CN105717066B - A kind of near infrared spectrum identification model based on weighted correlation coefficient - Google Patents
A kind of near infrared spectrum identification model based on weighted correlation coefficient Download PDFInfo
- Publication number
- CN105717066B CN105717066B CN201610064824.4A CN201610064824A CN105717066B CN 105717066 B CN105717066 B CN 105717066B CN 201610064824 A CN201610064824 A CN 201610064824A CN 105717066 B CN105717066 B CN 105717066B
- Authority
- CN
- China
- Prior art keywords
- spectrum
- correlation coefficient
- weighted correlation
- near infrared
- identification
- 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.)
- Active
Links
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 29
- 238000001228 spectrum Methods 0.000 claims abstract description 64
- 238000004364 calculation method Methods 0.000 claims abstract description 8
- 230000003595 spectral effect Effects 0.000 claims description 12
- 239000013598 vector Substances 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 10
- 238000004519 manufacturing process Methods 0.000 claims description 9
- 241000208125 Nicotiana Species 0.000 claims description 7
- 235000002637 Nicotiana tabacum Nutrition 0.000 claims description 7
- 238000004611 spectroscopical analysis Methods 0.000 claims description 4
- 230000017105 transposition Effects 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims 2
- 235000019504 cigarettes Nutrition 0.000 abstract description 21
- 238000004458 analytical method Methods 0.000 abstract description 12
- 238000004587 chromatography analysis Methods 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 abstract description 2
- 230000007613 environmental effect Effects 0.000 abstract description 2
- 238000001819 mass spectrum Methods 0.000 abstract description 2
- 239000000047 product Substances 0.000 description 51
- 239000000523 sample Substances 0.000 description 24
- 238000000034 method Methods 0.000 description 23
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000010521 absorption reaction Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000002203 pretreatment Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 1
- 238000000862 absorption spectrum Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000013401 experimental design Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 239000006101 laboratory sample Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000000491 multivariate analysis Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 230000000391 smoking effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 239000013589 supplement Substances 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
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 present invention establishes a kind of near infrared spectrum identification model, and a series of spectrum of normal similar products is scanned using near infrared spectrometer, calculates averaged spectrum and is used as with reference to spectrum；Then the weighted correlation coefficient for calculating product spectrum and reference spectra identifies section by the average value and standard deviation calculation of weighted correlation coefficient, establishes identification model.Compared with the Instrumental Analysis such as traditional chromatography, mass spectrum, there is green, environmental protection, it is simple and fast, easily operated advantage, and institute's established model identification accuracy is high, detection efficiency is high, it is at low cost, provide technical guarantee for the product stability analysis of cigarette enterprise and truth identification.
Description
Technical field
The present invention relates to near-infrared spectrum technique field, specifically a kind of near infrared spectrum based on weighted correlation coefficient is known
Other model can be used for the cigarette product true and false and differentiate and quality stability analysis.
Background technology
Near-infrared spectrum technique has the modern analysis feature of analytic process efficiently, green, environmentally friendly, thus as in recent years
Develop one of very fast, noticeable spectral analysis technique.According to the regulation of U.S.'s experiment and materials association (ASTM), wavelength
Ranging from 780~2526mn.Molecule the areas NIR absorption mainly by the sum of fundamental frequencies of the groups such as C-H, 0-H, N-H and C=0 absorb with
Frequency multiplication absorbs composition, and the absorption intensity in this area is low, bands of a spectrum are complicated, overlapping is serious, can not use classical qualitative, quantitative method,
Calibration modeling must be carried out by the multivariate statistics in Chemical Measurement, curve matching, the methods of clustering, and combine it is suitable
The quick multicomponent analysis of model realization.Near-infrared spectrum technique has many advantages, such as quick, lossless, real-time detection, has become
The powerful tool of industrial products analysis.However, near infrared spectrum is collected together feature is weak, data volume is big, visual identity and tradition
Matching algorithm is difficult to obtain the weakness of reliable results.Therefore, there is an urgent need to develop it is a kind of effectively, fast and automatically change degree it is high
Recognizer.
For a long time, cigarette product inherent quality characterization lacks determining for visual pattern mainly by the method for sensory evaluating smoking
Measure description method.With product market competition be growing more intense and the increasingly raising of industrial enterprise's production automation degree, product
The stability of quality and control highlight increasingly, and it is steady for cigarette product quality that there is an urgent need to quick, efficient, easy analysis methods
Qualitatively evaluation and control.
The present invention is in view of the above-mentioned problems, propose a kind of identification model based on weighted correlation coefficient.The model is with a system
Based on the near infrared spectrum for arranging normal similar product, identification model is established by weighted correlation coefficient.In model application, quilt
It is determined as that the near infrared spectrum of normal similar product can be added in model again, to realize the update to identification model, makes
Its is more adaptable, as a result more acurrate.
The similitude of spectrum is weighed in the present invention by weighted correlation coefficient, weighted correlation coefficient can be effectively by light
Spectrum signature is used for the calculating of similitude, to improve the reliability of result.The near infrared spectrum of above-mentioned normal similar product with
Reference spectra height is similar, but exists different；Both denominator is embodied, individual difference is also reflected.Thereby determine that out one
The section of a spectral similarity, the product in this section is similar product, is otherwise non-similar product or abnormal products.
Invention content
To further increase the accuracy of identification of model, the present invention proposes a kind of special based on the extraction of weighted correlation coefficient method
Levy spectrum.Identification model proposed by the present invention is made of reference spectra and identification section.
A series of spectrum of normal similar products is scanned by the present invention using near infrared spectrometer, and then extraction is each
The characteristic of spectrum, using averaged spectrum as with reference to spectrum；The weighted correlation coefficient of product spectrum and reference spectra is calculated, is led to
Average value and the standard deviation calculation identification section for crossing weighted correlation coefficient, establish identification model, the identification model is by reference light
Spectrum and identification section composition.
Specific modeling procedure is as follows：
(1) pre-treatment is carried out to the similar sample of m different batches production first, sample spectra is carried out using near-infrared
Scanning, with vectorial siIndicate that (i=1,2 ..., m), each spectrum includes n data point for the spectroscopic data of i-th of sample.
(2) with spectral vector siFor row vector, the data matrix S of following form is sorted out,
It is calculate by the following formula out averaged spectrum
(3) calculate all spectrum s withWeighted correlation coefficient wcc, wherein w be weight
Wherein, sjWithRespectively indicate spectrum s andJ-th of data point；wjIndicate j-th of data of weight vectors w
Point.
(4) the weight vectors w in step 3 is calculate by the following formula to obtain
Wherein, vectorial d is calculate by the following formula to obtain
Wherein,Subscript T representing matrix transposition.
(5) mean value and standard deviation for calculating wcc, are expressed asAnd d.Establish identification sectionWherein k is
Proportionality coefficient, according to calibration set data setting, so that all wcc are all higher thanIt will
Identification section as such product.
For Unknown Product, its near infrared spectrum is scanned first, with sxIt indicates, is then calculated by the formula in step 3
Weighted correlation coefficient wccx.Judge wccxWhether in identification section If it is then thinking the Unknown Product
It is identical as calibration set product；By sxIt is added in calibration set, repeats step 1-4, update identification section.If not, it is considered that
The Unknown Product is different from calibration set product.
Application weighting related coefficient calculation formula calculates the mean value and mark of the weighted correlation coefficient wcc of all similar spectrum
Quasi- deviation, wherein mean value are usedIt indicates, standard deviation indicates with d, establishes identification sectionWherein k is ratio system
Number.
According to the calculated identification section of weighted correlation coefficient and calibration set data setting, the weighting phase of all similar spectrum
Relationship number wcc is all higher thanThe identification section of such product is
The spectrum in application, by scanning sample to be analysed is being carried out to model, calculates weighted correlation coefficient wccxIf should
Coefficient falls into identification sectionIt can determine that it is similar normal product.
The model is established by weighted correlation coefficient and is identified based on a series of near infrared spectrum of normal similar products
Model.
The near infrared spectrum identification model based on weighted correlation coefficient：It is by sample comminution including step before scanning
40-80 mesh.Affiliated sample is pipe tobacco, offal/or offal.
In model application, being judged as the near infrared spectrum of normal similar product can be added in model again, to
It realizes the supplement to identification model and update, keeps Model suitability stronger, prediction result is more accurate.
Compared with the existing technology, the present invention has following remarkable advantage：
1, a kind of method that authenticity of products and stability recognition model are established based on weighted correlation coefficient proposed by the present invention,
Spectral signature can be effectively used for the calculating of similitude by weighted correlation coefficient, greatly improve the reliable of identification model
Property.
2, it by weighted correlation coefficient, determines the section of a spectral similarity, has both reflected being total to for each spectrum
Same characteristic, and reflect individual difference.Using the near infrared spectrum and reference spectra high similarity of normal similar product, establish
Regional space, it is similar product that Sample Scan spectrum, which is fallen in this section, is non-similar product or abnormal products outside section, can
It effectively avoids judging inaccurate phenomenon, improves Model Identification precision, be the quality stability of the product of tobacco productive corporation
Analysis and the true and false differentiate, provide technical guarantee.
3, used near-infrared spectrum technique, compared with the Instrumental Analysis such as traditional chromatography, mass spectrum, in entire analytic process
Without using chemical reagent, there is green, environmental protection, simple and fast, easily operated advantage, application matrix, weighting in model foundation
The Chemical Measurements tool such as related coefficient, institute's established model identification accuracy is high, and detection efficiency is high, at low cost.
Description of the drawings：
Fig. 1 is the modeling procedure figure of the present invention；
Fig. 2 is the original spectrogram of infrared diaphanoscopy of cigarette shreds；
Fig. 3 is the identification model that A trade mark cigarette shreds near infrared spectrums are established；
Fig. 4 is A, B trade mark Classification and Identification model；
Specific implementation mode：
The specific implementation mode of the present invention is described in further detail below in conjunction with the accompanying drawings.
The modeling procedure of the present invention and embodiment is as follows：Experimental design is carried out first, and sample collection is carried out according to design, it is right
Collected representational sample is pre-processed, and spectra collection is carried out near infrared spectrometer, to the spectrum parameter of acquisition
It optimizes, preprocessing procedures are using the filtering of Norris derivative smoothings, differential process, multiplicative scatter correction, standard normalizing
The methods of change；Waveband selection carries out spectral band in the way of Partial Least Squares, genetic algorithm, without information variable elimination etc.
Optimization.Qualitative analysis model is established after spectrum optimization, according to extraction spectrum characteristic data, establishes data matrix, calculating average light
Spectrum, calculate weighted correlation coefficient and etc. establish near-infrared identification model, after model foundation, spectrum is carried out to sample to be tested and is swept
It retouches, application model is analyzed.See Fig. 1
Embodiment one
In the present embodiment, identification model is used for the stability recognition of similar product.
1, laboratory apparatus
The MPA type Fourier transform near infrared instrument of BRUKER companies (Germany) production, 1095Cyclotec (XF-98B) type
Whirlwind precision cracker.
2, sample collection
In order to make the identification model of foundation that there is extensive fit in the cigarette product of prediction different periods, different platform production
With property, this laboratory sample have chosen 3 different platforms the same trade mark (A) cigarette product 83 produced the 1-12 months in 2015 just
Normal sample is used for model foundation, chooses 31 unknown samples and carries out model external certificate.
3, sample preparation
Cigarette shreds are stripped out, are dried in 40 DEG C of baking oven, so that the moisture content of sample is consistent substantially, then use
1095Cyclotec (XF-98B) type whirlwind precision cracker fully crushes, and crosses 60 mesh sieve.
4, spectral scan and data processing
The MPA type Fourier transform near infrared instrument that the scanning of cigarette shreds sample spectrogram is produced using BRUKER companies (Germany)
(the gold-plated big integrating sphere of band Near-Infrared Quantitative Analysis diffusing reflection and sample spinner sample attachment) carries out, using Bruker OPUS
Middle qualitative analysis software QUANT6.5 handles spectrogram, and concrete operations are as follows：Tobacco powder is packed into specimen cup, in cup
Height be about 3cm, counterweight is pressed on sample after 10s and is taken out, with gauze by the quartz glass wiped clean of bottom of cups, so
Specimen cup is placed in progress NIR scannings on rotating platform afterwards.Operating parameter is：12000~4000cm of spectral scanning range-1, light
Spectral resolution 8cm-1, scanning times 64 times (about 30S).To acquire spectroscopic data through in a manner of and handle the single order for absorption spectrum
Differential.The original scan figure of cigarette shreds is shown in Fig. 2.In modeling process, to eliminate the influence of noise and baseline, led using single order
Number 9 points smooth (Savitzky-Golay) pre-processes the original spectrum after scanning.After Sample Scan, statistics software is used
Spectroscopic data is handled.
5, identification model is established
The establishment step of model is as follows：
5.1 with spectral vector siFor row vector, the data matrix S of following form is sorted out,
It is calculate by the following formula out averaged spectrum
By above-mentioned formula, calculate
5.2 calculate all spectrum s withWeighted correlation coefficient wcc, wherein w be weight
Wherein, sjWithRespectively indicate spectrum s andJ-th of data point；wjIndicate j-th of data of weight vectors w
Point.
Weight vectors w in 5.3 above-mentioned steps is calculate by the following formula to obtain
Wherein, vectorial d is calculate by the following formula to obtain
Wherein,Subscript T representing matrix transposition.
5.4 calculate the mean value and standard deviation of wcc, are expressed asAnd d.Establish identification sectionWherein k is
Proportionality coefficient, according to calibration set data setting, so that all wcc are all higher thanIt will As such product
Identification section.
By the averaged spectrum of 83 A trade mark cigarette shreds spectrum to scanning, in this, as reference spectra；By above-mentioned
Formula calculates the weighted correlation coefficient of 83 trade mark pipe tobacco spectrum and reference spectra；The mean value and mark of these weighted correlation coefficients
Quasi- deviation is 0.9998 and 0.0002025 respectively；It is found by analysis, all weighted correlation coefficients are all higher than 0.9998-3*
0.0002025=0.9992, so the identification section of such product is determined as [0.9992,1], the A trade mark cigarette cigarettes of foundation
The identification model that silk near infrared spectrum is established is shown in Fig. 3：
After will be with batch sample pre-treatment, 6 hours in air be positioned over, then higher level's scanning optical spectrum, calculates the product
Near infrared spectrum and model in reference spectra weighted correlation coefficient, result of calculation 0.9985.This numerical value is known in model
Other section [0.9992,1], so, judge that the product is different from normal product described in identification model.In fact, the product
It is long placed in air before near infrared spectrum scanning, moisture absorption is than more serious, although pipe tobacco essence does not become, moisture is become
Change, quality is affected, abnormal from not seeing spectrally, but the weighted correlation coefficient of spectrum is far below similar production after scanning
Product illustrate that the model can be used for the quality stability analysis of identical product.
6, model is verified
In order to preferably verify the recognition capability of model, the method that this experiment uses external certificate, selection has neither part nor lot in modeling
31 batch samples, with institute's established model to different batches, different platform production A trade mark cigarette be identified, the results are shown in Table 1:
The recognition result of table 1 " A " brand product characteristic model
As a result it shows：31 samples of different batches different platform successfully identify that discrimination 100% illustrates to be built
The accuracy of forecast of model is higher, can be used for the quality stability analysis of cigarette product.
Embodiment two
In the present embodiment, identification model is used for the truth identification of product.
1, laboratory apparatus
The MPA type Fourier transform near infrared instrument of BRUKER companies (Germany) production, 1095Cyclotec (XF-98B) type
Whirlwind precision cracker.
2, sample collection
The cigarette sample chosen in the present embodiment is the trade mark A and B, and product has chosen 5 different platforms, and the production time is
The 1-12 months in 2015, the normal specimens 83 for choosing trade mark A altogether are used for model foundation, choose 17 unknown samples of trade mark B into
Row model truth identification.
3, sample preparation
Cigarette shreds are stripped out, are dried in 40 DEG C of baking ovens, so that the moisture content of sample is consistent substantially, then use
1095Cyclotec (XF-98B) type whirlwind precision cracker fully crushes, and crosses 80 mesh sieve.
The spectral scan and data processing of the present embodiment and method for establishing model are as in the first embodiment, built A, B trade mark is classified
Identification model is shown in Fig. 4：
Use the non-similar product trade mark of infrared diaphanoscopy 51 for the pipe tobacco near infrared spectrum of B, calculating and identification model
The weighted correlation coefficient of middle reference spectra, as a result as shown in Fig. 2 solid dots.It can be seen from the figure that these data point whole positions
In identifying except section, discrimination 100%, therefore, it is determined that being non-similar product.The conclusion and actual conditions are completely the same, from
And demonstrate the validity of identification model.
4, model is verified
In order to preferably verify the recognition capability of model, the method that this experiment uses external certificate, selection has neither part nor lot in modeling
The different trades mark 29 batch cigarette samples, the A trades mark false smoke and the trade mark collected to market with institute's established model are B and the cigarette of C
It is identified, concrete outcome is shown in Table 1:
The recognition result of table 1 " A " brand product characteristic model
As a result it shows：It is not that 29 samples of cigarette of the certified products A trades mark successfully identify that discrimination 100% illustrates to be built
Model can be used for authenticity of products identification.
The above embodiment of the present invention only clearly demonstrates examples made by the present invention, and is not the reality to the present invention
The restriction of mode is applied, for those of ordinary skill in the art, other can also be made on the basis of the above description
Various forms of variations or variation here can not be exhaustive embodiment used, every to belong to technical solution of the present invention
Row of the changes and variations that derived from still in protection scope of the present invention.
Claims (6)
1. a kind of near infrared spectrum identification model based on weighted correlation coefficient, will be a series of normal same using near infrared spectrometer
The spectrum of class product is scanned, and then extracts the characteristic of each spectrum, using averaged spectrum as with reference to spectrum；Calculate production
The weighted correlation coefficient of product spectrum and reference spectra passes through the average value and standard deviation calculation cog region of weighted correlation coefficient
Between, identification model is established, which is made of reference spectra and identification section；
The model foundation includes the following steps：
(1) spectral scan：Near infrared spectrum scanning is carried out to sample to be tested, extracts characteristic spectrum；
(2) data matrix is established：With vectorial siIndicate that (i=1,2 ..., m), each spectrum includes for the spectroscopic data of i-th of sample
N data point；With spectral vector siFor row vector, spectrum data matrix S-shaped formula is as follows,
(3) averaged spectrum is calculated：It is calculated on the basis of step (2) Matrix Formula as follows：
In formula,
(4) calculate all spectrum s withWeighted correlation coefficient, indicated with wcc, formula is as follows：
In formula, sjWithJ-th of data point of spectrum s and s are indicated respectively；wjIndicate that j-th of data point of weight vectors w, w are
Weight；
(5) the weight vectors w calculation formula in step (4) are as follows：
In formula, the calculation formula of vectorial d is as follows：
In formula,Subscript T representing matrix transposition.
2. the near infrared spectrum identification model according to claim 1 based on weighted correlation coefficient, it is characterised in that：Using
Weighted correlation coefficient calculation formula calculates the mean value and standard deviation of the weighted correlation coefficient wcc of all similar spectrum, wherein
Value is usedIt indicates, standard deviation indicates with d, establishes identification sectionWherein k is proportionality coefficient.
3. the near infrared spectrum identification model according to claim 1 or 2 based on weighted correlation coefficient, it is characterised in that：
According to the calculated identification section of weighted correlation coefficient and calibration set data setting, the weighted correlation coefficient of all similar spectrum
Wcc is all higher thanThe identification section of such product is
4. the near infrared spectrum identification model according to claim 3 based on weighted correlation coefficient, it is characterised in that：Right
Model carries out the spectrum in application, by scanning sample to be analysed, calculates weighted correlation coefficient wccxIf the coefficient falls into identification
SectionIt can determine that it is similar normal product.
5. the near infrared spectrum identification model according to claim 4 based on weighted correlation coefficient, it is characterised in that：Including
Sample comminution is 40-80 mesh by step before scanning.
6. the near infrared spectrum identification model according to claim 5 based on weighted correlation coefficient, it is characterised in that：It is affiliated
Sample is pipe tobacco, offal/or offal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610064824.4A CN105717066B (en) | 2016-01-29 | 2016-01-29 | A kind of near infrared spectrum identification model based on weighted correlation coefficient |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610064824.4A CN105717066B (en) | 2016-01-29 | 2016-01-29 | A kind of near infrared spectrum identification model based on weighted correlation coefficient |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105717066A CN105717066A (en) | 2016-06-29 |
| CN105717066B true CN105717066B (en) | 2018-09-18 |
Family
ID=56154383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610064824.4A Active CN105717066B (en) | 2016-01-29 | 2016-01-29 | A kind of near infrared spectrum identification model based on weighted correlation coefficient |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105717066B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107402192A (en) * | 2017-03-03 | 2017-11-28 | 广西中烟工业有限责任公司 | A kind of method of quick analysis essence and flavoring agent quality stability |
| CN108982402B (en) * | 2018-08-01 | 2021-01-08 | 华北电力科学研究院有限责任公司 | Method and system for predicting harm of similar organic pollutants to environment |
| CN109738342B (en) * | 2019-03-18 | 2022-02-18 | 山东金璋隆祥智能科技有限责任公司 | Method for detecting particle size distribution based on near infrared spectrum technology |
| CN110632024B (en) * | 2019-10-29 | 2022-06-24 | 五邑大学 | Quantitative analysis method, device and equipment based on infrared spectrum and storage medium |
| CN112834451B (en) * | 2021-01-12 | 2023-04-18 | 深圳网联光仪科技有限公司 | Sample identification method and device based on infrared spectrum and storage medium |
| CN112697744A (en) * | 2021-01-14 | 2021-04-23 | 中国林业科学研究院木材工业研究所 | Infrared spectrum-based identification method for Dongfei yellow sandalwood artware |
| US20220397560A1 (en) * | 2021-06-10 | 2022-12-15 | Thermo Finnigan Llc | Auto outlier injection identification |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5661558A (en) * | 1994-06-30 | 1997-08-26 | Hitachi, Ltd. | Optical detector for flowing sample and optical detection method for flowing sample |
| CN101620180A (en) * | 2009-05-08 | 2010-01-06 | 合肥美亚光电技术有限责任公司 | Method for rapidly detecting tea quality through near infrared technology |
| CN105891147A (en) * | 2016-03-30 | 2016-08-24 | 浙江中烟工业有限责任公司 | Near infrared spectrum information extraction method based on canonical correlation coefficients |
-
2016
- 2016-01-29 CN CN201610064824.4A patent/CN105717066B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5661558A (en) * | 1994-06-30 | 1997-08-26 | Hitachi, Ltd. | Optical detector for flowing sample and optical detection method for flowing sample |
| CN101620180A (en) * | 2009-05-08 | 2010-01-06 | 合肥美亚光电技术有限责任公司 | Method for rapidly detecting tea quality through near infrared technology |
| CN105891147A (en) * | 2016-03-30 | 2016-08-24 | 浙江中烟工业有限责任公司 | Near infrared spectrum information extraction method based on canonical correlation coefficients |
Non-Patent Citations (3)
| Title |
|---|
| 近红外光谱峰谷相关系数法的研究与验证初探;张学博 等;《中国药师》;20131231;第16卷(第10期);1540－1544 * |
| 近红外光谱相关系数法测定野木瓜片中异性有机物;徐东来 等;《药物分析杂志》;20111231;第31卷(第7期);1423－1424 * |
| 近红外特征谱段相关系数法测定中药胶囊中添加枸橼酸西地那非;王学良;《分析化学》;20091231;第37卷(第12期);1825－1828 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105717066A (en) | 2016-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105717066B (en) | A kind of near infrared spectrum identification model based on weighted correlation coefficient | |
| Fortier et al. | Identification of cotton and cotton trash components by Fourier transform near-infrared spectroscopy | |
| CN104990894B (en) | A kind of gasoline property detection method based on weighting absorbance and similar sample | |
| CN103278473B (en) | The mensuration of pipering and moisture and method for evaluating quality in white pepper | |
| CN106501208A (en) | A kind of tobacco style similitude sorting technique based near infrared light spectrum signature | |
| CN105740898A (en) | Method for establishing classification models by utilizing spectral feature vectors and principal component analysis | |
| CN103091274B (en) | The method of near-infrared diffuse-reflectance spectroscopic assay Radix Salviae Miltiorrhizae for injection Polyphenol Acids moisture | |
| CN101738373A (en) | Method for distinguishing varieties of crop seeds | |
| CN107402192A (en) | A kind of method of quick analysis essence and flavoring agent quality stability | |
| CN102778442A (en) | Method for rapidly identifying type of balsam material liquid for cigarette | |
| CN104062258A (en) | Method for rapid determination of soluble solids in compound ass-hide glue pulp by near infrared spectroscopy | |
| CN106770003A (en) | Wood Identification Method and system based on near-infrared spectrum technique | |
| Li et al. | Nondestructive detection of frying times for soybean oil by NIR-spectroscopy technology with Adaboost-SVM (RBF) | |
| CN107478595A (en) | The method that a kind of the quick discriminating pearl powder true and false and quantitative forecast mix pseudo- shell powder content | |
| CN108051410A (en) | A kind of tobacco root cadmium content rapid detection method based on laser induced breakdown spectroscopy | |
| CN110346445A (en) | A method of based on gas analysis mass spectrogram and near-infrared spectrum analysis tobacco mildew | |
| CN106226267B (en) | A kind of near-infrared assay method of dry chili color value | |
| CN112485216B (en) | Multi-source information fusion Thailand jasmine rice adulteration identification method | |
| CN109540837A (en) | The method that near-infrared quickly detects Boehmeria nivea leaves wood fibre cellulose content | |
| CN105806803A (en) | Multi-index collaborative analysis wavelength combination and selection method thereof | |
| CN102680427A (en) | Method for identifying surface fragrance quality of cigarettes by near infrared spectral analysis technology | |
| CN108318446A (en) | It is a kind of detection the total content of vitamin E of peanut seed near-infrared spectroscopy and application | |
| CN107688007A (en) | A kind of detection method of the heat conduction oil quality based on near-infrared spectral analysis technology | |
| CN106442400B (en) | A kind of method that near infrared spectrum quickly determines soil type fresh tea leaves | |
| Li et al. | Chlorophyll assessment and sensitive wavelength exploration for tea (Camellia sinensis) based on reflectance spectral characteristics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |