Simultaneous analysis of main catechins contents in green tea (Camellia sinensis (L.)) by Fourier transform near infrared reflectance (FT-NIR) spectroscopy

This paper reported the results of simultaneous analysis of main catechins (i.e., EGC, EC, EGCG and ECG) contents in green tea by the Fourier transform near infrared reflectance (FT-NIR) spectroscopy and the multivariate calibration. Partial least squares (PLS) algorithm was conducted on the calibration of regression model. The number of PLS factors and the spectral preprocessing methods were optimised simultaneously by cross-validation in the model calibration. The performance of the final model was evaluated according to root mean square error of cross-validation (RMSECV), root mean square error of prediction (RMSEP) and correlation coefficient (R). The correlations coefficients (R) in the prediction set were achieved as follows: R = 0.9852 for EGC model, R = 0.9596 for EC model, R = 0.9760 for EGCG model and R = 0.9763 for ECG model. This work demonstrated that NIR spectroscopy with PLS algorithm could be used to analyse main catechins contents in green tea.     

Value Adding to Red Grape Pomace Exploiting Eco-friendly FT-NIR Spectroscopy Technique

Agro-food industries require sustainable and profitable alternatives to disposal of their by-products. Grape pomace is a winemaking residue that represents a low-cost natural source of phenolic compounds with recognized antioxidant properties. In this work, Fourier-transform near-infrared (FT-NIR) spectroscopy and chemometric analysis were exploited to the characterization of red grape pomace composition (content of seeds and skins) and chemical properties as total phenolic content (TPC) and total antioxidant capacity (TAC). Raw (n?=?96) and milled (n?=?96) samples were evaluated by NIR spectroscopy and by classical batchwise assays, Folin-Ciocalteu, and ABTS for TPC and TAC, respectively, after different storage times (1 week to 2 months). Grape seeds had higher levels of TPC and TAC per sample dry weight when compared to grape skins. FT-NIR spectra of raw and milled samples were calibrated against content (%) of skins and seeds, TPC, and TAC using partial least squares (PLS) modeling. Spectral wavelength selection and latent variables were optimized for the lowest root-mean-square errors. PLS models’ results showed higher linearity for milled samples (0.936?>?R ²?>?0.914) when compared to raw samples (0.885?>?R ²?>?0.928). The range error ratio (RER) was between 10 and 14 for raw samples, while for milled grape pomace, it ranged from 15 to 18. Results confirmed that NIR spectroscopy can be applied to winemaking residues with virtually no sample processing needed to estimate the content of grape seeds and skins, the total phenolics, and total antioxidant capacity. Therefore, FT-NIR technique represents a non-destructive and eco-friendly technique to foster added value of grape pomace residues before time-consuming extraction steps are performed.     

Development of a rapid, non-destructive method for egg content determination in dry pasta using FT-NIR technique

A quick, non-destructive method, based on Fourier transform near-infrared (FT-NIR) spectroscopy for egg content determination of dry pasta is presented. Multivariate calibration was carried out by using partial least squares (PLS) regression. A calibration set of 108 samples, a validation set of 22 samples and a prediction set of 11 samples of egg pasta were used. The diffuse reflection spectra of different types of pastas were measured by FT-NIR analyzer in the 800-2500 nm spectral range. The optimal results for egg content (root mean square error of prediction (RMSEP) = 0.7; R² = 90.7, Rank = 4) were obtained when the spectra were subjected to the first derivation combined with multiplicative scatter correction (MSC) and smoothing. Egg content was determined from FT-NIR results by introducing a mathematical correction step.     

Determination of degree of substitution of carboxymethyl starch by Fourier transform mid-infrared spectroscopy coupled with partial least squares

The degree of substitution (DS) markedly affects the properties of carboxymethyl starch (CMS). The conventional methods for the DS determination are time-consuming and not environment friendly. Fourier transform mid-infrared (FT-MIR) spectroscopy coupled with partial least squares (PLS) regression is applied to determine the DS of CMS in the present study. Calibration models with direct titration as the reference method were optimised by cross validation. A PLS regression model with a coefficient of determination (R²) of 0.9593 and root-mean-square error of cross validation (RMSECV) of 0.0141 was obtained in the spectral range from 500 to 4000 cm⁻¹. The prediction set gave a coefficient of determination (R²) and root-mean-square error of prediction (RMSEP) of 0.9368 and 0.0228, respectively. The results obtained in this study indicate that FT-MIR spectroscopy can be used as an easy, rapid, and novel tool to quantitatively predict the DS of CMS.     

Novel Prediction of Total Fat Content in Cocoa Beans by FT-NIR Spectroscopy Based on Effective Spectral Selection Multivariate Regression

Total fat content is a major quality parameter that chocolate manufactures consider when selecting cocoa beans. This paper attempted the feasibility of measuring total fat content in cocoa beans by using Fourier transform near-infrared (FT-NIR) spectroscopy based on a novel systematic study on efficient spectral variables selection multivariate regression. After the efficient spectra interval selection by synergy interval partial least squares (Si-PLS), the data were treated with support vector machine regression (SVMR) leading to synergy interval support vector machine regression (Si-SVMR). Experimental results showed that the model based on the novel Si-SVMR algorithm was superior to the others. The optimum results were assessed by root-mean-square error of prediction (RMSEP) and correlation coefficient (R _pre) in the prediction set. The performance of Si-SVMR model was RMSEP?=?0.015 and R _pre?=?0.9708. This study has demonstrated that the total fat content in cocoa beans could rapidly be predicted by FT-NIR spectroscopy and Si-SVMR technique. The novel strength and accuracy of Si-SVMR in contrast to other multivariate algorithms has been derived.     

Determination of Three Alcohols in Chinese Dukang Base Liquor by FT-NIR Spectroscopy

Alcohols are important aroma compounds in Chinese liquors. In this work, 3-methyl-1-butanol, 1-butanol, and 1-propanol in Dukang base liquor were simultaneously analyzed by gas chromatography (GC) and fourier-transform near-infrared (FT-NIR) spectroscopy. The optimal combinations of spectral intervals for three alcohols were selected for modeling. The calibration models, which are based on FT-NIR spectral variables and the chemical values, were established with partial least square (PLS) and validated using internal cross validation. In calibration set, the coefficients of determination (R ²) for 1-propanol, 1-butanol, and 3-methyl-1-butanol were 95.21, 98.05, and 98.05, respectively; corresponding root mean square errors of calibration (RMSEC) were 0.27, 0.49, and 0.67 mg per 100 mL. In validation set, the R ² were 94.72, 97.96, and 95.22; the root mean square errors of prediction (RMSEP) were 0.40, 0.81, and 1.35 mg per 100 mL. The results indicated that the correlation between the values determined by GC and the values estimated by the calibration for the three alcohols was excellent. The FT-NIR spectroscopy calibration models, which with good prediction performance and high precision, could be used as a rapid methods for determination of alcohols in Chinese liquor.     

Quantification of total polysaccharides and triterpenoids in Ganoderma lucidum and Ganoderma atrum by near infrared spectroscopy and chemometrics

Two chemometrics, the partial least-squares (PLS) and radial basis function (RBF) network were performed to develop a quantification method for total polysaccharides and triterpenoids in Ganoderma lucidum and Ganoderma atrum from different origins based on near infrared reflectance spectroscopy (NIR). The influences of spectral window and spectral pre-treatments were initially studied in the construction of PLS model. The best result was obtained when the standard normal transformation (SNV) +1st derivative spectrum over 4100–7750 cm⁻¹ was used for the modelling. Then based on each principle, both of the two models were optimised respectively. The final results with high determination coefficient (R²) (higher than 0.973, 0.989 for PLS and RBF, respectively) and low root mean square errors of prediction (RMSEP) (low to 0.1109 and 0.01298 for polysaccharides and triterpenoids, respectively) confirm the good predictability of the two models. The overall results show that NIR spectroscopy combined with chemometrics can be efficiently utilised for accurate analysis of routine chemical compositions in G. lucidum and G. atrum.     

A feasibility study on quantitative analysis of glucose and fructose in lotus root powder by FT-NIR spectroscopy and chemometrics

The feasibility of rapid analysis of glucose and fructose in lotus root powder by Fourier transform near-infrared (FT-NIR) spectroscopy was studied. Diffuse reflectance spectra were collected between 4000 and 12,432 cm⁻¹. Calibration models established by partial least-squares regression (PLSR), interval PLS of forward (FiPLS) and backward (BiPLS), back propagation-artificial neural networks (BP-ANN) and least squares-support vector machine (LS-SVM) were compared. The optimal models for glucose and fructose were obtained by LS-SVM with the first 10 latent variables (LVs) as input. For fructose the correlation coefficients of calibration (r_c) and prediction (r_p), the root-mean-square errors of calibration (RMSEC) and prediction (RMSEP), and the residual predictive deviation (RPD) were 0.9827, 0.9765, 0.107%, 0.115% and 4.599, respectively. For glucose the indexes were 0.9243, 0.8286, 0.543%, 0.812% and 1.785. The results indicate that NIR spectroscopy technique with LS-SVM offers effective quantitative capability for glucose and fructose in lotus root powder.     

Rapid and Simultaneous Analysis of Xanthines and Polyphenols as Bitter Taste Markers in Bakery Products by FT-NIR Spectroscopy

The food industry has a direct interest into bitter-tasting substances either for the identification of negative off-flavors or for the monitoring of a desired organoleptic quality. A rapid technique, based on Fourier transform-near infrared (FT-NIR) spectroscopy and able to detect taste molecular markers in bakery commodities, was developed, focusing the attention on biscuits category. Xanthines (caffeine, theobromine, and theophylline) and polyphenols (catechins and epicathechins), considered as mainly responsible for the bitter-taste of coffee\cocoa\chocolate based products, were firstly checked using a confirmatory liquid chromatography (LC)-ESI\mass spectrometry (MS)-MS procedure after hot methanol–water extraction. Correspondent data were used for the calibration of the FT-NIR through PLS regression. Values of the standard errors of prediction (lower than 10 %) were comparable to the values of the standard errors of cross-validation. Coefficients of determination indicated a good predictive power in the calibration model (R ² xanthines?=?0.97, R ² polyphenols?=?0.96) and a satisfying discriminating power among different contents in the validation models (R ² xanthines?=?0.96, R ² polyphenols?=?0.96). A testing phase on the generated model was executed by a comparison of LC-MS and sensory panel data with FT-NIR responses recorded on unknown biscuits: differences between found and predicted levels were generally below 5 % and the best predictability was achievable in chocolate-based biscuits. This methodology is able to work directly on solid products, has the potential to be expanded on other categories of gustative molecular markers (like sugars) and can be conceived as applicable for a routine control of a standardized bitter taste quality in a real industrial production.     

Variable selection in visible and near-infrared spectra: Application to on-line determination of sugar content in pears

Informative variable (or wavelength) selection plays an important role in quantitative analysis by visible and near-infrared (Vis-NIR) spectroscopy. Four different variable selection methods, namely, stepwise multiple linear regression (SMLR), genetic algorithm-partial least squares regression (GA-PLS), interval PLS (iPLS), and successive projection algorithm-multiple linear regression combined with GA (GA-SPA-MLR), were studied to determine the sugar content of pears. The results derived by these techniques were then compared. The calibration model built using GA-SPA-MLR on 18 selected wavelengths (2% of the total number of variables) exhibited higher coefficient of determination (R²) = 0.880 and root mean square error of prediction (RMSEP) = 0.459°Brix for the validation set. Results show that the accuracy of the quantitative analysis conducted by Vis-NIR spectroscopy can be improved through appropriate wavelength selection. Despite the RMSEP value of GA-SPA-MLR was a slightly higher than that of GA-PLS, considering that this model was simpler and easier to interpret, GA-SPA-MLR can be used for industrial applications.     

Rapid and non-invasive analysis of deoxynivalenol in durum and common wheat by Fourier-Transform Near Infrared (FT-NIR) spectroscopy

Fourier transform near-infrared spectroscopy (FT-NIR) was used for rapid and non-invasive analysis of deoxynivalenol (DON) in durum and common wheat. The relevance of using ground wheat samples with a homogeneous particle size distribution to minimize measurement variations and avoid DON segregation among particles of different sizes was established. Calibration models for durum wheat, common wheat and durum + common wheat samples, with particle size <500 µm, were obtained by using partial least squares (PLS) regression with an external validation technique. Values of root mean square error of prediction (RMSEP, 306–379 µg kg^–1) were comparable and not too far from values of root mean square error of cross-validation (RMSECV, 470–555 µg kg^–1). Coefficients of determination (r ²) indicated an “approximate to good” level of prediction of the DON content by FT-NIR spectroscopy in the PLS calibration models (r ² = 0.71–0.83), and a “good” discrimination between low and high DON contents in the PLS validation models (r ² = 0.58–0.63). A “limited to good” practical utility of the models was ascertained by range error ratio (RER) values higher than 6. A qualitative model, based on 197 calibration samples, was developed to discriminate between blank and naturally contaminated wheat samples by setting a cut-off at 300 µg kg^–1 DON to separate the two classes. The model correctly classified 69% of the 65 validation samples with most misclassified samples (16 of 20) showing DON contamination levels quite close to the cut-off level. These findings suggest that FT-NIR analysis is suitable for the determination of DON in unprocessed wheat at levels far below the maximum permitted limits set by the European Commission.     

First Break Forward Interval PLS (FB-FiPLS) Procedure as Potential Tool in Analysis of FTIR Data for Fast and Robust Quantitative Determination of Food Adulteration

Ternary mixtures of sugar solutions containing maple syrup were studied quantitatively using Fourier transform infrared (FTIR) attenuated total reflectance (ATR) technique coupled with partial least squares regression (PLS) and selection of spectral variables. Two ternary mixtures were analyzed; first ternary mixture contained maple syrup, white sugar solution, and fully inverted sugar solution; second ternary mixture comprised maple syrup, white, and brown sugar solutions. In this paper, a procedure for selection of spectral variables with PLS, called first break forward interval PLS (FB-FiPLS), is tested on maple syrup adulteration. The method achieved almost exactly the same performance as synergy interval PLS (SiPLS) but with much shorter computational time. The upper limit of number of latent variables (LVs), which is the critical factor for both interval PLS methods, was determined using repeated double cross-validation on whole spectral region of calibration set for each analyzed component in each analyzed ternary mixture set. FB-FiPLS procedure for selection of spectral variables, using only root mean square error of cross validation (RMSECV) values for whole optimization of spectral variables, is fast and robust. After spectral variables and LVs for each particular model had been selected with minimum RMSECV of FB-FiPLS procedure, final results in terms of RMSECV and RMSEP for FB-FiPLS were in most cases statistically significantly better than PLS on whole spectral region and on selected spectral regions. Predictions of each component in analyzed ternary mixture set is promising (R ²(training set)?>?0.98, R ²(test set)?>?0.97), especially for fully inverted sugar solution (RMSEP?=?0.142 % w/w).     

Simultaneous Measurement of Titratable Acidity and Fermentation Index in Cocoa Beans by Electronic Tongue Together with Linear and Non-linear Multivariate Technique

Titratable acidity (TA) and fermentation index (FI) are important quality indicators of cocoa beans. This paper attempted the simultaneous analysis of these indicators by electronic tongue (ET) and two multivariate calibrations. ET was used for data acquisition, while partial least squares (PLSs) and principal component support vector machine regression (PC-SVMR) were used to build the calibration models. Some parameters were optimized simultaneously by leave-one-out cross-validation (LOOCV) in calibrating the model. The performance of the model was tested according to root mean square error of prediction (RMSEP) and correlation coefficient (R _pre) in the prediction set. The results revealed that PC-SVMR model was superior to PLS model in this work. The optimal PC-SVMR model for TA was R _pre?=?0.960 and RMSEP?=?0.0077, while for FI, this was R _pre?=?0.954 and RMSEP?=?0.058. This study demonstrated that ET together with SVMR could be used to analyze titratable acidity and fermentation index in cocoa beans for quality control purposes.     

Feasibility study of quantifying and discriminating soybean oil adulteration in camellia oils by attenuated total reflectance MIR and fiber optic diffuse reflectance NIR

Camellia oil is often the target for adulteration or mislabeling in China because of it is a high priced product with high nutritional and medical values. In this study, the use of attenuated total reflectance infrared spectroscopy (MIR-ATR) and fiber optic diffuse reflectance near infrared spectroscopy (FODR-NIR) as rapid and cost-efficient classification and quantification techniques for the authentication of camellia oils have been preliminarily investigated. MIR spectra in the range of 4000–650 cm⁻¹ and NIR spectra in the range of 10,000–4000 cm⁻¹ were recorded for pure camellia oils and camellia oil samples adulterated with varying concentrations of soybean oil (5–25% adulterations in the weight of camellia oil). Identifications is successfully made base on the slightly difference in raw spectra in the MIR ranges of 1132–885 cm⁻¹ and NIR ranges of 6200–5400 cm⁻¹ between the pure camellia oil and those adulterated with soybean oil with soft independent modeling of class analogy (SIMCA) pattern recognition technique. Such differences reflect the compositional difference between the two oils with oleic acid being the main ingredient in camellia oil and linoleic acid in the soybean oil. Furthermore, a partial least squares (PLS) model was established to predict the concentration of the adulterant. Models constructed using first derivative by combination of standard normal variate (SNV), variance scaling (VS), mean centering (MC) and Norris derivative (ND) smoothing pretreatments yielded the best prediction results With MIR techniques. The R value for PLS model is 0.994.The root mean standard error of the calibration set (RMSEC) is 0.645, the root mean standard error of prediction set (RMSEP) and the root mean standard error of cross validation (RMSECV) are 0.667 and 0.85, respectively. While with NIR techniques, NIR data without derivative gave the best quantification results. The R value for NIR PLS model is 0.992. The RMSEC, RMSEP and RMSECV are 0.70, 1.78 and 1.79, respectively. Overall, either of the spectral method is easy to perform and expedient, avoiding problems associated with sample handling and pretreatment than the conventional technique.     

Chemometric Models for the Quantitative Descriptive Sensory Properties of Green Tea (<Emphasis Type="Italic">Camellia sinensis</Emphasis> L.) Using Fourier Transform Near Infrared (FT-NIR) Spectroscopy

Multivariable models based on chemometric analyses of the tea infusion sensory data and FT-NIR spectra of 70 “Biluochun” green tea (Camellia sinensis L.) samples were generated aiming to predict the scores of sensory attributes of green tea. Modified BP_AdaBoost algorithm was used to develop the models. The synergy interval partial least square (siPLS) algorithm was applied to select the wavenumbers for the prediction model of sensory properties in order to take only significant spectral intervals into account. Some parameters were optimized by cross-validation in model calibrations. Experimental results showed that the optimal BP_AdaBoost model was achieved with four principal components (PCs), when 184 variables in the combination of four spectral intervals [3 17 19 21] were selected by siPLS. The predicted precision of the best model obtained were as follows: the root mean square error of cross-validation (RMSECV) was 5.0305 and the correlation coefficient (R _c) was 0.8554 in the calibration set; the root mean square error of prediction (RMSEP) was 6.0807, the correlation coefficient (R _p) was 0.7717, and the ratio performance deviation (RPD) was 1.59 in the prediction set. Finally, the BP_AdaBoost model revealed its superior performance when compared with back propagation neural network (BPNN) model. The overall results demonstrate that FT-NIR spectroscopy technique can be successfully used in the evaluation of sensory quality of green tea, and BP_AdaBoost algorithm shows its superiority in model calibration.     

Predicting of intramuscular fat content in pork using near infrared spectroscopy and multivariate analysis

The potential of near infrared (NIR) spectroscopy combined with chemometrics methods was studied to rapidly detect intramuscular fat (IMF) content in pork. Near infrared diffuse reflectance spectra were recorded both with an FT-NIR and a USB4000 spectrometer. The data analysis was compared on different sample preparation, spectral range and spectra pretreatment. According to calibration statistics, best calibration for IMF showed R²_cal of 0.94, R²_val of 0.92, RMSEC of 0.233, RMSEP of 0.462 and RPD of 2.29. The prediction of IMF content for minced samples was more accurate than that for intact samples. The spectra obtained using FT-NIR contained much information correlating to the IMF content than the Vis-NIR spectra of USB4000. The results showed that NIR spectroscopy technique can be used to determine the IMF content in pork as a rapid, convenient, and feasible analysis tool.     

Near-infrared spectroscopy coupled chemometric algorithms for prediction of antioxidant activity of black goji berries (<Emphasis Type="Italic">Lycium ruthenicum</Emphasis> Murr.)

In this study, near-infrared (NIR) spectroscopy coupled with partial least-squares (PLS) regression and various efficient variable selection algorithms, synergy interval-PLS (Si-PLS), backward interval PLS (Bi-PLS) and genetic algorithm-PLS (GA-PLS) were applied comparatively for the prediction of antioxidant activity in black wolfberry (BW). The eight assays were used for quantification of antioxidant content. The developed models were assessed using correlation coefficients (R²) of the calibration (Cal.) and prediction (Pre.); root mean square error of prediction, RMSEP; standard Error of Cross-Validation, RMSECV and residual predictive deviation, RPD. The performance of the built model greatly improved by the application of Si-PLS, Bi-PLS and GA-PLS compared with full spectrum PLS. The R² values determined for calibration and prediction set ranged from 0.8479 to 0.9696 and 0.8401 to 0.9638, respectively. These findings revealed that NIR spectroscopy combined with chemometric algorithms can be used for quantification of antioxidant activity in BW samples.     

Nondestructive determination of soluble solids content and pH in tomato juice using NIR transmittance spectroscopy

The potential of near-infrared (NIR) transmittance spectroscopy to nondestructively detect soluble solids content (SSC) and pH in tomato juices was investigated. A total of 200 tomato juice samples were used for NIR spectroscopy analysis at 800–2400 nm using an FT-NIR spectrometer. Multiplicative signal correction (MSC), and the first and second derivative were applied for pre-processing spectral data. The relationship between SSC, pH, and FT-NIR spectra of tomato juice were analyzed via partial least-squares (PLS) regression. PLS regression models were able to predict SSC and pH in tomato juices. The r _c, RMSEC, RMSEP, and RMSECV for SSC were 0.92, 0.0703°Brix, 0.150°Brix, and 0.138°Brix, respectively, whereas those values for pH were 0.90, 0.0333, 0.0316, and 0.0489, respectively. It is concluded that the combination of NIR transmittance spectroscopy and PLS methods can be used to provide a technique of convenient, versatile, and rapid analysis for SSC and pH in tomato juices.     

Prediction of titratable acidity, malic acid, and citric acid in bayberry fruit by near-infrared spectroscopy

An experiment was conducted to simultaneously measure titratable acidity, malic acid, and citric acid of bayberry fruit in a nondestructive manner using near-infrared (NIR) transmittance spectroscopy and chemometrics. The sampling set included different cultivars that were obtainable from different areas in China. Calibration models using partial least squares (PLS) regression were developed based on GB 12293-90 of China and with high-performance liquid chromatography (HPLC) as reference methods. Different preprocessing methods and different wave bands were applied. The correlation coefficient of calibration (r_c), root-mean-square error of calibration (RMSEC), and root-mean-square error of prediction (RMSEP) of the best model for titratable acidity was 0.8959, 2.24, and 2.89 g/L, respectively, with the range of 10,000-5405 cm⁻¹. R_c, RMSEC, and RMSEP values for malic acid and citric acid were 0.6689, 0.32, 0.47 and 0.8970, 1.51, 2.12 g/L, respectively. The prediction accuracies could not be improved by using first and second derivative pretreatment methods. Due to the short time consumption and low monitoring cost, NIR spectroscopic technique has its potential for the rapid and nondestructive prediction of titratable acidity and citric acid in bayberry fruit in a temperature-controlled room, although the accuracy was not high.     

Estimation of rheological properties of gelato by FT-NIR spectroscopy

The control of gelato powder mixture production usually is carried out evaluating the gelato liquid phase. The rheological measurements from the present study were conduced on gelato unfrozen liquid phase in order to indirectly evaluate its rheological properties by FT-NIR spectroscopy applied on gelato powders. The calibration set was composed by samples obtained from different recipes having increasing percentage of thickeners, maintaining the proportions of the others compounds constant. After the NIR acquisitions the powders were mixed with warm milk, blended and than settled in order to obtain the unfrozen liquid phase needed for the rheological measurements. For each of the 60 tested recipes three batches with the same thickeners concentration were prepared. The flow curves were obtained with a rotational viscosimeter and were evaluated by using the Ostwald de Waele’s equation and the goodness of fit was evaluated by the R², which was above 0.95. Predictive models of rheological parameters were set up by means of PLS regressions in order to predict the apparent viscosity (η), the consistency coefficient (K) and the flow behaviour index (n) from spectral acquisitions. A high correlation of calibration was found between NIR spectra and apparent viscosity with R² of 0.943. A good correlation was also found between the NIR spectra and the consistency coefficient (K) and flow behaviour index (n), with a determination coefficient (R²) of 0.895 and 0.874, respectively.The good prediction of the models encourages applying them to reduce significantly the time of the powder mixing control during production.