CN114166794A - Method, medium and equipment for predicting quality of tobacco lamina - Google Patents
Method, medium and equipment for predicting quality of tobacco lamina Download PDFInfo
- Publication number
- CN114166794A CN114166794A CN202111321480.8A CN202111321480A CN114166794A CN 114166794 A CN114166794 A CN 114166794A CN 202111321480 A CN202111321480 A CN 202111321480A CN 114166794 A CN114166794 A CN 114166794A
- Authority
- CN
- China
- Prior art keywords
- tobacco
- quality
- instrument
- near infrared
- lamina
- 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.)
- Granted
Links
- 241000208125 Nicotiana Species 0.000 title claims abstract description 131
- 235000002637 Nicotiana tabacum Nutrition 0.000 title claims abstract description 131
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000001228 spectrum Methods 0.000 claims abstract description 37
- 238000002329 infrared spectrum Methods 0.000 claims abstract description 26
- 238000006243 chemical reaction Methods 0.000 claims abstract description 9
- 238000013441 quality evaluation Methods 0.000 claims abstract description 6
- 238000011156 evaluation Methods 0.000 claims description 12
- 238000012937 correction Methods 0.000 claims description 10
- 238000005070 sampling Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 8
- 238000002790 cross-validation Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 5
- 238000013461 design Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000009499 grossing Methods 0.000 claims description 2
- 238000012827 research and development Methods 0.000 claims description 2
- 230000003595 spectral effect Effects 0.000 claims description 2
- 239000000779 smoke Substances 0.000 claims 1
- 235000019504 cigarettes Nutrition 0.000 description 8
- 241000196324 Embryophyta Species 0.000 description 4
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 229910052739 hydrogen Inorganic materials 0.000 description 2
- 239000001257 hydrogen Substances 0.000 description 2
- 239000000843 powder Substances 0.000 description 2
- 230000001953 sensory effect Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 229930013930 alkaloid Natural products 0.000 description 1
- 150000003797 alkaloid derivatives Chemical class 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000000227 grinding Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 229930014626 natural product Natural products 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 229920000642 polymer Polymers 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 238000007873 sieving Methods 0.000 description 1
- 235000019505 tobacco product Nutrition 0.000 description 1
- 238000012795 verification 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
- G01N21/359—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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- 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)
- Manufacture Of Tobacco Products (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides a method for predicting the quality of tobacco flakes, which comprises the following steps: 1) acquiring the near infrared spectrum data of the instrument A in the past year and corresponding quality evaluation data; 2) the instrument A and an instrument B of a redrying processing center respectively collect near infrared spectra of the same batch of standard samples, and a spectrum conversion model of the instrument A and the instrument B of the redrying processing center is suggested based on the near infrared spectrum data; 3) according to the spectrum conversion model obtained in the step 2), the step 1) is carried out, and a tobacco lamina quality prediction model is suggested according to the converted near infrared spectrum data and the quality evaluation data in the step 1); 4) collecting corresponding near infrared spectrum in an instrument B of the raw tobacco to be processed, and predicting the quality of the batch according to the tobacco sheet quality prediction model obtained in the step 3); 5) weighting and calculating the predicted value of the quality of each module tobacco lamina produced according to the proportion of each grade in the original tobacco formula list; 6) and correcting the predicted value of each tobacco sheet to form a final predicted quality value.
Description
Technical Field
The invention belongs to the field of agricultural product (tobacco leaf) processing, and particularly relates to a method, a system, a medium and equipment for predicting the quality of a processed finished product (tobacco lamina) before processing.
Background
The quality of cigarette products is the basis of the healthy development of cigarette enterprises, and the stability of the quality of the products mainly depends on the stability of the quality of tobacco leaf raw materials. The tobacco shred in the cigarette is formed by mixing (formulating) a plurality of tobacco sheet modules according to a proportion. Each tobacco slice module is formed by matching tobacco leaves in different producing areas (generally different cities, counties and villages), different varieties and different grades according to a certain proportion and then threshing and redrying the tobacco leaves.
At present, the design and evaluation of a tobacco lamina module are completed by depending on the working experience of a formulator and combining sensory evaluation, and 2 problems exist: firstly, raw tobacco of each grade used for designing and evaluating the tobacco flakes is obtained by sampling from a large batch of samples, the sampling representativeness can not be guaranteed, and the problem of workload can not be solved by sampling in multiple batches; after the design of the tobacco flake formula is finished, the tobacco flake is produced and processed in a redrying workshop, and the evaluation of the tobacco flake quality is finished through the sensory evaluation of a formulator at present. If the quality of the tobacco lamina does not meet the requirements or differs significantly from what is expected, it can cause degradation of the quality of the tobacco lamina and a corresponding economic loss.
For the evaluation of the quality of the tobacco flakes, a plurality of working bases for judgment through technologies such as chemical indexes and near infrared spectrums exist. The near infrared spectrum is sensitive to the hydrogen-containing groups such as C-H, O-H, N-H and the like, and is suitable for analyzing related components which are directly or indirectly related to the hydrogen-containing groups in natural products. The main components of total sugar, reducing sugar, total plant alkaloid, total nitrogen and the like in the tobacco can be predicted through the near infrared spectrum, and the difference of the main chemical components is closely related to the quality of the tobacco leaves, so that the technical rationality is realized by utilizing the near infrared spectrum to judge the quality of the tobacco leaves.
The near infrared technology has several key problems in the application of tobacco lamina quality prediction: firstly, the redrying plant is limited by resources, talents, funds and the like, only has data acquisition capacity, and does not have modeling and analyzing capacity. And secondly, even if a model is established, the prediction of the model needs to be based on the tobacco flake real object, and when the situation that the quality difference with the expected quality is large occurs, the problem of economic loss caused by degradation cannot be solved.
Disclosure of Invention
The invention provides a method, a system, a medium and equipment for predicting the quality of tobacco flakes, aiming at pre-judging the quality of tobacco flakes produced by planning through a model transfer algorithm based on near-infrared data sampled from raw tobacco and a tobacco flake recipe list before the tobacco flakes are processed:
in order to achieve the above object, according to a first aspect, the present invention provides a method for predicting a quality of a tobacco lamina, the method comprising the steps of:
1) acquiring the near infrared spectrum data of the instrument A in the past year and corresponding quality evaluation data;
2) the instrument A and an instrument B of a redrying processing center respectively collect near infrared spectra of the same batch of standard samples, and a spectrum conversion model of the instrument A and the instrument B of the redrying processing center is suggested based on the near infrared spectrum data;
3) converting the near infrared spectrum data of the instrument A in the step 1) into the near infrared spectrum data of the instrument B according to the spectrum conversion model obtained in the step 2), and recommending a sheet tobacco quality prediction model according to the converted near infrared spectrum data and the quality evaluation data in the step 1);
4) sampling the raw tobacco to be processed according to the formula design, collecting a corresponding near infrared spectrum in an instrument B, and predicting the quality of the batch according to the tobacco sheet quality prediction model obtained in the step 3);
5) weighting and calculating the predicted value of the quality of each module tobacco lamina produced according to the proportion of each grade in the original tobacco formula list;
6) and correcting the predicted value of each tobacco sheet to form a final predicted quality value.
In some embodiments, instrument a is an analytical instrument with years of data accumulation in research and development centers, technical centers. If the field instrument of the redrying plant meets the data accumulation requirement, a model can be directly established through the instrument B.
In some embodiments, the instrument a spectrum is converted to an instrument B spectrum using a piece-wise direct normalization (PDS) method.
In some embodiments, the near infrared spectrum obtained in step 2) is pre-processed to reduce scattering interference in the sample; the processing means includes one or more of first derivative, second derivative, vector normalization, multivariate signal correction, standard normal correction, and spectral smoothing.
In some embodiments, the modeling method in step 3) is partial least squares, 5-fold cross validation is adopted, and the number of latent variables of the model is selected according to the error of the cross validation.
In some embodiments, the range of raw tobacco sample samples in step 4) is to cover all of the origins, grades, varieties and other factors involved in the recipe. If a plurality of sampling data exist in the tobacco leaves of the same producing area, grade and variety, the average spectrum of the plurality of data is used for subsequent calculation.
In some embodiments, the method for predicting the quality of the tobacco lamina in the step 5) is
Wherein y is the predicted value of the quality of the tobacco lamina. bh,yhRespectively the proportion of raw tobacco contained in the tobacco sheet and the predicted value of the quality of the raw tobacco.
In some embodiments, the method for correcting the predicted value in step 6) is
Wherein y isiIs the predicted value of the ith tobacco lamina,
for the ith tobacco lamina evaluation value, the correction is to eliminate the homogeneous deviation in the model transfer between instruments and the prediction of the tobacco lamina-raw tobacco model.
In some embodiments, the obtaining of the tobacco lamina quality label in step 1) comprises the following: the quality score is obtained by evaluation according to the specifications of a YC/T138-; the quality score is given in a mode that the application grade of the tobacco flakes in the cigarettes, the cost price of the tobacco flakes and the like can be objectively calculated.
In a second aspect, the present invention provides a medium having a computer program stored thereon, wherein the computer program is executed by a processor to perform the above-mentioned method for predicting quality of a tobacco lamina.
In a third aspect, the present invention provides an apparatus comprising a processor and a memory; the memory is used for storing a computer program, and the processor is used for executing the computer program stored by the memory so as to enable the device to execute the tobacco lamina quality prediction method.
Compared with the prior art, the invention has the following beneficial effects:
the invention realizes the prediction of the quality of the tobacco flakes before the tobacco flakes are processed; the method solves the problem that a near-infrared instrument in a production workshop has no prediction model in a model transfer mode; the quality label obtained by prediction is given by industry standard evaluation or by modes of objectively accounting the application grade of the tobacco flakes in cigarettes, the cost price of the tobacco flakes and the like.
Drawings
FIG. 1 is a flow chart of a method provided by the present invention;
FIG. 2 is a spectrum of instrument A according to an embodiment of the present invention;
FIG. 3 is a spectrum of instrument B in an example of the invention;
FIG. 4 is an instrument difference spectrum of instrument A and instrument B in an embodiment of the present invention;
FIG. 5 is a spectrum of instrument A according to an embodiment of the present invention;
FIG. 6 shows the conversion of the spectrum of instrument A to the spectrum of instrument B in accordance with an embodiment of the present invention;
FIG. 7 is a difference spectrum of the transformed spectrum of FIG. 6 and instrument B in accordance with an embodiment of the present invention;
FIG. 8 is a cross validation error curve for a tobacco lamina quality prediction model;
FIG. 9 is a graph of regression coefficients for the quality model;
FIG. 10 compares the quality score predicted by raw tobacco with the actual score of lamina (before correction);
in fig. 11, the quality score predicted from raw tobacco is compared with the actual score of lamina (after correction).
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below, and the scope of the present invention is not limited by the embodiments, and is determined by the claims. 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.
Example 1
A method for predicting the quality of a tobacco sheet, as shown in fig. 1, the method comprising the steps of:
step 1) taking the quality prediction of the tobacco lamina of the redrying processing center in a certain place in Yunnan as an example; selecting 40 tobacco leaf samples of different counties and cities and grades, sampling, preparing the samples into powder samples according to tobacco industry standard YC/T31-1996 tobacco and tobacco product sample preparation and moisture determination oven method (placing the tobacco leaves in an oven, drying for 4h at 40 ℃, grinding by a cyclone mill (FOSS) and sieving by a 40-mesh sieve), sealing and balancing.
Step 2) respectively collecting spectra of the sample powder in a near-infrared instrument A at the technical center and a near-infrared instrument B at a redrying plant, and converting the spectrum of the instrument A into the spectrum of the instrument B by using a PDS (polymer dispersed system) method; wherein, the window width parameter of the PDS is set to 1;
FIGS. 2-4 illustrate the spectra of instrument A, instrument B and the difference spectrum between the two; after the conversion, fig. 5-7 illustrate the spectrum of the instrument a, the spectrum of the instrument a converted into the spectrum of the instrument B, and the difference spectrum between the converted spectrum and the instrument B in the embodiment, and it can be found that the spectrum of the instrument a converted into the instrument B overlaps with the actually measured spectrum of the instrument B, and the conversion is proved to be achieved;
step 3) converting the spectrum of 132 samples in total accumulated historical tobacco flakes in the instrument A into the spectrum of the instrument B; the quality label of the tobacco lamina is determined by combining tobacco lamina evaluation with the grade grading of the subsequently applied cigarette brand, and the distribution range of the quality score is 6-8.
And 4) establishing a relation between the near infrared spectrum and the quality score by using partial least squares, adopting 5-fold cross validation, and selecting the number of latent variables of the model according to cross validation errors. As shown in fig. 4, the number of latent variables of the built model is 8. The regression coefficients of the model are shown in FIG. 5.
And 5) collecting the spectrum of the raw tobacco used in each tobacco lamina module in the same way as the tobacco lamina sampling before the tobacco season processing starts. If a plurality of samples of raw tobacco of the same producing area, grade and variety exist, the average spectrum is used as the spectrum of the sample.
Step 6) for a given tobacco flake formula, substituting each grade of raw tobacco in the formula list into the model in the step 4) to obtain a quality prediction score; the quality prediction of the tobacco slice module is divided into the prediction scores of all the raw tobacco grades and added according to the proportion of the formula.
The method for predicting the quality of the tobacco lamina comprises
Wherein y is the predicted value of the quality of the tobacco lamina. bh,yhRespectively the proportion of raw tobacco contained in the tobacco sheet and the predicted value of the quality of the raw tobacco.
Table 1 shows the recipe list of the YN-CKF module and the grade, quantity and model predicted value of raw tobacco contained in the recipe list. The quality predicted value of the module can be obtained by adding the ratio and the raw tobacco quality predicted value, and the quality predicted value of YN-CKF is as follows: 6.84.
calculating the prediction results of all the tobacco strips in sequence: the verification data includes two years 2019, 2020. Wherein, including 15 cigarette chips modules in 2019, raw tobacco sample number is 1047, including 12 cigarette chips in 2020, raw tobacco sample number is 945.
The predicted value of the quality of the tobacco lamina calculated from the raw tobacco is shown in table 1. And (4) simultaneously, after the processing of the tobacco sheet module is finished, evaluating the quality of the tobacco sheet according to the same mode in the step (3) to obtain an actual quality score value. A comparison of the two is shown in FIG. 10. The correlation coefficient between the predicted result and the actual result was 0.82 as calculated from table 1.
TABLE 1 formulation of YN-CKF modules and raw tobacco quality prediction scores
| Tobacco flake code | Raw tobacco producing area | County area | Cured tobacco variety | After selection grade | Number of | Ratio of | Quality score |
| YN-CKF | JQ | LN | Cloud 87 | |
2000 | 5.2％ | 7.16 |
| YN-CKF | JQ | LN | Cloud 87 | C2FA1 | 2761.6 | 7.2％ | 7.00 |
| YN-CKF | JQ | LM | Cloud 87 | |
2000 | 5.2％ | 7.10 |
| YN-CKF | JQ | LM | Cloud 87 | C2FC3 | 3242.64 | 8.4％ | 7.01 |
| YN-CKF | JQ | LM | Cloud 87 | C3FA1 | 2200 | 5.7％ | 7.02 |
| YN-CKF | JQ | LP | Cloud 87 | C1FC3 | 4197.28 | 10.9％ | 6.67 |
| YN-CKF | JQ | LP | Cloud 87 | |
5000 | 13.0％ | 6.61 |
| YN-CKF | JQ | LP | Cloud 87 | C1FA1 | 1700.04 | 4.4％ | 6.70 |
| YN-CKF | DO | DJ | Cloud 87 | |
4000 | 10.4％ | 6.50 |
| YN-CKF | DO | DH | Cloud 87 | C1FA1 | 1500 | 3.9％ | 7.04 |
| YN-CKF | DO | DH | Cloud 87 | |
1000 | 2.6％ | 7.16 |
| YN-CKF | DO | DN | Cloud 87 | C2FC3 | 715.42 | 1.9％ | 6.85 |
| YN-CKF | NI | XD | Cloud 87 | C2FC3 | 1688.76 | 4.4％ | 7.01 |
| YN-CKF | NI | XD | Cloud 87 | C2FA1 | 606.84 | 1.6％ | 6.89 |
| YN-CKF | NI | XD | Cloud 87 | C1FC3 | 2817.62 | 7.3％ | 6.90 |
| YN-CKF | NI | XD | Cloud 87 | C1FA1 | 933.78 | 2.4％ | 6.82 |
| YN-CKF | GH | SJ | Cloud 87 | C3FA1 | 2095.42 | 5.4％ | 6.70 |
And 7) because the tobacco flakes are formed by threshing and redrying raw tobacco, the characteristics of the tobacco flakes are possibly different from those of the raw tobacco. The predicted data is corrected by the method as described above
Wherein yi is the predicted value of the ith tobacco lamina,
the aim of correction is to eliminate the homogeneous deviation in model transfer between instruments and the prediction of a tobacco lamina-raw tobacco model for the evaluation value of the ith tobacco lamina; here, the corrected value is calculated to be-0.21, the corrected result is shown in Table 2 and FIG. 11, and the corrected predicted value corresponds to the actual result as compared with FIG. 10 before the correction.
TABLE 2 tobacco lamina quality prediction value and actual evaluation value based on raw tobacco
Claims (10)
1. A method for predicting the quality of tobacco lamina, characterized in that the method comprises the following steps:
1) acquiring the near infrared spectrum data of the instrument A in the past year and corresponding quality evaluation data;
2) the instrument A and an instrument B of a redrying processing center respectively collect near infrared spectra of the same batch of standard samples, and a spectrum conversion model of the instrument A and the instrument B of the redrying processing center is suggested based on the near infrared spectrum data;
3) converting the near infrared spectrum data of the instrument A in the step 1) into the near infrared spectrum data of the instrument B according to the spectrum conversion model obtained in the step 2), and recommending a sheet tobacco quality prediction model according to the converted near infrared spectrum data and the quality evaluation data in the step 1);
4) sampling the raw tobacco to be processed according to the formula design, collecting a corresponding near infrared spectrum in an instrument B, and predicting the quality of the batch according to the tobacco sheet quality prediction model obtained in the step 3);
5) weighting and calculating the predicted value of the quality of each module tobacco lamina produced according to the proportion of each grade in the original tobacco formula list;
6) and correcting the predicted value of each tobacco sheet to form a final predicted quality value.
2. The method of claim 1, wherein instrument a is an analytical instrument with years of data accumulation in research and development centers, technical centers.
3. The method of claim 1, wherein instrument a spectra are converted to instrument B spectra using a Piecewise direct normalization (PDS) method.
4. The method according to claim 1, wherein the near infrared spectrum obtained in step 2) is pre-processed to reduce scattering interference in the sample; the processing means includes one or more of first derivative, second derivative, vector normalization, multivariate signal correction, standard normal correction, and spectral smoothing.
5. The method as claimed in claim 1, wherein the modeling method in step 3) is partial least squares, 5-fold cross validation is adopted, and the number of latent variables of the model is selected according to the error of the cross validation.
6. The method of claim 1, wherein the range of raw smoke sample in step 4) is to cover all of the origin, grade, variety and other factors involved in the recipe. If a plurality of sampling data exist in the tobacco leaves of the same producing area, grade and variety, the average spectrum of the plurality of data is used for subsequent calculation.
7. The method according to claim 1, wherein the method for predicting the quality of the tobacco lamina in the step 5) is
Wherein y is the predicted value of the quality of the tobacco lamina. bh,yhRespectively the proportion of raw tobacco contained in the tobacco sheet and the predicted value of the quality of the raw tobacco.
8. The method according to claim 1, wherein the predicted value correction method in step 6) is
Wherein y isiIs the predicted value of the ith tobacco lamina,
the evaluation value of the ith tobacco lamina is used for eliminating homogeneous deviation in model transfer between instruments and prediction of a tobacco lamina-raw tobacco model.
9. A medium having a computer program stored thereon, wherein the computer program is executed by a processor to perform the method of predicting the quality of a tobacco lamina as claimed in any one of claims 1 to 8.
10. An apparatus, comprising: a processor and a memory; the memory is used for storing a computer program, and the processor is used for executing the computer program stored by the memory to enable the device to execute the tobacco lamina quality prediction method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111321480.8A CN114166794B (en) | 2021-11-09 | 2021-11-09 | Method, medium and equipment for predicting tobacco flake quality |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111321480.8A CN114166794B (en) | 2021-11-09 | 2021-11-09 | Method, medium and equipment for predicting tobacco flake quality |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114166794A true CN114166794A (en) | 2022-03-11 |
| CN114166794B CN114166794B (en) | 2024-04-09 |
Family
ID=80478463
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111321480.8A Active CN114166794B (en) | 2021-11-09 | 2021-11-09 | Method, medium and equipment for predicting tobacco flake quality |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114166794B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009014700A (en) * | 2007-01-31 | 2009-01-22 | Osaka Univ | Green tea quality prediction method |
| CN101995388A (en) * | 2009-08-26 | 2011-03-30 | 北京凯元盛世科技发展有限责任公司 | Near infrared quality control analysis method and system of tobacco |
| CN111160425A (en) * | 2019-12-17 | 2020-05-15 | 湖北中烟工业有限责任公司 | Neural network-based flue-cured tobacco comfort classification evaluation method |
| CN111815149A (en) * | 2020-07-03 | 2020-10-23 | 云南省烟草质量监督检测站 | Comprehensive evaluation method of flue-cured tobacco grade quality evaluation index system |
| CN113158575A (en) * | 2021-04-29 | 2021-07-23 | 晶格码（青岛）智能科技有限公司 | Method for transferring online near-infrared spectrum model of assumed standard sample |
-
2021
- 2021-11-09 CN CN202111321480.8A patent/CN114166794B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009014700A (en) * | 2007-01-31 | 2009-01-22 | Osaka Univ | Green tea quality prediction method |
| CN101995388A (en) * | 2009-08-26 | 2011-03-30 | 北京凯元盛世科技发展有限责任公司 | Near infrared quality control analysis method and system of tobacco |
| CN111160425A (en) * | 2019-12-17 | 2020-05-15 | 湖北中烟工业有限责任公司 | Neural network-based flue-cured tobacco comfort classification evaluation method |
| CN111815149A (en) * | 2020-07-03 | 2020-10-23 | 云南省烟草质量监督检测站 | Comprehensive evaluation method of flue-cured tobacco grade quality evaluation index system |
| CN113158575A (en) * | 2021-04-29 | 2021-07-23 | 晶格码（青岛）智能科技有限公司 | Method for transferring online near-infrared spectrum model of assumed standard sample |
Non-Patent Citations (1)
| Title |
|---|
| 杨凯;刘鹏;王维妙;石超;何利波;: "原烟在线近红外光谱模型转移研究", 中国烟草学报, no. 06 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114166794B (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105181643B (en) | A kind of near infrared detection method of rice quality and application | |
| CN108181263B (en) | Tobacco leaf position feature extraction and discrimination method based on near infrared spectrum | |
| CN109975238B (en) | Substitution method of tobacco leaf and cigarette leaf group formula based on near infrared spectrum | |
| CN104020127B (en) | A kind of near infrared spectrum is utilized quickly to measure the method for inorganic elements in Nicotiana tabacum L. | |
| Sun et al. | Detection of internal qualities of hami melons using hyperspectral imaging technology based on variable selection algorithms | |
| CN104990895B (en) | A kind of near infrared spectrum signal standards normal state bearing calibration based on regional area | |
| CN109540837B (en) | Method for rapidly detecting lignocellulose content of ramie leaves by near infrared | |
| CN107917897A (en) | The method of the special doctor's food multicomponent content of near infrared ray | |
| CN105138834A (en) | Tobacco chemical value quantifying method based on near-infrared spectrum wave number K-means clustering | |
| WO2020248961A1 (en) | Method for selecting spectral wavenumber without reference value | |
| Puttipipatkajorn et al. | Development of calibration models for rapid determination of moisture content in rubber sheets using portable near-infrared spectrometers | |
| Lee et al. | Near-infrared (NIR) spectrometry as a fast and reliable tool for fat and moisture analyses in olives | |
| CN109324016A (en) | A kind of determination method of redried odor type style | |
| CN112945901A (en) | Method for detecting quality of ensiled soybeans based on near infrared spectrum | |
| Liu et al. | Research on the online rapid sensing method of moisture content in famous green tea spreading | |
| CN104316492A (en) | Method for near-infrared spectrum measurement of protein content in potato tuber | |
| CN114295579A (en) | Tobacco mellowing determination method based on near infrared spectrum | |
| CN114166794A (en) | Method, medium and equipment for predicting quality of tobacco lamina | |
| CN105787518B (en) | A kind of near infrared spectrum preprocess method based on kernel projection | |
| CN112179870A (en) | Cigarette classification recognition model construction method based on near infrared spectrum and OPLS-DA | |
| CN113984708B (en) | Maintenance method and device for chemical index detection model | |
| Wang et al. | Monitoring model for predicting maize grain moisture at the filling stage using NIRS and a small sample size | |
| Liu et al. | Building kinetic models to determine moisture content in apples and predicting shelf life based on spectroscopy | |
| CN113740394B (en) | Qualitative identification method of doped bovine coloctrum based on dielectric spectrum technology | |
| CN115327023A (en) | Plant leaf nitrogen content detection method and system |
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 |