CN114062300A - Trace additive detection technology based on infrared multi-source spectrum - Google Patents
Trace additive detection technology based on infrared multi-source spectrum Download PDFInfo
- Publication number
- CN114062300A CN114062300A CN202111439151.3A CN202111439151A CN114062300A CN 114062300 A CN114062300 A CN 114062300A CN 202111439151 A CN202111439151 A CN 202111439151A CN 114062300 A CN114062300 A CN 114062300A
- Authority
- CN
- China
- Prior art keywords
- data
- matrix
- model
- sample
- infrared
- 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
- 238000001228 spectrum Methods 0.000 title claims abstract description 34
- 238000001514 detection method Methods 0.000 title claims abstract description 29
- 239000000654 additive Substances 0.000 title claims abstract description 25
- 230000000996 additive effect Effects 0.000 title claims abstract description 19
- 238000005516 engineering process Methods 0.000 title claims abstract description 11
- 230000004927 fusion Effects 0.000 claims abstract description 37
- 238000012937 correction Methods 0.000 claims abstract description 22
- 238000000034 method Methods 0.000 claims abstract description 17
- 239000000446 fuel Substances 0.000 claims abstract description 12
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 45
- 230000003595 spectral effect Effects 0.000 claims description 12
- 238000005259 measurement Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000012417 linear regression Methods 0.000 claims description 6
- 238000013178 mathematical model Methods 0.000 claims description 6
- 238000010561 standard procedure Methods 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000012569 chemometric method Methods 0.000 claims description 3
- 230000002860 competitive effect Effects 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 230000004069 differentiation Effects 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000012067 mathematical method Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 3
- 238000010239 partial least squares discriminant analysis Methods 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000004445 quantitative analysis Methods 0.000 claims description 3
- 238000007430 reference method Methods 0.000 claims description 3
- 238000011160 research Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000004611 spectroscopical analysis Methods 0.000 claims 6
- 238000011156 evaluation Methods 0.000 claims 1
- 230000009466 transformation Effects 0.000 claims 1
- 239000002699 waste material Substances 0.000 abstract description 3
- 239000002816 fuel additive Substances 0.000 abstract description 2
- 230000006872 improvement Effects 0.000 description 13
- 239000000295 fuel oil Substances 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction 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
- G01N21/3577—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing liquids, e.g. polluted water
-
- 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
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 trace additive detection technology based on infrared multi-source spectrum, which comprises the following steps: acquiring near-infrared and mid-infrared multi-source spectrum data; preprocessing data, including selecting parameters and extracting characteristics; picking up a data correction model through data fusion, wherein the data fusion comprises low-layer data fusion, middle-layer data fusion and high-layer data fusion; and evaluating sample result data. The invention realizes the accurate detection of trace additives in the fuel by means of near-infrared and mid-infrared multi-source spectrums and through a multi-source spectrum data layer fusion technology and a chemometrics algorithm. When the fuel additive is measured, the method can be completed only by performing near-infrared and intermediate-infrared multi-source spectrum detection, and the content of the original internal trace additive can be quickly, efficiently and accurately obtained without using a method specified by national standards. The waste of detection samples is avoided, and the retrieval efficiency and precision are improved.
Description
Technical Field
The invention relates to the field of detection of trace additives in fuel oil, in particular to a trace additive detection technology based on infrared multi-source spectrum.
Background
The content of additives in the fuel has a significant impact on the fuel quality. Therefore, the detection of the trace additive in the fuel oil has important significance for the quality control of the fuel oil, the improvement of the production process and the control of the production cost.
In the prior art, when the trace additive of the fuel is quantitatively analyzed, a chemical quantitative detection method specified by national standards is often adopted, so that a detection sample and a chemical reagent are wasted, only a single component can be detected in each detection, and the multiple trace additives in the fuel cannot be quickly and efficiently detected.
Therefore, a detection method which is rapid and efficient and does not generate waste of detection samples is needed in the field of detection of trace additives in fuel oil.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, provides a trace additive detection technology based on infrared multi-source spectrum, and adopts the following technical scheme for realizing the purpose:
a trace additive detection technology based on infrared multi-source spectrum comprises the following steps:
s1, acquiring near-infrared and mid-infrared multi-source spectrum data;
s2, preprocessing data, including parameter selection and feature extraction;
s3, establishing a data correction model through data fusion, wherein the data fusion comprises low-layer data fusion, middle-layer data fusion and high-layer data fusion;
s3-1, the low-level fusion is data-level fusion of spectra, data of all data sources are simply connected into a matrix according to the sequence of samples, the number of rows of the matrix is the same as that of analysis samples, the number of columns of the matrix is the same as that of the spectral data sources, and then a single model for final classification or prediction is provided by a chemometric method;
s3-2, extracting relevant features from each data source respectively by the middle layer fusion, combining the relevant features into a matrix, and processing the matrix by a classification or correction method;
s3-3, the high level fusion computes individual classification or regression models from each data source and combines the individual model results to obtain a final decision;
and S4, evaluating sample result data.
As an improvement, the establishment of the correction model in S3 includes the following steps:
a. collecting representative samples, and collecting optical data of the samples by using a research instrument; strictly controlling measurement conditions including measurement parameters such as sample preparation, sample loading, test conditions, instrument parameters and the like;
b. accurately measuring the attribute to be measured, namely a standard reference value, of the sample by using a national standard method;
c. correlating the spectrum data with the detected data by a mathematical method, generally converting the spectrum data, selecting an effective load wave band, performing regression calculation with a standard method measured value, then obtaining a calibration equation, and establishing a mathematical model;
d. when an unknown sample is analyzed, firstly, a sample to be detected is scanned to obtain a spectrum, a proper pre-established mathematical model is called according to spectral characteristics, and the component content or attribute classification of the sample to be detected is calculated by utilizing the established model.
As a refinement, the representative sample in step a is a sample whose composition and range of variation are close to those of the sample to be analyzed.
As an improvement, the step c of converting the spectral data includes normalization, first or second order differentiation, and the like.
As an improvement, the method for extracting the characteristic wavelength comprises the following steps: one or more of partial least squares discriminant analysis (PLS-DA), competitive adaptive re-weighting algorithm (CARS), spaced partial least squares (BiPLS), joint spaced partial least squares (SiPLS), continuous projection algorithm (SPA), invariant information elimination (UVE), and random frog-leap (SFLA).
As improvement, the fuel quality index parameters are analyzed and calculated by adopting multiple regression:
multiple regression (or univariate) calculations, based on the following models:
Y=β0+β1X1+β2X2+…+βmXm+e
e represents the random error after removing the influence of m independent variables on Y. After the least square method, the estimation is as follows:
thus, the fuel component concentration value can be obtained from the characteristic band spectrum information.
As an improvement, the most commonly adopted quantitative analysis in the data fusion is a partial least square method, the partial least square method simultaneously extracts useful information from the X matrix and the Y matrix one by one, and a linear regression model is established until a certain principal component exists;
the PLS step:
(1) is subjected to matrix decomposition, and the model is
X=TP+E
Y=UQ+F
In the formula: a scoring matrix of the T, U-X matrix and the Y matrix;
load (principal component) matrices of the P, Q-X and Y matrices;
e, F-errors introduced when fitting X and Y with a PLS model;
(2) linear regression of T and U
B is a correlation coefficient matrix
U=TB
B=T'U(T'T)-1
In prediction, from the matrix X of the unknown sampleIs unknownAnd P obtained by correctionCorrection ofIt finds the T of the X matrix of the unknown sampleIs unknown. Then, the following results were obtained:
Yis unknown=TIs unknownBQ。
As an improvement, SEC (standard error correction) is used to evaluate the model performance of the correction model:
in the formula:
yi-calibration set sample reference method measurements;
d is the degree of freedom of the correction model, equal to n-k;
n-number of calibration samples;
the number of k-PLS major factors;
if the spectral data and the reference data are subjected to mean centering before the calibration model is established, d is n-k-1.
The invention has the advantages that:
1. the invention realizes the accurate detection of trace additives in the fuel by means of near-infrared and mid-infrared multi-source spectrums and through a multi-source spectrum data layer fusion technology and a chemometrics algorithm.
2. When the fuel additive is measured, the method can be completed only by performing near-infrared and intermediate-infrared multi-source spectrum detection, and the content of the original internal trace additive can be quickly, efficiently and accurately obtained without using a method specified by national standards. The waste of detection samples is avoided, and the retrieval efficiency and precision are improved.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The present invention will be described in detail and specifically with reference to the following examples so as to facilitate the understanding of the present invention, but the following examples do not limit the scope of the present invention.
Example 1
The embodiment discloses a trace additive detection technology based on infrared multi-source spectrum, which comprises the following steps:
s1, acquiring near-infrared and mid-infrared multi-source spectrum data;
s2, preprocessing data, including parameter selection and feature extraction;
s3, establishing a data correction model through data fusion, wherein the data fusion comprises low-layer data fusion, middle-layer data fusion and high-layer data fusion;
s3-1, the low-level fusion is data-level fusion of spectra, data of all data sources are simply connected into a matrix according to the sequence of samples, the number of rows of the matrix is the same as that of analysis samples, the number of columns of the matrix is the same as that of the spectral data sources, and then a single model for final classification or prediction is provided by a chemometric method;
s3-2, extracting relevant features from each data source respectively by the middle layer fusion, combining the relevant features into a matrix, and processing the matrix by a classification or correction method;
s3-3, the high level fusion computes individual classification or regression models from each data source and combines the individual model results to obtain a final decision;
and S4, evaluating sample result data.
As an improvement, the establishment of the correction model in S3 includes the following steps:
a. collecting representative samples, and collecting optical data of the samples by using a research instrument; strictly controlling measurement conditions including measurement parameters such as sample preparation, sample loading, test conditions, instrument parameters and the like;
b. accurately measuring the attribute to be measured, namely a standard reference value, of the sample by using a national standard method;
c. correlating the spectrum data with the detected data by a mathematical method, generally converting the spectrum data, selecting an effective load wave band, performing regression calculation with a standard method measured value, then obtaining a calibration equation, and establishing a mathematical model;
d. when an unknown sample is analyzed, firstly, a sample to be detected is scanned to obtain a spectrum, a proper pre-established mathematical model is called according to spectral characteristics, and the component content or attribute classification of the sample to be detected is calculated by utilizing the established model.
As a refinement, the representative sample in step a is a sample whose composition and range of variation are close to those of the sample to be analyzed.
As an improvement, the step c of converting the spectral data includes normalization, first or second order differentiation, and the like.
As an improvement, the method for extracting the characteristic wavelength comprises the following steps: one or more of partial least squares discriminant analysis (PLS-DA), competitive adaptive re-weighting algorithm (CARS), spaced partial least squares (BiPLS), joint spaced partial least squares (SiPLS), continuous projection algorithm (SPA), invariant information elimination (UVE), and random frog-leap (SFLA).
As improvement, the fuel quality index parameters are analyzed and calculated by adopting multiple regression:
multiple regression (or univariate) calculations, based on the following models:
Y=β0+β1X1+β2X2+…+βmXm+e
e represents the random error after removing the influence of m independent variables on Y. After the least square method, the estimation is as follows:
thus, the fuel component concentration value can be obtained from the characteristic band spectrum information.
As an improvement, the most commonly adopted quantitative analysis in the data fusion is a partial least square method, the partial least square method simultaneously extracts useful information from the X matrix and the Y matrix one by one, and a linear regression model is established until a certain principal component exists;
the PLS step:
(1) is subjected to matrix decomposition, and the model is
X=TP+E
Y=UQ+F
In the formula: a scoring matrix of the T, U-X matrix and the Y matrix;
load (principal component) matrices of the P, Q-X and Y matrices;
e, F-errors introduced when fitting X and Y with a PLS model;
(2) linear regression of T and U
B is a correlation coefficient matrix
U=TB
B=T'U(T'T)-1
In prediction, from the matrix X of the unknown sampleIs unknownAnd P obtained by correctionCorrection ofIt finds the T of the X matrix of the unknown sampleIs unknown. Then, the following results were obtained:
Yis unknown=TIs unknownBQ。
As an improvement, SEC (standard error correction) is used to evaluate the model performance of the correction model:
in the formula:
yi-calibration set sample reference method measurements;
d is the degree of freedom of the correction model, equal to n-k;
n-number of calibration samples;
the number of k-PLS major factors;
if the spectral data and the reference data are subjected to mean centering before the calibration model is established, d is n-k-1.
The embodiments of the present invention have been described in detail, but they are merely exemplary, and the present invention is not equivalent to the above-described embodiments. Any equivalent modifications and substitutions to those skilled in the art are also within the scope of the present invention. Accordingly, it is intended that all equivalent alterations and modifications be included within the scope of the invention, without departing from the spirit and scope of the invention.
Claims (8)
1. A trace additive detection technology based on infrared multi-source spectrum is characterized by comprising the following steps:
s1, acquiring near-infrared and mid-infrared multi-source spectrum data;
s2, preprocessing data, including parameter selection and feature extraction;
s3, establishing a data correction model through data fusion, wherein the data fusion comprises low-layer data fusion, middle-layer data fusion and high-layer data fusion;
s3-1, the low-level fusion is data-level fusion of spectra, data of all data sources are simply connected into a matrix according to the sequence of samples, the number of rows of the matrix is the same as that of analysis samples, the number of columns of the matrix is the same as that of the spectral data sources, and then a single model for final classification or prediction is provided by a chemometric method;
s3-2, extracting relevant features from each data source respectively by the middle layer fusion, combining the relevant features into a matrix, and processing the matrix by a classification or correction method;
s3-3, the high level fusion computes individual classification or regression models from each data source and combines the individual model results to obtain a final decision;
and S4, evaluating sample result data.
2. A trace additive detection technique based on infrared multi-source spectroscopy as claimed in claim 1, wherein the establishment of the calibration model in S3 includes the following steps:
a. collecting representative samples, and collecting optical data of the samples by using a research instrument; strictly controlling measurement conditions including measurement parameters such as sample preparation, sample loading, test conditions, instrument parameters and the like;
b. accurately measuring the attribute to be measured, namely a standard reference value, of the sample by using a national standard method;
c. correlating the spectrum data with the detected data by a mathematical method, generally converting the spectrum data, selecting an effective load wave band, performing regression calculation with a standard method measured value, then obtaining a calibration equation, and establishing a mathematical model;
d. when an unknown sample is analyzed, firstly, a sample to be detected is scanned to obtain a spectrum, a proper pre-established mathematical model is called according to spectral characteristics, and the component content or attribute classification of the sample to be detected is calculated by utilizing the established model.
3. A trace additive detection technique based on infrared multisource spectroscopy as claimed in claim 2, wherein the representative sample in step a is a sample whose composition and variation range are close to those of the sample to be analyzed.
4. A trace additive detection technique based on infrared multisource spectroscopy as claimed in claim 2, wherein the transformation of the spectral data in step c comprises normalization, first or second order differentiation, etc.
5. A trace additive detection technique based on infrared multisource spectroscopy as claimed in claim 1, wherein the method for extracting characteristic wavelength is as follows: one or more of partial least squares discriminant analysis (PLS-DA), competitive adaptive re-weighting algorithm (CARS), spaced partial least squares (BiPLS), joint spaced partial least squares (SiPLS), continuous projection algorithm (SPA), invariant information elimination (UVE), and random frog-leap (SFLA).
6. A trace additive detection technique based on infrared multi-source spectroscopy as claimed in claim 1, wherein the fuel quality index parameter is analyzed and calculated using multiple regression:
multiple regression (or univariate) calculations, based on the following models:
Y=β0+β1X1+β2X2+…+βmXm+e
e represents the random error after removing the influence of m independent variables on Y. After the least square method, the estimation is as follows:
thus, the fuel component concentration value can be obtained from the characteristic band spectrum information.
7. The infrared multi-source spectrum-based trace additive detection technology as claimed in claim 1, wherein the most commonly used quantitative analysis in the data fusion is partial least squares, which extracts useful information from the X matrix and the Y matrix one by one, and builds a linear regression model until a certain principal component;
the PLS step:
(1) is subjected to matrix decomposition, and the model is
X=TP+E
Y=UQ+F
In the formula: score matrix of T, U-X matrix and Y matrix
Load (principal component) matrix of P, Q-X matrix and Y matrix
E, F-errors introduced when fitting X and Y with a PLS model
(2) Linear regression of T and U
B is a correlation coefficient matrix
U=TB
B=T'U(T'T)-1
In prediction, from the matrix X of the unknown sampleIs unknownAnd P obtained by correctionCorrection ofIt finds the T of the X matrix of the unknown sampleIs unknown. Then, the following results were obtained:
Yis unknown=TIs unknownBQ。
8. A trace additive detection technique based on infrared multisource spectroscopy as claimed in claim 1, characterized in that the calibration model is subjected to model performance evaluation using SEC (calibration standard error):
in the formula:
yi-calibration set sample reference method measurements;
d is the degree of freedom of the correction model, equal to n-k;
n-number of calibration samples;
the number of k-PLS major factors;
if the spectral data and the reference data are subjected to mean centering before the calibration model is established, d is n-k-1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111439151.3A CN114062300A (en) | 2021-11-27 | 2021-11-27 | Trace additive detection technology based on infrared multi-source spectrum |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111439151.3A CN114062300A (en) | 2021-11-27 | 2021-11-27 | Trace additive detection technology based on infrared multi-source spectrum |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114062300A true CN114062300A (en) | 2022-02-18 |
Family
ID=80277399
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111439151.3A Pending CN114062300A (en) | 2021-11-27 | 2021-11-27 | Trace additive detection technology based on infrared multi-source spectrum |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114062300A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101299022A (en) * | 2008-06-20 | 2008-11-05 | 河南中医学院 | Method for evaluating Chinese medicine comprehensive quality using near infrared spectra technique |
CN104807803A (en) * | 2015-04-20 | 2015-07-29 | 武汉轻工大学 | Quantitative adulteration detection method for peanut oil based on multiple-source spectroscopic data fusion |
CN106018329A (en) * | 2016-05-09 | 2016-10-12 | 广西大学 | Method for fast detecting indexes of white granulated sugar through near infrared spectrum |
CN111595807A (en) * | 2020-07-03 | 2020-08-28 | 南京农业大学 | Quantitative detection method for caprolactam in bio-based food packaging film |
CN112179871A (en) * | 2020-10-22 | 2021-01-05 | 南京农业大学 | Method for nondestructive detection of caprolactam content in sauce food |
-
2021
- 2021-11-27 CN CN202111439151.3A patent/CN114062300A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101299022A (en) * | 2008-06-20 | 2008-11-05 | 河南中医学院 | Method for evaluating Chinese medicine comprehensive quality using near infrared spectra technique |
CN104807803A (en) * | 2015-04-20 | 2015-07-29 | 武汉轻工大学 | Quantitative adulteration detection method for peanut oil based on multiple-source spectroscopic data fusion |
CN106018329A (en) * | 2016-05-09 | 2016-10-12 | 广西大学 | Method for fast detecting indexes of white granulated sugar through near infrared spectrum |
CN111595807A (en) * | 2020-07-03 | 2020-08-28 | 南京农业大学 | Quantitative detection method for caprolactam in bio-based food packaging film |
CN112179871A (en) * | 2020-10-22 | 2021-01-05 | 南京农业大学 | Method for nondestructive detection of caprolactam content in sauce food |
Non-Patent Citations (3)
Title |
---|
杨巧玲 等: "光谱数据融合技术在食品检测中的应用研究进展", 食品工业科技, no. 18, 8 April 2020 (2020-04-08), pages 324 - 328 * |
胡翼然;李杰庆;刘鸿高;范茂攀;王元忠;: "红外光谱数据融合对美味牛肝菌产地鉴别", 光谱学与光谱分析, no. 04, 15 April 2020 (2020-04-15), pages 1276 - 1281 * |
邹小波;封韬;郑开逸;石吉勇;黄晓玮;孙悦;: "利用近红外及中红外融合技术对小麦产地和烘干程度的同时鉴别", 光谱学与光谱分析, no. 05, 15 May 2019 (2019-05-15), pages 1445 - 1449 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107703097B (en) | Method for constructing model for rapidly predicting crude oil property by using near-infrared spectrometer | |
CN109324014B (en) | Self-adaptive near-infrared rapid prediction method for crude oil properties | |
CN113155809A (en) | Novel spectral detection method for ore classification and real-time quantitative analysis | |
CN113340874B (en) | Quantitative analysis method based on combination ridge regression and recursive feature elimination | |
CN111999258A (en) | Spectral baseline correction-oriented weighting modeling local optimization method | |
CN114611582A (en) | Method and system for analyzing substance concentration based on near infrared spectrum technology | |
CN104316492A (en) | Method for near-infrared spectrum measurement of protein content in potato tuber | |
CN113484278A (en) | Tomato comprehensive quality nondestructive testing method based on spectrum and principal component analysis | |
CN105259136A (en) | Measuring-point-free temperature correction method of near-infrared correction model | |
CN112485238A (en) | Method for identifying turmeric essential oil producing area based on Raman spectrum technology | |
CN116578851A (en) | Method for predicting effective boron content of hyperspectral soil | |
CN114062300A (en) | Trace additive detection technology based on infrared multi-source spectrum | |
CN108267422B (en) | Abnormal sample removing method based on near infrared spectrum analysis | |
CN112858208A (en) | Biomass potassium content measurement and modeling method based on infrared spectrum principal component and neural network | |
CN116662751A (en) | Tobacco leaf moisture content detection method for removing abnormal samples based on principal component analysis and lever value method | |
CN115392305A (en) | Soil organic matter content high spectrum modeling method based on improved time convolution network | |
CN112949169A (en) | Coal sample test value prediction method based on spectral analysis | |
CN114166792A (en) | Method for determining ethanol content in gasoline | |
CN112861412A (en) | Biomass volatile component content measurement and modeling method based on near infrared spectrum principal component and neural network | |
Mondal | Performance Evaluation of Hyperspectral Radiometric Measurement Technique for Coal Quality Assessment | |
WO2024011687A1 (en) | Method and apparatus for establishing oil product physical property fast evaluation model | |
CN112861416A (en) | Biomass fixed carbon measurement and modeling method based on near infrared spectrum principal component and neural network | |
CN111103259B (en) | Rapid detection method for frying oil quality based on spectrum technology | |
CN116380875A (en) | Novel method for quickly establishing quantitative prediction model of coal components based on small sample size | |
CN114428067A (en) | Method for predicting gasoline octane number |
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 |