CN108693139A - The near infrared prediction model method for building up of electronics tobacco tar physical and chemical index and application - Google Patents
The near infrared prediction model method for building up of electronics tobacco tar physical and chemical index and application Download PDFInfo
- Publication number
- CN108693139A CN108693139A CN201810480159.6A CN201810480159A CN108693139A CN 108693139 A CN108693139 A CN 108693139A CN 201810480159 A CN201810480159 A CN 201810480159A CN 108693139 A CN108693139 A CN 108693139A
- Authority
- CN
- China
- Prior art keywords
- tobacco tar
- near infrared
- electronics tobacco
- physical
- chemical index
- 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
- 241000208125 Nicotiana Species 0.000 title claims abstract description 54
- 235000002637 Nicotiana tabacum Nutrition 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 36
- 239000000126 substance Substances 0.000 title claims abstract description 30
- 239000002245 particle Substances 0.000 claims abstract description 26
- 238000002329 infrared spectrum Methods 0.000 claims abstract description 12
- 238000001228 spectrum Methods 0.000 claims abstract description 11
- 238000012549 training Methods 0.000 claims abstract description 11
- 239000003571 electronic cigarette Substances 0.000 claims abstract description 9
- 238000004458 analytical method Methods 0.000 claims abstract description 6
- 238000004611 spectroscopical analysis Methods 0.000 claims abstract description 6
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 4
- 230000006978 adaptation Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 11
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 239000003921 oil Substances 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 235000019504 cigarettes Nutrition 0.000 description 4
- 230000003595 spectral effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000010183 spectrum analysis Methods 0.000 description 3
- 241000208340 Araliaceae Species 0.000 description 2
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 2
- 235000003140 Panax quinquefolius Nutrition 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 235000008434 ginseng Nutrition 0.000 description 2
- SNICXCGAKADSCV-JTQLQIEISA-N (-)-Nicotine Chemical compound CN1CCC[C@H]1C1=CC=CN=C1 SNICXCGAKADSCV-JTQLQIEISA-N 0.000 description 1
- 238000009614 chemical analysis method Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 239000002283 diesel fuel Substances 0.000 description 1
- 239000008157 edible vegetable oil Substances 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000796 flavoring agent Substances 0.000 description 1
- 235000019634 flavors Nutrition 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 229960002715 nicotine Drugs 0.000 description 1
- SNICXCGAKADSCV-UHFFFAOYSA-N nicotine Natural products CN1CCCC1C1=CC=CN=C1 SNICXCGAKADSCV-UHFFFAOYSA-N 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000001373 regressive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
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
- G01N21/3577—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing liquids, e.g. polluted water
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2201/00—Features of devices classified in G01N21/00
- G01N2201/12—Circuits of general importance; Signal processing
- G01N2201/129—Using chemometrical methods
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The near infrared prediction model method for building up of electronics tobacco tar physical and chemical index and application, acquisition obtain the glossy spectrum information of training set electronic cigarette, establish tobacco tar near infrared spectrum data training set, pre-processed to spectroscopic data;Then relative density, refraction index and the pH value for obtaining electronics tobacco tar are measured using analysis metrical instrument;Using particle group optimizing-Support vector regression (Particle Swarm Optimization-Support Vector Regression, PSO-SVR) algorithm, near infrared prediction model is established in conjunction with the physical and chemical index obtained is measured.It obtains the near infrared light spectrum information of electronics tobacco tar to be measured and is pre-processed, then with the near infrared prediction model established, relative density, refraction index and the pH value of the electronics tobacco tar are directly measured, quick nondestructive measurement obtains the important physical and chemical index of electronics tobacco tar.The present invention can realize the quick and precisely measurement of the important physical and chemical index of electronics tobacco tar, and the quick measurement of the real time on-line monitoring and other mass parameters to the important physical and chemical index of electronics tobacco tar is had laid a good foundation.
Description
Technical field
The invention belongs to utilize near-infrared spectrum analysis electronic cigarette oil tech field, and in particular to one kind being used for electronics tobacco tar
The near infrared spectrum method for fast measuring of important physical and chemical index and its application.
Background technology
Electronic cigarette need not burn to tobacco during transmitting nicotine, and relative to conventional cigarette, it is more pacified
Entirely and there is less oxious component, therefore is increasingly becoming a new substitute of conventional cigarette.Electronic cigarette tobacco tar is as electricity
The stability of sub- cigarette main feature raw material, ingredient and quality determines the flavor taste of electronic cigarette and the stability of product.
As the important foundation physical and chemical index of electronics tobacco tar, relative density, refraction index and pH value are often used in determining tobacco tar quality
Stability.The measurement of these physical and chemical indexes at present is mainly measured by using instrument and equipments such as densitometer, refractometer and PH meters
It obtains, that there are detection times is long, needs sample pretreatment, requires the shortcomings of high to operating personnel.Therefore, a kind of standard is researched and developed
Really, the physical and chemical index that quick, lossless detection method obtains electronics tobacco tar has the quality and technique that control electronics tobacco tar
Important meaning.
Near-infrared spectral analysis technology have it is easy, quickly, pre-treatment it is simple, to sample without destructive pollution-free and can be more
The advantages that component measures simultaneously, in the fields such as agricultural, oil, tobacco extensive application.Domestic and foreign scholars are near infrared spectrum
Method detects the quality of different oil products and purity has carried out numerous studies, and it is a variety of to have been set up oil, diesel oil, edible oil etc. at present
The near-infrared Quantitative Prediction Model of oil kind, but the near infrared spectrum detection research of electronics tobacco tar not yet occurs in sky at present
In vain.It is different for the trap of near infrared spectrum due to oily kind of difference, thus different oil kinds need to establish respective near-infrared it is fixed
Prediction model is measured, does not have versatility between each other.
Invention content
Near-infrared spectral analysis technology, parallel connection are utilized present invention aims to solve the deficiencies of the prior art, and provides a kind of a kind of
Implement the algorithm of support vector machine in syntype identification models the near infrared spectrum fast quantification of electronics tobacco tar, and application is built
Model quickly measures the important physical and chemical index for obtaining electronics tobacco tar.
To achieve the goals above, the technical solution adopted by the present invention is as follows:
The near infrared prediction model method for building up of electronics tobacco tar physical and chemical index, includes the following steps:
(1) representative multi items are chosen, multiple batches of this conduct of electronic cigarette oil sample models training set, using closely red
External spectrum instrument acquires the glossy spectrum information of training set electronic cigarette, obtains the near infrared light spectrum information of training set electronics tobacco tar, establishes cigarette
Then oily near infrared spectrum data training set uses Wavelet Transformation Algorithm, Savitzky-Golay convolution exponential smoothing, polynary scattering
A kind of method in correction method, First derivative spectrograply, second derivative method pre-processes spectroscopic data;
(2) the important physical and chemical index of use analysis metrical instrument measurement acquisition electronics tobacco tar, including electronics tobacco tar are opposite
Density, refraction index and pH value;
(3) PSO-SVR regression algorithms are used, near infrared spectrum is established in conjunction with the physical and chemical index obtained is measured in step (2)
Prediction model;The PSO-SVR algorithms are to seek optimal ginseng when SVR algorithms carry out regression forecasting by using PSO algorithms
The kernel function of number, SVR selects RBF kernel functions, the realization process of algorithm to mainly include the following steps that:
(a) speed of each particle and position in population are initialized, and sets searching for SVM penalty parameter cs and nuclear parameter δ
Rope range;
(b) the fitness value f (x of each particle are calculatedi);
(c) the fitness value f (x that will be calculatedi) and the adaptive optimal control angle value f (p of itselfibest) be compared, if f
(xi) < f (pibest), then adjust optimal location of the current location as the particle of particle, i.e. f (pibest)=f (xi);
(d) by the fitness value f (x of each particlei) with the adaptive optimal control angle value f (p of populationgbest) be compared, if f
(xi) < f (pgbest), then using the current location of particle as the optimal location of all particles;
(e) according to the speed and position of step (c) and (d) more new particle;
(f) judge whether to obtain optimal adaptation angle value, optimized parameter is exported if reaching;If not up to, return to step
(b) it repeats the above process;
(g) SVR regression models are established using obtained best parameter group and carries out regression forecasting.
Analysis metrical instrument of the present invention includes densitometer, refractometer, PH meters.
The application of near infrared prediction model of the present invention is to be measured using near infrared spectrometer acquisition measurement acquisition
It measures the near infrared light spectrum information of electronics tobacco tar and carries out pretreatment operation, then use the near infrared prediction model established, directly
Relative density, refraction index and the pH value for measuring the electronics tobacco tar are connect, quick nondestructive measurement obtains the important physics and chemistry of electronics tobacco tar
Index.
The present invention is based on near-infrared spectral analysis technology, in conjunction with machine learning and mode identification technology to electronics tobacco tar
Carry out quantitative modeling.Compared with existing detection method, detection method proposed by the invention have quick and precisely, green it is lossless
The advantages that, the quick and precisely measurement of the common physical and chemical index of electronics tobacco tar can be realized, to the reality of the important physical and chemical index of electronics tobacco tar
When on-line monitoring and other mass parameters it is quick measure have laid a good foundation.
Attached drawing table explanation
Fig. 1 is the primary light spectrogram of electronics tobacco tar selected by the embodiment of the present invention;
Fig. 2 is spectrograms of the Fig. 1 after pretreatment operation;
Fig. 3 is the comparison diagram of the relative density indicator measurements and model predication value of forecast sample;
Fig. 4 is the comparison diagram of the refraction index indicator measurements and model predication value of forecast sample;
Fig. 5 is the comparison diagram of the pH value indicator measurements and model predication value of forecast sample.
Specific implementation mode
Invention is further described in detail with reference to the accompanying drawings and detailed description, but protection scope of the present invention
It is not limited to the content.
The near infrared prediction model method for building up of electronics tobacco tar physical and chemical index, includes the following steps:
(1) the near infrared light spectrum information of training set electronics tobacco tar is obtained, and pretreatment operation is carried out to spectroscopic data.This reality
Apply in example using existing near infrared spectrometer carry out spectral information acquisition, acquisition range wavelength 1000nm-2500nm it
Between or in which arbitrary portion.Pretreatment to spectral information includes eliminating baseline drift and removal spectral noise;Spectral information is pre-
Processing method includes Wavelet Transformation Algorithm, Savitzky-Golay (SG) convolution exponential smoothing, multiplicative scatter correction method, first derivative
Any one in method, second derivative method, the above method is well known to those of ordinary skill in the art.With SG convolution exponential smoothings
For, it carries out data by the method for moving window fitting of a polynomial smooth.If window width is 2w+1, order of a polynomial
For n, SG smoothing methods can be described as follows:With the data (i> in window i-w to i+w;W and i≤p-w) polynomial fitting ginseng
Number calculates i-th point of match value with fitting parameter;Increase i moving windows and calculate the match value each put, you can realizes that SG is flat
It is sliding.When calculating, to determining window width and order of a polynomial, the parameter used be it is identical, so SG smoothing computations speed compared with
Soon.In this example, select window size be 15 first derivative SG convolution algorithms and multiplicative scatter correction to spectroscopic data into
Row pretreatment.Wherein Fig. 1 is the primary light spectrogram of electronics tobacco tar selected by the present embodiment, and Fig. 2 is Fig. 1 after pretreatment operation
Spectrogram.
(2) instruments such as densitometer, refractometer and PH meters is used to obtain relative density, refraction index and the pH value of electronics tobacco tar
Equal physical and chemical indexes information, above-mentioned instrument or method are existing physics, chemical analysis instrument and method, are that this field is common
Technology known to technical staff.
(3) physical and chemical indexes such as relative density, refraction index and pH value of electronics tobacco tar corresponding near infrared spectrum, knot are utilized
Close the near infrared spectrum regressive prediction model that PSO-SVR algorithms establish this three kinds of physical and chemical indexes of electronics tobacco tar.SVR methods have place
Non-thread sexuality is managed by force with accurate advantage of classifying, and is widely used in the fields such as statistical classification and regression analysis.It is led
If by a Nonlinear Mapping p, sample space is mapped in a higher-dimension or even infinite dimensional feature space
(spaces Hilbert) so that the problem of Nonlinear separability is converted into linear in feature space in original sample space
The problem of can dividing.PSO algorithms are to find optimal solution by iteration from RANDOM SOLUTION, it is also to evaluate solution by fitness
Quality, but it is more simpler than genetic algorithm rule, it does not have " intersection " (Crossover) of genetic algorithm and " variation "
(Mutation) operate, it by follow current search to optimal value find global optimum.And it is used in the present invention
PSO-SVR algorithms are to seek optimized parameter when SVR algorithms carry out regression forecasting by using PSO algorithms.
In the present embodiment, the kernel function of SVR selects RBF kernel functions, the realization process of algorithm to mainly include the following steps that:
(a) speed of each particle and position in population are initialized, and sets searching for SVM penalty parameter cs and nuclear parameter δ
Rope range;
(b) the fitness value f (x of each particle are calculatedi);
(c) the fitness value f (x that will be calculatedi) and the adaptive optimal control angle value f (p of itselfibest) be compared, if f
(xi) < f (pibest), then adjust optimal location of the current location as the particle of particle, i.e. f (pibest)=f (xi);
(d) by the fitness value f (x of each particlei) with the adaptive optimal control angle value f (p of populationgbest) be compared, if f
(xi) < f (pgbest), then using the current location of particle as the optimal location of all particles;
(e) according to the speed and position of step (c) and (d) more new particle;
(f) judge whether to obtain optimal adaptation angle value, optimized parameter is exported if reaching;If not up to, return to step
(b) it repeats the above process;
(g) SVR regression models are established using obtained best parameter group and carries out regression forecasting.
Programming platform used by the present embodiment is Matlab2016b, and used SVR algorithms are Taiwan Univ. woods
Intelligence benevolence professor libsvm kits freely shared on its interconnection network personal homepage.
The application for the near infrared prediction model that the method for the present invention is established is to acquire to obtain first near infrared spectrometer
The near infrared light spectrum information of electronics tobacco tar to be measured, then with the near infrared prediction model established, quick nondestructive measures electric
The important physical and chemical index of sub- tobacco tar.Pretreatment operation first specially is carried out to the spectroscopic data of the electronics tobacco tar to be measured of acquisition,
In conjunction with the near infrared prediction model of foundation, relative density, refraction index and the pH value three of the electronics tobacco tar are directly measured
Physical and chemical index.
The relative density of electronics tobacco tar to be measured is acquired using chemical analysis method, three physics and chemistry of refraction index and pH value refer to
Mark, tests to prediction result and verifies.Specific prediction result is as shown in Fig. 3-5 and table 1, and experimental result is shown, electronics
Related coefficient (the R of three tobacco tar relative density, refraction index and pH value index prediction models2) it is respectively 0.93374,
0.99561,0.99439, forecast set standard deviation (RMSEP) is respectively 0.0215,0.00184,0.0919, and inspection result shows this
It is feasible that invention, which quickly measures the important physical and chemical index of electronics tobacco tar,.
Table 1 is that prediction result is compared with actual measured results
Claims (3)
1. the near infrared prediction model method for building up of electronics tobacco tar physical and chemical index, which is characterized in that specifically include following step
Suddenly:
(1) representative multi items, multiple batches of electronic cigarette oil sample this conduct modeling training set are chosen, near infrared light is utilized
Spectrometer acquires the glossy spectrum information of training set electronic cigarette, obtains the near infrared light spectrum information of training set electronics tobacco tar, it is close to establish tobacco tar
Then ir data training set uses Wavelet Transformation Algorithm, Savitzky-Golay convolution exponential smoothing, multiplicative scatter correction
A kind of method in method, First derivative spectrograply, second derivative method pre-processes spectroscopic data;
(2) it uses and analyzes the important physical and chemical index that metrical instrument measures acquisition electronics tobacco tar, including the relative density of electronics tobacco tar,
Refraction index and pH value;
(3) PSO-SVR regression algorithms are used, near infrared spectrum prediction is established in conjunction with the physical and chemical index obtained is measured in step (2)
Model;The PSO-SVR algorithms are to seek optimized parameter when SVR algorithms carry out regression forecasting by using PSO algorithms,
The kernel function of SVR selects RBF kernel functions, the realization process of algorithm to mainly include the following steps that:
(a) speed of each particle and position in the population of initialization algorithm, and set SVM penalty parameter cs and nuclear parameter δ
Search range;
(b) the fitness value f (x of each particle are calculatedi);
(c) the fitness value f (x that will be calculatedi) and the adaptive optimal control angle value f (p of itselfibest) be compared, if f (xi) < f
(pibest), then adjust optimal location of the current location as the particle of particle, i.e. f (pibest)=f (xi);
(d) by the fitness value f (x of each particlei) with the adaptive optimal control angle value f (p of populationgbest) be compared, if f (xi)
< f (pgbest), then using the current location of particle as the optimal location of all particles;
(e) according to the speed and position of step (c) and (d) more new particle;
(f) judge whether to obtain optimal adaptation angle value, optimized parameter is exported if reaching;If not up to, return to step (b) weight
The multiple above process;
(g) SVR regression models are established using obtained best parameter group and carries out regression forecasting.
2. the near infrared prediction model method for building up of electronics tobacco tar physical and chemical index according to claim 1, feature
It is, the analysis metrical instrument includes densitometer, refractometer, PH meters.
3. the application for the near infrared prediction model that method as claimed in claim 1 or 2 is established, which is characterized in that using closely
Infrared spectrometer acquisition, which measures, to be obtained the near infrared light spectrum information of electronics tobacco tar to be measured and simultaneously carries out pretreatment operation, then with building
Vertical near infrared prediction model, directly measures relative density, refraction index and the pH value of the electronics tobacco tar, and quick nondestructive is surveyed
Measure the important physical and chemical index of electronics tobacco tar.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810480159.6A CN108693139A (en) | 2018-05-18 | 2018-05-18 | The near infrared prediction model method for building up of electronics tobacco tar physical and chemical index and application |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810480159.6A CN108693139A (en) | 2018-05-18 | 2018-05-18 | The near infrared prediction model method for building up of electronics tobacco tar physical and chemical index and application |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108693139A true CN108693139A (en) | 2018-10-23 |
Family
ID=63846708
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810480159.6A Pending CN108693139A (en) | 2018-05-18 | 2018-05-18 | The near infrared prediction model method for building up of electronics tobacco tar physical and chemical index and application |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108693139A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111713746A (en) * | 2020-06-08 | 2020-09-29 | 深圳市康泓威科技有限公司 | Method for detecting and controlling solution temperature of electronic atomization device and electronic atomization device thereof |
| CN113125377A (en) * | 2021-03-30 | 2021-07-16 | 武汉理工大学 | Method and device for detecting diesel oil property based on near infrared spectrum |
| CN114354534A (en) * | 2021-12-30 | 2022-04-15 | 中国航空油料有限责任公司 | Method for establishing aviation kerosene property prediction model by utilizing binary linear classifier |
| CN114397269A (en) * | 2022-01-25 | 2022-04-26 | 湖北中烟工业有限责任公司 | Method for measuring content of triacetyl glycerine of cigarette filter stick |
| NL2036603A (en) * | 2023-10-25 | 2024-03-25 | Yunnan Tobacco Quality Supervision And Testing Station | Construction method for prediction model of nicotine content in liquid sample and prediction method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1828271A (en) * | 2006-03-30 | 2006-09-06 | 将军烟草集团有限公司 | Method for detecting chemical ingredient of tobacco adopting near infrared light |
| US20120262583A1 (en) * | 2011-04-18 | 2012-10-18 | Xerox Corporation | Automated method and system for detecting the presence of a lit cigarette |
| CN103884670A (en) * | 2014-03-13 | 2014-06-25 | 西安交通大学 | Smoke component quantitative analysis method based on near infrared spectrum |
| CN107491784A (en) * | 2017-08-09 | 2017-12-19 | 云南瑞升烟草技术（集团）有限公司 | Tobacco leaf near infrared spectrum quantitative modeling method and application based on deep learning algorithm |
-
2018
- 2018-05-18 CN CN201810480159.6A patent/CN108693139A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1828271A (en) * | 2006-03-30 | 2006-09-06 | 将军烟草集团有限公司 | Method for detecting chemical ingredient of tobacco adopting near infrared light |
| US20120262583A1 (en) * | 2011-04-18 | 2012-10-18 | Xerox Corporation | Automated method and system for detecting the presence of a lit cigarette |
| CN103884670A (en) * | 2014-03-13 | 2014-06-25 | 西安交通大学 | Smoke component quantitative analysis method based on near infrared spectrum |
| CN107491784A (en) * | 2017-08-09 | 2017-12-19 | 云南瑞升烟草技术（集团）有限公司 | Tobacco leaf near infrared spectrum quantitative modeling method and application based on deep learning algorithm |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111713746A (en) * | 2020-06-08 | 2020-09-29 | 深圳市康泓威科技有限公司 | Method for detecting and controlling solution temperature of electronic atomization device and electronic atomization device thereof |
| CN111713746B (en) * | 2020-06-08 | 2024-03-15 | 深圳市康泓威科技有限公司 | Method for detecting and controlling solution temperature of electronic atomization device and electronic atomization device |
| CN113125377A (en) * | 2021-03-30 | 2021-07-16 | 武汉理工大学 | Method and device for detecting diesel oil property based on near infrared spectrum |
| CN113125377B (en) * | 2021-03-30 | 2024-02-23 | 武汉理工大学 | Method and device for detecting property of diesel based on near infrared spectrum |
| CN114354534A (en) * | 2021-12-30 | 2022-04-15 | 中国航空油料有限责任公司 | Method for establishing aviation kerosene property prediction model by utilizing binary linear classifier |
| CN114397269A (en) * | 2022-01-25 | 2022-04-26 | 湖北中烟工业有限责任公司 | Method for measuring content of triacetyl glycerine of cigarette filter stick |
| CN114397269B (en) * | 2022-01-25 | 2023-12-08 | 湖北中烟工业有限责任公司 | Method for measuring content of triacetin in cigarette filter stick |
| NL2036603A (en) * | 2023-10-25 | 2024-03-25 | Yunnan Tobacco Quality Supervision And Testing Station | Construction method for prediction model of nicotine content in liquid sample and prediction method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108693139A (en) | The near infrared prediction model method for building up of electronics tobacco tar physical and chemical index and application | |
| CN102879353B (en) | The method of content of protein components near infrared detection peanut | |
| CN104990894B (en) | A kind of gasoline property detection method based on weighting absorbance and similar sample | |
| Sinambela et al. | Application of an inductive sensor system for identifying ripeness and forecasting harvest time of oil palm | |
| CN101520412A (en) | Near infrared spectrum analyzing method based on isolated component analysis and genetic neural network | |
| CN105486658B (en) | A kind of near-infrared physical parameter measurement method with no measuring point temperature compensation function | |
| CN105424641B (en) | A kind of near infrared spectrum recognition methods of crude oil type | |
| CN105466884B (en) | It is a kind of by near infrared light spectrum discrimination crude oil species and its method for property | |
| CN105092519B (en) | Sample component assay method based on increment PLS | |
| CN101769866B (en) | Device for detecting milk components and method thereof | |
| CN109324013A (en) | A method of it is quickly analyzed using Gaussian process regression model building oil property near-infrared | |
| CN107817223A (en) | The construction method of quick nondestructive real-time estimate oil property model and its application | |
| CN106841083A (en) | Sesame oil quality detecting method based on near-infrared spectrum technique | |
| CN105388123A (en) | Method for predicting crude oil characteristic through near infrared spectrum | |
| Zhu et al. | Wavelength selection of hyperspectral scattering image using new semi-supervised affinity propagation for prediction of firmness and soluble solid content in apples | |
| CN109540836A (en) | Near infrared spectrum pol detection method and system based on BP artificial neural network | |
| CN101995389A (en) | Method for fast recognition of crude oil variety through near infrared spectrum | |
| CN107703097A (en) | Utilize the method and its application of decay total reflection probe and the model of near infrared spectrometer structure fast prediction oil property | |
| CN109324014A (en) | A kind of adaptive oil property near-infrared method for quick predicting | |
| CN102841069B (en) | Method for rapidly identifying types of crude oil by using mid-infrared spectrum | |
| CN107860743A (en) | Utilize the method and its application of the model of reflective near infrared fibre-optical probe structure fast prediction oil property | |
| CN109961179A (en) | A kind of aquatic products quality detecting method and portable Raman device | |
| CN106529680B (en) | A kind of multiple dimensioned extreme learning machine integrated modelling approach based on empirical mode decomposition | |
| Huang et al. | Optimal wavelength selection for hyperspectral scattering prediction of apple firmness and soluble solids content | |
| CN107356556A (en) | A kind of double integrated modelling approach of Near-Infrared Spectra for Quantitative Analysis |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181023 |