CN112179870A - Cigarette classification recognition model construction method based on near infrared spectrum and OPLS-DA - Google Patents
Cigarette classification recognition model construction method based on near infrared spectrum and OPLS-DA Download PDFInfo
- Publication number
- CN112179870A CN112179870A CN202011102013.1A CN202011102013A CN112179870A CN 112179870 A CN112179870 A CN 112179870A CN 202011102013 A CN202011102013 A CN 202011102013A CN 112179870 A CN112179870 A CN 112179870A
- Authority
- CN
- China
- Prior art keywords
- near infrared
- spectrum
- sample
- infrared spectrum
- opls
- 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
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 54
- 235000019504 cigarettes Nutrition 0.000 title claims abstract description 51
- 238000010276 construction Methods 0.000 title abstract description 5
- 238000001228 spectrum Methods 0.000 claims abstract description 57
- 238000012937 correction Methods 0.000 claims abstract description 49
- 238000012360 testing method Methods 0.000 claims abstract description 45
- 238000000034 method Methods 0.000 claims abstract description 40
- 238000007781 pre-processing Methods 0.000 claims abstract description 31
- 238000004458 analytical method Methods 0.000 claims abstract description 11
- 238000012423 maintenance Methods 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims abstract description 6
- 230000003595 spectral effect Effects 0.000 claims description 10
- 230000004069 differentiation Effects 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 4
- 241000208125 Nicotiana Species 0.000 abstract description 50
- 235000002637 Nicotiana tabacum Nutrition 0.000 abstract description 50
- 230000008569 process Effects 0.000 abstract description 4
- 238000004497 NIR spectroscopy Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000013145 classification model Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000012067 mathematical method Methods 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000001320 near-infrared absorption spectroscopy Methods 0.000 description 1
- 238000010239 partial least squares discriminant analysis Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000003313 weakening effect Effects 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
- G01N21/359—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
- 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
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The embodiment of the invention provides a method for constructing a cigarette classification and identification model based on near infrared spectrum and OPLS-DA, which comprises the following steps: maintaining a sample to be detected according to a preset maintenance step by selecting the sample; carrying out spectrum scanning on a sample to obtain a near infrared spectrum of the sample, dividing the near infrared spectrum into a correction set and a test set, processing the near infrared spectrum through different types of spectrum preprocessing schemes, carrying out OPLS-DA analysis on the correction set to obtain a cigarette classification recognition model and the recognition accuracy of the correction set, bringing the test set into the cigarette classification recognition model to obtain the recognition accuracy of the test set, determining the spectrum preprocessing scheme meeting the preset requirement according to the recognition accuracy, and obtaining the cigarette classification recognition model corresponding to the spectrum preprocessing scheme meeting the preset requirement. By adopting the method, the construction method of the tobacco classification identification model with high accuracy can be provided, and the tobacco type can be identified more accurately in the follow-up process.
Description
Technical Field
The invention relates to the technical field of tobacco component analysis, in particular to a method for constructing a cigarette classification recognition model based on near infrared spectrum and OPLS-DA.
Background
The style characteristics of cigarettes are important components of the quality characteristics of cigarette products, are the core competitiveness of cigarette brands, and are main marks for distinguishing the cigarette brands. The finished cigarette maintains the quality and style characteristics of cigarette brands mainly by blending tobacco leaf formulas. For a long time, the quality and style characteristics of cigarettes are mainly judged and identified by methods such as tobacco shred chemical components, mainstream smoke, sensory quality evaluation and the like.
In recent years, in the tobacco industry, quantitative analysis such as measurement and monitoring of the content of various chemical components of tobacco by using near infrared spectroscopy has been started, but at present, when the tobacco is analyzed by using the near infrared spectroscopy, because of the complexity of the components of the tobacco, no determined analysis method is used for judging the components and the types of the tobacco with high accuracy.
Disclosure of Invention
Aiming at the problems in the prior art, the embodiment of the invention provides a method for constructing a cigarette classification and identification model based on near infrared spectrum and OPLS-DA.
The embodiment of the invention provides a method for constructing a cigarette classification and identification model based on near infrared spectrum and OPLS-DA, which comprises the following steps:
selecting a plurality of types of samples to be detected, and maintaining the samples according to a preset maintenance step;
performing spectral scanning on the sample to obtain a near infrared spectrum of the sample;
dividing the near infrared spectrum into a correction set and a test set, and processing the near infrared spectrum by different spectrum pretreatment schemes;
carrying out OPLS-DA analysis on the correction set to obtain a cigarette classification recognition model and the recognition accuracy of the correction set, and bringing the test set into the cigarette classification recognition model to obtain the recognition accuracy of the test set;
and determining a spectrum preprocessing scheme meeting preset requirements according to the identification accuracy of the correction set and the identification accuracy of the test set, and acquiring a cigarette classification identification model corresponding to the spectrum preprocessing scheme meeting the preset requirements.
In one embodiment, the spectral pre-processing scheme comprises:
multivariate scattering correction, standard normal variable transformation, first order differentiation, second order differentiation, Savitzky-Golay filter and algorithm combination.
In one embodiment, the method further comprises:
and calculating the sum of the identification accuracy of the correction set and the identification accuracy of the test set, and acquiring the spectrum preprocessing scheme with the maximum sum.
In one embodiment, the method further comprises:
and dividing the near infrared spectrum into a correction set and a test set according to the ratio of 2 to 1 of the correction set to the test set.
In one embodiment, the method further comprises:
and controlling the temperature and the water content of the sample within corresponding preset ranges, and controlling the humidity and the temperature of the environment corresponding to the sample within the preset ranges.
In one embodiment, the method further comprises:
and carrying out N times of spectral scanning on the sample, and taking the average value of the results of the N times of spectral scanning as the near infrared spectrum of the sample, wherein N is a natural number greater than 1.
In one embodiment, the method further comprises:
the scanning range of the spectrum is set to 10000 to 4000cm-1Scanning resolution was set to 8 cm-1And setting the scanning times to be 64 times, and putting the sample into a rotating cup to rotate and collect the near infrared diffuse reflection spectrum to obtain the spectrum scanning result of the sample.
According to the construction method of the cigarette classification and identification model based on the near infrared spectrum and the OPLS-DA, provided by the embodiment of the invention, a plurality of types of samples to be detected are selected, and the samples are maintained according to the preset maintenance steps; the method comprises the steps of carrying out spectrum scanning on a sample to obtain a near infrared spectrum of the sample, dividing the near infrared spectrum into a correction set and a test set, processing the near infrared spectrum through different types of spectrum preprocessing schemes, carrying out OPLS-DA analysis on the correction set to obtain a cigarette classification recognition model and the recognition accuracy of the correction set, bringing the test set into the cigarette classification recognition model to obtain the recognition accuracy of the test set, determining the spectrum preprocessing scheme meeting preset requirements according to the recognition accuracy of the correction set and the recognition accuracy of the test set, and obtaining the cigarette classification recognition model corresponding to the spectrum preprocessing scheme meeting the preset requirements.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a flow chart of a method for constructing a cigarette classification recognition model based on near infrared spectroscopy and OPLS-DA in the embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a method for constructing a cigarette classification recognition model based on a near infrared spectrum and OPLS-DA according to an embodiment of the present invention, and as shown in fig. 1, the embodiment of the present invention provides a method for constructing a cigarette classification recognition model based on a near infrared spectrum and OPLS-DA, including:
step S101, selecting a plurality of types of samples to be tested, and maintaining the samples according to a preset maintenance step.
Specifically, the cut tobacco of a plurality of cigarettes is selected as a sample to be tested, and the sample is maintained in corresponding steps according to preset maintenance steps, wherein the specific maintenance steps can be, for example, controlling the temperature and the water content of the sample in corresponding preset ranges, and controlling the humidity and the temperature of the environment corresponding to the sample in the preset ranges
And S102, performing spectrum scanning on the sample to obtain a near infrared spectrum of the sample.
Specifically, the near infrared spectrum of the tobacco shred sample is scanned to obtain a scanning result, that is, the near infrared spectrum of the sample, and in addition, when the near infrared spectrum of the sample is obtained, N times of spectrum scanning may be performed on the sample, an average value of the N times of spectrum scanning results is taken as the near infrared spectrum of the sample, N is a natural number greater than 1, for example, the sample is scanned 3 times, and the average spectrum is taken as the final spectrum data of the sample.
Step S103, dividing the near infrared spectrum into a correction set and a test set, and processing the near infrared spectrum through different spectrum preprocessing schemes.
Specifically, samples corresponding to each tobacco shred are divided into a correction set and a test set, wherein the correction set is used for correcting the model in the process of building the cigarette classification identification model, the test set is used for verifying the cigarette classification identification model, the samples can be randomly divided into the correction set and the test set according to the ratio of 2:1 during division, preset spectrum pretreatment schemes of different types are obtained to process near infrared spectra, redundant information can be removed to the maximum degree through the spectrum pretreatment schemes, the influence of baseline drift and noise is reduced, therefore, the method is more beneficial to extracting effective information from complex spectra, optimizing spectrum information, enhancing spectrum availability and improving the robustness of subsequent classification identification models to a certain degree, and the spectrum pretreatment schemes comprise multiple scattering correction, standard normal variable transformation, first-order differential, second-order differential, Savitzky-Golay filters, algorithmic combinations, pre-processing the spectra by the spectral pre-processing scheme described above, or any combination.
And step S104, obtaining a cigarette classification recognition model and the recognition accuracy of the correction set by analyzing the correction set through OPLS-DA, and bringing the test set into the cigarette classification recognition model to obtain the recognition accuracy of the test set.
The method comprises the steps of analyzing a correction set OPLS-DA, correcting orthogonal signals in the OPLS-DA analysis to obtain a cigarette classification recognition model and the recognition accuracy rate of the correction set, testing the cigarette classification recognition model through a test set, and obtaining the recognition accuracy rate corresponding to the test set.
And S105, determining a spectrum preprocessing scheme meeting preset requirements according to the identification accuracy of the correction set and the identification accuracy of the test set, and acquiring a cigarette classification identification model corresponding to the spectrum preprocessing scheme meeting the preset requirements.
Specifically, the spectrum preprocessing scheme meeting the preset requirement is determined according to the identification accuracy of the correction set and the identification accuracy of the test set obtained by the OPLS-DA analysis, and according to the identification accuracy of the correction set and the identification accuracy of the test set, where the spectrum preprocessing scheme meeting the preset requirement is, for example, the spectrum preprocessing scheme meeting the preset requirement when the identification accuracy of the correction set and the identification accuracy of the test set are the maximum, and after the spectrum preprocessing scheme meeting the preset requirement is obtained, the corresponding cigarette classification recognition model is determined.
According to the construction method of the cigarette classification and identification model based on the near infrared spectrum and the OPLS-DA, provided by the embodiment of the invention, a plurality of types of samples to be detected are selected, and the samples are maintained according to the preset maintenance steps; the method comprises the steps of carrying out spectrum scanning on a sample to obtain a near infrared spectrum of the sample, dividing the near infrared spectrum into a correction set and a test set, processing the near infrared spectrum through different types of spectrum preprocessing schemes, carrying out OPLS-DA analysis on the correction set to obtain a cigarette classification recognition model and the recognition accuracy of the correction set, bringing the test set into the cigarette classification recognition model to obtain the recognition accuracy of the test set, determining the spectrum preprocessing scheme meeting preset requirements according to the recognition accuracy of the correction set and the recognition accuracy of the test set, and obtaining the cigarette classification recognition model corresponding to the spectrum preprocessing scheme meeting the preset requirements.
In another embodiment, a method for constructing a cigarette classification and identification model based on near infrared spectrum and OPLS-DA is provided, which comprises the following steps:
1) randomly selecting finished cut tobacco on 5 brands (JS, RL, JD, RH and DC are respectively used for representing different brands) of tobacco manufacturing lines of cigarettes as a research object, collecting finished cut tobacco samples at a certain fixed position after the flavoring process of the cut tobacco lines under the condition of normal working conditions, sampling 30 times in each batch, wherein the sampling interval time is about 90 s each time, and the sampling mass is about 200 g each time, and placing the samples in a sealed bag; each brand takes only one batch of samples per month as a sample for near infrared spectrometry. The JS mark takes 60 finished tobacco shred samples in 2 batches, and the RL, JD, RH and DC marks take 1 batch of samples respectively, which are 30 finished tobacco shred samples respectively, and 180 finished tobacco shred samples in total.
Drying each finished tobacco shred sample at low temperature (25-30 ℃), controlling the water content of the finished tobacco shred sample to be 10% -12%, cooling to room temperature (20 +/-2 ℃), balancing in a constant temperature and humidity box (22 +/-2 ℃, 60 +/-5 RH) for 48 h, and then putting into a sealing bag for low-temperature dark storage.
2) In order to ensure the stability of the measurement of the finished tobacco shred sample, the relative humidity of a laboratory is controlled between 20% and 80%, the temperature is controlled between 18 ℃ and 26 ℃, and before the spectrum scanning of the finished tobacco shred sample, a near infrared spectrum instrument is started to preheat for not less than 1 hour. The main working parameters of the near infrared spectrum instrument are set as follows: the spectrum scanning range is 10000-4000 cm < -1 >; the scanning resolution is 8 cm < -1 >; the number of scans was 64. And directly and sequentially placing finished tobacco shred samples in a rotating cup to rotate and collect near-infrared diffuse reflection spectrums, collecting spectrums for 3 times by each finished tobacco shred sample in order to eliminate the influence of non-uniformity and other environmental factors of the finished tobacco shred samples, and taking the average spectrums as final spectrum data of the finished tobacco shred samples. And sequentially acquiring the near infrared spectrums of 180 finished tobacco shred samples of JS, RL, JD, RH and DC grades taken from the production line.
3) Each grade of finished tobacco shred sample is divided into a sample set by adopting a random method, namely the near infrared spectrum of each grade of finished tobacco shred sample is randomly divided into a correction set and a test set according to the proportion of 2:1, and the correction sets selected by each grade are combined into a total correction set of tobacco shred samples (total 120 tobacco shred samples, wherein JS is 40 samples, and other grades are 20 samples respectively) for correcting the tobacco shred classification model; and combining the test sets of each grade of finished tobacco shreds into a total test set of tobacco shred samples (60 tobacco shred samples, wherein 20 samples of the JS grade, and 10 samples of other grades) for verifying the tobacco shred classification model.
And then preprocessing the tobacco shred spectrum, namely weakening or eliminating the influence of interference factors on the tobacco shred spectrum by adopting a mathematical method and extracting useful information so as to improve the accuracy and reliability of the analysis of the tobacco shred classification and discrimination model. The spectrum is preprocessed by a preprocessing method combining a Multivariate Scattering Correction (MSC), a standard normal variable transformation (SNV), a First Differential (FD), a Second Differential (SD), a Savitzky-Golay filter (SG) and an algorithm, so that the influence of factors such as tobacco physical structure, environmental noise, optical path change, characteristic tobacco nonuniformity and the like is eliminated.
4) And decomposing the tobacco shred near infrared spectrum data set X into two parts, namely an orthogonal variable and a non-orthogonal variable of a tobacco shred dependent variable Y by an orthogonal partial least squares discriminant analysis method and utilizing the idea of orthogonal signal correction, removing the orthogonal variable, and then performing PLS-DA analysis on the corrected X data to obtain better pattern recognition accuracy.
In another embodiment, the classification and identification results of the OPLS-DA model obtained by different spectrum preprocessing methods can be as shown in table 1:
TABLE 1
The four columns in the table 1 are respectively the near infrared spectrum pretreatment type, the sample, the correction set accuracy and the test set accuracy, and the classification identification accuracy of the correction set except for the SNV and MSC pretreatment is respectively 99.2-100.0%; for the test set, particularly the MSC + SD preprocessing method, the classification and identification accuracy is 100.0%, and finished cut tobaccos with different brands can be completely and correctly identified. The result shows that the model established by the OPLS-DA method can well classify and identify the finished tobacco shreds with 5 brands.
TABLE 2
In addition, as shown in table 2, after the near infrared spectra of 120 finished tobacco samples in the calibration set are subjected to MSC + SD pretreatment, an OPLS-DA model is constructed, and the model is verified by a cross verification method. R increases as the number of predicted principal components and orthogonal principal components to be selected increases2X（cum），R2Y (cum) and R2The value of Y (cum) will gradually increase, and when 4 prediction principal components and 5 orthogonal principal components are screened, the model will fit the index R to the independent variable2X (cum) = 0.485, which indicates that the interpretability of variation of near infrared spectrum variables of cut tobacco by 5 main components is 48.5% (wherein the main component is predicted to be 25.3%, and the orthogonal main component is 23.2%); fitting index R to dependent variable2Y (cum) = 0.907, and the result shows that the interpretability of 4 predicted principal components in the model to the variable variation of different-grade categorical variables is 90.7%, and the model has better generalized interpretability(ii) a Model prediction index Q2(cum) = 0.748, which shows that the model has the prediction capability of 74.8% on finished tobacco shred samples of different grades, and has better prediction capability. The results in table 1 show that when 4 predicted principal components and 5 orthogonal principal components are screened, the classification recognition accuracy of the correction set and the test set is 100.0%, which indicates that the constructed OPLS-DA model has good stability and prediction capability and is stable and reliable.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (7)
1. A method for constructing a cigarette classification recognition model based on near infrared spectrum and OPLS-DA is characterized by comprising the following steps:
selecting a plurality of types of samples to be detected, and maintaining the samples according to a preset maintenance step;
performing spectral scanning on the sample to obtain a near infrared spectrum of the sample;
dividing the near infrared spectrum into a correction set and a test set, and processing the near infrared spectrum by different spectrum pretreatment schemes;
carrying out OPLS-DA analysis on the correction set to obtain a cigarette classification recognition model and the recognition accuracy of the correction set, and bringing the test set into the cigarette classification recognition model to obtain the recognition accuracy of the test set;
and determining a spectrum preprocessing scheme meeting preset requirements according to the identification accuracy of the correction set and the identification accuracy of the test set, and acquiring a cigarette classification identification model corresponding to the spectrum preprocessing scheme meeting the preset requirements.
2. The method for constructing the cigarette classification and identification model based on the near infrared spectrum and the OPLS-DA according to claim 1, wherein the spectrum preprocessing scheme comprises:
multivariate scattering correction, standard normal variable transformation, first order differentiation, second order differentiation, Savitzky-Golay filter and algorithm combination.
3. The method for constructing the cigarette classification and identification model based on the near infrared spectrum and the OPLS-DA according to claim 1, wherein the spectrum preprocessing scheme meeting the preset requirements is determined according to the identification accuracy of the correction set and the identification accuracy of the test set, and comprises the following steps:
and calculating the sum of the identification accuracy of the correction set and the identification accuracy of the test set, and acquiring the spectrum preprocessing scheme with the maximum sum.
4. The method for constructing the cigarette classification and identification model based on the near infrared spectrum and the OPLS-DA as claimed in claim 1, wherein the method further comprises:
and dividing the near infrared spectrum into a correction set and a test set according to the ratio of 2 to 1 of the correction set to the test set.
5. The method for constructing the cigarette classification and identification model based on the near infrared spectrum and the OPLS-DA according to claim 1, wherein the sample is maintained according to preset maintenance steps, and the method comprises the following steps:
and controlling the temperature and the water content of the sample within corresponding preset ranges, and controlling the humidity and the temperature of the environment corresponding to the sample within the preset ranges.
6. The method for constructing the cigarette classification and identification model based on the near infrared spectrum and the OPLS-DA according to claim 1, wherein the step of performing spectral scanning on the sample to obtain the near infrared spectrum of the sample comprises the following steps:
and carrying out N times of spectral scanning on the sample, and taking the average value of the results of the N times of spectral scanning as the near infrared spectrum of the sample, wherein N is a natural number greater than 1.
7. The method for constructing a cigarette classification and identification model based on near infrared spectrum and OPLS-DA according to claim 1, wherein the spectral scanning of the sample comprises:
the scanning range of the spectrum is set to 10000 to 4000cm-1Scanning resolution was set to 8 cm-1And setting the scanning times to be 64 times, and putting the sample into a rotating cup to rotate and collect the near infrared diffuse reflection spectrum to obtain the spectrum scanning result of the sample.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011102013.1A CN112179870A (en) | 2020-10-15 | 2020-10-15 | Cigarette classification recognition model construction method based on near infrared spectrum and OPLS-DA |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011102013.1A CN112179870A (en) | 2020-10-15 | 2020-10-15 | Cigarette classification recognition model construction method based on near infrared spectrum and OPLS-DA |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112179870A true CN112179870A (en) | 2021-01-05 |
Family
ID=73950363
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011102013.1A Pending CN112179870A (en) | 2020-10-15 | 2020-10-15 | Cigarette classification recognition model construction method based on near infrared spectrum and OPLS-DA |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112179870A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114946485B (en) * | 2022-05-13 | 2023-07-07 | 广西壮族自治区林业科学研究院 | Method for prejudging eucalyptus iron deficiency yellow disease based on VNIR and OPLS-DA |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101285768A (en) * | 2008-05-29 | 2008-10-15 | 红云烟草(集团)有限责任公司 | Method for damage-free discrimination for genuine-fake cigarette by near-infrared spectral analysis technology |
| CN102338780A (en) * | 2010-07-28 | 2012-02-01 | 中国科学院大连化学物理研究所 | Method for discriminating cigarette brands |
| CN104596981A (en) * | 2015-01-30 | 2015-05-06 | 云南中烟工业有限责任公司 | Method for distinguishing paper process reconstituted tobacco products via near infrared spectroscopy in combination with PLS-DA |
| CN109655532A (en) * | 2017-10-12 | 2019-04-19 | 贵州中烟工业有限责任公司 | A kind of method of pair of cigarette taxonomic history |
-
2020
- 2020-10-15 CN CN202011102013.1A patent/CN112179870A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101285768A (en) * | 2008-05-29 | 2008-10-15 | 红云烟草(集团)有限责任公司 | Method for damage-free discrimination for genuine-fake cigarette by near-infrared spectral analysis technology |
| CN102338780A (en) * | 2010-07-28 | 2012-02-01 | 中国科学院大连化学物理研究所 | Method for discriminating cigarette brands |
| CN104596981A (en) * | 2015-01-30 | 2015-05-06 | 云南中烟工业有限责任公司 | Method for distinguishing paper process reconstituted tobacco products via near infrared spectroscopy in combination with PLS-DA |
| CN109655532A (en) * | 2017-10-12 | 2019-04-19 | 贵州中烟工业有限责任公司 | A kind of method of pair of cigarette taxonomic history |
Non-Patent Citations (1)
| Title |
|---|
| 王俊等: "基于化学指标的烟叶产区正交偏最小二乘判别分析", 《中国烟草科学》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114946485B (en) * | 2022-05-13 | 2023-07-07 | 广西壮族自治区林业科学研究院 | Method for prejudging eucalyptus iron deficiency yellow disease based on VNIR and OPLS-DA |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105928901B (en) | A kind of near-infrared quantitative model construction method that qualitative, quantitative combines | |
| CN108181263B (en) | Tobacco leaf position feature extraction and discrimination method based on near infrared spectrum | |
| CN105891147A (en) | Near infrared spectrum information extraction method based on canonical correlation coefficients | |
| CN104990895B (en) | A kind of near infrared spectrum signal standards normal state bearing calibration based on regional area | |
| CN112801300A (en) | Method, device and computer readable medium for predicting aroma amount of tobacco sample | |
| CN111257277B (en) | Tobacco leaf similarity judgment method based on near infrared spectrum technology | |
| CN110967313A (en) | Near infrared spectrum prediction modeling method for nicotine content in tobacco tar of electronic cigarette and application | |
| CN112179870A (en) | Cigarette classification recognition model construction method based on near infrared spectrum and OPLS-DA | |
| CN106124440A (en) | A kind of quality evaluating method of volume tobacco aromatics using | |
| CN110672578A (en) | Model universality and stability verification method for polar component detection of frying oil | |
| CN113030007B (en) | Method for rapidly testing quality stability of tobacco essence based on similarity learning algorithm | |
| CN114088661A (en) | Online prediction method for chemical components in tobacco leaf curing process based on transfer learning and near infrared spectrum | |
| CN109358022A (en) | A kind of method of the quick-fried pearl type of quick discrimination cigarette | |
| CN102680427A (en) | Method for identifying surface fragrance quality of cigarettes by near infrared spectral analysis technology | |
| CN108120694B (en) | Multi-element correction method and system for chemical component analysis of sun-cured red tobacco | |
| CN110186870B (en) | Method for distinguishing fresh tea leaf producing area of Enshi Yulu tea by extreme learning machine spectrum model | |
| CN113984708B (en) | Maintenance method and device for chemical index detection model | |
| CN115824996A (en) | Tobacco conventional chemical component general model modeling method based on near infrared spectrum | |
| CN102706811A (en) | Method for identifying sugar quality of cigarette by utilizing near infrared light spectral analysis technique | |
| US11525774B2 (en) | Sensory evaluation method for spectral data of mainstream smoke | |
| CN110320174B (en) | Method for rapidly predicting time for smoldering yellow tea by applying polynomial net structure artificial neural network | |
| CN110160985B (en) | Method for detecting nicotine content by adjusting online chemical component detector | |
| CN107238557A (en) | A kind of method of utilization near infrared spectroscopy quick detection calcium carbonate particle diameter distribution | |
| CN113029980B (en) | Rapid nondestructive testing method for stability of sensory quality of tobacco sheet | |
| CN106568741B (en) | A kind of method that near infrared spectrum quickly determines the fresh tea leaves place of production |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210105 |