CN114239692B - Method and device for identifying fresh milk fat adulteration - Google Patents
Method and device for identifying fresh milk fat adulteration Download PDFInfo
- Publication number
- CN114239692B CN114239692B CN202111401454.6A CN202111401454A CN114239692B CN 114239692 B CN114239692 B CN 114239692B CN 202111401454 A CN202111401454 A CN 202111401454A CN 114239692 B CN114239692 B CN 114239692B
- Authority
- CN
- China
- Prior art keywords
- sample
- fresh milk
- model
- adulteration
- fat
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The invention discloses a method and a device for identifying fresh milk fat adulteration. The method comprises the following steps: constructing a classification model based on a support vector machine, and training, testing and evaluating the classification model to obtain an optimal fresh milk fat adulteration discrimination model; and collecting chromatogram data of the fresh milk sample to be detected, introducing the chromatogram data into the optimal fresh milk fat adulteration judging model, identifying the fresh milk sample to be detected, and determining whether the fresh milk to be detected is fat adulterated. The device comprises an optimizing module and a judging module. The invention can efficiently, quickly and simply identify the fat adulteration of the fresh milk, thereby achieving the purpose of monitoring the milk quality on line in early stage, and having high detection efficiency and accurate detection result.
Description
Technical Field
The invention relates to a method and a device for identifying fresh milk fat adulteration, belonging to the technical field of food detection.
Background
The raw milk contains about 3.1% -4.0% of fat, and the main components of the raw milk are triglyceride (about 98%), phospholipid, sterols and the like, and the raw milk is rich in essential fatty acid linoleic acid required by human body, is dispersed in the emulsion in the form of small granular fat balls, is easy to be absorbed by human body, is high-quality fat, has good smell, and makes cow milk present pleasant fragrance. In recent years, as the demand for milk fat has increased, the price of milk fat has increased. Some illegal manufacturers see this opportunity to adulterate with inexpensive vegetable fats to reduce production costs and increase profit margins.
Currently, methods for detecting extraneous fat in milk fat include determining its physicochemical properties, detecting the components of unsaponifiable matter, identifying water-soluble or non-water-soluble volatile fatty acids, and the like. In addition, the method also comprises thin layer chromatography, gas chromatography, high performance liquid chromatography, infrared spectrum and the like based on the chemical property. Although these methods have proven their effectiveness in detecting milk fat, most of the detection methods only ensure their effectiveness when the adulterant content is sufficiently high, and these generally require relatively complex sample pretreatment means and cause irreversible damage to the sample to be detected, so there is a need to develop a method capable of detecting fresh milk fat adulteration in a nondestructive and high-throughput manner, thereby achieving the purpose of early on-line monitoring of milk quality.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: a method for identifying fresh milk fat adulteration.
In order to solve the technical problems, the invention provides a method for identifying fresh milk fat adulteration, which comprises the following steps:
step 1): constructing a classification model based on a support vector machine, and training, testing and evaluating the classification model to obtain an optimal fresh milk fat adulteration discrimination model;
step 2): and collecting chromatogram data of the fresh milk sample to be detected, introducing the chromatogram data into the optimal fresh milk fat adulteration judging model, identifying the fresh milk sample to be detected, and determining whether the fresh milk to be detected is fat adulterated.
Preferably, the method for constructing the classification model in the step 1) is as follows: detecting different raw milk samples by adopting a rapid gas-phase electronic nose to obtain chromatograms of the different raw milk samples, constructing data sets of the different raw milk samples by taking peak areas of different retention times as independent variables and types of the different raw milk samples as dependent variables, preprocessing the data sets, and dividing the preprocessed data sets into a training set and a testing set according to a preset proportion.
More preferably, the classification model is a support vector machine SVM classification model constructed using Python language, and the input vector is mapped to the high-dimensional feature space by a nonlinear mapping function, where the nonlinear mapping function is: k (x) i ,x)＝exp(-γ{|x-x i |}) 2 Wherein, gamma is a kernel function parameter, x i For the ith sample vector, x is the support vector.
Further, searching an optimal regression hyperplane in the high-dimensional feature space so as to minimize a target loss function, wherein the expression of the optimal regression hyperplane is as follows:
determination by solving the following quadratic convex programming problemAnd b:
the constraint conditions are as follows:
in the above formula:is a weight coefficient matrix; b is a threshold; />Is a mapping function; x is a support vector; zeta type toy i 、/>Is a relaxation variable; c is penalty factor, C>0; epsilon is the tolerance; x is x i Is the i-th sample vector; y is i Is x i Output value of (2); />Is the loss value of the i-th sample vector.
Preferably, the method for evaluating in the step 1) is to evaluate the obtained optimal fresh milk fat adulteration discrimination model by using discrimination Accuracy Accurcy and F1 fraction as indexes, wherein:
wherein: TP is a positive sample that is model predicted as a positive class, TN is a negative sample that is model predicted as a negative class, FP is a negative sample that is model predicted as a positive class, and FN is a positive sample that is model predicted as a negative class.
The invention also provides a device for identifying fresh milk fat adulteration, comprising:
and an optimization module: constructing a classification model based on a support vector machine, and training, testing and evaluating the classification model to obtain an optimal fresh milk fat adulteration discrimination model;
and a judging module: and collecting chromatogram data of the fresh milk sample to be detected, introducing the chromatogram data into the optimal fresh milk fat adulteration judging model, identifying the fresh milk sample to be detected, and determining whether the fresh milk to be detected is fat adulterated.
Each module is operated by a singlechip.
Preferably, the optimization module detects different raw milk samples by adopting a rapid gas-phase electronic nose to obtain chromatograms of the different raw milk samples, constructs data sets of the different raw milk samples by taking peak areas of different retention times as independent variables and types of the different raw milk samples as dependent variables, preprocesses the data sets, and divides the preprocessed data sets into a training set and a testing set according to a preset proportion.
More preferably, the optimization module uses a support vector machine SVM classification model constructed in Python language to map the input vector to the high-dimensional feature space through a nonlinear mapping function, wherein the nonlinear mapping function is: k (x) i ,x)＝exp(-γ{|x-x i |}) 2 Wherein, gamma is a kernel function parameter, x i For the ith sample vector, x is the support vector.
Further, the optimization module searches for an optimal regression hyperplane in the high-dimensional feature space so as to minimize a target loss function, and the expression of the optimal regression hyperplane is:
determination by solving the following quadratic convex programming problemAnd b:
the constraint conditions are as follows:
in the above formula:is a weight coefficient matrix; b is a threshold; />Is a mapping function; x is a support vector; zeta type toy i 、/>Are relaxation variables; c is penalty factor, C>0; epsilon is the tolerance; x is x i Is the i-th sample vector; y is i Is x i Output value of (2); />Is the loss value of the i-th sample vector.
Preferably, the method further comprises an evaluation module, wherein the evaluation module is used for evaluating the obtained optimal fresh milk fat adulteration judgment model by taking the judgment Accuracy Accurcy and the F1 score as indexes, and the judgment Accuracy Accurcy and the F1 score are used as indexes, wherein:
wherein: TP is a positive sample that is model predicted as a positive class, TN is a negative sample that is model predicted as a negative class, FP is a negative sample that is model predicted as a positive class, and FN is a positive sample that is model predicted as a negative class.
According to the invention, the optimal fresh milk fat adulteration judging model is obtained by creating and training a classification model based on a support vector machine; and collecting chromatogram data of the fresh milk sample to be detected, introducing the chromatogram data into the optimal fresh milk fat adulteration discrimination model, discriminating the fresh milk sample to be detected, and determining whether the fresh milk to be detected is fat adulterated or not, so that the fresh milk fat adulteration can be discriminated efficiently, quickly and simply, the purpose of monitoring the milk quality on line in early stage is achieved, the detection efficiency is high, and the detection result is accurate.
Drawings
FIG. 1 is a flow chart of a method for identifying fat adulteration of raw milk according to the invention;
FIG. 2 is a block diagram of the apparatus for discriminating raw fresh milk fat adulteration according to the present invention.
Detailed Description
In order to make the invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Example 1
As shown in figure 1, the method for identifying fresh milk fat adulteration provided by the invention comprises the following steps:
s1: and constructing a classification model based on a support vector machine, and training, testing and evaluating the classification model to obtain an optimal fresh milk fat adulteration discrimination model.
In the step, firstly, a fresh raw milk sample is obtained and raw milk samples doped with different vegetable oils are prepared; and then constructing data sets of different fresh milk samples, preprocessing the data sets, and dividing the preprocessed data sets into a training set and a testing set according to a preset proportion. In one embodiment, the predetermined ratio is 7:3.
the pretreatment method adopts min-max standardization (normalization) and a specific formula:
wherein: x is x i For the ith sample feature value, x max 、x min ，Respectively, the maximum value, the minimum value and the average value of the sample characteristic, and x' is the sample characteristic value after pretreatment.
Preferably, a support vector machine SVM classification model is constructed using the Python language, and the input vector is mapped to the high-dimensional feature space by a nonlinear mapping function, wherein the nonlinear mapping function is:
k(x i ,x)＝exp(-γ{|x-x i |}) 2
wherein, gamma is a kernel function parameter, x i Is the firsti sample vectors, x is the support vector.
The SVM converts input sample data into a high-dimensional feature space by nonlinear variation defined by a kernel function, and finds a linear relationship between an input variable and an output variable in this high-dimensional space, and the present embodiment selects a Radial Basis Function (RBF) commonly used to deal with nonlinear problems as a mapping function.
Preferably, an optimal regression hyperplane is found in the high-dimensional feature space, so that the target loss function is minimum, and the expression of the optimal regression hyperplane is:
determination by solving the following quadratic convex programming problemAnd b:
the constraint conditions are as follows:
in the above formula:is a weight coefficient matrix; b is a threshold; />Is a mapping function; x is a support vector; zeta type toy i 、/>Are relaxation variables; c is penalty factor, C>0; epsilon is the tolerance; x is x i Is the i-th sample vector; y is i Is x i Is the input of (2)Outputting a value; />Is the loss value of the i-th sample vector.
In the process of searching the optimal hyperplane, smoothing of the functional relationship is ensured by minimizing the square sum of weight coefficients, and errors smaller than epsilon are allowed.
Preferably, among the determined key parameters, the penalty factor C is 1.3 and the allowable error ε is 0.001.
Preferably, the optimal fresh milk fat adulteration discriminating model is evaluated by taking the discrimination Accuracy Accurcy and the F1 fraction as indexes, wherein:
wherein: TP is a positive sample that is model predicted as a positive class, TN is a negative sample that is model predicted as a negative class, FP is a negative sample that is model predicted as a positive class, and FN is a positive sample that is model predicted as a negative class.
In the model training process, a 10-fold cross validation method is adopted to evaluate the discrimination effect of the specific combination of parameters, and the optimal parameter combination is selected according to the discrimination effect.
S2: and collecting chromatogram data of the fresh milk sample to be detected, introducing the chromatogram data into the optimal fresh milk fat adulteration judging model, identifying the fresh milk sample to be detected, and determining whether the fresh milk to be detected is fat adulterated.
Specifically, a rapid gas-phase electronic nose is adopted to detect different raw milk samples, chromatograms of the different raw milk samples are obtained, peak areas of different retention times are used as independent variables, types of the different raw milk samples are used as dependent variables to construct data sets of the different raw milk samples, the data sets are preprocessed, and the preprocessed data sets are divided into training sets and test sets according to a preset proportion.
The model of the rapid gas-phase electronic nose is Herales II of Alpha MOS company in France, and the model of the chromatographic column adopted by the rapid gas-phase electronic nose is MXT-5 and MXT-1701 respectively; accordingly, the following method is adopted in constructing the data set: the spectra obtained from chromatographic columns with the model numbers of MXT-5 and MXT-1701 are combined and arranged according to the retention time, substances with different peak areas of response values and similar retention time are regarded as the same substance, peak areas with different retention time are taken as independent variables, and the types of different fresh milk samples are taken as dependent variables to establish a data set.
The conditions for detecting the rapid gas phase electronic nose are as follows:
sample amount: 5g; sample incubation temperature: 50 ℃; sample incubation time: 20min; sample injection volume: 5000. Mu.L; sample injection speed: 125. Mu.L/s; sample injection mode: injecting a headspace; tenax trap collection temperature: 40 ℃; tenax trap collection time: 50s; carrier gas: hydrogen gas; splitting: 10mL/min; sampler temperature: 200 ℃; heating program: keeping the temperature at 80 ℃ for 0s, heating to 250 ℃ at 3 ℃/s, and keeping the temperature at 250 ℃ for 21s; detector temperature: 260 ℃; FID gain: FID1/FID2.
One specific experimental procedure for this example is given below.
Simulation of adulterated raw fresh milk samples:
taking a proper amount of skimmed milk sample in a beaker, adding different vegetable oil samples (3.1% w/w) singly, fully stirring and homogenizing, thereby obtaining uniform milk samples doped with different vegetable oils.
Detection of a rapid gas phase electronic nose:
accurately weighing 5g of sample to be detected in a 20mL sample bottle, sequentially placing the sample in a sample rack of an instrument, sequentially and accurately detecting the sample by a mechanical arm of the sample, setting a sampling sequence by software, and detecting volatile compounds of the sample to be detected by using a rapid gas phase type electronic nose, wherein the detection conditions are as follows: the sample bottle was closed with a leak-proof cap and covered with a silicon/polytetrafluoroethylene septum. Samples were incubated at 50℃for 20min, then an autosampler injected 5000. Mu.L of sample from the headspace to the GC at a rate of 125. Mu.L/s, and analytes were collected in a Tenax trap at 40℃for 50s. After rapid heating, the analytes were separated and transferred to two parallel short GC chromatographic columns: nonpolar chromatography columns (MXT-5:5% biphenyl, 95% methylpolysiloxane, 10m×0.180mm×0.4 μm) and weakly polar chromatography columns (MXT-1701:14% cyanopropyl-phenyl, 86% methylpolysiloxane, 10m×0.180mm×0.4 μm). Hydrogen is used as a carrier gas. The system was operated at a constant pressure of 80kPa with a column head split flow rate of 10mL/min. The temperature conditions are as follows: the temperature of the sampler is 200 ℃; the temperature-raising program comprises the steps of keeping the temperature at 80 ℃ for 0s, raising the temperature to 250 ℃ at 3 ℃/s, and keeping the temperature at 250 ℃ for 21s; flame ionization detection at 260 ℃ (FID 1/FID 2). Each sample was tested in six replicates to obtain better parallel effect and model performance.
Data preprocessing and establishment of a data set:
the spectra obtained from two rapid chromatographic columns are combined and arranged according to retention time, substances with different response values and similar retention time are regarded as the same substance, the peak areas of different retention time are taken as independent variables, the types of different raw milk samples are taken as dependent variables, a data set is established, the data set is preprocessed, and then the data set is randomly divided into a training set and a test set according to the ratio of 7:3.
Establishing a discrimination model:
a Support Vector Machine (SVM) classification model is built on a Pycharm (version: 2021.2.1) platform by using a Python language, the SVM maps an input vector to a high-dimensional feature space through nonlinear mapping based on a structural risk minimization principle, and an optimal regression hyperplane is found in the space, so that a target loss function is minimized.
SVM modeling results:
the determined key parameters are as follows: the penalty factor C is 1.3, the tolerance epsilon is 0.001 and the kernel parameter gamma is RBF. The discrimination accuracy of the optimized SVM discrimination model to the test set is 95.65%, the F1 fraction is 0.9778, and the result shows that the discrimination performance of the model is excellent.
Application of fresh milk fat adulteration discrimination model:
30 fresh milk samples containing different vegetable oils are randomly prepared, the fresh milk samples are detected by an electronic nose to obtain a blind sample data set, the blind sample data set is imported into the SVM judgment constructed in the earlier stage to judge the types of the fresh milk samples, and the result shows that the judgment accuracy of the SVM judgment model on the blind sample data set is 93.47% and the F1 fraction is 0.9523.
The embodiment utilizes a fast gas-phase electronic nose (FGC E-nose) and chemometrics to realize fast identification of fresh milk fat adulteration, does not need complex sample pretreatment steps, has simple and fast measurement process and has good practical application value; the embodiment can perform nondestructive and high-throughput identification on whether vegetable oil and the type thereof are mixed in the raw and fresh milk, can be used for rapidly detecting fat adulteration in the raw and fresh milk, and provides reference for quality control of the raw and fresh milk in the dairy industry.
Example 2
As shown in fig. 2, the present invention provides a device for identifying fresh milk fat adulteration, comprising:
the optimizing module is used for constructing a classification model based on a support vector machine, training, testing and evaluating the classification model to obtain an optimal fresh milk fat adulteration judging model;
the judging module is used for collecting the chromatogram data of the fresh milk sample to be detected, leading the chromatogram data into the optimal fresh milk fat adulteration judging model, identifying the fresh milk sample to be detected, and determining whether the fresh milk to be detected is fat adulterated or not.
Each module is operated by a singlechip.
Preferably, the optimization module is configured to:
detecting different raw milk samples by adopting a rapid gas-phase electronic nose to obtain chromatograms of the different raw milk samples, constructing data sets of the different raw milk samples by taking peak areas of different retention times as independent variables and the types of the different raw milk samples as dependent variables, preprocessing the data sets, and dividing the preprocessed data sets into a training set and a testing set according to a preset proportion.
Preferably, the optimization module is configured to:
constructing a Support Vector Machine (SVM) classification model by using a Python language, and mapping an input vector to a high-dimensional feature space through a nonlinear mapping function, wherein the nonlinear mapping function is as follows:
k(x i ,x)＝exp(-γ{|x-x i |}) 2
wherein, gamma is a kernel function parameter, x i For the ith sample vector, x is the support vector.
Preferably, the optimization module is configured to:
searching an optimal regression hyperplane in the high-dimensional feature space so as to minimize a target loss function, wherein the expression of the optimal regression hyperplane is as follows:
determination by solving the following quadratic convex programming problemAnd b:
the constraint conditions are as follows:
in the above formula:is a weight coefficient matrix; b is a threshold; />Is a mapping function; x is a support vector; zeta type toy i 、/>Are relaxation variables; c is penalty factor, C>0; epsilon is the tolerance; x is x i Is the i-th sample vector; y is i Is x i Output value of (2); />Is the loss value of the i-th sample vector.
Preferably, the apparatus further comprises an evaluation module for:
and evaluating the optimal fresh milk fat adulteration judging model by taking the judging Accuracy Accurcy and the F1 fraction as indexes, wherein:
wherein: TP is a positive sample that is model predicted as a positive class, TN is a negative sample that is model predicted as a negative class, FP is a negative sample that is model predicted as a positive class, and FN is a positive sample that is model predicted as a negative class.
The implementation process of the functions implemented by each module in this embodiment 2 is the same as the implementation process of each step in embodiment 1, and will not be described here again.
Claims (2)
1. A method of identifying a fresh milk fat adulteration comprising the steps of:
step 1): constructing a classification model based on a support vector machine, and training, testing and evaluating the classification model to obtain an optimal fresh milk fat adulteration discrimination model;
the construction method of the classification model comprises the following steps: detecting different raw milk samples by adopting a rapid gas-phase electronic nose to obtain chromatograms of the different raw milk samples, constructing data sets of the different raw milk samples by taking peak areas of different retention times as independent variables and types of the different raw milk samples as dependent variables, preprocessing the data sets, and dividing the preprocessed data sets into a training set and a testing set according to a preset proportion; the classification model is a support direction constructed by using Python languageThe vector machine SVM classification model maps an input vector to a high-dimensional feature space through a nonlinear mapping function, wherein the nonlinear mapping function is as follows: k (x) i ,x)＝exp(-γ{|x-x i |}) 2 Wherein, gamma is a kernel function parameter, x i The i sample vector is the ith sample vector, and x is a support vector; searching an optimal regression hyperplane in the high-dimensional feature space so as to minimize a target loss function, wherein the expression of the optimal regression hyperplane is as follows:
determination by solving the following quadratic convex programming problemAnd b:
the constraint conditions are as follows:
in the above formula:is a weight coefficient matrix; b is a threshold; />Is a mapping function; x is a support vector; zeta type toy i 、/>Are relaxation variables; c is penalty factor, C>0; epsilon is the tolerance; x is x i Is the i-th sample vector; y is i Is x i Output value of (2)；/>A loss value for the i-th sample vector;
the evaluation method is to evaluate the obtained optimal fresh milk fat adulteration judgment model, and adopts judgment Accuracy Accurcy and F1 fraction as indexes, wherein:
wherein: TP is a positive sample predicted by the model as a positive class, TN is a negative sample predicted by the model as a negative class, FP is a negative sample predicted by the model as a positive class, FN is a positive sample predicted by the model as a negative class;
step 2): and collecting chromatogram data of the fresh milk sample to be detected, introducing the chromatogram data into the optimal fresh milk fat adulteration judging model, identifying the fresh milk sample to be detected, and determining whether the fresh milk to be detected is fat adulterated.
2. An apparatus for identifying the adulteration of fresh milk fat comprising:
and an optimization module: constructing a classification model based on a support vector machine, and training, testing and evaluating the classification model to obtain an optimal fresh milk fat adulteration discrimination model; the optimizing module adopts a rapid gas-phase electronic nose to detect different raw milk samples to obtain chromatograms of the different raw milk samples, takes peak areas of different retention times as independent variables and types of the different raw milk samples as dependent variables to construct data sets of the different raw milk samples, preprocesses the data sets, and divides the preprocessed data sets into training sets and test sets according to a preset proportion; support Vector Machine (SVM) constructed by using Python language by using optimization moduleAnd the classification model maps the input vector to a high-dimensional feature space through a nonlinear mapping function, wherein the nonlinear mapping function is as follows: k (x) i ,x)＝exp(-γ{|x-x i |}) 2 Wherein, gamma is a kernel function parameter, x i The i sample vector is the ith sample vector, and x is a support vector; the optimization module searches an optimal regression hyperplane in the high-dimensional feature space so as to minimize a target loss function, and the expression of the optimal regression hyperplane is as follows:
determination by solving the following quadratic convex programming problemAnd b:
the constraint conditions are as follows:
in the above formula:is a weight coefficient matrix; b is a threshold; />Is a mapping function; x is a support vector; />Are relaxation variables; c is penalty factor, C>0; epsilon is the tolerance; x is x i Is the i-th sample vector; y is i Is x i Output value of (2); />A loss value for the i-th sample vector;
and a judging module: collecting chromatogram data of a fresh milk sample to be detected, introducing the chromatogram data into the optimal fresh milk fat adulteration discrimination model, discriminating the fresh milk sample to be detected, and determining whether the fresh milk to be detected is fat adulterated;
and an evaluation module: the method is used for evaluating the obtained optimal fresh milk fat adulteration judgment model by taking the judgment Accuracy Accury and the F1 fraction as indexes, wherein the judgment Accuracy Accury and the F1 fraction are used as indexes, and the method comprises the following steps:
wherein: TP is a positive sample that is model predicted as a positive class, TN is a negative sample that is model predicted as a negative class, FP is a negative sample that is model predicted as a positive class, and FN is a positive sample that is model predicted as a negative class.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111401454.6A CN114239692B (en) | 2021-11-24 | Method and device for identifying fresh milk fat adulteration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111401454.6A CN114239692B (en) | 2021-11-24 | Method and device for identifying fresh milk fat adulteration |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114239692A CN114239692A (en) | 2022-03-25 |
| CN114239692B true CN114239692B (en) | 2023-09-22 |
Family
ID=
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102590128A (en) * | 2012-01-10 | 2012-07-18 | 上海市兽药饲料检测所 | Method for discriminating adulterated raw and fresh milk by using near infrared spectrum |
| CN105588925A (en) * | 2015-12-16 | 2016-05-18 | 新希望双喜乳业（苏州）有限公司 | Method for quickly identifying and detecting milk adulteration |
| CN107543838A (en) * | 2017-09-20 | 2018-01-05 | 北京市食品安全监控和风险评估中心（北京市食品检验所） | A kind of adulterated magnetic resonance detection method for planting butter cream in dilute cream |
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102590128A (en) * | 2012-01-10 | 2012-07-18 | 上海市兽药饲料检测所 | Method for discriminating adulterated raw and fresh milk by using near infrared spectrum |
| CN105588925A (en) * | 2015-12-16 | 2016-05-18 | 新希望双喜乳业（苏州）有限公司 | Method for quickly identifying and detecting milk adulteration |
| CN107543838A (en) * | 2017-09-20 | 2018-01-05 | 北京市食品安全监控和风险评估中心（北京市食品检验所） | A kind of adulterated magnetic resonance detection method for planting butter cream in dilute cream |
Non-Patent Citations (2)
| Title |
|---|
| 张鑫;顾欣;倪力军;张立国;韩奕奕.基于近红外光谱技术的掺假生鲜乳识别平台的研发.中国奶牛.2012,(第13期),全文. * |
| 褚璇;王伟;赵昕;姜洪喆;王伟;刘声泉.近红外光谱和特征光谱的山茶油掺假鉴别方法研究.光谱学与光谱分析.2017,(第01期),全文. * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Majchrzak et al. | Electronic noses in classification and quality control of edible oils: A review | |
| Zhu et al. | Rapid detection of peanut oil adulteration using low-field nuclear magnetic resonance and chemometrics | |
| CN103472094A (en) | Olfactory analog instrument and on-site analysis method for odor grade of specific substance | |
| CN105954412B (en) | For the sensor array optimization method of hickory nut freshness detection | |
| CN113406249B (en) | Method for predicting adulterated oil types in tea oil | |
| Tian et al. | Rapid identification and quantification of vegetable oil adulteration in raw milk using a flash gas chromatography electronic nose combined with machine learning | |
| Jurado et al. | Differentiation of certified brands of origins of Spanish white wines by HS-SPME-GC and chemometrics | |
| Jiang et al. | Qualitative identification of the edible oil storage period using a homemade portable electronic nose combined with multivariate analysis | |
| CN111189868A (en) | Method for rapidly screening adulterated illegal cooking oil in edible oil by using low-field nuclear magnetic resonance | |
| Ellefson | Fat analysis | |
| CN114239692B (en) | Method and device for identifying fresh milk fat adulteration | |
| Costa et al. | Evaluating an e-nose ability to detect biogas plant efficiency: A case study | |
| CN110887944A (en) | Tea-seed oil quality short-term test device | |
| CN118169272A (en) | Method for measuring volatile components of Kazakhstan grease and application thereof | |
| CN110398472A (en) | A kind of vegetable oil identification classification method based on two-dimensional correlation spectra quantization | |
| Yin et al. | A selection method for feature vectors of electronic nose signal based on wilks Λ–statistic | |
| Zhang et al. | Combination of excitation-emission matrix fluorescence spectroscopy and chemometric methods for the rapid identification of cheaper vegetable oil adulterated in walnut oil | |
| CN109884282B (en) | Novel illegal cooking oil detection method and detection system based on GRNN neural network | |
| CN107764793A (en) | Detection method of the electronic nose to aspergillus oryzae fermentation situation in bean paste yeast making process | |
| Vinaixa et al. | A fuzzy ARTMAP-and PLS-based MS e-nose for the qualitative and quantitative assessment of rancidity in crisps | |
| CN110426366A (en) | Meat adulteration ratio detection method based on visualization olfactory sensor and near-infrared | |
| CN114239692A (en) | Method and device for identifying adulteration of fresh milk fat | |
| Hosseini et al. | A dedicated electronic nose combined with chemometric methods for detection of adulteration in sesame oil | |
| Lazaro et al. | Chemometric data analysis for black tea fermentation using principal component analysis | |
| CN114184725A (en) | Method and device for detecting palm oil content in raw fresh milk |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |