CN107064042B - Qualitative analysis method of infrared spectrum - Google Patents
Qualitative analysis method of infrared spectrum Download PDFInfo
- Publication number
- CN107064042B CN107064042B CN201710120444.2A CN201710120444A CN107064042B CN 107064042 B CN107064042 B CN 107064042B CN 201710120444 A CN201710120444 A CN 201710120444A CN 107064042 B CN107064042 B CN 107064042B
- Authority
- CN
- China
- Prior art keywords
- components
- sample
- spectrum
- infrared spectrum
- component
- 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
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 34
- 238000004451 qualitative analysis Methods 0.000 title claims abstract description 20
- 238000012216 screening Methods 0.000 claims abstract description 31
- 240000008791 Antiaris toxicaria Species 0.000 claims abstract description 16
- 230000003595 spectral effect Effects 0.000 claims abstract description 12
- 238000001228 spectrum Methods 0.000 claims description 21
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000000862 absorption spectrum Methods 0.000 claims description 8
- 238000002835 absorbance Methods 0.000 claims description 5
- 239000013598 vector Substances 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 238000006386 neutralization reaction Methods 0.000 claims description 2
- 230000000717 retained effect Effects 0.000 claims 1
- 238000004458 analytical method Methods 0.000 abstract description 12
- 125000004122 cyclic group Chemical group 0.000 abstract description 5
- 230000008030 elimination Effects 0.000 abstract description 3
- 238000003379 elimination reaction Methods 0.000 abstract description 3
- 239000000523 sample Substances 0.000 description 28
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 238000010521 absorption reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 238000005033 Fourier transform infrared spectroscopy Methods 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000004566 IR spectroscopy Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 125000000524 functional group Chemical group 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 239000013074 reference sample Substances 0.000 description 1
- 238000012549 training Methods 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
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a qualitative analysis method of infrared spectrum, which adopts an ENet method to perform primary analysis on a spectrogram of a sample to be detected from a spectral databaseScreening the components; then, a CLS model is established to carry out cyclic iterative computation and elimination CAE<0, completing secondary screening of the components; finally, fitting Y according to the secondary screening spectral dataACCalculating and judging PA1And PA2The method has the advantages that three times of component screening is completed, the whole process combines the variable selection capability of the ENet method, rapid and accurate qualitative identification and analysis of the infrared spectrum are realized through the loop iteration CLS process and the UPAs process, meanwhile, the method does not need to be modeled in advance, and the problem of serious multiple collinearity of the spectral components in the multi-component infrared spectrum can be solved.
Description
Technical Field
The invention relates to the field of infrared spectrum analysis, in particular to a qualitative analysis method of infrared spectrum.
Background
The infrared spectrum analysis is an important method for substance characterization, the analysis of the method can provide a lot of information about functional groups, can help to determine partial or all molecular types and structures, and the qualitative analysis has the advantages of high characteristics, short analysis time, less required sample amount, no damage to samples, convenient measurement and the like. The infrared spectrum qualitative analysis is mainly used for qualitative discrimination of substances, namely, the spectrum of an unknown sample is compared with the spectrum of a known reference sample set to determine the attribution of the unknown substance. With the development of qualitative analysis methods for infrared spectroscopy, particularly fourier transform infrared spectroscopy, there are a number of methods available in the prior art for qualitative analysis of fourier transform infrared spectroscopy: such as classical least squares regression (CLS), Partial Least Squares (PLS), Artificial Neural Network (ANN), etc., all of which have certain drawbacks when they are used to qualitatively analyze infrared spectra. For example, when component identification is performed by using CLS, firstly, absorbance data of all spectra of a band to be inspected needs to be selected, but all the spectrum data can influence the identification result of the algorithm finally, and meanwhile, the CLS analysis method cannot solve the problem of multiple collinearity of spectra in a spectrum database, and when qualitative analysis is performed by using PLS modeling, the identification accuracy is reduced due to the occurrence of new components; in recent years, an artificial neural network algorithm develops rapidly, but the algorithm needs a complex training process, and a single artificial neural network algorithm can only carry out qualitative identification on a single component and cannot realize rapid qualitative identification analysis.
Meanwhile, with the increase of infrared spectrum types in an infrared spectrum database, the collinearity of the absorption spectrum characteristics of the components is increased, and the problems are difficult to solve by the existing qualitative analysis method of the infrared spectrum. Therefore, for real-time online application, it is still difficult to realize accurate and rapid qualitative analysis of the infrared spectrum of a sample to be detected from a large database of infrared spectra.
Disclosure of Invention
The invention aims to provide a qualitative analysis method of infrared spectrum, which is used for carrying out accurate and rapid qualitative analysis on the infrared spectrum of a sample to be detected in real time and on line to identify sample components.
In order to achieve the purpose, the invention adopts the following technical scheme: a qualitative analysis method of infrared spectrum comprises the following steps: (A) preparing a sample to be detected; (B) calling a spectral database of the field to which the sample to be detected belongs; (C) acquiring an infrared spectrogram of a sample to be detected by using a spectrometer; (D) selecting sample components from a spectrum database for the first time by adopting an ENet (variable selection technology based on an elastic network) method, and establishing an absorbance matrix X of the infrared spectrum components of the sampleAEI.e. n rows mAEIs given as a matrix (X is a component standard absorption spectrum, n is the number of component spectrum data points, m isNumber of component spectra); (E) and D, establishing a CLS (linear least square fitting) model according to the sample component data in the step D: cAE＝(XAE TXAE)-1XAE TY, then entering a loop to iteratively calculate and remove CAE<0, performing secondary screening to obtain new sample component data XAC，mAC，CAC(C is component concentration and Y is infrared absorbance spectrum); (F) and E, fitting and calculating again according to the sample component data secondarily screened in the step E to obtain YACValue, XAC*CACEach column of (B) is in YACProjection length in direction and YACThe ratio of the lengths thereof is recorded as PA1，XAC*CACLength of (2) and YACThe ratio of the projected lengths in the directions of the respective components is denoted as PA2Comparison of PA1And PA2Screening the components for three times; (G) and F, integrating the components screened for three times in the step F to obtain a qualitative analysis result of the infrared spectrum of the sample.
Compared with the prior art, the method adopts an ENet method to carry out primary screening on components from the spectrogram database of the sample to be detected; then, a CLS model is established to carry out cyclic iterative computation and elimination CAE<0, completing secondary screening of the components; finally, fitting Y according to the secondary screening spectral dataACCalculating and judging PA1And PA2The method has the advantages that three times of component screening is completed, the whole process combines the variable selection capability of the ENet method, rapid and accurate qualitative identification and analysis of the infrared spectrum are realized through the loop iteration CLS process and the UPAs process, meanwhile, the method does not need modeling in advance, and the problem of serious multiple collinearity of the spectral components in the multi-component infrared spectrum can be solved.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 shows an example of 2700cm-1～3040cm-1Absorbance spectrum of the band;
FIG. 3 is a diagram showing results of primary screening using the ENet method;
FIG. 4 is a table of components and concentrations screened using the ENet method;
FIG. 5 is a diagram of the results of one iteration of LCLS;
FIG. 6 is a table of the components and concentrations for one iteration of LCLS screening;
FIG. 7 is a diagram of the results of LCLS two iterations;
FIG. 8 is a table of components and concentrations for LCLS two-pass iterative screening;
FIG. 9 is a graph of the results of three iterations of LCLS;
FIG. 10 is a table of components, concentrations for three iterations of LCLS screening;
FIG. 11 is a chart of three screening calculations of UPAs values;
figure 12 is a fit of the final screening results.
Detailed Description
The invention is further described with reference to the accompanying drawings 1-12:
a qualitative analysis method of infrared spectrum comprises the following steps: (A) preparing a sample to be detected; (B) calling a spectral database of the field to which the sample to be detected belongs; (C) acquiring an infrared spectrogram of a sample to be detected by using a spectrometer; (D) selecting sample components from a spectrum database for the first time by adopting an ENet (variable selection technology based on an elastic network) method, and establishing an absorbance matrix X of the infrared spectrum components of the sampleAEI.e. n rows mAEThe matrix (X is the component standard absorption spectrum, n is the number of component spectrum data points, and m is the number of component spectra); (E) and D, establishing a CLS (linear least square fitting) model according to the sample component data in the step D: cAE＝(XAE TXAE)-1XAE TY, then entering a loop to iteratively calculate and remove CAE<0, performing secondary screening to obtain new sample component data XAC，mAC，CAC(C is component concentration and Y is infrared absorbance spectrum); (F) and E, fitting and calculating again according to the sample component data secondarily screened in the step E to obtain YACValue, XAC*CACEach column of (B) is in YACProjection length in direction and YACThe ratio of the lengths thereof is recorded as PA1，XAC*CACLength of (2) and YACThe ratio of the projected lengths in the directions of the respective components is denoted as PA2Comparison of PA1And PA2Screening the components for three times; (G) and F, integrating the components screened for three times in the step F to obtain a qualitative analysis result of the infrared spectrum of the sample. Performing primary screening on components from a spectrogram database of a sample to be detected by adopting an ENet method; then, a CLS model is established to carry out cyclic iterative computation and elimination CAE<0, completing secondary screening of the components; finally, fitting Y according to the secondary screening spectral dataACCalculating and judging PA1And PA2The method has the advantages that three times of component screening is completed, the whole process combines the variable selection capability of the ENet method, rapid and accurate qualitative identification and analysis of the infrared spectrum are realized through loop iteration CLS calculation and PA judgment, meanwhile, modeling is not needed in advance, and the problem of serious multiple collinearity of the spectral components in the multi-component infrared spectrum can be solved.
And the step E carries out secondary screening according to the following steps: (E1) performing variable initialization C(0)＝(XAE TXAE)- 1XAE T*Y，X(0)＝XAE(ii) a (E2) Performing loop iteration, wherein the iteration number k is k + 1; (E3) and removing X(k-1)Neutralization of C(k-1)The spectrum column vector of the corresponding position of the middle is less than 0 to obtain a new spectrum matrix X(k)Wherein the number of the selected column vectors is m(k)(ii) a (E4) Calculating C(k)＝(X(k)TX(k))-1X(k)TY; (E5) and determining that i belongs to {1.. m ] for any i, i(k)When is (C) }iWhether the result is equal to or greater than 0 or not is judged, if yes, E6 is entered, and if not, E2 is entered; (E6) calculating the result to obtain new sample component data XAC，mAC，CAC. This process may be referred to as LCLS (cyclic linear least squares fitting process), and the model is built from a belronbo quantitative model Y ═ XAEC + ε, for any i, i ∈ {1.. m(k)When is (C) }iNot less than 0, so that a new model parameter C can be calculated by a linear least square fitting methodAE＝(XAE TXAE)-1XAE TY, there will be C insideAE<Case of 0, in fact CAE<0 is caused by overfitting, so corresponding components need to be removed, and the components which do not accord with the model parameters are removed by secondary screening of the components through circular iterative calculation to obtain new sample component data XAC，mAC，CAC。
And the step F carries out three times of screening according to the following steps: (F1) according to formula CAC＝(XAC TXAC)-1XAC T*YACX obtained in step EAC，mAC，CACSubstituting to obtain the refitted YAC；(F2)、XAC*CACEach column of (B) is in YACProjection length in direction and YACThe length ratio of the material is recorded as PA1，XAC*CACLength of (2) and YACThe ratio of the projected lengths in the directions of the respective components is denoted as PA2(ii) a (F3) According to PA1、PA2Definition of
(lambda is more than or equal to 0 and less than or equal to 1); (F4) defining the size of a lambda value according to artificial experience, and calculating the size of UPAs; (F5) inputting a preset threshold ThreadUPAs in advance, if UPAs<Directly removing the current corresponding components from ThreadUPAs, and otherwise, keeping the current corresponding components; if all components are UPAs<ThreadUPAs then judged to retain all components. This is the UPAs analysis process, and the greater the PA value the greater the probability of existence and the greater the importance in the actual composition, so the fitting calculation screening definition is performed
The larger the lambda value is, the more importance is placed on PA1The more difficult it is to reject interfering components and absorb the smaller components, but the fitting error of the model is small; the smaller the lambda value, the more important the PA2In this case, although it becomes easier to eliminate the interfering component and the component having a small absorption, the fitting error of the model becomes large, and thus the λ value and the pre-input threshold value are determined by human experienceThreadUPAs completes the judgment of UPAs value and the components are accurate.
The following are specific examples of the method of the present invention:
(1) collecting a strip of C-containing material by using Fourier spectrometer transform infrared instrument4H10Calculating the absorption spectrogram of gas components and the background absorption spectrogram of pure nitrogen to obtain a spectrum with a band of 2700cm-1～3040cm-1The wavelength band, as shown in FIG. 2, is the absorbance spectrum;
(2) analyzing by an ENet method, primarily screening 368 air components in an infrared spectrum database, and selecting 15 components as shown in figures 3 and 4;
(3) performing iterative computation by using LCLS (least squares) cyclic linear least square fitting, and after 3 iterations, sorting the mixture to be limited to 3 components, as shown in FIGS. 5-10;
(4) calculating PA of each component according to the algorithm formula by adopting a UPAs analysis process and setting the parameter lambda to be 0.5 and the ThreadUPAs to be 0.51、PA2And UPAs value, removing the components with the UPAs value smaller than ThreadUPAs to obtain qualitative identification result C4H10By using C4H10The results of the individual fits are shown in fig. 12. The whole algorithm process runs on a win7 platform, is realized by adopting matlabR2012b coding, and consumes 10.02266s to calculate to obtain a result. Therefore, the method can quickly and accurately identify the components in the infrared spectrum of the sample to be detected in the large database of the infrared spectrum.
In the fitting graph of the figure, in order to distinguish the original spectrum, the dotted line is actually a continuous line segment representing the fitted spectrum.
Claims (2)
1. A qualitative analysis method of infrared spectrum comprises the following steps:
(A) preparing a sample to be detected;
(B) calling a spectral database of the field to which the sample to be detected belongs;
(C) acquiring an infrared spectrogram of a sample to be detected by using a spectrometer;
(D) using ENet (elastic net based)Variable selection technology) method for primarily selecting sample components from a spectral database and establishing an absorbance matrix X of the infrared spectral components of the sampleAEI.e. n rows mAEA matrix of (a);
wherein n is the number of component spectrum data points, and m is the number of component spectra;
(E) and D, establishing a CLS (linear least square fitting) model according to the sample component data in the step D: cAE=（XAE TXAE）- 1XAE TY, then entering a loop to iteratively calculate and remove CAE<0, performing secondary screening to obtain new sample component data XAC，mAC，CAC；
Wherein, XACThe absorbance matrix of the infrared spectrum components of the sample obtained by secondary screening is shown, C is the component concentration, and Y is the infrared absorbance spectrum;
(F) and E, fitting and calculating again according to the sample component data secondarily screened in the step E to obtain YACValue, XAC*CACEach column of (B) is in YACProjection length in direction and YACThe ratio of the lengths thereof is recorded as PA1，XAC*CACLength of (2) and YACThe ratio of the projected lengths in the directions of the respective components is denoted as PA2Comparison of PA1And PA2Screening the components for three times;
(G) integrating the components screened for three times in the step F to obtain a qualitative analysis result of the infrared spectrum of the sample;
step F, screening three times as follows:
(F1) according to formula CAC=（XAC TXAC）-1XAC T*YACX obtained in step EAC，mAC，CACSubstituting to obtain the refitted YAC；
（F2）、XAC*CACEach column of (B) is in YACProjection length in direction and YACThe length ratio of the material is recorded as PA1，XAC*CACLength of (2) and YACThe ratio of the projected lengths in the directions of the respective components is denoted as PA2；
(F3) According to PA1、PA2Definition UPAs =Wherein λ is more than or equal to 0 and less than or equal to 1;
(F4) defining the size of a lambda value according to artificial experience, and calculating the size of UPAs;
(F5) inputting a preset threshold ThreadUPAs in advance, directly removing the current corresponding component if the UPAs is less than the ThreadUPAs, and keeping the current corresponding component if the UPAs is not less than the ThreadUPAs; all components are judged to be retained if they are UPAs < ThreadUPAs.
2. The method for qualitative analysis of the infrared spectrum according to claim 1, characterized in that: and the step E carries out secondary screening according to the following steps:
(E1) performing variable initialization C（0）=（XAE TXAE）-1XAE T*Y，X（0）=XAE；
(E2) Performing loop iteration, wherein the iteration times k = k + 1;
(E3) and removing X（k-1）Neutralization of C（k-1）The spectrum column vector of the corresponding position of the middle is less than 0 to obtain a new spectrum matrix X（k）Wherein the number of the selected column vectors is m（k）；
(E4) Calculating C（k）=（X（k）TX（k））-1X（k）T*Y；
(E5) And determining that i belongs to {1.. m ] for any i, i（k）When is (C) }iWhether the result is equal to or greater than 0 or not is judged, if yes, E6 is entered, and if not, E2 is entered;
(E6) calculating the result to obtain new sample component data XAC，mAC，CAC。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710120444.2A CN107064042B (en) | 2017-03-02 | 2017-03-02 | Qualitative analysis method of infrared spectrum |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710120444.2A CN107064042B (en) | 2017-03-02 | 2017-03-02 | Qualitative analysis method of infrared spectrum |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107064042A CN107064042A (en) | 2017-08-18 |
| CN107064042B true CN107064042B (en) | 2020-01-10 |
Family
ID=59621822
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710120444.2A Active CN107064042B (en) | 2017-03-02 | 2017-03-02 | Qualitative analysis method of infrared spectrum |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107064042B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109615358B (en) * | 2018-11-01 | 2020-11-03 | 北京伟景智能科技有限公司 | Deep learning image recognition-based restaurant automatic settlement method and system |
| CN110414169B (en) * | 2019-08-05 | 2023-05-02 | 上海神开石油科技有限公司 | Fourier infrared gas logging method and device thereof |
| CN113406037B (en) * | 2021-06-17 | 2023-07-25 | 中国科学院合肥物质科学研究院 | Infrared spectrum online rapid identification analysis method based on sequence forward selection |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1288647A2 (en) * | 2001-08-24 | 2003-03-05 | Bayer Ag | Spectroscopic test system based on microcapillaries |
| CN104237158A (en) * | 2014-09-04 | 2014-12-24 | 浙江科技学院 | Near infrared spectrum qualitative analysis method with universality |
| CN104616022A (en) * | 2015-01-13 | 2015-05-13 | 浙江科技学院 | Classification method of near infrared spectrum |
| CN106198433A (en) * | 2016-06-27 | 2016-12-07 | 中国科学院合肥物质科学研究院 | Infrared spectrum method for qualitative analysis based on LM GA algorithm |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6687620B1 (en) * | 2001-08-01 | 2004-02-03 | Sandia Corporation | Augmented classical least squares multivariate spectral analysis |
-
2017
- 2017-03-02 CN CN201710120444.2A patent/CN107064042B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1288647A2 (en) * | 2001-08-24 | 2003-03-05 | Bayer Ag | Spectroscopic test system based on microcapillaries |
| CN104237158A (en) * | 2014-09-04 | 2014-12-24 | 浙江科技学院 | Near infrared spectrum qualitative analysis method with universality |
| CN104616022A (en) * | 2015-01-13 | 2015-05-13 | 浙江科技学院 | Classification method of near infrared spectrum |
| CN106198433A (en) * | 2016-06-27 | 2016-12-07 | 中国科学院合肥物质科学研究院 | Infrared spectrum method for qualitative analysis based on LM GA algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107064042A (en) | 2017-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114424058B (en) | Tracing method for VOCs pollution | |
| CN107064042B (en) | Qualitative analysis method of infrared spectrum | |
| WO2018010352A1 (en) | Qualitative and quantitative combined method for constructing near infrared quantitative model | |
| CN108169213B (en) | Automatic identification method for peak elements of laser-induced breakdown spectroscopy | |
| JP6760380B2 (en) | Analytical data processing method and analytical data processing equipment | |
| CN112414997B (en) | ICP-AES overlapping spectral line separation method based on RBF neural network | |
| CN107958267B (en) | Oil product property prediction method based on spectral linear representation | |
| CN107563448B (en) | Sample space clustering division method based on near infrared spectrum analysis | |
| CN101825567A (en) | Screening method for near infrared spectrum wavelength and Raman spectrum wavelength | |
| CN110726694A (en) | Characteristic wavelength selection method and system of spectral variable gradient integrated genetic algorithm | |
| CN108956583A (en) | Characteristic spectral line automatic selecting method for laser induced breakdown spectroscopy analysis | |
| CN109738413A (en) | Mixture Raman spectra qualitative analysis method based on sparse non-negative least square | |
| CN116646030B (en) | Tobacco tar component identification method and system based on electronic smoke detection | |
| GB2561879A (en) | Spectroscopic analysis | |
| CN109145685B (en) | Fruit and vegetable hyperspectral quality detection method based on ensemble learning | |
| CN108663334B (en) | Method for searching spectral characteristic wavelength of soil nutrient based on multi-classifier fusion | |
| CN114216877B (en) | Automatic detection and reconstruction method and system for spectral peak in tea near infrared spectral analysis | |
| CN108120694B (en) | Multi-element correction method and system for chemical component analysis of sun-cured red tobacco | |
| JP2020091872A (en) | Method for discriminating and analyzing substance | |
| CN114577967B (en) | Chromatographic analysis method for traditional Chinese medicine compound sample based on artificial neural network and difference spectrum | |
| CN106198433B (en) | Infrared spectroscopy method for qualitative analysis based on LM-GA algorithm | |
| CN109145887B (en) | Threshold analysis method based on spectral latent variable confusion discrimination | |
| CN114199989B (en) | Method and system for identifying pericarpium citri reticulatae based on mass spectrum data fusion | |
| CN113406037B (en) | Infrared spectrum online rapid identification analysis method based on sequence forward selection | |
| CN114067169A (en) | Raman spectrum analysis method based on convolutional neural network |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |