CN109298139B - Tobacco leaf quality evaluation method and device - Google Patents
Tobacco leaf quality evaluation method and device Download PDFInfo
- Publication number
- CN109298139B CN109298139B CN201811270215.XA CN201811270215A CN109298139B CN 109298139 B CN109298139 B CN 109298139B CN 201811270215 A CN201811270215 A CN 201811270215A CN 109298139 B CN109298139 B CN 109298139B
- Authority
- CN
- China
- Prior art keywords
- chemical
- indexes
- score
- fitting
- ratio
- 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.)
- Expired - Fee Related
Links
- 235000002637 Nicotiana tabacum Nutrition 0.000 title claims abstract description 111
- 238000013441 quality evaluation Methods 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 44
- 244000061176 Nicotiana tabacum Species 0.000 title 1
- 239000000126 substance Substances 0.000 claims abstract description 168
- 241000208125 Nicotiana Species 0.000 claims abstract description 110
- 238000011156 evaluation Methods 0.000 claims abstract description 91
- 230000001953 sensory effect Effects 0.000 claims abstract description 52
- 238000012216 screening Methods 0.000 claims abstract description 26
- 238000012886 linear function Methods 0.000 claims abstract description 13
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 70
- 230000006870 function Effects 0.000 claims description 55
- 229910052757 nitrogen Inorganic materials 0.000 claims description 40
- SNICXCGAKADSCV-UHFFFAOYSA-N nicotine Natural products CN1CCCC1C1=CC=CN=C1 SNICXCGAKADSCV-UHFFFAOYSA-N 0.000 claims description 29
- SNICXCGAKADSCV-JTQLQIEISA-N (-)-Nicotine Chemical compound CN1CCC[C@H]1C1=CC=CN=C1 SNICXCGAKADSCV-JTQLQIEISA-N 0.000 claims description 25
- 229960002715 nicotine Drugs 0.000 claims description 25
- 238000002329 infrared spectrum Methods 0.000 claims description 18
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 claims description 16
- 239000011591 potassium Substances 0.000 claims description 16
- 229910052700 potassium Inorganic materials 0.000 claims description 16
- NMLQNVRHVSWEGS-UHFFFAOYSA-N [Cl].[K] Chemical compound [Cl].[K] NMLQNVRHVSWEGS-UHFFFAOYSA-N 0.000 claims description 14
- 238000013178 mathematical model Methods 0.000 claims description 11
- 239000000203 mixture Substances 0.000 claims description 11
- VEXZGXHMUGYJMC-UHFFFAOYSA-M Chloride anion Chemical compound [Cl-] VEXZGXHMUGYJMC-UHFFFAOYSA-M 0.000 claims description 8
- ZAMOUSCENKQFHK-UHFFFAOYSA-N Chlorine atom Chemical compound [Cl] ZAMOUSCENKQFHK-UHFFFAOYSA-N 0.000 claims description 8
- 239000000460 chlorine Substances 0.000 claims description 8
- 229910052801 chlorine Inorganic materials 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 230000003595 spectral effect Effects 0.000 claims description 5
- 238000009795 derivation Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- WCUXLLCKKVVCTQ-UHFFFAOYSA-M Potassium chloride Chemical compound [Cl-].[K+] WCUXLLCKKVVCTQ-UHFFFAOYSA-M 0.000 claims 4
- 235000011164 potassium chloride Nutrition 0.000 claims 2
- 239000001103 potassium chloride Substances 0.000 claims 2
- 238000007781 pre-processing Methods 0.000 claims 2
- 238000001303 quality assessment method Methods 0.000 claims 1
- 238000011161 development Methods 0.000 abstract description 5
- 239000002585 base Substances 0.000 description 16
- 238000009826 distribution Methods 0.000 description 8
- 239000002994 raw material Substances 0.000 description 8
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 230000007774 longterm Effects 0.000 description 4
- 239000003513 alkali Substances 0.000 description 3
- 238000012887 quadratic function Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 244000086363 Pterocarpus indicus Species 0.000 description 1
- 235000009984 Pterocarpus indicus Nutrition 0.000 description 1
- 235000019504 cigarettes Nutrition 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000001228 spectrum Methods 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
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0001—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00 by organoleptic means
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Physics & Mathematics (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Manufacture Of Tobacco Products (AREA)
Abstract
The embodiment of the invention provides a tobacco leaf quality evaluation method and device. The method comprises the following steps: obtaining various chemical indexes of tobacco leaves; screening various chemical indexes according to the correlation coefficient of each chemical index and the sensory quality evaluation value to obtain chemical component evaluation indexes; selecting a hook, a quadratic form and a piecewise linear function method respectively for each chemical component evaluation index according to a relevant trend rule to establish a corresponding fitting scoring function so as to obtain a corresponding fitting score; and setting a corresponding weight value for each chemical evaluation index according to the correlation coefficient of the fitting score and the sensory evaluation score, and obtaining a formula for evaluating the tobacco leaf quality in a weighted summation mode. The formula for evaluating the quality of the tobacco leaves, which is acquired by the embodiment of the invention, is more accurate, the quality of the tobacco leaves can be effectively evaluated, and the stable development of the quality of tobacco leaf products is promoted.
Description
Technical Field
The embodiment of the invention relates to the technical field of tobacco processing, in particular to a method and a device for evaluating the quality of tobacco.
Background
The tobacco quality evaluation is the basis of a plurality of tobacco research directions, such as the research of style-specific tobacco leaves, the research of tobacco processing characteristics, the research of module formula means, the research of leaf group replacement technology and the like. The quality of the tobacco leaves is greatly influenced by the variety, the producing area, the position, the growing environment, the climate condition and other factors of the tobacco leaves. At present, the quality of tobacco leaves is mainly evaluated from four aspects of sensory quality, appearance quality, chemical components and physical properties. The sensory quality and the appearance quality are mainly evaluated by professional staff, the steps are complicated, sensory fatigue is easy to generate due to large workload, subjective errors may exist in evaluation results, the repeatability is unstable, the preference and the evaluation score gradient among different evaluation individuals are difficult to be consistent, and large fluctuation of product quality may be caused. Therefore, the quality of the tobacco leaves is evaluated by using the chemical index data of the tobacco leaves, and the problems of unstable quality of finished cigarettes and the like caused by quality mixing of the tobacco leaves can be effectively avoided.
However, in the existing method for evaluating the quality of the tobacco leaves by using the chemical indexes of the tobacco leaves, the final tobacco leaf evaluation equation is not accurate due to incomplete setting and unreasonable screening of the evaluation indexes, and long-term sustainable stable development of the quality of tobacco leaf products is not utilized.
Disclosure of Invention
Embodiments of the present invention provide a method and an apparatus for evaluating tobacco leaf quality, which overcome the above problems or at least partially solve the above problems.
In a first aspect, an embodiment of the present invention provides a method for evaluating tobacco leaf quality, including: obtaining various chemical indexes of tobacco leaves; screening various chemical indexes according to the correlation coefficient of each chemical index and the sensory quality evaluation value to obtain chemical component evaluation indexes; selecting a hook, a quadratic form and a piecewise linear function method respectively for each chemical component evaluation index according to a relevant trend rule to establish a corresponding fitting scoring function so as to obtain a corresponding fitting score; and setting a corresponding weight value for each chemical evaluation index according to the correlation coefficient of the fitting score and the sensory evaluation score, and obtaining a formula for evaluating the tobacco leaf quality in a weighted summation mode.
In a second aspect, an embodiment of the present invention provides a tobacco leaf quality evaluation device, including: the acquisition module is used for acquiring various chemical indexes of the tobacco leaves; the screening module is used for screening various chemical indexes according to the correlation coefficient of each chemical index and the sensory quality evaluation value to obtain chemical component evaluation indexes; the fitting module is used for establishing a corresponding fitting scoring function for each chemical component evaluation index to obtain a corresponding fitting score; and the evaluation module is used for setting a corresponding weight value for each chemical evaluation index according to the correlation coefficient of the fitting score and the sensory evaluation score, and obtaining a formula for evaluating the tobacco quality in a weighted summation mode.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program that is stored in the memory and is executable on the processor, and when the processor executes the computer program, the steps of the tobacco quality evaluation method in the first aspect are implemented.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the tobacco quality evaluation method of the first aspect.
According to the embodiment of the invention, the chemical indexes are screened according to the correlation coefficient of each chemical index and the sensory quality evaluation value by acquiring various chemical indexes of the tobacco leaf raw material, and the chemical component evaluation indexes are reasonably and comprehensively set; and establishing a corresponding fitting scoring function for each chemical component evaluation index to obtain a corresponding fitting score, reasonably setting a corresponding weight value of each chemical evaluation index according to a correlation coefficient of the fitting score and the sensory evaluation score, and finally obtaining a formula for evaluating the quality of the tobacco leaves in a weighted summation mode. The obtained formula for evaluating the quality of the tobacco leaves is more accurate, and the quality of the tobacco leaves can be effectively evaluated, so that the long-term sustainable stable development of the quality of tobacco leaf products is promoted.
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 described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a tobacco leaf quality evaluation method provided by an embodiment of the invention;
FIG. 2 is a schematic structural diagram of a tobacco leaf quality evaluation method and device provided by an embodiment of the invention;
fig. 3 is a schematic physical structure diagram of an electronic device according to an embodiment of the present 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 tobacco leaf quality evaluation method provided by an embodiment of the invention. As shown in fig. 1, the tobacco leaf quality evaluation method includes:
101, acquiring various chemical indexes of tobacco leaves;
102, screening various chemical indexes according to the correlation coefficient of each chemical index and the sensory quality evaluation value to obtain chemical component evaluation indexes;
103, respectively selecting hook-to-hook, quadratic form and piecewise linear function methods to establish corresponding fitting scoring functions for each chemical component evaluation index according to a relevant trend rule, and obtaining corresponding fitting scores;
and 104, setting a corresponding weight value for each chemical evaluation index according to the correlation coefficient of the fitting score and the sensory evaluation score, and obtaining a formula for evaluating the tobacco leaf quality in a weighted summation mode.
Specifically, in step 101, a tobacco sample of a production area or type to be tested is selected, and various chemical indexes of each tobacco raw material are extracted from the tobacco sample. The chemical indexes can be used for evaluating the quality of the tobacco leaves.
And 102, screening the multiple chemical indexes selected in the step 101 according to the correlation coefficient of each chemical index and the sensory quality evaluation score, and taking the screened chemical indexes as chemical component evaluation indexes. For example, a chemical index having a correlation coefficient with the sensory quality evaluation score larger than a preset value is screened as a chemical composition evaluation index.
And 103, establishing a corresponding fitting score function for each chemical component evaluation index screened in the step 102, and obtaining a fitting score corresponding to the corresponding fitting score function. For example, the chemical component evaluation indexes to be screened are the sugar nitrogen ratio, the nitrogen-base ratio, the nicotine ratio, and the potassium-chlorine ratio, respectively. And for the sugar-nitrogen ratio, setting a fitting function type according to the distribution trend of the scatter diagram of the sugar-nitrogen ratio and the sensory quality evaluation score, and obtaining a fitting score function of the sugar-nitrogen ratio by adopting a hook function, wherein the fitting score function comprises the following steps:
wherein, y1Fitting score, x, for sugar to nitrogen ratio1Is a numerical value of sugar nitrogen ratio.
And for the nitrogen-base ratio, setting the type of a fitting function according to the distribution trend of a fitting graph of the nitrogen-base ratio and the sensory quality evaluation score, and obtaining a fitting score function of the nitrogen-base ratio by adopting a hook function, wherein the fitting score function is as follows:
wherein, y2Fitting score, x, for the nitrogen to base ratio2Is a numerical value of the nitrogen-base ratio.
For nicotine, the type of a fitting function is set according to the distribution trend of a fitting graph of the nicotine and the sensory quality evaluation score, and a fitting score function of nicotine is obtained by adopting a quadratic function as follows:
y3＝-15x3 2+90x3-40， (3)
wherein, y3Is the fit score, x, of nicotine3Is the value of nicotine.
And for the potassium-chlorine ratio, setting the type of a fitting function according to the distribution trend of a fitting graph of the potassium-chlorine ratio and the sensory quality evaluation score, and obtaining a fitting score function of the potassium-chlorine ratio by adopting a piecewise linear function, wherein the fitting score function comprises the following steps:
wherein, y4Fitting score, x, for the potassium to chloride ratio4Is a numerical value of the ratio of potassium to chlorine.
And substituting each chemical evaluation index of each selected sample into a corresponding fitting scoring function to obtain a corresponding fitting score. For example, if the number of samples selected is 100, then fitting each chemical evaluation index for each sample into the corresponding fitting score function yields 100 corresponding fitting scores for each chemical evaluation index.
And step 104, performing relevance analysis on the fitting score and the sensory evaluation score obtained in the step 103, setting a corresponding weight value for each chemical evaluation index according to the corresponding relevance coefficient and the size of the relevance coefficient, and performing weighted summation on the fitting score function corresponding to each chemical component evaluation index obtained in the step 103 to obtain a formula for evaluating the quality of the tobacco leaves. For example: according to the correlation coefficient of the fitting score and the sensory evaluation score, the weight values of the sugar-nitrogen ratio, the nitrogen-alkali ratio, the nicotine ratio and the potassium-chlorine ratio are set to be 0.4, 0.3, 0.2 and 0.1 respectively in a manual or software calculation mode, and then a formula for evaluating the tobacco quality is obtained in a weighting summation mode, and the following formula is obtained:
wherein Y is a fitting value of the tobacco leaf quality; x is the number of1Is the numerical value of the sugar nitrogen ratio; x is the number of2Is the numerical value of the nitrogen-base ratio; x is the number of3Is the value of nicotine; x is the number of4Is a numerical value of the ratio of potassium to chlorine.
According to the embodiment of the invention, the chemical indexes are screened according to the correlation coefficient of each chemical index and the sensory quality evaluation value by acquiring various chemical indexes of the tobacco leaf raw material, and the chemical component evaluation indexes are reasonably and comprehensively set; and establishing a corresponding fitting scoring function for each chemical component evaluation index to obtain a corresponding fitting score, reasonably setting a corresponding weight value of each chemical evaluation index according to a correlation coefficient of the fitting score and the sensory evaluation score, and finally obtaining a formula for evaluating the quality of the tobacco leaves in a weighted summation mode. The obtained formula for evaluating the quality of the tobacco leaves is more accurate, and the quality of the tobacco leaves can be effectively evaluated, so that the long-term sustainable stable development of the quality of tobacco leaf products is promoted.
On the basis of the above embodiment, as an alternative embodiment, the chemical indexes include: chemical composition indices and chemical composition derivative indices; accordingly, various chemical indexes of the tobacco leaves are obtained, including: acquiring near infrared spectrum data of tobacco leaves, and constructing a near infrared quantitative mathematical model of the near infrared spectrum data; calculating to obtain various chemical component indexes through a near infrared quantitative mathematical model; and calculating to obtain various chemical derivative indexes according to the chemical component indexes.
Specifically, the chemical indexes of the tobacco leaves comprise chemical component indexes and chemical component derivative indexes. As an alternative embodiment, the chemical composition indicators include: total sugar, total nitrogen, nicotine, total potassium, and total chloride. As an alternative embodiment, the chemical derivation indicators include: sugar nitrogen ratio, nitrogen-base ratio, potassium-chlorine ratio.
Selecting tobacco leaf samples of a production area or type to be detected, scanning all the samples by using a near-infrared instrument, acquiring near-infrared spectrum data of tobacco leaf raw materials, and constructing a near-infrared quantitative mathematical model of the near-infrared spectrum data. As an alternative embodiment, after acquiring the near infrared spectrum data of the tobacco leaf raw material, the method further includes: the near infrared spectral data is preprocessed using a derivation and smoothing process. As an alternative embodiment, the spectral range of the near infrared spectral data comprises: 4000-8000 cm-1。
For example, collecting 465 parts of near infrared spectrum data of tobacco leaves in total in 2014 and 2015 years, namely Liangshan, Panzhihua, Luzhou, Yibin and Guangyuan areas; and establishing a near-infrared quantitative mathematical model of the contents of total sugar, total nitrogen, nicotine, organic potassium and total chlorine, wherein the near-infrared spectrum range is limited to 4000-8000 cm during modeling-1And the spectra were pre-processed using first derivative and 15-point smoothing. Analyzing the total sugar, total nitrogen, nicotine, organic potassium and total chlorine contents of 200 tobacco leaf samples in total in 2016 and 2017 years of summer hills, climbing rosewood, Luzhou, Yibin and Guangyuan areas by using the constructed near-infrared quantitative mathematical model; and calculating the numerical values of the sugar-nitrogen ratio, the nitrogen-alkali ratio and the potassium-chlorine ratio of the tobacco leaf sample.
According to the embodiment of the invention, the near infrared quantitative mathematical model of the near infrared spectrum data is constructed by selecting the tobacco leaf sample of the production area or type to be detected and acquiring the near infrared spectrum data of the tobacco leaf raw material. Corresponding chemical component indexes and chemical derivative indexes can be conveniently and quickly obtained by directly inputting the near infrared spectrum data of the tobacco leaf samples in the same production area or type into the near infrared quantitative mathematical model.
On the basis of the above embodiments, as an optional embodiment, screening multiple chemical indexes according to the correlation coefficient between each chemical index and the sensory quality evaluation score to obtain chemical component evaluation indexes, including: fitting the sensory quality evaluation values and the chemical indexes by a linear function fitting method to obtain corresponding correlation coefficients, screening the chemical indexes according to the correlation coefficients, and selecting the chemical indexes of which the correlation coefficients reach a set threshold value as chemical component evaluation indexes.
Specifically, the tobacco leaves have various chemical indexes, and the influence of each chemical index on the quality of the tobacco leaves is different, so that the various chemical indexes of the tobacco leaves need to be screened. Fitting the existing sensory quality evaluation values and the correlation of various chemical indexes of the tobacco leaves by a linear function fitting method, obtaining correlation coefficients by fitting, comprehensively considering the conditions of co-correlation and the like among the indexes, and screening out the chemical indexes of which the correlation coefficients reach a set threshold value from the various chemical indexes of the tobacco leaves as chemical component evaluation indexes. For example, 2016 sensory quality evaluation values and various chemical indexes of tobacco leaves are fitted by a linear function fitting method to obtain correlation coefficients between the 2016 sensory quality evaluation values and the various chemical indexes, and sugar-nitrogen ratio, nitrogen-base ratio, nicotine and potassium-chlorine ratio are screened out as the chemical component evaluation indexes according to the magnitude of the correlation coefficients and by comprehensively considering the co-correlation and other conditions between the indexes.
According to the embodiment of the invention, the chemical indexes are screened according to the sensory quality evaluation score and the correlation coefficient of the chemical indexes, so that the corresponding chemical component evaluation indexes are obtained. The chemical component evaluation indexes for evaluating the quality of the tobacco leaves can be set more comprehensively and reasonably.
Fig. 2 is a device for evaluating the quality of tobacco leaves provided by the embodiment of the present invention, which includes: the method comprises the following steps of obtaining a module 1, a screening module 2, a fitting module 3 and an evaluation module 4; wherein:
the acquisition module 1 is used for acquiring various chemical indexes of the tobacco leaves;
the screening module 2 is used for screening various chemical indexes according to the correlation coefficient of each chemical index and the sensory quality evaluation score to obtain chemical component evaluation indexes;
the fitting module 3 is used for respectively selecting a hook-to-hook method, a quadratic function method and a piecewise linear function method to establish corresponding fitting scoring functions for each chemical component evaluation index according to a relevant trend rule to obtain corresponding fitting scores;
and the evaluation module 4 is used for setting a corresponding weight value for each chemical evaluation index according to the correlation coefficient of the fitting score and the sensory evaluation score, and obtaining a formula for evaluating the tobacco quality in a weighted summation mode.
Specifically, a tobacco sample of a production area or type to be tested is selected, and the obtaining module 1 extracts various chemical indexes of tobacco raw materials from the tobacco sample. The chemical indexes can be used for evaluating the quality of the tobacco leaves.
And the screening module 2 screens the selected multiple chemical indexes according to the correlation coefficient of each chemical index and the sensory quality evaluation score, and takes the screened chemical indexes as chemical component evaluation indexes. For example, the screening module 2 screens out a chemical index having a correlation coefficient with the sensory quality evaluation score larger than a preset value as a chemical composition evaluation index.
The fitting module 3 establishes a corresponding fitting score function for each chemical component evaluation index screened by the screening module 2, and obtains a fitting score corresponding to the corresponding fitting score function. For example, the chemical component evaluation indexes to be screened are the sugar nitrogen ratio, the nitrogen-base ratio, the nicotine ratio, and the potassium-chlorine ratio, respectively. And for the sugar-nitrogen ratio, setting a fitting function type according to the distribution trend of the scatter diagram of the sugar-nitrogen ratio and the sensory quality evaluation score, and obtaining a fitting score function of the sugar-nitrogen ratio by adopting a hook function, wherein the fitting score function comprises the following steps:
wherein, y1Fitting score, x, for sugar to nitrogen ratio1Is a numerical value of sugar nitrogen ratio.
And for the nitrogen-base ratio, setting the type of a fitting function according to the distribution trend of a fitting graph of the nitrogen-base ratio and the sensory quality evaluation score, and obtaining a fitting score function of the nitrogen-base ratio by adopting a hook function, wherein the fitting score function is as follows:
wherein, y2Fitting score, x, for the nitrogen to base ratio2Is a numerical value of the nitrogen-base ratio.
For nicotine, the type of a fitting function is set according to the distribution trend of a fitting graph of the nicotine and the sensory quality evaluation score, and a fitting score function of nicotine is obtained by adopting a quadratic function as follows:
y3＝-15x3 2+90x3-40， (3)
wherein, y3Is the fit score, x, of nicotine3Is the value of nicotine.
And for the potassium-chlorine ratio, setting the type of a fitting function according to the distribution trend of a fitting graph of the potassium-chlorine ratio and the sensory quality evaluation score, and obtaining a fitting score function of the potassium-chlorine ratio by adopting a piecewise linear function, wherein the fitting score function comprises the following steps:
wherein, y4Fitting score, x, for the potassium to chloride ratio4Is a numerical value of the ratio of potassium to chlorine.
And substituting each chemical evaluation index of each selected sample into a corresponding fitting scoring function to obtain a corresponding fitting score. For example, if the number of samples selected is 100, then fitting each chemical evaluation index for each sample into the corresponding fitting score function yields 100 corresponding fitting scores for each chemical evaluation index.
And the evaluation module 4 is used for carrying out relevancy analysis on the fitting value and the sensory evaluation value obtained by the fitting module 3, setting each chemical evaluation index according to a corresponding relevancy value and a corresponding weight value, and carrying out weighted summation on the fitting scoring function corresponding to each chemical component evaluation index obtained by the fitting module 3 to obtain a formula for evaluating the quality of the tobacco leaves. For example: according to the relevance numerical values of the fitting score and the sensory evaluation score, the weight values of the sugar-nitrogen ratio, the nitrogen-alkali ratio, the nicotine ratio and the potassium-chlorine ratio are set to be 0.4, 0.3, 0.2 and 0.1 respectively through manual or software calculation and other modes, and then a formula for evaluating the tobacco quality is obtained through a weighted summation mode, and the formula is as follows:
wherein Y is a fitting value of the tobacco leaf quality; x is the number of1Is the numerical value of the sugar nitrogen ratio; x is the number of2Is the numerical value of the nitrogen-base ratio; x is the number of3Is the value of nicotine; x is the number of4Is a numerical value of the ratio of potassium to chlorine.
The embodiment of the invention obtains various chemical indexes of the tobacco leaf raw material through the obtaining module, and screens the chemical indexes through the screening module according to the correlation coefficient of each chemical index and the sensory quality evaluation value, so as to reasonably and comprehensively set the chemical component evaluation indexes; and establishing a corresponding fitting scoring function for each chemical component evaluation index through a fitting module to obtain a corresponding fitting score, reasonably setting a corresponding weight value of each chemical evaluation index through an evaluation module according to a correlation coefficient of the fitting score and the sensory evaluation score, and finally obtaining a formula for evaluating the quality of the tobacco leaves in a weighted summation mode. The obtained formula for evaluating the quality of the tobacco leaves is more accurate, and the quality of the tobacco leaves can be effectively evaluated, so that the long-term sustainable stable development of the quality of tobacco leaf products is promoted.
Fig. 3 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention. As shown in fig. 3, the electronic apparatus includes: a processor (processor)310, a communication Interface (communication Interface)320, a memory (memory)330 and a communication bus 340, wherein the processor 310, the communication Interface 320 and the memory 330 communicate with each other via the communication bus 340. The processor 310 may call logic instructions in the memory 330 to perform the following method: obtaining various chemical indexes of tobacco leaves; screening various chemical indexes according to the correlation coefficient of each chemical index and the sensory quality evaluation value to obtain chemical component evaluation indexes; establishing a corresponding fitting score function for each chemical component evaluation index to obtain a corresponding fitting score; and setting a corresponding weight value for each chemical evaluation index according to the correlation coefficient of the fitting score and the sensory evaluation score, and obtaining a formula for evaluating the tobacco leaf quality in a weighted summation mode.
In addition, the logic instructions in the memory 330 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
An embodiment of the present invention provides a non-transitory computer-readable storage medium, where the non-transitory computer-readable storage medium stores a computer instruction, and the computer instruction causes a computer to execute the method for evaluating tobacco leaf quality provided in the foregoing embodiment, for example, the method includes: obtaining various chemical indexes of tobacco leaves; screening various chemical indexes according to the correlation coefficient of each chemical index and the sensory quality evaluation value to obtain chemical component evaluation indexes; establishing a corresponding fitting score function for each chemical component evaluation index to obtain a corresponding fitting score; and setting a corresponding weight value for each chemical evaluation index according to the correlation coefficient of the fitting score and the sensory evaluation score, and obtaining a formula for evaluating the tobacco leaf quality in a weighted summation mode.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
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 of the various 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 tobacco leaf quality evaluation method is characterized by comprising the following steps:
obtaining various chemical indexes of tobacco leaves;
screening a plurality of chemical indexes according to the correlation coefficient of each chemical index and the sensory quality evaluation score to obtain chemical component evaluation indexes;
selecting a hook-to-hook, quadratic and piecewise linear function method respectively for each chemical component evaluation index according to a relevant trend rule to establish a corresponding fitting scoring function so as to obtain a corresponding fitting score;
setting a corresponding weight value for each chemical evaluation index according to the correlation coefficient of the fitting score and the sensory quality evaluation score, and obtaining a formula for evaluating the tobacco leaf quality in a weighted summation mode;
the chemical indicators include: chemical composition indices and chemical composition derivative indices;
correspondingly, the obtaining of various chemical indexes of the tobacco leaves comprises the following steps:
acquiring near infrared spectrum data of tobacco leaves, and constructing a near infrared quantitative mathematical model of the near infrared spectrum data;
calculating and obtaining a plurality of chemical component indexes through the near infrared quantitative mathematical model;
according to the chemical component indexes, calculating to obtain a plurality of chemical derivative indexes;
after the near infrared spectrum data of the tobacco leaves are obtained, the method further comprises the following steps:
preprocessing the near infrared spectrum data by using derivation and smoothing processing;
screening a plurality of chemical indexes according to the correlation coefficient of each chemical index and the sensory quality evaluation score to obtain chemical component evaluation indexes, wherein the chemical component evaluation indexes comprise:
fitting the sensory quality evaluation values and the chemical indexes by a linear function fitting method to obtain corresponding correlation coefficients, screening the chemical indexes according to the correlation coefficients, and selecting the chemical indexes of which the correlation coefficients reach a set threshold value as chemical component evaluation indexes;
the chemical composition evaluation index includes: sugar to nitrogen ratio, nitrogen to base ratio, nicotine and potassium to chloride ratio;
sugar nitrogen ratio fit score function:
wherein, y1Fitting score, x, for sugar to nitrogen ratio1Is the numerical value of the sugar nitrogen ratio;
nitrogen to base ratio fit score function:
wherein, y2Fitting score, x, for the nitrogen to base ratio2Is the numerical value of the nitrogen-base ratio;
nicotine fit score function: y is3＝-15x3 2+90x3-40；
Wherein, y3Is the fit score, x, of nicotine3Is the value of nicotine;
potassium chloride ratio score function:
wherein, y4Fitting score, x, for the potassium to chloride ratio4Is a numerical value of the ratio of potassium to chlorine.
2. The tobacco leaf quality evaluation method according to claim 1, wherein the spectral range of the near infrared spectral data is 4000-8000 cm-1。
3. The tobacco leaf quality evaluation method according to claim 1, wherein the chemical component indicators comprise: total sugar, total nitrogen, nicotine, total potassium, and total chloride.
4. The tobacco leaf quality evaluation method according to claim 1, wherein the chemically derived indicators comprise: sugar nitrogen ratio, nitrogen-base ratio, potassium-chlorine ratio.
5. A tobacco leaf quality evaluation device is characterized by comprising:
the acquisition module is used for acquiring various chemical indexes of the tobacco leaves;
the screening module is used for screening various chemical indexes according to the correlation coefficient of each chemical index and the sensory quality evaluation score to obtain chemical component evaluation indexes;
the fitting module is used for respectively selecting a hook-to-hook method, a quadratic method and a piecewise linear function method to establish corresponding fitting scoring functions for each chemical component evaluation index according to a relevant trend rule to obtain corresponding fitting scores;
the evaluation module is used for setting a corresponding weight value for each chemical evaluation index according to the correlation coefficient of the fitting score and the sensory quality evaluation score, and obtaining a formula for evaluating the tobacco quality in a weighted summation mode;
the chemical indicators include: chemical composition indices and chemical composition derivative indices;
correspondingly, the obtaining module is specifically configured to:
acquiring near infrared spectrum data of tobacco leaves, and constructing a near infrared quantitative mathematical model of the near infrared spectrum data;
calculating and obtaining a plurality of chemical component indexes through the near infrared quantitative mathematical model;
according to the chemical component indexes, calculating to obtain a plurality of chemical derivative indexes;
after the near infrared spectrum data of the tobacco leaves are obtained, the method further comprises the following steps:
preprocessing the near infrared spectrum data by using derivation and smoothing processing;
the screening module is specifically configured to:
fitting the sensory quality evaluation values and the chemical indexes by a linear function fitting method to obtain corresponding correlation coefficients, screening the chemical indexes according to the correlation coefficients, and selecting the chemical indexes of which the correlation coefficients reach a set threshold value as chemical component evaluation indexes;
the chemical composition evaluation index includes: sugar to nitrogen ratio, nitrogen to base ratio, nicotine and potassium to chloride ratio;
sugar nitrogen ratio fit score function:
wherein, y1Fitting score, x, for sugar to nitrogen ratio1Is the numerical value of the sugar nitrogen ratio;
nitrogen to base ratio fit score function:
wherein, y2Fitting score, x, for the nitrogen to base ratio2Is the numerical value of the nitrogen-base ratio;
nicotine fit score function: y is3＝-15x3 2+90x3-40；
Wherein, y3Is the fit score, x, of nicotine3Is the value of nicotine;
potassium chloride ratio score function:
wherein, y4Fitting score, x, for the potassium to chloride ratio4Is a numerical value of the ratio of potassium to chlorine.
6. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the tobacco leaf quality assessment method according to any one of claims 1 to 4.
7. A non-transitory computer-readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the steps of the tobacco quality evaluation method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811270215.XA CN109298139B (en) | 2018-10-29 | 2018-10-29 | Tobacco leaf quality evaluation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811270215.XA CN109298139B (en) | 2018-10-29 | 2018-10-29 | Tobacco leaf quality evaluation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109298139A CN109298139A (en) | 2019-02-01 |
| CN109298139B true CN109298139B (en) | 2020-09-08 |
Family
ID=65159076
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811270215.XA Expired - Fee Related CN109298139B (en) | 2018-10-29 | 2018-10-29 | Tobacco leaf quality evaluation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109298139B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109993413B (en) * | 2019-03-04 | 2021-04-23 | 中国地质大学（武汉） | Data-driven flue-cured tobacco quality benefit comprehensive evaluation method and system |
| CN112067756A (en) * | 2020-09-18 | 2020-12-11 | 湖北中烟工业有限责任公司 | Automatic evaluation method for tobacco appearance quality |
| CN113554299B (en) * | 2021-07-19 | 2023-02-28 | 云南省烟草烟叶公司 | System, method and device for evaluating comprehensive grade quality of tobacco leaves and electronic equipment |
| CN117745148A (en) * | 2024-02-10 | 2024-03-22 | 安徽省农业科学院烟草研究所 | Multi-source data-based rice stubble flue-cured tobacco planting quality evaluation method and system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170269067A1 (en) * | 2016-03-17 | 2017-09-21 | Charles L. GINSBURGH | Use of fusion proteins to improve the availability of antigenic peptide epitopes in immunoassays |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103578037A (en) * | 2012-07-26 | 2014-02-12 | 中国海洋大学 | Method and system for evaluating quality of tobacco materials |
| CN104063599B (en) * | 2014-06-26 | 2017-02-15 | 江苏中烟工业有限责任公司 | Index screening and processing method for evaluating quality of tobacco leaves |
| CN104698143A (en) * | 2015-04-02 | 2015-06-10 | 中国烟草总公司贵州省公司 | Tobacco quality qualitative and quantitative comprehensive evaluation method |
| CN105467081A (en) * | 2015-11-25 | 2016-04-06 | 中国烟草总公司重庆市公司 | Tobacco leaf chemistry routine index weight assignment method for tobacco leaf quality evaluation |
| CN106022650A (en) * | 2016-06-13 | 2016-10-12 | 上海烟草集团有限责任公司 | Cigarette comprehensive quality analysis method |
| CN107315673A (en) * | 2017-06-29 | 2017-11-03 | 努比亚技术有限公司 | Power consumption monitoring method, mobile terminal and computer-readable recording medium |
| CN107862456B (en) * | 2017-11-02 | 2020-08-11 | 江苏中烟工业有限责任公司 | Method for comprehensively evaluating quality of batch tobacco leaves |
-
2018
- 2018-10-29 CN CN201811270215.XA patent/CN109298139B/en not_active Expired - Fee Related
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170269067A1 (en) * | 2016-03-17 | 2017-09-21 | Charles L. GINSBURGH | Use of fusion proteins to improve the availability of antigenic peptide epitopes in immunoassays |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109298139A (en) | 2019-02-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109298139B (en) | Tobacco leaf quality evaluation method and device | |
| CN107862456B (en) | Method for comprehensively evaluating quality of batch tobacco leaves | |
| CN107731304A (en) | A kind of prediction of height method and system | |
| CN108181263B (en) | Tobacco leaf position feature extraction and discrimination method based on near infrared spectrum | |
| Jing et al. | Multiblock partial least squares regression based on wavelet transform for quantitative analysis of near infrared spectra | |
| CN107796782A (en) | Redrying quality stability evaluation method based on tobacco leaf characteristic spectrum consistency metric | |
| CN109744580B (en) | Intelligent smoking control method and device | |
| CN106529584A (en) | Flue-cured tobacco aroma type and quality judgment intelligent evaluation method | |
| CN108414471B (en) | Method for distinguishing sensory characterization information based on near infrared spectrum and sensory evaluation mutual information | |
| CN101685092A (en) | Method for judging alcoholization quality of flue-cured tobacco by pH detection value of tobacco leaf | |
| CN105138834A (en) | Tobacco chemical value quantifying method based on near-infrared spectrum wave number K-means clustering | |
| CN103868957B (en) | A kind of method evaluating beating and double roasting operation sheet cigarette organoleptic quality stability | |
| Jianqiang et al. | Characterization of deep green infection in tobacco leaves using a hand-held digital light projection based near-infrared spectrometer and an extreme learning machine algorithm | |
| CN105205333B (en) | A kind of design method of tobacco formulation | |
| WO2022001829A1 (en) | Near-infrared spectrum wavelength screening method based on improved team progress algorithm | |
| Endrizzi et al. | Implementing sensory analysis principles in the quality control of pdo products: a critical evaluation of a real‐world case study | |
| CN102680427A (en) | Method for identifying surface fragrance quality of cigarettes by near infrared spectral analysis technology | |
| CN108346468B (en) | Data processing method and device | |
| CN110852322A (en) | Method and device for determining region of interest | |
| CN102706811A (en) | Method for identifying sugar quality of cigarette by utilizing near infrared light spectral analysis technique | |
| WO2021253874A1 (en) | Cigarette mainstream smoke spectral data sensory evaluation method | |
| CN104897608A (en) | Oolong tea quality evaluating method based on near-infrared spectrum technology | |
| CN115660608A (en) | One-stop innovative entrepreneurship incubation method | |
| CN108267424A (en) | Quickly differentiate the method for edible oil type based on various features ingredient | |
| CN108416489B (en) | Processing method and processing system for sensory evaluation data of tobacco products |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200908 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |