CN112798555A - Modeling method for improving adaptability of coarse protein correction model of wheat flour - Google Patents
Modeling method for improving adaptability of coarse protein correction model of wheat flour Download PDFInfo
- Publication number
- CN112798555A CN112798555A CN202011561285.8A CN202011561285A CN112798555A CN 112798555 A CN112798555 A CN 112798555A CN 202011561285 A CN202011561285 A CN 202011561285A CN 112798555 A CN112798555 A CN 112798555A
- Authority
- CN
- China
- Prior art keywords
- wheat flour
- crude protein
- samples
- correction
- correction model
- 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.)
- Pending
Links
- 235000013312 flour Nutrition 0.000 title claims abstract description 129
- 238000012937 correction Methods 0.000 title claims abstract description 84
- 241000209140 Triticum Species 0.000 title claims abstract description 68
- 235000021307 Triticum Nutrition 0.000 title claims abstract description 68
- 238000000034 method Methods 0.000 title claims abstract description 30
- 102000004169 proteins and genes Human genes 0.000 title description 3
- 108090000623 proteins and genes Proteins 0.000 title description 3
- 235000019750 Crude protein Nutrition 0.000 claims abstract description 80
- 238000002329 infrared spectrum Methods 0.000 claims abstract description 18
- 238000005259 measurement Methods 0.000 claims abstract description 8
- 238000013480 data collection Methods 0.000 claims abstract description 3
- 238000012549 training Methods 0.000 claims description 18
- 235000011844 whole wheat flour Nutrition 0.000 claims description 18
- 230000002269 spontaneous effect Effects 0.000 claims description 17
- 238000010606 normalization Methods 0.000 claims description 8
- 238000002790 cross-validation Methods 0.000 claims description 4
- 238000010561 standard procedure Methods 0.000 claims description 3
- 238000004497 NIR spectroscopy Methods 0.000 claims 2
- 238000001514 detection method Methods 0.000 abstract description 5
- 238000004458 analytical method Methods 0.000 abstract description 2
- 238000011156 evaluation Methods 0.000 description 8
- 230000003595 spectral effect Effects 0.000 description 6
- 238000001228 spectrum Methods 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 235000013339 cereals Nutrition 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 240000004808 Saccharomyces cerevisiae Species 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 235000018102 proteins Nutrition 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 241000698776 Duma Species 0.000 description 1
- 239000004793 Polystyrene Substances 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009841 combustion method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 238000010238 partial least squares regression Methods 0.000 description 1
- 229920002223 polystyrene Polymers 0.000 description 1
- 239000004810 polytetrafluoroethylene Substances 0.000 description 1
- 229920001343 polytetrafluoroethylene Polymers 0.000 description 1
- 235000004252 protein component Nutrition 0.000 description 1
- 230000036186 satiety Effects 0.000 description 1
- 235000019627 satiety Nutrition 0.000 description 1
- 238000007873 sieving Methods 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
- 235000015099 wheat brans Nutrition 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/3581—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using far infrared light; using Terahertz radiation
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B40/00—ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B5/00—ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic networks
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biotechnology (AREA)
- Evolutionary Biology (AREA)
- Chemical & Material Sciences (AREA)
- Artificial Intelligence (AREA)
- Toxicology (AREA)
- Molecular Biology (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Physiology (AREA)
- Bioethics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Epidemiology (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- Software Systems (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides a modeling method for improving the adaptability of a crude protein correction model of wheat flour, belonging to the technical field of quality detection and analysis. Firstly, collecting 3 types of wheat flour samples, and carrying out near infrared spectrum data collection and crude protein physicochemical value measurement on the 3 types of wheat flour samples; then dividing 3 types of wheat flour samples into a correction set and a prediction set respectively; and establishing a three-component mixed crude protein correction model of the 3 types of wheat flour samples according to the mathematical relationship between the near infrared spectrum data of the wheat flour samples in the correction set and the crude protein content value, and finally predicting the crude protein content of the wheat flour samples in the prediction set by using the three-component mixed crude protein correction model. The invention enlarges the application range of the correction model and effectively improves the stability of the correction model.
Description
Technical Field
The invention relates to the technical field of quality detection and analysis, in particular to a modeling method for improving the adaptability of a crude protein correction model of wheat flour.
Background
The wheat flour product is used as a staple food for solving the problem of satiety in diet by people due to high protein and high nutritional value. In recent years, Chinese economy is rapidly developed, the living standard of consumers is continuously improved, and more special flours such as whole wheat flour, spontaneous flour, special flour and the like are provided. In order to meet the requirements of the Chinese market, the research on the rapid quality detection method of the special flour is very necessary.
At present, most researches adopt a near-red spectrum technology to establish a correction model of a single wheat flour quality index, and a chemometrics method is combined to optimize the correction model, so that although the prediction precision and the prediction speed of the correction model are improved, a modeling sample has uniqueness, the adaptability, the application range and the actual application effect of the established model are not ideal, and the quality of various commercial flours or other special flours cannot be accurately predicted.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a modeling method for improving the adaptability of a crude protein correction model of wheat flour, so that the crude protein content of commercial special flour can be accurately predicted.
The present invention achieves the above-described object by the following technical means.
A modeling method for improving the adaptability of a crude protein correction model of wheat flour comprises the following steps:
s1, collecting 3 types of wheat flour samples, and carrying out near infrared spectrum data collection and crude protein physicochemical value measurement on the 3 types of wheat flour samples;
s2, dividing the 3 types of wheat flour samples into a correction set and a prediction set respectively;
s3, establishing a three-component mixed crude protein correction model of the 3 types of wheat flour samples according to the mathematical relationship between the near infrared spectrum data of the wheat flour samples in the correction set and the crude protein content value, and predicting the crude protein content of the wheat flour samples in the prediction set by using the three-component mixed crude protein correction model.
According to a further technical scheme, before a three-component mixed crude protein correction model is established, vector normalization is utilized to process near infrared spectrum data.
According to a further technical scheme, the 3 types of wheat flour samples comprise general flour, spontaneous flour and whole wheat flour.
In a further technical scheme, the three-component mixed crude protein correction model predicts the crude protein content of the wheat flour sample in the prediction set, and the evaluation is carried out through a correction set correlation coefficient Rc, a correction set cross validation root mean square error RMSECV, a prediction set correlation coefficient Rp and a prediction set cross validation root mean square error RMSEP.
According to the further technical scheme, the parameters of a spectrometer for collecting near infrared spectrum data are set as follows: the scanning wavelength range is 900-2500nm, the wavelength points are 1601 and the resolution is 8cm-1The number of scans was 16.
In a further technical scheme, the measurement of the physicochemical value of the crude protein adopts a national standard method.
According to a further technical scheme, the correction set and the prediction set are divided by adopting a K-S algorithm, namely all wheat flour samples are taken as training set candidate samples, and samples are selected from the training set candidate samples in sequence and are classified into the training set.
According to a further technical scheme, the selecting samples from the samples in sequence and inputting the samples into the training set specifically comprises the following steps: firstly selecting two wheat flour samples with the farthest Euclidean distance to be divided into a training set, then calculating the Euclidean distance from each remaining wheat flour sample to each known wheat flour sample in the training set, finding two samples with the farthest distance and the nearest distance from the known wheat flour sample, dividing the two samples into the training set, and repeating the process until the number of the samples meets the requirement.
Compared with the prior art, the invention has the following advantages and beneficial effects:
according to the method, the three-component mixed crude protein correction model of the 3-class wheat flour sample is established through the mathematical relationship between the near infrared spectrum data of the wheat flour sample and the crude protein content value in the correction set, the crude protein content of the wheat flour sample in the prediction set is predicted by utilizing the three-component mixed crude protein correction model, the application range of the correction model is expanded, and the anti-interference capability of the correction model is effectively improved; according to the method, before the three-component mixed crude protein correction model is established, the near infrared spectrum data is processed by using vector normalization, so that the prediction precision of the correction model is further improved. The method can quickly detect the crude protein content of various commercial special flours, solves the market demand of the special flour quality research at the present stage, and has good practical application value.
Drawings
FIG. 1 is a flow chart of a modeling method for improving the adaptability of a wheat flour crude protein correction model according to the present invention;
FIG. 2 is a near infrared spectrum of a class 3 wheat flour sample;
FIG. 3(a) is a linear fit of a calibration set of a three-component mixed crude protein calibration model constructed after vector normalization preprocessing of spectral data according to the present invention;
FIG. 3(b) is a linear fit of the prediction set of the three-component mixed crude protein calibration model established after vector normalization of the preprocessed spectral data according to the present invention.
Detailed Description
The invention will be further described with reference to the following figures and specific examples, but the scope of the invention is not limited thereto.
As shown in fig. 1, a modeling method for improving the adaptability of a wheat flour crude protein correction model specifically includes the following steps:
step (1), collection of wheat flour sample
A total of 215 wheat flour samples were collected and classified into 3 types: the two types of flour are respectively 142 parts of general flour sold in the market and 16 parts of spontaneous flour sold in the market in supermarkets in various regions at home, and the other type of flour is 57 parts of wholewheat flour prepared by crushing wheat grains provided by a certain flour factory in Jiangsu by a multifunctional crusher and sieving the crushed grains by a 100-mesh sieve.
Step (2), acquisition of near infrared spectrum
The adopted instrument is as follows: the Shanghai prism light S450 near-infrared spectrometer is provided with an integrating sphere diffuse reflection system, a PTFE reference module and a polystyrene wavelength standard sheet, and can automatically complete reference correction and wavelength monitoring;
spectral measurement conditions: the scanning wavelength range of the instrument is 900-2500nm, 1601 wavelength points are provided in total, and the resolution ratio is 8cm-1The scanning times are 16 times;
the spectral measurement method comprises the following steps: weighing 215 parts of wheat flour samples by 300g respectively, and filling the samples into sample cups matched with an instrument, wherein the filling height of the samples is 3.0 cm; when the spectrum is collected, repeatedly collecting 3 times of spectra for each sample, and averaging the original spectra to obtain 215 original spectra, so as to obtain a 3-class wheat flour original spectrogram shown in figure 2; the same measurement conditions were used for scanning and background subtraction before each sample measurement.
Step (3), measuring the physical and chemical values of the crude protein of wheat flour
The measurement of the physical and chemical values of the wheat flour crude protein is detected according to the method and experimental conditions specified by national standard method GB/T31578-2015 Dumas combustion method for measuring crude protein in grains and products for grain and oil inspection; performing parallel detection on each wheat flour sample for 3 times, ensuring that the maximum relative range in a group detected for 3 times is not more than 4 percent, and taking the average value of the detection results of 3 times; specific crude protein content ranges for the class 3 wheat flour samples are shown in table 1.
Table 13 type of wheat flour physico-chemically measured crude protein content value
Step (4), dividing sample set of wheat flour sample
The wheat flour samples are divided into a correction set and a prediction set based on a Kennard-Stone (K-S) algorithm, namely all the wheat flour samples are regarded as training set candidate samples, and the samples are sequentially selected from the training set and classified into the training set. Firstly selecting two wheat flour samples with the farthest Euclidean distance to be divided into a training set, then calculating the Euclidean distance from each remaining wheat flour sample to each known wheat flour sample in the training set, finding two samples with the farthest distance and the nearest distance from the known wheat flour sample, dividing the two samples into the training set, and then repeating the process until the number of the samples meets the requirement. Finally determining 100 parts of a universal flour correction set, 42 parts of a prediction set, 11 parts of a spontaneous flour correction set, 5 parts of a prediction set, 40 parts of a wholewheat flour correction set and 17 parts of a prediction set.
Step (5), establishing a crude protein correction model by using the general flour to predict spontaneous flour and whole wheat flour
The method comprises the steps of establishing a single general flour crude protein correction model by taking 100 parts of general flour correction sets (namely, establishing a mathematical relation between near infrared spectrum data of wheat flour samples in the correction sets and crude protein content values by using a partial least squares regression method), predicting the crude protein content of 42 parts of general flour prediction set samples, and evaluating the prediction result of the correction model by using a correction set correlation coefficient Rc, a correction set interactive verification root mean square error RMSECV, a prediction set correlation coefficient Rp and a prediction set interactive verification root mean square error RMSEP, wherein the evaluation result is shown in a table 2.
TABLE 2 evaluation of the predicted results of the generic flour crude protein calibration model
As can be seen from table 2, the predicted results of the universal flour crude protein calibration model include: the Rp is 0.9606, the RMSEP is 0.4425, which shows that the prediction result of the crude protein correction model is ideal, and crude protein content prediction can be carried out on the self-raising flour and the whole wheat flour.
Taking 16 parts of spontaneous flour and 57 parts of wholemeal flour as external verification samples of the general flour crude protein correction model, and inspecting the adaptability of the general flour crude protein correction model to unknown samples. The results of spontaneous and whole wheat flours were predicted using a universal flour crude protein calibration model are shown in table 3.
TABLE 3 general flour crude protein correction model crude protein content prediction results for spontaneous and whole wheat flours
As can be seen from Table 3, the general flour crude protein correction model has a poor prediction result on the crude protein content of the self-leavening flour, and is partly because additives such as yeast are added into the self-leavening flour, so that the spectral absorption of the flour is influenced, and the model is not suitable for the prediction of the self-leavening flour; the general flour correction model has a relatively good prediction result on the crude protein content of the whole wheat flour, but a certain amount of wheat bran exists in the whole wheat flour, and the bran also contains protein components, so that the model prediction accuracy is not high, and the correction model is not suitable for the prediction of the whole wheat flour.
Step (6), establishing a two-component and three-component mixed crude protein correction model by using the universal flour, the spontaneous flour and the whole wheat flour
In view of the poor prediction effect of the crude protein correction model established by single universal flour under the influence of external interference factors (yeast and bran), crude protein correction models of universal flour + spontaneous flour, universal flour + wholemeal flour, universal flour + spontaneous flour + wholemeal flour are established, the crude protein contents of samples of all prediction sets are predicted, the prediction result evaluation is compared with the single-component universal flour correction model, and the comparison result is shown in the following table 4.
TABLE 4 evaluation of prediction results for single flour correction model and two-component, three-component mixed correction model
As can be seen from Table 4, compared with the single-component crude protein correction model established by the universal flour, in the prediction result evaluation of the two-component mixed crude protein correction model of the universal flour and the spontaneous flour, the Rc is reduced to 0.9588, the RMSECV is increased to 0.5108, the Rp is reduced to 0.9514, and the RMSEP is reduced to 0.4144, which indicates that the spontaneous flour greatly interferes with the model, and the spontaneous flour is added into the original sample, so that the overall prediction effect of the mixed model is reduced; in the evaluation of the prediction result of the general flour and whole wheat flour two-component mixed crude protein correction model, Rc is 0.9804, RMSECV is 0.3983, Rp is 0.9736 and RMSECP is 0.3872, which shows that the interference of the whole wheat flour to the model is small, and the whole prediction precision of the mixed model is improved and the prediction result of a prediction set sample is improved in a small amplitude by adding the whole wheat flour to the original sample. Three-component mixed modeling is carried out on 3 types of wheat flour samples, in the evaluation of prediction results, Rc is 0.9762, RMSECV is reduced to 0.4237, Rp is 0.9722, and RMSECP is reduced to 0.3851, the overall prediction effect and prediction precision of the established 3 types of sample mixed crude protein model are improved, the method for carrying out three-component mixed crude protein modeling on the general flour, the spontaneous flour and the wholewheat flour is feasible, the three-component mixed crude protein correction model of the general flour, the spontaneous flour and the wholewheat flour can effectively improve the adaptability of the correction model, enhance the anti-interference capability of the model and greatly improve the practical value of the correction model.
In order to optimize the stability and the prediction accuracy of the three-component mixed crude protein correction model, before the three-component mixed crude protein correction model is established, the present embodiment selects three preprocessing methods to process the near infrared spectrum data of the wheat flour sample, then establishes the three-component mixed crude protein correction model, and predicts the crude protein content of the sample of the prediction set by using the three-component mixed crude protein correction model for spectrum data preprocessing, and the prediction result is shown in table 5.
TABLE 5 prediction results of three-component mixed crude protein correction model for spectral data preprocessing
As can be seen from table 5, the prediction accuracy of the established three-component hybrid correction model is improved by using the near infrared spectrum data processed by the SNV (standard normal variable transform), vector normalization and MSC (multivariate scattering correction) methods, wherein the established three-component hybrid correction model has the best prediction effect on the near infrared spectrum data processed by the vector normalization, and the Rc of the model reaches 0.9810, the RMSECV of the model is 0.3749, the Rp of the model is 0.9805, and the RMSEP of the model is 0.3242. Finally, the near infrared spectrum data are processed through vector normalization, the prediction accuracy and the stability of the three-component mixed correction model are effectively improved, the linear fitting result is shown in a graph 3(a) and a graph 3(b), and as can be seen from the graph 3, the three-component mixed correction model established after the near infrared spectrum data are preprocessed can effectively improve the adaptability of the wheat flour crude protein correction model, enhance the anti-interference capability of the model and improve the robustness and the prediction accuracy of the model.
The present invention is not limited to the above-described embodiments, and any obvious improvements, substitutions or modifications can be made by those skilled in the art without departing from the spirit of the present invention.
Claims (8)
1. A modeling method for improving the adaptability of a crude protein correction model of wheat flour is characterized by comprising the following steps:
s1, collecting 3 types of wheat flour samples, and carrying out near infrared spectrum data collection and crude protein physicochemical value measurement on the 3 types of wheat flour samples;
s2, dividing the 3 types of wheat flour samples into a correction set and a prediction set respectively;
s3, establishing a three-component mixed crude protein correction model of the 3 types of wheat flour samples according to the mathematical relationship between the near infrared spectrum data and the crude protein content value of the correction set wheat flour samples, and predicting the crude protein content of the wheat flour samples of the prediction set by using the three-component mixed crude protein correction model.
2. The method of claim 1, wherein the near infrared spectroscopy data is processed using vector normalization before the three-component mixed crude protein calibration model is constructed.
3. The crude protein corrected model adapted modeling method of claim 1, wherein said class 3 wheat flour samples comprise universal flour, spontaneous flour and whole wheat flour.
4. The method of claim 1, wherein the three-component blended crude protein correction model predicts the crude protein content of the wheat flour sample of the prediction set as evaluated by the correction set correlation coefficient Rc, the correction set cross-validation root mean square error RMSECV, the prediction set correlation coefficient Rp, and the prediction set cross-validation root mean square error RMSEP.
5. The method of claim 1, wherein the light collected from the near infrared spectroscopy data is used to adaptively model the crude protein calibration modelThe spectrometer parameters were set as: the scanning wavelength range is 900-2500nm, the wavelength points are 1601 and the resolution is 8cm-1The number of scans was 16.
6. The method as claimed in claim 1, wherein the crude protein physicochemical value is measured by a national standard method.
7. The method of claim 1, wherein the calibration set and the prediction set are divided by K-S algorithm, i.e. all wheat flour samples are used as candidate samples of the training set, and samples are selected from the candidate samples and classified into the training set.
8. The method for adaptively modeling a crude protein correction model according to claim 7, wherein the selecting samples in sequence is performed by: firstly selecting two wheat flour samples with the farthest Euclidean distance to be divided into a training set, then calculating the Euclidean distance from each remaining wheat flour sample to each known wheat flour sample in the training set, finding two samples with the farthest distance and the nearest distance from the known wheat flour sample, dividing the two samples into the training set, and repeating the process until the number of the samples meets the requirement.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011561285.8A CN112798555A (en) | 2020-12-25 | 2020-12-25 | Modeling method for improving adaptability of coarse protein correction model of wheat flour |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011561285.8A CN112798555A (en) | 2020-12-25 | 2020-12-25 | Modeling method for improving adaptability of coarse protein correction model of wheat flour |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112798555A true CN112798555A (en) | 2021-05-14 |
Family
ID=75804843
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011561285.8A Pending CN112798555A (en) | 2020-12-25 | 2020-12-25 | Modeling method for improving adaptability of coarse protein correction model of wheat flour |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112798555A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101403689A (en) * | 2008-11-20 | 2009-04-08 | 北京航空航天大学 | Nondestructive detection method for physiological index of plant leaf |
| CN106092962A (en) * | 2016-08-17 | 2016-11-09 | 山西省农业科学院农作物品种资源研究所 | A kind of near infrared spectroscopy quickly detects the method for millet crude protein content |
| CN106908408A (en) * | 2017-03-01 | 2017-06-30 | 四川农业大学 | A kind of assay method of Itanlian rye crude protein content |
| CN106950192A (en) * | 2017-03-27 | 2017-07-14 | 中国食品发酵工业研究院 | A kind of method of Contents of Main Components quick detection in vegetable protein beverage based on near-infrared spectral analysis technology |
| CN107917897A (en) * | 2017-12-28 | 2018-04-17 | 福建医科大学 | The method of the special doctor's food multicomponent content of near infrared ray |
| CN107991264A (en) * | 2017-11-17 | 2018-05-04 | 西南大学 | A kind of wheat flour protein matter and wet gluten content quick determination method |
| CN110044841A (en) * | 2019-05-16 | 2019-07-23 | 四川省草原科学研究院 | Utilize the method for near infrared spectrum detection Phalaris grass crude protein content |
-
2020
- 2020-12-25 CN CN202011561285.8A patent/CN112798555A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101403689A (en) * | 2008-11-20 | 2009-04-08 | 北京航空航天大学 | Nondestructive detection method for physiological index of plant leaf |
| CN106092962A (en) * | 2016-08-17 | 2016-11-09 | 山西省农业科学院农作物品种资源研究所 | A kind of near infrared spectroscopy quickly detects the method for millet crude protein content |
| CN106908408A (en) * | 2017-03-01 | 2017-06-30 | 四川农业大学 | A kind of assay method of Itanlian rye crude protein content |
| CN106950192A (en) * | 2017-03-27 | 2017-07-14 | 中国食品发酵工业研究院 | A kind of method of Contents of Main Components quick detection in vegetable protein beverage based on near-infrared spectral analysis technology |
| CN107991264A (en) * | 2017-11-17 | 2018-05-04 | 西南大学 | A kind of wheat flour protein matter and wet gluten content quick determination method |
| CN107917897A (en) * | 2017-12-28 | 2018-04-17 | 福建医科大学 | The method of the special doctor's food multicomponent content of near infrared ray |
| CN110044841A (en) * | 2019-05-16 | 2019-07-23 | 四川省草原科学研究院 | Utilize the method for near infrared spectrum detection Phalaris grass crude protein content |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Næs et al. | Locally weighted regression in diffuse near-infrared transmittance spectroscopy | |
| Chen et al. | Determination of protein, total carbohydrates and crude fat contents of foxtail millet using effective wavelengths in NIR spectroscopy | |
| CN104749132A (en) | Method for measuring content of azodicarbonamide in flour | |
| CN108613943B (en) | Near-infrared single-grain crop component detection method based on spectrum morphology transfer | |
| WO2020248961A1 (en) | Method for selecting spectral wavenumber without reference value | |
| CN105044022A (en) | Method for rapidly nondestructively detecting wheat hardness based on near infrared spectrum technology and application | |
| Ferrão et al. | Horizontal attenuated total reflection applied to simultaneous determination of ash and protein contents in commercial wheat flour | |
| CN105806803B (en) | A kind of multi objective Cooperative Analysis wavelength combination and its selection method | |
| CN110231306A (en) | A kind of method of lossless, the quick odd sub- seed protein content of measurement | |
| CN109932336A (en) | A kind of method for quick identification of wholemeal | |
| CN110231302A (en) | A kind of method of the odd sub- seed crude fat content of quick measurement | |
| US7420170B2 (en) | Fourier transform infrared (FTIR) chemometric method to determine cetane number of diesel fuels containing fatty acid alkyl ester additives | |
| CN107991265A (en) | A kind of wheat flour Rubus biflorus Buch quick determination method based on information fusion | |
| CN117309776A (en) | Raw chicken ingredient detection method based on hyperspectral and single-tag regression | |
| CN112798555A (en) | Modeling method for improving adaptability of coarse protein correction model of wheat flour | |
| CN104181125A (en) | Method for rapidly determining Kol-bach value of beer malt | |
| Wang et al. | Rapid detection of quality of Japanese fermented soy sauce using near-infrared spectroscopy | |
| Yang et al. | Analysis and estimate of corn quality by near infrared reflectance (NIR) spectroscopy | |
| CN113125378A (en) | Near infrared spectrum-based method for rapidly detecting nutritional components in camel meat at different parts | |
| Yang | Development of an integrated variety and appearance quality measurement system for milled rice | |
| Joe et al. | Performance Evaluation of Chemometric Prediction Models—Key Components of Wheat Grain | |
| CN106501212A (en) | Based on the method that the ripe rear quality of beef is roasted in the information prediction of raw meat near infrared spectrum | |
| CN109580525A (en) | A kind of detection method of quick predict wheat baking quality | |
| Tao et al. | Authentication of gluten-free flour by Fourier-transform infrared spectroscopic technique | |
| CN115184298B (en) | Method for on-line monitoring of soy sauce quality based on near infrared spectrum |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210514 |