳糖定量分析模型.用偏最小二乘法(Partial Least SqHales.PUS)将原始数据压缩主成分,取前3个主成分的14个吸收峰值输入Elman网络,网络中间层神经元个数为53.Elman网络模型对样品中3个组分含量的预测决定系数(R2)分别为:0.985、0.951、0.967,表明所建Elman网络预测模型能够较准确预测鲜乳中脂肪、蛋白质和乳糖的含量,从而为近红外光谱的多组分定量分析提供了新思路.     

衍生化-富集-表面增强拉曼光谱法快速筛查奶粉中亚硝酸盐

目的 建立衍生化-富集-表面增强拉曼光谱法快速检测奶粉中亚硝酸盐的分析方法.方法 样品水溶液通过除蛋白、衍生化后,采用阳离子小柱PSY-001对衍生化合物进行富集,再使用表面增强拉曼光谱对样品中的亚硝酸盐含量进行定性检测.结果 7类不同奶粉,采用本研究所建立的方法进行检测,根据不同的批处理量,单个样品检测全过程只需3～...     

Simultaneous detection for adulterations of maltodextrin,sodium carbonate,and whey in raw milk using Raman spectroscopy and chemometrics

To achieve rapid on-site identification of raw milk adulteration and simultaneously quantify the levels of various adulterants, we combined Raman spectroscopy with chemometrics to detect 3 of the most common adulterants. Raw milk was artificially adulterated with maltodextrin (0.5–15.0%; wt/wt), sodium carbonate (10–100 mg/kg), or whey (1.0–20.0%; wt/wt). Partial least square discriminant analysis (PLS-DA) classification and a partial least square (PLS) regression model were established using Raman spectra of 144 samples, among which 108 samples were used for training and 36 were used for validation. A model with excellent performance was obtained by spectral preprocessing with first derivative, and variable selection optimization with variable importance in the projection. The classification accuracy of the PLS-DA model was 95.83% for maltodextrin, 100% for sodium carbonate, 95.84% for whey, and 92.25% for pure raw milk. The PLS model had a detection limit of 1.46% for maltodextrin, 4.38 mg/kg for sodium carbonate, and 2.64% for whey. These results suggested that Raman spectroscopy combined with PLS-DA and PLS model can rapidly and efficiently detect adulterants of maltodextrin, sodium carbonate, and whey in raw milk.     

近红外光谱快速检测食用植物油中酸价

目的 建立基于近红外光谱快速测定食用植物油中酸价的分析方法。方法 采用冷溶剂指示剂滴定法检测371个食用植物油样品的酸价,并采集样品的近红外光谱。经过标准正态变换结合一阶导数对近红外光谱进行数据预处理,选用竞争性自适应重加权采样算法选取重要变量,建立食用植物油酸价的偏最小二乘回归模型。结果 蒙特卡洛交互验证结果显示,食用植物油酸价预测模型的验证集决定系数Q2为0.9983,交互检验的均方根误差(root mean square error of cross validation, RMSECV)为0.0461,模型预测的独立测试集的酸价与实测值相关系数为0.9834,预测效果良好。结论 本研究建立的食用植物油酸价近红外光谱快速检测方法能够满足检测要求,为评价或跟踪食用油品质提供快速无损的技术思路。     

基于近红外光谱的SSA-RELM的菠萝含水率快速检测

目的：建立快速无损检测菠萝含水率的方法。方法：提出一种基于连续投影法的特征波长选择和麻雀搜索算法（SSA）优化正则化极限学习机（RELM）的菠萝含水率检测模型。针对菠萝近红外光谱数据具有维度高、冗余信息多的特点,分别对比连续投影法、主成分分析法和全波段等筛选特征波长的结果,确定菠萝近红外光谱特征波长筛选方法;针对RELM模型性能受其输入层权值和隐含层偏置的影响,运用麻雀搜索算法优化RELM模型的输入层权值和隐含层偏置,提出一种基于麻雀搜索算法改进正则化极限学习机的菠萝含水率检测模型。结果：与遗传算法改进正则化极限学习机（GA-RELM）、粒子群算法改进正则化极限学习机（PSO-RELM）和RELM相比,基于麻雀算法改进正则化极限学习机（SSA-RELM）的菠萝含水率检测模型的检测精度最高。结论：麻雀搜索算法优化RELM模型可以有效提高RELM模型的菠萝含水率检测精度。