CN1831516A - Method for nondistructive discriminating variety and true and false of cigarette using visible light and near-infrared spectrum technology - Google Patents
Method for nondistructive discriminating variety and true and false of cigarette using visible light and near-infrared spectrum technology Download PDFInfo
- Publication number
- CN1831516A CN1831516A CN 200610050168 CN200610050168A CN1831516A CN 1831516 A CN1831516 A CN 1831516A CN 200610050168 CN200610050168 CN 200610050168 CN 200610050168 A CN200610050168 A CN 200610050168A CN 1831516 A CN1831516 A CN 1831516A
- Authority
- CN
- China
- Prior art keywords
- cigarette
- spectrum
- sample
- true
- false
- 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
- 235000019504 cigarettes Nutrition 0.000 title claims abstract description 113
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 21
- 238000005516 engineering process Methods 0.000 title description 2
- 238000001228 spectrum Methods 0.000 claims abstract description 102
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 230000000007 visual effect Effects 0.000 claims abstract description 6
- 239000000523 sample Substances 0.000 claims description 94
- 230000003595 spectral effect Effects 0.000 claims description 20
- 238000012937 correction Methods 0.000 claims description 11
- 230000004069 differentiation Effects 0.000 claims description 8
- 238000000513 principal component analysis Methods 0.000 claims description 8
- 238000007689 inspection Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 7
- 239000013074 reference sample Substances 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 6
- 239000000463 material Substances 0.000 claims description 6
- 238000000862 absorption spectrum Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 238000012850 discrimination method Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 238000003909 pattern recognition Methods 0.000 claims description 4
- 238000004611 spectroscopical analysis Methods 0.000 claims description 4
- 230000005477 standard model Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 3
- 230000001915 proofreading effect Effects 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 239000000779 smoke Substances 0.000 claims description 3
- 238000010200 validation analysis Methods 0.000 claims description 3
- 238000007621 cluster analysis Methods 0.000 claims description 2
- 238000013210 evaluation model Methods 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000012216 screening Methods 0.000 claims description 2
- 229910052736 halogen Inorganic materials 0.000 abstract description 2
- 150000002367 halogens Chemical class 0.000 abstract description 2
- 238000010521 absorption reaction Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 125000004435 hydrogen atom Chemical group [H]* 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000000985 reflectance spectrum Methods 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 208000003351 Melanosis Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 238000007705 chemical test Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 229910052739 hydrogen Inorganic materials 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 229920000642 polymer Polymers 0.000 description 1
- 238000006116 polymerization reaction Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Images
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
A method of using visual light and near infrared spectrum to identify variety of cigarette nondestructively includes fixing halogen lamp on A - frame, using power supply wire to provide 220V power to spectrograph and light source as well as computer, connecting spectrograph to computer through data line for transmitting collected sample spectrum data to computer, applying spectrum special software of ASD View Spec Pro V2.4 and Unscramble V9.2 to carry out process and analysis on collected data then feeding analyzed data back to information platform for displaying variety of tested sample.
Description
Technical field
The present invention relates to cigarette kind and true and false discrimination method, relate in particular to a kind of with visible light and harmless cigarette kind and the true and false method differentiated of near-infrared spectrum technique.
Technical background
Panoramic cigarette product on the market, the consumer is difficult to by naked eyes difference quality of cigarette quality and different cigarette products, and exists a large amount of counterfeit and shoddy goods.
It is long that the discriminating that conventional chemical method is carried out the cigarette different cultivars has the cycle, the shortcoming of poor reproducibility.
Summary of the invention
In order to overcome the problem of above-mentioned existence, the object of the present invention is to provide a kind of with visible light and harmless cigarette kind and the true and false method differentiated of near-infrared spectrum technique.Can not only differentiate cigarette kind and true and false fast in real time, and not need chemical test, need not sample is carried out destructive pre-service, can, fast and effectively discriminating harmless to cigarette kind and true and false realization.
Near infrared spectrum mainly is the frequency multiplication and the sum of fundamental frequencies absorption spectrum of organic molecule, this spectral coverage can access structure, the composition of molecule, the information of state, and can also obtain the physical state information of the materials such as diameter of the degree of polymerization of density, granularity, polymer of sample and fiber from near-infrared reflection spectrum.Because the absorption near infrared spectrum district mainly is that molecule or atomic vibration fundamental frequency are at 2000cm
-1Above frequency multiplication, sum of fundamental frequencies absorb, so the organism near infrared spectrum mainly comprises C-H, N-H, O-H etc. contain the frequency multiplication and the sum of fundamental frequencies absorption band of hydrogen group.These absorption frequency characteristics that contain hydrogen group are strong, are subjected to the influence of molecule internal and external environment little, and very stable in the spectral characteristic of near infrared spectrum district sample.The spectral signature of visible-range can reflect visual signatures such as the color, texture of sample.The essential characteristic of visible light and near infrared spectrum is for differentiating cigarette kind and true and false laying a good foundation fast.The true cigarette sample and the spectroscopic data of known kind are carried out correlation analysis, set up cigarette kind and true and false discriminating model.Use apparatus and method of the present invention, use the spectral illumination sample, the absorption of test sample and reflectance spectrum are determined to carry out modeling and prediction to satisfying the correlationship between absorption and reflectance spectrum and the sample characteristics of for example.
The technical solution adopted for the present invention to solve the technical problems is that it comprises:
1) a kind ofly is based upon different cultivars cigarette sample and from closing the cigarette kind fastened and true and false discrimination method between the visible light of sample, the near-infrared absorption spectrum; Spectrometer transforms through A/D by data line interface and links to each other with computing machine; Light source is fixed with three-legged support, regulates the light source depression angle, and supporting power lead links to each other with external power supply; Spectrometer is fixed with supporting three-legged support, regulates its height and visual angle; Fix the position of light source, spectrometer and cigarette sample.Light source irradiation is on the cigarette sample with sample introduction container splendid attire, and spectrometer receives reflection and scattered light from sample after proofreading and correct through blank; Gather the spectrum picture of cigarette sample, convert the spectrum master data again to;
2) different cultivars cigarette and true and false discriminating comprise two stages of evaluation of setting up kind discriminating model and unknown sample:
In the cigarette kind discriminating model stage: must collect the cigarette of various known kinds, and obtain the visible light and the near infrared spectrum of cigarette; For a certain cigarette to be identified can by with model in standard cigarettes spectrum analyze and calculate the pairing threshold value of this cigarette, this threshold value is exactly to identify the standard of new unknown sample; By collecting standard model spectrum, after calculating the corresponding threshold value of certain cigarette and model being tested, just set up the kind discriminating model; In fact checkout procedure is exactly to confirm that each cigarette in the model all can only be by only evaluation, and can not obscure mutually with other materials;
At the validation phase of unknown sample, the spectrum of unknown sample obtains the back and just can differentiate it; The spectrum of unknown cigarette sample can compare with the reference spectra of each cigarette in the storehouse; If a certain cigarette reference spectra distance is less than the reference spectra corresponding threshold in unknown sample spectrum and the model, so this unknown sample just with model in this cigarette belong to a kind of material.In like manner, the cigarette of collecting in the storehouse all is genuine, when the reference spectra distance of the cigarette gained of same kind greater than the reference spectra corresponding threshold, this cigarette promptly is judged as false smoke so.
The visible light near infrared is differentiated the cigarette kind and true and falsely can specifically be divided into following step:
1) foundation of standard or reference sample spectra collection:
Spectrum is differentiated the cigarette kind and true and falsely exactly sample spectrum and standard spectrum is compared, and sets up reliable and stable standard spectra collection, at first will measure the standard spectrum of various cigarette samples; General same sample needs repeatedly duplicate measurements, and the sample of different lot numbers also needs duplicate measurements, and is approximate as this sample standard spectrum with averaged spectrum; Convert the cigarette spectrum picture of various kinds to sample spectrum master data.
2) correction of spectrum and pre-service:
The first step behind the acquisition sample spectrum is that sample spectrum is proofreaied and correct and pre-service, the effect of spectrum correction is the standardization of spectrogram, offset the quality of background interference and raising spectrum, here adopt level and smooth, centralization, differentiate, normalization, polynary scatter correction, SNV, Reduce, a kind of among the Noise, any two kinds or any three kinds of spectrum pre-service, adopt which kind of bearing calibration to select according to the quality of spectrum and the situation of interference, pre-service also can amplify the original signal difference of hiding out, improve the resolution of spectrum, it is more directly perceived that kind is differentiated, reliably;
3) extraction of spectral signature:
The important evidence of cigarette kind and true and false discriminating is the similarity (or otherness) of spectral signature, therefore correctly obtaining spectral signature is key one ring of accurately differentiating, the characteristics of visible light near infrared spectrum are that the spectroscopic data amount is big, and spectrum has very complicacy of polytrope, background; Therefore, differentiate that near infrared spectrum cigarette kind and true and false several peak groups of the more dependence of qualitative discrimination analysis or frequency band even full spectrum carry out qualitative discrimination, extract spectral signature to improve the reliability of analyzing identification result as the deviation method of weighting, Kruskal-Wallistesting check, principal component analysis (PCA), partial least square method, DPLS, SIMCA, LLM, Fisher differentiation, KNN, wavelet analysis or ANN feature screening technique;
4) foundation of discriminating model:
Cigarette sample for large amount of complex, determine that unknown sample belongs to a certain kind, adopt pattern-recognition to differentiate, differentiate that cigarette kind and true and false mode identification method are with Fisher differentiation, Bayes differentiation, progressively differentiation, linear learning machine, KNN, SIMCA, DPLS, cluster analysis, least square regression, Euclidean distance or neural network; Carry out discriminatory analysis with pattern-recognition, the spectrum of known kind sample need be divided into study collection and inspection set two parts, the foundation of division be the study collection with classification kind in the inspection set should be identical, have representativeness widely; Then various cigarette samples are carried out initialize according to priori, set up the kind discriminating model, come the performance of evaluation model then with inspection set;
5) the unknown sample kind is differentiated
The measuring method that is adopted when obtaining unknown cigarette sample spectrum, the measuring method that must be adopted with obtain reference spectra the time is consistent, and the source of variation between reference sample in the model and the unknown sample spectrum should reduce as far as possible; The method of sampling, resolution, sweep spacing or sweep time measurement parameter, should be consistent; Through spectrum correction and pre-service, discriminating model is sent in the extraction of spectral signature and reference sample compares the spectrum of unknown kind sample.
The present invention compares the beneficial effect that has with background technology:
1) utilize spectral technique to differentiate cigarette kind and true and false, its analysis speed is accelerated greatly.The mensuration process of spectrum generally can be finished (multichannel instrument can be finished) in 1 second in 30 seconds.
2) do not use any chemical reagent, reduced the detection cost, also free from environmental pollution.
3) compare with chemical method, systematic error and personal error reduce greatly, have improved measuring accuracy.
4) can handle the great amount of samples analysis, save time, detection technique can be good at being applied to the cigarette quality monitoring in real time.
Description of drawings
Fig. 1 is harmless cigarette kind and the true and false schematic diagram differentiated of visible light and near-infrared spectrum technique;
Fig. 2 is the exemplary spectrum curve map of three kind cigarette and true and false China;
Fig. 3 is the shot chart of the major component 1 and the major component 2 of each sample correspondence.
Embodiment
As shown in Figure 1, the present invention it comprise:
1) a kind ofly is based upon different cultivars cigarette sample and the true and false cigarette of same kind and from closing the cigarette kind fastened and true and false discrimination method between the visible light of sample, the near-infrared absorption spectrum; Spectrometer transforms through A/D by data line interface and links to each other with computing machine; Light source is fixed with three-legged support, regulates the light source depression angle, and supporting power lead links to each other with external power supply; Spectrometer is fixed with supporting three-legged support, regulates its height and visual angle; Fix the position of light source, spectrometer and cigarette sample.Light source irradiation is on the cigarette sample with sample introduction container splendid attire, and spectrometer receives reflection and scattered light from sample after proofreading and correct through blank; Gather the spectrum picture of cigarette sample, convert the spectrum master data again to.
2) different cultivars cigarette and true and false discriminating comprise two stages of evaluation of setting up kind discriminating model and unknown sample:
In cigarette kind and true and false discriminating model stage: must collect the cigarette of various known kinds, and obtain the visible light and the near infrared spectrum of cigarette; For a certain cigarette to be identified can by with model in standard cigarettes spectrum analyze and calculate the pairing threshold value of this cigarette, this threshold value is exactly to identify the standard of new unknown sample; By collecting standard model spectrum, after calculating the corresponding threshold value of certain cigarette and model being tested, just set up the kind discriminating model; In fact checkout procedure is exactly to confirm that each cigarette in the model all can only be by only evaluation, and can not obscure mutually with other materials;
At the validation phase of unknown sample, the spectrum of unknown sample obtains the back and just can differentiate it; The spectrum of unknown cigarette sample can compare with the reference spectra of each cigarette in the storehouse; If a certain cigarette reference spectra distance is less than the reference spectra corresponding threshold in unknown sample spectrum and the model, so this unknown sample just with model in this cigarette belong to a kind of material.In like manner, the cigarette of collecting in the storehouse all is genuine, when the reference spectra distance of the cigarette gained of same kind greater than the reference spectra corresponding threshold, this cigarette promptly is judged as false smoke so.
Native system is made up of the supporting 14.5V Halogen lamp LED of Handheld FieldSpec spectrometer, the spectrometer of U.S. ASD (Analytical Spectral Device) company, computing machine, correction blank, sample introduction container, power supply etc.This spectrometer wavelength is 325～1075nm, scanning times 30 times, resolution 3.5cm
-1, the probe field angle is 20 degree.With data line spectrometer is linked to each other with the PC computer, sample places special container.The sample introduction container is that certain altitude (greater than 10mm) glass container or melanism glass container are arranged.Spectrometer probe distance sample height is fixed as 80-200mm, and light source becomes miter angle apart from sample container center 300mm.It more than is data collector.Treat that spectrum data gathering finishes, carry out Data Management Analysis with spectrum dedicated analysis software ASD ViewSpec ProV2.14 and Unscramble V9.2.With the data feedback information receiving platform of analyzing, show the kind situation of monitoring in real time at last.
With bright red hawk, Double Happiness, true and false middle Huawei example illustrates cigarette kind and true and false discrimination method, the true and false China of three kind cigarette and same kind is used to set up kind and true and false discriminating model.
1) foundation of standard or reference sample spectra collection:
Standard model is carried out spectral scan, and spectrometer links to each other with computing machine through the A/D conversion by data line interface; Light source is fixed with three-legged support, regulates the light source depression angle, and supporting power lead links to each other with external power supply; Spectrometer is fixed with supporting three-legged support, regulates its height and visual angle; Set measurement parameters such as the method for sampling, resolution, sweep spacing or sweep time.Obtain spectrum picture as shown in Figure 2.
2) spectrum correction and pre-service:
Spectral image dataization, the first step behind the acquisition sample spectroscopic data is that sample spectrum is proofreaied and correct and pre-service, here adopt level and smooth, polynary scatter correction preprocessing procedures, pre-service amplifies the original signal difference of hiding out, improve the resolution of spectrum, it is directly perceived more, reliable that kind is differentiated;
3) extraction of spectral signature:
Use principal component analysis (PCA) and extract the spectrum principal character, on principal component scores figure, can see the cigarette of different cultivars and the dendrogram of true and false China.The cigarette of major component 1 and 2 pairs of three kinds of major component and the cluster effect of true and false China are as shown in Figure 3.Illustrate that major component has comprised the characteristic information to the kind sensitivity.Major component has been carried out compression to the original spectrum data and has been extracted spectral information for the kind sensitivity.
4) foundation of discriminating model:
Set up discriminating model with neural network method, the spectrum of known kind sample is divided into study collection and inspection set two parts, and the study collection is 80 samples randomly drawing from all samples, 20 samples of each kind.20 remaining samples are as test samples.Preceding four major components that the process principal component analysis (PCA) obtains have determined that through repetition learning the hidden layer node number of neural network is 8 as the input of neural network, and minimum training speed gets 0.2, maximum iteration time 1000.Set up neural network model through training, the error of fitting of sample has been equaled 8.833 * 10
-5
5) the unknown sample kind is differentiated:
20 samples to the unknown are differentiated.Identification result is as shown in table 1.
This discriminating model of table 1. is to the identification result of unknown 20 samples
| The forecast sample sequence number | Actual value | Predicted value | The forecast sample sequence number | Actual value | Predicted value |
| (1) (2) (3) (4) (5) (6) (7) (8) (9) (10) | 0 0 0 0 0 1 1 1 1 1 | 0.01329 0.01786 0.02199 0.0206 0.02147 0.99857 0.99789 0.97556 0.97161 1.08065 | (11) (12) (13) (14) (15) (16) (17) (18) (19) (20) | 2 2 2 2 2 3 3 3 3 3 | 2.04604 2.09909 2.11520 1.98160 2.01597 2.98253 2.98489 2.98100 2.98461 2.96048 |
Annotate: the bright red hawk of 0-, 1-Double Happiness, 2-be China firmly, the false China of 3-
This model is 100% to the kind resolution of unknown 20 samples, illustrate utilize visible light and near-infrared spectrum technique harmless discriminating cigarette kind and true and false be feasible.
Claims (2)
1. one kind with harmless cigarette kind and the true and false method differentiated of visible light and near-infrared spectrum technique, it is characterized in that it comprises:
1) a kind ofly is based upon different cultivars cigarette sample or the true and false cigarette sample of same kind and from closing the cigarette kind fastened and true and false discrimination method between the visible light of sample, the near-infrared absorption spectrum; Spectrometer transforms through A/D by data line interface and links to each other with computing machine; Light source is fixed with three-legged support, regulates the light source depression angle, and supporting power lead links to each other with external power supply; Spectrometer is fixed with supporting three-legged support, regulates its height and visual angle; Fix the position of light source, spectrometer and cigarette sample, light source irradiation is on the cigarette sample with sample introduction container splendid attire, and spectrometer receives reflection and scattered light from sample after proofreading and correct through blank; Gather the spectrum picture of cigarette sample, convert the spectrum master data again to;
2) discriminating of different cultivars cigarette and the true and false discriminating of same kind comprise two stages of evaluation of setting up kind discriminating model and unknown sample:
In the model stage of discriminating of cigarette kind and true and false discriminating: must collect the cigarette of various known kinds and the true and false cigarette of same kind, and obtain the visible light and the near infrared spectrum of various cigarette; For a certain cigarette to be identified can by with model in standard cigarettes spectrum analyze and calculate the pairing threshold value of this cigarette, this threshold value is exactly to identify the standard of new unknown sample; By collecting standard model spectrum, after calculating the corresponding threshold value of certain cigarette and model being tested, just set up the kind discriminating model; In fact checkout procedure is exactly to confirm that each cigarette in the model all can only be by only evaluation, and can not obscure mutually with other materials;
At the validation phase of unknown sample, the spectrum of unknown sample obtains the back and just can differentiate it; The spectrum of unknown cigarette sample can compare with the reference spectra of each cigarette in the storehouse; If a certain cigarette reference spectra distance is less than the reference spectra corresponding threshold in unknown sample spectrum and the model, so this unknown sample just with model in this cigarette belong to same kind.In like manner, the cigarette of collecting in the storehouse all is genuine, when the reference spectra distance of the cigarette gained of same kind greater than the reference spectra corresponding threshold, this cigarette promptly is judged as false smoke so.
2. according to claim 1 with harmless cigarette kind and the true and false method differentiated of visible light and near-infrared spectrum technique, it is characterized in that the visible light near infrared differentiates the cigarette kind and true and falsely can specifically be divided into following step:
1) foundation of standard or reference sample spectra collection:
Spectrum is differentiated the cigarette kind and true and falsely exactly sample spectrum and standard spectrum is compared, and sets up reliable and stable standard spectra collection, at first will measure the standard spectrum of various cigarette samples, and these cigarette is necessary for genuine article; General same sample needs repeatedly duplicate measurements, and the sample of different lot numbers also needs duplicate measurements, and is approximate as this sample standard spectrum with averaged spectrum; Convert the spectrum picture of various cigarette to sample spectrum master data;
2) correction of spectrum and pre-service:
The first step behind the acquisition sample spectrum is that sample spectrum is proofreaied and correct and pre-service, the effect of spectrum correction is the standardization of spectrogram, offset the quality of background interference and raising spectrum, here adopt level and smooth, centralization, differentiate, normalization, polynary scatter correction, SNV, Reduce, a kind of among the Noise, any two kinds or any three kinds of method preprocessing procedures, adopt which kind of bearing calibration to select according to the quality of spectrum and the situation of interference, pre-service also can amplify the original signal difference of hiding out, improve the resolution of spectrum, it is more directly perceived that kind is differentiated, reliably;
3) extraction of spectral signature:
The important evidence that the cigarette kind is differentiated is the similarity (or otherness) of spectral signature, therefore correctly obtaining spectral signature is key one ring of accurately differentiating, the characteristics of visible light near infrared spectrum are that the spectroscopic data amount is big, and spectrum has very complicacy of polytrope, background; Therefore, differentiate that near infrared spectrum cigarette kind and true and false several peak groups of the more dependence of qualitative discrimination analysis or frequency band even full spectrum carry out qualitative discrimination, extract spectral signature to improve the reliability of analyzing identification result as the deviation method of weighting, Kruskal-Wallistesting check, principal component analysis (PCA), partial least square method, DPLS, SIMCA, LLM, Fisher differentiation, KNN, wavelet analysis or ANN feature screening technique;
4) foundation of discriminating model:
Cigarette sample for large amount of complex, determine that unknown sample belongs to a certain kind, adopt pattern-recognition to differentiate, differentiate that cigarette kind and true and false mode identification method are with Fisher differentiation, Bayes differentiation, progressively differentiation, linear learning machine, KNN, SIMCA, DPLS, cluster analysis, least square regression, Euclidean distance or neural network; Carry out discriminatory analysis with pattern-recognition, the spectrum of known kind sample need be divided into study collection and inspection set two parts, the foundation of division be the study collection with classification kind in the inspection set should be identical, have representativeness widely; Then various cigarette samples (comprising true and false) are carried out initialize according to priori, set up the kind discriminating model, come the performance of evaluation model then with inspection set;
5) the unknown sample kind is differentiated:
The measuring method that is adopted when obtaining unknown cigarette sample spectrum, the measuring method that must be adopted with obtain reference spectra the time is consistent, and the source of variation between reference sample in the model and the unknown sample spectrum should reduce as far as possible; The method of sampling, resolution, sweep spacing or sweep time measurement parameter, should be consistent; Through spectrum correction and pre-service, discriminating model is sent in the extraction of spectral signature and reference sample compares the spectrum of unknown kind sample.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200610050168 CN1831516A (en) | 2006-04-03 | 2006-04-03 | Method for nondistructive discriminating variety and true and false of cigarette using visible light and near-infrared spectrum technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200610050168 CN1831516A (en) | 2006-04-03 | 2006-04-03 | Method for nondistructive discriminating variety and true and false of cigarette using visible light and near-infrared spectrum technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN1831516A true CN1831516A (en) | 2006-09-13 |
Family
ID=36993933
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 200610050168 Pending CN1831516A (en) | 2006-04-03 | 2006-04-03 | Method for nondistructive discriminating variety and true and false of cigarette using visible light and near-infrared spectrum technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1831516A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101285768B (en) * | 2008-05-29 | 2010-06-02 | 红云红河烟草(集团)有限责任公司 | Method for nondestructively identifying cigarette authenticity by applying near infrared spectrum analysis technology |
| CN101710071B (en) * | 2009-12-09 | 2011-04-06 | 川渝中烟工业公司 | Sampling method for establishing tobacco near-infrared model |
| CN101498661B (en) * | 2008-01-30 | 2011-07-20 | 香港浸会大学 | Infrared spectrum characteristic extraction method for high-precision discriminating variety, producing area and growth mode of traditional Chinese medicinal materials |
| CN103235086A (en) * | 2013-04-01 | 2013-08-07 | 中国烟草总公司北京市公司 | Cigarette authenticity identification method based on mainstream smoke indexes |
| US8543348B2 (en) | 2008-06-10 | 2013-09-24 | Endress + Hauser Conducta Gesellschaft für Mess- und Regeltechnik mbH + Co. KG | Method and arrangement for automatic calibrating of spectrometers |
| CN103674884A (en) * | 2012-09-17 | 2014-03-26 | 福建中烟工业有限责任公司 | Random forest classification method for tobacco leaf style characteristics based on near infrared spectral information |
| CN104406935A (en) * | 2014-12-23 | 2015-03-11 | 深圳因特安全技术有限公司 | Identifying and detecting method of 2-bromo-3,3,3-trifluoropropene extinguishant |
| CN104596981A (en) * | 2015-01-30 | 2015-05-06 | 云南中烟工业有限责任公司 | Method for distinguishing paper process reconstituted tobacco products via near infrared spectroscopy in combination with PLS-DA |
| CN105067556A (en) * | 2015-08-17 | 2015-11-18 | 绍兴文理学院 | Optical device and optical method for quickly detecting biological liquid sample |
| CN105606552A (en) * | 2016-02-04 | 2016-05-25 | 云南中烟工业有限责任公司 | Method for analyzing quality trends of cigarette tobaccos based on whole spectral range molecular spectrum |
| CN106404689A (en) * | 2016-09-23 | 2017-02-15 | 广东食品药品职业学院 | Identification method of components of exocarpium |
| CN106769906A (en) * | 2016-12-14 | 2017-05-31 | 重庆川仪自动化股份有限公司 | Spectrometer data wander compensation method |
| CN107238557A (en) * | 2016-03-27 | 2017-10-10 | 中烟施伟策（云南）再造烟叶有限公司 | A kind of method of utilization near infrared spectroscopy quick detection calcium carbonate particle diameter distribution |
| CN108872090A (en) * | 2017-05-08 | 2018-11-23 | 西派特（北京）科技有限公司 | DYNAMIC SOLID sample in line spectrum method for automatic measurement and device |
| CN109000797A (en) * | 2018-06-12 | 2018-12-14 | 云南中烟工业有限责任公司 | A kind of radium-shine cigarette-brand chromatism measurement method |
| CN109358022A (en) * | 2018-11-22 | 2019-02-19 | 陕西中烟工业有限责任公司 | A kind of method of the quick-fried pearl type of quick discrimination cigarette |
| CN110346445A (en) * | 2019-07-05 | 2019-10-18 | 云南腾辉科技开发有限公司 | A method of based on gas analysis mass spectrogram and near-infrared spectrum analysis tobacco mildew |
-
2006
- 2006-04-03 CN CN 200610050168 patent/CN1831516A/en active Pending
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101498661B (en) * | 2008-01-30 | 2011-07-20 | 香港浸会大学 | Infrared spectrum characteristic extraction method for high-precision discriminating variety, producing area and growth mode of traditional Chinese medicinal materials |
| CN101285768B (en) * | 2008-05-29 | 2010-06-02 | 红云红河烟草(集团)有限责任公司 | Method for nondestructively identifying cigarette authenticity by applying near infrared spectrum analysis technology |
| US8543348B2 (en) | 2008-06-10 | 2013-09-24 | Endress + Hauser Conducta Gesellschaft für Mess- und Regeltechnik mbH + Co. KG | Method and arrangement for automatic calibrating of spectrometers |
| CN101710071B (en) * | 2009-12-09 | 2011-04-06 | 川渝中烟工业公司 | Sampling method for establishing tobacco near-infrared model |
| CN103674884A (en) * | 2012-09-17 | 2014-03-26 | 福建中烟工业有限责任公司 | Random forest classification method for tobacco leaf style characteristics based on near infrared spectral information |
| CN103235086A (en) * | 2013-04-01 | 2013-08-07 | 中国烟草总公司北京市公司 | Cigarette authenticity identification method based on mainstream smoke indexes |
| CN104406935A (en) * | 2014-12-23 | 2015-03-11 | 深圳因特安全技术有限公司 | Identifying and detecting method of 2-bromo-3,3,3-trifluoropropene extinguishant |
| CN104596981A (en) * | 2015-01-30 | 2015-05-06 | 云南中烟工业有限责任公司 | Method for distinguishing paper process reconstituted tobacco products via near infrared spectroscopy in combination with PLS-DA |
| CN105067556A (en) * | 2015-08-17 | 2015-11-18 | 绍兴文理学院 | Optical device and optical method for quickly detecting biological liquid sample |
| CN105606552A (en) * | 2016-02-04 | 2016-05-25 | 云南中烟工业有限责任公司 | Method for analyzing quality trends of cigarette tobaccos based on whole spectral range molecular spectrum |
| CN107238557A (en) * | 2016-03-27 | 2017-10-10 | 中烟施伟策（云南）再造烟叶有限公司 | A kind of method of utilization near infrared spectroscopy quick detection calcium carbonate particle diameter distribution |
| CN106404689A (en) * | 2016-09-23 | 2017-02-15 | 广东食品药品职业学院 | Identification method of components of exocarpium |
| CN106769906A (en) * | 2016-12-14 | 2017-05-31 | 重庆川仪自动化股份有限公司 | Spectrometer data wander compensation method |
| CN108872090A (en) * | 2017-05-08 | 2018-11-23 | 西派特（北京）科技有限公司 | DYNAMIC SOLID sample in line spectrum method for automatic measurement and device |
| CN109000797A (en) * | 2018-06-12 | 2018-12-14 | 云南中烟工业有限责任公司 | A kind of radium-shine cigarette-brand chromatism measurement method |
| CN109000797B (en) * | 2018-06-12 | 2023-07-25 | 云南中烟工业有限责任公司 | Laser cigarette label color difference measurement method |
| CN109358022A (en) * | 2018-11-22 | 2019-02-19 | 陕西中烟工业有限责任公司 | A kind of method of the quick-fried pearl type of quick discrimination cigarette |
| CN110346445A (en) * | 2019-07-05 | 2019-10-18 | 云南腾辉科技开发有限公司 | A method of based on gas analysis mass spectrogram and near-infrared spectrum analysis tobacco mildew |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN1831516A (en) | Method for nondistructive discriminating variety and true and false of cigarette using visible light and near-infrared spectrum technology | |
| CN1831515A (en) | Method for nondistructive discriminating crop seed variety using visible light and near-infrared spectrum technology | |
| CN102636450A (en) | Method for detecting wolfberry polyose content in Chinese wolfberry in a nondestructive way based on near infrared spectrum technology | |
| CN102590129B (en) | Method for detecting content of amino acid in peanuts by near infrared method | |
| CN104897607A (en) | Food modeling and rapid detecting integration method and system adopting portable NIRS (near infrared spectroscopy) | |
| CN103134765A (en) | Chinese medicine sample authenticity preliminary screening method based on terahertz time-domain spectrum | |
| CN111428561B (en) | Broadband electromagnetic interference source identification method and system, storage medium and equipment | |
| CN101221125A (en) | Method for measuring eutrophication water body characteristic parameter by spectrum technology | |
| US20050010374A1 (en) | Method of analysis of NIR data | |
| CN100357725C (en) | Method and device for rapidly detecting tenderness of beef utilizing near infrared technology | |
| CN108844941B (en) | Method for identifying and classifying different-grade phosphate ores based on Raman spectrum and PCA-HCA | |
| CN106951458A (en) | A kind of product ontology is traced to the source Jianzhen's method for anti-counterfeit and system | |
| CN105300954A (en) | Method for Raman spectrum characterization of heterogeneous foam layer minerals in antimony ore flotation | |
| CN110632021A (en) | Spectrum detection method and system based on portable near-infrared spectrometer | |
| CN103959426A (en) | Method for identifying microorganisms by mass spectrometry | |
| CN110749565A (en) | Method for rapidly identifying storage years of Pu' er tea | |
| CN103940767A (en) | Gas concentration inversion method based on multi-manifold learning | |
| CN101074927A (en) | Method for diagnosing fruit diseases based on visible and near-infrared spectral characteristic band | |
| CN112101459A (en) | Animal bone identification method and system based on near-infrared spectral characteristics | |
| CN109146003B (en) | Hyperspectral imaging-based classification identification method, device and system | |
| CN113655027A (en) | Method for rapidly detecting tannin content in plant by near infrared | |
| CN117250169A (en) | Method for nondestructively and rapidly distinguishing wild cordyceps sinensis based on model transfer technology | |
| CN106770018A (en) | The method of near infrared spectrum quick test oil plant species | |
| CN109709060B (en) | Method for measuring asphalt softening point, penetration degree and mass loss | |
| CN107238557A (en) | A kind of method of utilization near infrared spectroscopy quick detection calcium carbonate particle diameter distribution |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |