CN114971259A - Method for analyzing quality consistency of formula product by using near infrared spectrum - Google Patents
Method for analyzing quality consistency of formula product by using near infrared spectrum Download PDFInfo
- Publication number
- CN114971259A CN114971259A CN202210554490.4A CN202210554490A CN114971259A CN 114971259 A CN114971259 A CN 114971259A CN 202210554490 A CN202210554490 A CN 202210554490A CN 114971259 A CN114971259 A CN 114971259A
- Authority
- CN
- China
- Prior art keywords
- spectral data
- sample
- quality
- standard product
- matrix
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 22
- 230000003595 spectral effect Effects 0.000 claims abstract description 57
- 239000011159 matrix material Substances 0.000 claims abstract description 39
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000001228 spectrum Methods 0.000 claims description 17
- 238000004497 NIR spectroscopy Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000002835 absorbance Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000005304 joining Methods 0.000 claims description 2
- 238000013507 mapping Methods 0.000 claims description 2
- 238000011946 reduction process Methods 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 13
- 238000004458 analytical method Methods 0.000 abstract description 9
- 230000008901 benefit Effects 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000004519 manufacturing process Methods 0.000 abstract description 4
- 238000005259 measurement Methods 0.000 abstract description 2
- 239000000126 substance Substances 0.000 description 8
- 238000011156 evaluation Methods 0.000 description 7
- 238000005034 decoration Methods 0.000 description 2
- 229910052739 hydrogen Inorganic materials 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 description 1
- 238000000862 absorption spectrum Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000002290 gas chromatography-mass spectrometry Methods 0.000 description 1
- 239000001257 hydrogen Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- 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
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Strategic Management (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Development Economics (AREA)
- Computational Mathematics (AREA)
- Algebra (AREA)
- General Engineering & Computer Science (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Computing Systems (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a method for analyzing the quality consistency of a formula product by utilizing near infrared spectrum, which belongs to the technical field of spectral measurement and comprises the following steps: collecting near infrared spectrum data of m samples and a standard product; generating a high-dimensional spectral data matrix by using the acquired spectral data; performing dimensionality reduction processing on the high-dimensional spectral data matrix; calculating the distance between the sample spectral data subjected to dimensionality reduction and the standard product spectral data; and judging the consistency of the quality of the sample and the quality of the standard product according to the calculated distance. The invention designs a consistency detection method of the quality of multi-point production products based on the near infrared spectrum acquisition and analysis technology, not only can provide a judgment basis for the quality stability of formula products produced by the same brand and different processing plants, but also can realize batch detection of the formula products produced by a plurality of processing points, and has the advantages of high speed, high efficiency, no influence of artificial subjective factors on detection results and high reliability.
Description
Technical Field
The invention belongs to the technical field of spectral measurement, and particularly relates to a method for detecting quality consistency of a formula product processed by a plurality of production points by using near infrared spectrum.
Background
The quality of the formula product directly influences the economic benefit of enterprises, and factors influencing the product quality are many and include a plurality of indexes such as physics, chemistry, appearance and the like. At present, a plurality of formula products are distributed in different processing plants for production, and although the formula of the products is the same, the quality of the products produced by the different processing plants is often inconsistent due to the difference of the process and the batches of raw and auxiliary materials and the influence of other factors, so that the quality difference of the products of the same brand is larger.
At present, the evaluation method aiming at the quality of the formula product mainly comprises the following steps:
the first one is that the chemical index, physical index and the like of the formula product are used as the characterization vector, and the similarity method, the variance analysis method in statistical analysis, the Euclidean distance method and the like are adopted for evaluation, so that the stability of the quality of the product of the same brand produced by different manufacturers is judged.
Secondly, the consistency of the quality of the formula product is evaluated by adopting expert sensory evaluation and part of conventional physicochemical indexes, and the evaluation result is influenced by subjective factors of evaluation personnel and lacks objectivity.
Thirdly, the characteristics of fingerprint feature extraction, macroscopic inference analysis and the like in the chemical fingerprint spectrum, such as chromatogram, gas chromatography-mass spectrometry and the like, are analyzed so as to be used for monitoring the product quality, evaluating the quality consistency and the like. However, this evaluation method requires chemical pretreatment of the sample, and has a slow detection speed, and cannot complete batch detection and analysis in a short time.
Disclosure of Invention
The invention provides a method for detecting the quality consistency of a formula product based on a near infrared spectrum acquisition and analysis technology, and solves the problem that the conventional product quality evaluation method cannot scientifically, quickly and massively evaluate the quality consistency of the formula product produced at a plurality of processing points.
In order to solve the technical problems, the invention adopts the following technical scheme:
a method for analyzing the quality consistency of a formula product by using near infrared spectroscopy comprises the following steps:
collecting near infrared spectrum data of m samples and a standard product;
generating a high-dimensional spectral data matrix by using the acquired spectral data;
performing dimensionality reduction processing on the high-dimensional spectral data matrix;
calculating the distance between the sample spectral data subjected to dimensionality reduction and the standard product spectral data;
and judging the consistency of the quality of the sample and the quality of the standard product according to the calculated distance.
In some embodiments of the present application, in order to improve the accuracy of the product quality stability detection, in the process of acquiring the near infrared spectrum data of the m samples and the standard product, it is preferable to include: respectively placing m samples and a standard product in the same near-infrared spectrometer for spectrum collection; and selecting the absorbance corresponding to n identical wavelength variables in the spectrogram as the acquired spectral data, wherein the n wavelength variables preferably cover the wavelength ranges related to all characteristic peaks in all spectrograms.
In some embodiments of the present application, in order to improve the accuracy of the modeling analysis, in the generating the high-dimensional spectral data matrix using the acquired spectral data, it is preferable to include: combining the collected spectral data of the m samples with the spectral data of a standard product to form a (m +1) × n dimensional matrix X'; performing first derivative and norris smoothing on the matrix X'; and generating a high-dimensional spectral data matrix X by utilizing the preprocessed spectral data so as to obtain a spectral data matrix with better quality.
In some embodiments of the present application, in order to better meet the requirement of dimension reduction of the high-dimensional spectral data, in the process of performing dimension reduction processing on the high-dimensional spectral data matrix, it is preferable to include: dividing the neighborhood by adopting a manifold distance-based K nearest neighbor method, and calculating the similarity degree S ij (ii) a A projection vector w is required to make the objective functionMinimization; wherein the content of the first and second substances,y i 、y i respectively obtaining the spectral data of the ith sample and the jth sample in the reduced-dimension matrix Y; obtaining reduced low-dimensional matrix Y ═ Y 1 ,y 2 ,...,y m+1 ] T 。
In some embodiments of the present application, preferably, a mahalanobis distance calculation method is used to calculate a distance between the reduced sample spectrum data and the standard product spectrum data, and the process includes:
calculating the vector Y of the ith sample according to the low-dimensional matrix Y formed by the spectral data of m samples and a standard product i Vector y with standard product m+1 Mahalanobis distance between:
wherein S is a sample covariance matrix; i is 1,2, …, m.
In some embodiments of the present application, the process of discriminating the conformity of the sample quality with the standard product quality from the calculated distance comprises: setting a threshold value a; distance D between a sample and a standard product i >a, judging that the quality of the product produced by the sample processing plant is inconsistent with the standard product quality; distance D between a sample and a standard product i And (b) judging that the quality of the product produced by the processing plant of the sample is consistent with the quality of the standard product if the quality is not more than a.
Compared with the prior art, the invention has the advantages and positive effects that: the invention designs a consistency detection method for the quality of multi-point production products based on near infrared spectrum acquisition and analysis technology, and judges whether the quality of a sample to be detected and a standard product tends to be consistent or not according to the difference of the near infrared spectrum data of formula products produced at different processing points and the near infrared spectrum data of the standard product provided by an enterprise by acquiring the near infrared spectrum data of the formula products produced at different processing points and comparing the near infrared spectrum data with the near infrared spectrum data of the standard product provided by the enterprise, thereby not only providing a judgment basis for the quality stability problem of formula products produced by the same brand and different processing plants, but also being scientific, rapid and objective, being capable of realizing batch detection on formula products produced at multiple processing points simultaneously, having high efficiency, being free from the influence of human subjective factors on detection results and having high reliability.
Other features and advantages of the present invention will become more apparent from the detailed description of the embodiments of the present invention when taken in conjunction with the accompanying drawings.
Drawings
FIG. 1 is a general flow chart of one embodiment of a method for analyzing consistency of quality of a formula using near infrared spectroscopy.
Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings.
Near infrared spectroscopy (NIRS) is a method of obtaining an absorption spectrum in the near infrared region by diffuse reflection mainly using the overtone vibration or rotation of chemical bonds such as C-H, N-H, O-H, C-C contained in an organic substance. As for a formula product, main chemical components of the formula product generally have rich hydrogen-containing groups, so that key characteristics contained in a spectrum can be mined by means of modern metrology and an intelligent technical method, possibility is provided for qualitative and quantitative analysis of a near infrared spectrum, and the problem that quality consistency detection of the formula product cannot be completed quickly in batches only by a traditional chemical method is solved.
In order to determine whether the quality of products produced by the same brand and different processing plants is consistent, the quality of products produced by different processing plants (hereinafter referred to as samples) needs to be compared with the quality of standard products defined by enterprises so as to analyze the stability of the quality of the samples.
The embodiment adopts a near infrared spectrum collection and analysis technology, completes the consistency judgment of the quality of the sample and the quality of the standard product by collecting near infrared spectrum data of the sample and the standard product and carrying out comparative analysis on the collected spectrum data, and thus, scientific, rapid and batch detection and evaluation on the stability of the quality of the enterprise products can be realized.
The method for detecting and evaluating the consistency of the quality of the formula product in this embodiment is described in detail below with reference to fig. 1.
S101, collecting near infrared spectrum data of a sample and a standard product;
in this embodiment, the near infrared spectrometer may be used to collect spectra of the sample and the standard product respectively. Specifically, m samples provided by an enterprise and a standard product can be respectively placed in sample cups of the same near-infrared spectrometer for spectrum collection. The same near-infrared spectrometer is used for spectrum collection of all samples and standard products, so that the influence on the detection result of the quality stability of the product caused by map deviation caused by the self difference of the near-infrared spectrometer can be avoided.
The spectrum of a sample may be represented by a vector x i And representing, the spectra of the m samples can be represented by an m-n-dimensional matrix, wherein n is a wavelength variable in a spectrogram, and absorbances corresponding to n identical wavelength variables are selected from all sample spectrograms and spectrograms of standard products as spectral data to construct the matrix. When selecting n wavelength variables, it is better to cover the wavelength range related to all characteristic peaks in all spectrograms so as to improve the accuracy of detecting the stability of product quality.
The spectral data of the m samples and the spectral data x of a standard product provided by an enterprise are compared m+1 Taken together, form a (m +1) × n dimensional matrix X':
s102, preprocessing the collected near infrared spectrum data.
Because the near infrared spectrum data has the characteristics of large information amount, high latitude, multiple wave bands, serious band overlapping and the like, the accuracy of modeling analysis is reduced by the correlation and redundant information among the spectrums, and therefore, the original spectrum data needs to be preprocessed to obtain the spectrum with better quality. The embodiment preferably performs preprocessing by performing first derivative and norris smoothing on the acquired spectral data matrix X'.
And S103, generating a high-dimensional spectral data matrix X by utilizing the preprocessed spectral data.
and S104, performing dimensionality reduction on the high-dimensional spectral data matrix X to obtain an expressible low-dimensional matrix Y.
Because of the high dimensionality of the near infrared spectral data, it is desirable to have R in the low dimensional space l (l & lt n) finding a set of corresponding points Y ═ Y 1 ,y 2 ,...,y m+1 ] T So that y is i X can be expressed well in a sense i I.e. finding a projection direction w, such that y i =w T x i 。
The purpose of dimension reduction is to eliminate redundant information in the spectrum and construct a new coordinate axis, so that the original data point can be projected onto the new coordinate axis. The feature space after dimensionality reduction can keep the local structure of the original high-dimensional space.
The value of the projection direction w may be obtained by minimizing the objective function, i.e. seeking the projection direction w such that the objective function is minimized. The minimization objective function is formulated as:
in the formula, S ij The degree of similarity between the i-th and j-th samples that are neighbors. I.e. calculating a certain sample x i The distance between the sample and all other samples is selected after sorting i The nearest k samples are taken as neighboring points, and sample x is taken i The points are connected with the k adjacent points one by one. When the original sample point x i And x j At a close distance, the projected sample point y i And y j And also very close.
In the embodiment, a K neighbor method based on manifold distance is adopted to divide the neighborhood, and the similarity degree S is calculated ij 。
Calculating manifold distances between all sample points, and selecting the distance from the sample x i K sample points with nearest points form a neighborhood N k (x i )。
The manifold distance between any two points is calculated according to the formula:
wherein, P ij Representing connections x in a neighbor-joining graph i And x j A set of all paths of two points; p represents a connection x i And x j A path of two points; | p | represents the number of data points on the p path; p is a radical of k ,p k+1 Is two points on the p-path, and
wherein sigma is an adjustable parameter and is adjusted empirically according to data characteristics; d (p) k ,p k+1 ) Is p k ,p k+1 Two points of Euclidean distance, and
calculating the degree of similarity S ij :
Wherein t is an adjustment parameter.
Therefore, the objective function:
wherein D is ij For diagonal matrix:
D ii corresponding to the i-th sample, D ii The larger the size, the i-th sample is reflectedThe more important the item is, the projected y i The more important.
And solving the projection vector w when the objective function is minimum, wherein the linear dimension reduction mapping obtained after projection is as follows:
x i →y i ==w T x i ,i=1,2,...,
thus, the low-dimensional matrix Y after the dimension reduction can be obtained.
And S105, calculating the distance between the sample spectral data subjected to the dimensionality reduction and the standard product spectral data.
When calculating the distance between two samples, the influence caused by the distribution of the samples needs to be considered: one is that the variances in different dimensions are different, and then the importance of different dimensions in calculating the distance is different; furthermore, correlation may exist between different dimensions, and the distance calculation is interfered. Therefore, the embodiment preferably uses the mahalanobis distance method to calculate the distance between the sample spectral data after dimensionality reduction and the standard product spectral data.
Calculating the vector Y of the ith sample according to the low-dimensional matrix Y formed by the spectral data of m samples and a standard product i Vector y with standard product m+1 Mahalanobis distance between, i.e.:
wherein S is a sample covariance matrix; i is 1,2, …, m.
And S106, judging the quality consistency of the sample and the standard product according to the calculated distance.
In this embodiment, a threshold a may be set. If sample y i With standard products y m+1 Mahalanobis distance D of i >a, the quality of the product produced by the processing plant of the sample is not considered to be within the controllable range of the standard product quality, i.e., the sample y i The quality of the product produced by the processing plant is inconsistent with the quality of the standard product, and the product is judged to be an unqualified product; otherwise, consider sample y i The quality of the product produced by the processing plant is basically consistent with the quality of the standard product, and the product is judged to be qualified.
Therefore, the problem of consistency detection of product quality stability of enterprises and product quality produced by a plurality of processing plants of the same brand is solved.
Of course, the above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (7)
1. A method for analyzing the quality consistency of a formula product by using near infrared spectroscopy is characterized by comprising the following steps:
collecting near infrared spectrum data of m samples and a standard product;
generating a high-dimensional spectral data matrix by using the acquired spectral data;
performing dimensionality reduction processing on the high-dimensional spectral data matrix;
calculating the distance between the sample spectral data subjected to dimensionality reduction and the standard product spectral data;
and judging the consistency of the quality of the sample and the quality of the standard product according to the calculated distance.
2. The method of claim 1, wherein the step of collecting the NIR spectra data for the m samples and the standard product comprises:
respectively placing m samples and a standard product in the same near-infrared spectrometer for spectrum collection;
and selecting the absorbances corresponding to n identical wavelength variables in the spectrogram as the acquired spectral data, wherein the n wavelength variables cover the wavelength ranges related to all characteristic peaks in all spectrograms.
3. The method of claim 1, wherein the generating a high-dimensional spectral data matrix using the collected spectral data comprises:
combining the collected spectral data of the m samples with the spectral data of a standard product to form a (m +1) × n dimensional matrix X';
performing first derivative and norris smoothing on the matrix X';
and generating a high-dimensional spectral data matrix X by utilizing the preprocessed spectral data.
4. The method of claim 1, wherein the step of performing a dimensionality reduction process on the high-dimensional spectral data matrix comprises:
dividing the neighborhood by adopting a manifold distance-based K nearest neighbor method, and calculating the similarity degree S ij ;
Establishing an objective function:
wherein X is a high-dimensional spectral data matrix; d ij For diagonal matrix:
solving a projection vector w when the objective function is minimum, wherein the linear dimensionality reduction mapping obtained after projection is as follows:
x i →y i ==w T x i ,i=1,2,...;
obtaining reduced low-dimensional matrix Y ═ Y 1 ,y 2 ,...,y m+1 ] T ;
Wherein x is i The spectral data of the ith sample in the high-dimensional spectral data matrix X is obtained; y is i 、y i Respectively are the spectral data of the ith sample and the jth sample in the low-dimensional matrix Y after dimension reduction.
5. According to claimThe method of analyzing the consistency of quality of a formulated product using near infrared spectroscopy of claim 4, wherein the degree of similarity S ij The calculation process of (2) is as follows:
calculating manifold distances between all sample points, and selecting the distance from the sample x i K sample points with nearest points form a neighborhood N k (x i ) Wherein, the manifold distance calculation formula between any two points is:
in the formula, P ij Representing connected samples x in a neighbor joining map i Dot and sample x j A set of all paths of points; p represents a connection x i And x j A path of two points; | p | represents the number of data points on the p path; p is a radical of k ,p k+1 Is two points on the p-path, and
wherein σ is an adjustable parameter; d (p) k ,p k+1 ) Is p k ,p k+1 Euclidean distance of two points:
calculating the degree of similarity S ij :
Wherein t is an adjustment parameter.
6. The method of claim 4, wherein the step of calculating the distance between the reduced sample spectral data and the standard product spectral data comprises:
calculating the vector Y of the ith sample according to the low-dimensional matrix Y formed by the spectral data of m samples and a standard product i Vector y with standard product m+1 Mahalanobis distance between:
wherein S is a sample covariance matrix; i is 1,2, …, m.
7. The method according to any one of claims 1 to 6, wherein the step of discriminating the consistency of the sample quality with the standard product quality based on the calculated distance comprises:
setting a threshold value a;
distance D between a sample and a standard product i >a, judging that the quality of the product produced by the sample processing plant is inconsistent with the standard product quality;
distance D between a sample and a standard product i And (e) judging that the quality of the product produced by the processing plant of the sample is consistent with the quality of the standard product if the quality is not more than a.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210554490.4A CN114971259A (en) | 2022-05-20 | 2022-05-20 | Method for analyzing quality consistency of formula product by using near infrared spectrum |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210554490.4A CN114971259A (en) | 2022-05-20 | 2022-05-20 | Method for analyzing quality consistency of formula product by using near infrared spectrum |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114971259A true CN114971259A (en) | 2022-08-30 |
Family
ID=82985842
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210554490.4A Pending CN114971259A (en) | 2022-05-20 | 2022-05-20 | Method for analyzing quality consistency of formula product by using near infrared spectrum |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114971259A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118013258A (en) * | 2024-04-08 | 2024-05-10 | 山东星芭克生物科技有限公司 | Information acquisition method of intelligent water-soluble fertilizer production line |
-
2022
- 2022-05-20 CN CN202210554490.4A patent/CN114971259A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118013258A (en) * | 2024-04-08 | 2024-05-10 | 山东星芭克生物科技有限公司 | Information acquisition method of intelligent water-soluble fertilizer production line |
CN118013258B (en) * | 2024-04-08 | 2024-06-14 | 山东星芭克生物科技有限公司 | Information acquisition method of intelligent water-soluble fertilizer production line |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhao et al. | Application of hyperspectral imaging and chemometrics for variety classification of maize seeds | |
CN108181263B (en) | Tobacco leaf position feature extraction and discrimination method based on near infrared spectrum | |
Ye et al. | Non-destructive prediction of protein content in wheat using NIRS | |
CN109324015B (en) | Tobacco leaf replacing method based on spectrum similarity | |
Cui et al. | Identification of maize seed varieties based on near infrared reflectance spectroscopy and chemometrics | |
CN105158200A (en) | Modeling method capable of improving accuracy of qualitative near-infrared spectroscopic analysis | |
CN112903602A (en) | Multi-citrus diseased leaf identification method and system based on machine learning and hyperspectral imaging | |
CN114971259A (en) | Method for analyzing quality consistency of formula product by using near infrared spectrum | |
CN114112983B (en) | Tibetan medicine all-edge leaf green chorine artemisia origin discrimination method based on Python data fusion | |
CN109283153B (en) | Method for establishing quantitative analysis model of soy sauce | |
CN113655027A (en) | Method for rapidly detecting tannin content in plant by near infrared | |
CN109975236A (en) | A method of identifying the honeysuckle place of production using near-infrared spectrum technique | |
Dai et al. | Nondestructive identification of rice varieties by the data fusion of Raman and near-infrared (NIR) spectroscopies | |
Chen et al. | Monitoring green tea fixation quality by intelligent sensors: comparison of image and spectral information | |
CN114062306B (en) | Near infrared spectrum data segmentation preprocessing method | |
CN115561193A (en) | Fourier infrared spectrometer data processing and analyzing system | |
Cheng et al. | Identification of wine grape varieties based on near-infrared hyperspectral imaging | |
CN112697746A (en) | Spectrum information-based sweet potato powder alum content detection method | |
Wu et al. | Identification of lambda-cyhalothrin residues on Chinese cabbage using fuzzy uncorrelated discriminant vector analysis and MIR spectroscopy | |
NL2032367B1 (en) | Apple identification system and method based on information fusion technology | |
CN109406420B (en) | Method for predicting content of scopoletin in fructus lycii based on hyperspectral imaging technology | |
CN109406421B (en) | Method for predicting ferulic acid content in wolfberry fruit based on hyperspectral imaging technology | |
CN110188735A (en) | A kind of instruction plant recognition methods based on EO-1 hyperion | |
CN109406419B (en) | Method for predicting content of p-hydroxybenzoic acid in wolfberry based on hyperspectral imaging technology | |
CN112945899B (en) | Method for identifying polyglutamic acid compound fertilizer |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication |