CN105548070B - A kind of apple soluble solid near infrared detection position compensation method and system - Google Patents
A kind of apple soluble solid near infrared detection position compensation method and system Download PDFInfo
- Publication number
- CN105548070B CN105548070B CN201511031809.1A CN201511031809A CN105548070B CN 105548070 B CN105548070 B CN 105548070B CN 201511031809 A CN201511031809 A CN 201511031809A CN 105548070 B CN105548070 B CN 105548070B
- Authority
- CN
- China
- Prior art keywords
- apple
- soluble solid
- near infrared
- spectrum
- predetermined patterns
- 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
- 239000007787 solid Substances 0.000 title claims abstract description 135
- 238000001514 detection method Methods 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000000862 absorption spectrum Methods 0.000 claims abstract description 57
- 238000002329 infrared spectrum Methods 0.000 claims abstract description 42
- 238000001914 filtration Methods 0.000 claims abstract description 21
- 241000220225 Malus Species 0.000 claims description 165
- 238000001228 spectrum Methods 0.000 claims description 22
- 241001164374 Calyx Species 0.000 claims description 14
- 235000021016 apples Nutrition 0.000 claims description 10
- 238000011156 evaluation Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 7
- 238000001028 reflection method Methods 0.000 claims description 3
- 238000002835 absorbance Methods 0.000 claims description 2
- 230000008033 biological extinction Effects 0.000 claims 2
- 230000003595 spectral effect Effects 0.000 abstract description 23
- 238000004519 manufacturing process Methods 0.000 abstract description 6
- 230000004927 fusion Effects 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 7
- 235000013399 edible fruits Nutrition 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 3
- 230000001066 destructive effect Effects 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 238000004611 spectroscopical analysis Methods 0.000 description 3
- 239000002344 surface layer Substances 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000002860 competitive effect Effects 0.000 description 2
- 235000011389 fruit/vegetable juice Nutrition 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 229910000530 Gallium indium arsenide Inorganic materials 0.000 description 1
- 238000004566 IR spectroscopy Methods 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 229940088594 vitamin Drugs 0.000 description 1
- 229930003231 vitamin Natural products 0.000 description 1
- 235000013343 vitamin Nutrition 0.000 description 1
- 239000011782 vitamin Substances 0.000 description 1
- 150000003722 vitamin derivatives Chemical class 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
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 provides a kind of apple soluble solid near infrared detection position compensation method and system, which comprises obtains the absorbance spectrum of the predetermined patterns of apple；Obtain the soluble solid content of the predetermined patterns of the apple；According to the absorbance spectrum and the soluble solid content, characteristic wavelength relevant to apple soluble solid is selected out of all band spectral region using characteristic wavelength filtering algorithm, establishes apple soluble solid near infrared spectrum detection model.The spectral information that the present invention passes through the fusion multiple positions of apple, binding characteristic wavelength filtering algorithm, establish apple soluble solid near infrared spectrum detection model, overcome influence of the variation at spectral detection position to apple soluble solid near infrared spectrum detection model, the stability of model is improved, has established theoretical basis for the portable detection and on-line checking of apple soluble solid content in actual production.
Description
Technical field
The present invention relates to fruit quality detection field more particularly to a kind of apple soluble solid near infrared detection positions
Compensation method and system.
Background technique
Soluble solid refers to the general name of all compounds for being dissolved in water in liquid or fluid food, including sugar, acid,
Vitamin, minerals etc..The soluble solid content of apple is the important indicator of measuring apple internal quality, and influences to disappear
The determinant of the person's of expense purchase intention.
Currently, near-infrared spectrum technique is obtained with the advantage of its quick nondestructive in apple soluble solid context of detection
It is widely applied.However, the stability of model is often by the temperature change of apple, the shadow of the factors such as the place of production, kind, seasonal variation
It rings.In addition, the soluble solid content of apple surface is unevenly distributed, distribution trend is gradually risen along carpopodium to calyx direction
Height, accordingly, it is possible to cause to have differences between the spectrum of different parts.
In the prior art, the research about the detection of apple soluble solid near infrared spectrum is mostly to be directed to equator position,
By acquiring the spectral information at apple equator position, apple soluble solid near infrared spectrum detection model is established.Therefore, when
When removing the soluble solid content of prediction other positions of apple such as carpopodium with the model, precision of prediction will be affected.
Summary of the invention
For the defects in the prior art, the present invention provides a kind of apple soluble solid near infrared detection position compensation
Method and system, by merging the spectral information at the multiple positions of apple, binding characteristic wavelength filtering algorithm establishes apple solubility
Solid content near infrared spectrum detection model overcomes the variation at spectral detection position to apple soluble solid near infrared spectrum
The influence of detection model improves the stability of model.
In a first aspect, the present invention provides a kind of apple soluble solid near infrared detection position compensation method, the side
Method includes:
Obtain the absorbance spectrum of the predetermined patterns of apple；
Obtain the soluble solid content of the predetermined patterns of the apple；
According to the absorbance spectrum and the soluble solid content, binding characteristic wavelength filtering algorithm establishes apple
Fruit soluble solid near infrared spectrum detection model；
Wherein, the apple predetermined patterns include carpopodium, equator and the calyx of apple.
Preferably, the absorption spectrum degree of the predetermined patterns for obtaining apple, comprising:
By integrating sphere diffusing reflection method, the absorbance light of the predetermined patterns of the apple in default wave band section is obtained
Spectrum.
Preferably, the absorbance spectrum of the predetermined patterns for obtaining apple, comprising:
Acquire the absorbance spectrum of the predetermined patterns of multiple apples；
Second dervative processing is carried out to the absorbance spectrum of the predetermined patterns of the multiple apple, acquisition is multiple, and treated
Absorbance spectrum.
Preferably, described according to the absorbance spectrum and the soluble solid content, the screening of binding characteristic wavelength
Algorithm establishes apple soluble solid near infrared spectrum detection model, comprising:
Binding characteristic wavelength filtering algorithm is selected solvable with apple from all band absorbance spectrum of the predetermined patterns
The property relevant characteristic wavelength of solid content；
According to the absorbance spectrum and its corresponding solubility under the characteristic wavelength of the predetermined number apple predetermined patterns
Solid content establishes apple soluble solid near infrared spectrum detection model using partial least squares algorithm.
Preferably, the apple soluble solid near infrared spectrum detection model, specifically:
Y=∑ Akλk+B；
Wherein, Y is the estimated value of apple soluble solid content, and k is the characteristic wavelength selected, λkFor under k wavelength
Absorbance spectrum, AkFor λkRegression coefficient, B is constant.
Preferably, which is characterized in that the method also includes:
It tests to the apple soluble solid near infrared spectrum detection model.
It is preferably, described to test to the apple soluble solid near infrared spectrum detection model, comprising:
Obtain the measured value of the trap spectrum and soluble solid content of examining apple；
It is closely red using the apple soluble solid according to the trap spectrum under the characteristic wavelength for examining apple
External spectrum detection model obtains the estimated value of soluble solid content；
The estimated value of the measured value of the soluble solid content and the soluble solid content is compared,
Detection evaluation index is obtained, the detection evaluation index is for judging the apple soluble solid near infrared spectrum detection mould
The estimated performance of type.
Second aspect, the present invention provide a kind of apple soluble solid near infrared detection position compensation system, the system
System includes:
First acquisition unit, the absorbance spectrum of the predetermined patterns for obtaining apple；
Second acquisition unit, the soluble solid content of the predetermined patterns for obtaining the apple；
What modeling unit, the absorbance spectrum obtained according to the first acquisition unit and the second acquisition unit obtained
Soluble solid content, binding characteristic wavelength filtering algorithm establish apple soluble solid near infrared spectrum detection model；
Wherein, the apple predetermined patterns include carpopodium, equator and the calyx of apple.
Preferably, the first acquisition unit, is specifically used for,
Acquire the absorbance spectrum of the predetermined patterns of multiple apples；
Second dervative processing is carried out to the absorbance spectrum of the predetermined patterns of the multiple apple, acquisition is multiple, and treated
Absorbance spectrum.
Preferably, the modeling unit, is specifically used for,
Binding characteristic wavelength filtering algorithm is selected solvable with apple from all band absorbance spectrum of the predetermined patterns
The property relevant characteristic wavelength of solid content；
According to the absorbance spectrum and its corresponding solubility under the characteristic wavelength of the predetermined number apple predetermined patterns
Solid content establishes apple soluble solid near infrared spectrum detection model using partial least squares algorithm.
As shown from the above technical solution, the present invention provides a kind of apple soluble solid near infrared detection position compensation side
Method and system, by merging the spectral information of the multiple positions of apple such as carpopodium, equator and calyx, the screening of binding characteristic wavelength is calculated
Method, establishes apple soluble solid near infrared spectrum detection model, and the variation for overcoming spectral detection position is solvable to apple
Property solid content near infrared spectrum detection model influence, improve the stability of model, be that apple solubility is solid in actual production
The portable detection of shape object content and on-line checking have established theoretical basis.
Detailed description of the invention
In order to illustrate more clearly of the embodiment of the present disclosure or technical solution in the prior art, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Disclosed some embodiments for those of ordinary skill in the art without creative efforts, can be with
Other attached drawings are obtained according to these figures.
Fig. 1 is a kind of apple soluble solid near infrared detection position compensation method that one embodiment of the invention provides
Flow diagram；
Fig. 2 be another embodiment of the present invention provides a kind of apple soluble solid near infrared detection position compensation method
Flow diagram；
Fig. 3 is a kind of apple soluble solid near infrared detection position compensation method that one embodiment of the invention provides
Structure is intended to；
Fig. 4 is the apple spectra collection position schematic diagram that one embodiment of the invention provides；
Fig. 5 is the scatter diagram for the forecast set sample predictions result that one embodiment of the invention provides.
Specific embodiment
With reference to the accompanying drawings and examples, specific embodiments of the present invention will be described in further detail.Implement below
Example is not intended to limit the scope of the invention for illustrating the present invention.
Fig. 1 shows a kind of apple soluble solid near infrared detection position compensation side of one embodiment of the invention offer
The flow diagram of method, as shown in Figure 1, a kind of apple soluble solid near infrared detection position compensation side of the present embodiment
Method, which comprises
S11, obtain apple predetermined patterns absorbance spectrum.
It is understood that the apple predetermined patterns include carpopodium, equator and the calyx of apple.
Specifically, apple is obtained using InGaAs detector by Antaris II ft-nir spectrometer
The carpopodium of fruit, equator and calyx absorbance spectrum.
S12, obtain the apple predetermined patterns soluble solid content.
It is understood that the measurement of apple soluble solid content, which refers to, uses the semi-automatic Abbe of 500 type of Arias
Refractometer (Reichert Inc., USA).
Specifically, after the completion of spectra collection, and then using traditional destructive test successively from the carpopodium of apple, red
Road and calyx are adopted part and are cut with arillate surface layer pulp, and gauze for filtering is placed on, and squeeze out juice 1~2 and drip, measure apple
Soluble solid content.
S13, according to the absorbance spectrum and the soluble solid content, binding characteristic wavelength filtering algorithm is built
Vertical apple soluble solid near infrared spectrum detection model.
The present embodiment passes through the spectral information at the fusion multiple positions of apple, and binding characteristic wavelength filtering algorithm establishes apple
Soluble solid near infrared spectrum detection model, the variation for overcoming spectral detection position are closely red to apple soluble solid
The influence of external spectrum detection model improves the stability of model, just for apple soluble solid content in actual production
It takes detection and on-line checking has established theoretical basis.
Fig. 2 shows another embodiment of the present invention provides a kind of compensation of apple soluble solid near infrared detection position
The flow diagram of method, as shown in Fig. 2, a kind of apple soluble solid near infrared detection position compensation side of the present embodiment
Method, which comprises
S21, obtain apple predetermined patterns absorbance spectrum.
It is understood that obtaining the default of the apple in default wave band section by integrating sphere diffusing reflection method
The absorbance spectrum at position.Wherein, scanning times are 32 times, resolution ratio 4cm-1, the default wave band section is 10000-
4000cm-1。
Above-mentioned step S21 can be following step S211-S212 being not shown in the figure:
S211, the multiple apples of acquisition predetermined patterns absorbance spectrum.
It is understood that sample of multiple apples as modeling should be chosen in order to improve the accuracy of modeling.
S212, second dervative processing is carried out to the absorbance spectrum of the predetermined patterns of the multiple apple, obtains multiple places
Absorbance spectrum after reason.
It is understood that collected absorbance spectrum, often containing the random noise of instrument, in addition, baseline drift,
The spuious introducing for the information such as penetrating of light, also will affect the corresponding relationship between near infrared spectrum and soluble solid content, causes
The reliability and stability of model built reduce.
Specifically, in the present embodiment, second dervative processing, application are carried out by the absorbance spectrum to acquired original
Leading that treated through second order, spectroscopic data carries out subsequent modeling analysis.
S22, obtain the apple predetermined patterns soluble solid content.
It is understood that the measurement of apple soluble solid content, which refers to, uses the semi-automatic Abbe of 500 type of Arias
Refractometer (Reichert Inc., USA).
Specifically, after the completion of spectra collection, and then using traditional destructive test successively from the carpopodium of apple, red
Road and calyx are adopted part and are cut with arillate surface layer pulp, and gauze for filtering is placed on, and squeeze out juice 1~2 and drip, measure apple
Soluble solid content.
S23, according to the absorbance spectrum and the soluble solid content, binding characteristic wavelength filtering algorithm is built
Vertical apple soluble solid near infrared spectrum detection model.
Above-mentioned step S23 can be following step S231-S232 being not shown in the figure:
S231, binding characteristic wavelength filtering algorithm, are selected and apple from all band absorbance spectrum of the predetermined patterns
The relevant characteristic wavelength of fruit soluble solid.
It is understood that there are a large amount of redundancy and colinearity informations between spectral variables, to spectral effective information
The problems such as extraction produces biggish interference, causes model complicated, computationally intensive.
Preferably, in the present embodiment, the spectroscopic data based on above-mentioned multiple detection positions, using competitive adaptive weight
Weighting algorithm, from all band 10000-4000cm-1The characteristic wavelength for picking out apple soluble solid content, for establishing apple
Fruit soluble solid near infrared spectrum detection model.
S232, according under the characteristic wavelength of the predetermined number apple predetermined patterns absorbance spectrum and its it is corresponding can
Dissolubility solid content establishes apple soluble solid near infrared spectrum detection model using partial least squares algorithm.
Specifically, the apple soluble solid near infrared spectrum detection model are as follows:
Y=∑ Akλk+B；
Wherein, Y is the estimated value of apple soluble solid content, and k is the characteristic wavelength selected, λkFor under k wavelength
Absorbance spectrum, AkFor λkRegression coefficient, B is constant.
S24, it tests to the apple soluble solid near infrared spectrum detection model.
Above-mentioned step S24 can be following step S241-S243 being not shown in the figure:
S241, the measured value for obtaining the trap spectrum and soluble solid content of examining apple.
It is understood that can choose and build respectively to verify the precision of prediction and stability of above-mentioned established model
Apple used in mould and new apple obtain the trap spectrum for examining apple as apple is examined, and utilize the method for step S22
Obtain the measured value of its corresponding soluble solid content.
S242, according to it is described examine apple trap spectrum, utilize the apple soluble solid near infrared spectrum
Detection model obtains the estimated value of soluble solid content.
It is understood that utilizing model Y=∑ A according to the trap spectrum for examining applekλk+ B is obtained solvable
The estimated value of property solid content.
S243, the estimated value of the measured value of the soluble solid content and the soluble solid content is carried out
Compare, obtains detection evaluation index, the detection evaluation index is for judging the apple soluble solid near infrared spectrum
The estimated performance of detection model.
It is understood that detection evaluation index includes related coefficient and root-mean-square error.
The present embodiment passes through the spectral information at the fusion multiple positions of apple, and binding characteristic wavelength filtering algorithm establishes apple
Soluble solid near infrared spectrum detection model, the variation for overcoming spectral detection position are closely red to apple soluble solid
The influence of external spectrum detection model improves the stability of model, just for apple soluble solid content in actual production
It takes detection and on-line checking has established theoretical basis.
Fig. 3 show another embodiment of the present invention provides a kind of apple soluble solid near infrared detection position compensation
The structural schematic diagram of system, as shown in figure 3, a kind of apple soluble solid near infrared detection position of the present embodiment compensates system
System 30, comprising:
First acquisition unit 31, the absorbance spectrum of the predetermined patterns for obtaining apple；
Second acquisition unit 32, the soluble solid content of the predetermined patterns for obtaining the apple；
Modeling unit 33, the absorbance spectrum obtained according to the first acquisition unit 31 and the second acquisition unit 32
The soluble solid content of acquisition, binding characteristic wavelength filtering algorithm establish the inspection of apple soluble solid near infrared spectrum
Survey model；
Wherein, the apple predetermined patterns include carpopodium, equator and the calyx of apple.
Another embodiment of the present invention provides a kind of apple soluble solid near infrared detection position compensation system in,
The first acquisition unit 31, is specifically used for,
Acquire the absorbance spectrum of the predetermined patterns of multiple apples；
Second dervative processing is carried out to the absorbance spectrum of the predetermined patterns of the multiple apple, acquisition is multiple, and treated
Absorbance spectrum.
The modeling unit 33, is specifically used for,
Binding characteristic wavelength filtering algorithm is selected solvable with apple from all band absorbance spectrum of the predetermined patterns
The property relevant characteristic wavelength of solid content；
According to the absorbance spectrum and its corresponding solubility under the characteristic wavelength of the predetermined number apple predetermined patterns
Solid content establishes apple soluble solid near infrared spectrum detection model using partial least squares algorithm.
The present embodiment passes through the spectral information at the fusion multiple positions of apple, and binding characteristic wavelength filtering algorithm establishes apple
Soluble solid near infrared spectrum detection model, the variation for overcoming spectral detection position are closely red to apple soluble solid
The influence of external spectrum detection model improves the stability of model, just for apple soluble solid content in actual production
It takes detection and on-line checking has established theoretical basis.
In one particular embodiment of the present invention, as described below:
95 apples are chosen as calibration set, for establishing model；35 apples are chosen as forecast set, for being modeled
The inspection of type.
At room temperature, as shown in figure 4, to all 130 apples, successively from the carpopodium of each apple, equator and 3, calyx
Part acquisition absorbance spectrum.
After the completion of spectra collection, and then using traditional destructive test successively from the carpopodium of apple sample, equator and
Calyx is adopted part and is cut with arillate surface layer pulp, and the soluble solid content of apple is measured.
Second dervative processing is carried out to the absorbance spectrum of acquisition, using treated that spectroscopic data carries out through second dervative
Subsequent modeling analysis.
Binding characteristic wavelength filtering algorithm selects characteristic wave relevant to apple soluble solid out of full band range
It is long, particularly, in this example, using competitive adaptive weight weighting algorithm, from all band 10000-4000cm-1Pick out 66
It is solvable to establish the apple based on selected characteristic wavelength using partial least squares algorithm for the characteristic wavelength of a apple soluble solid
Property solid content near infrared spectrum detection model.
Model expression is as follows:
Y=-56525.898 λ4078.7-22856.338λ4182.8-36943.720λ4269.6+56956.642λ4271.5+
154815.334λ4313.9+113330.183λ4398.8+129408.255λ4504.8-117514.829λ4539.6-121295.514
λ4541.5-121564.421λ4545.3-84672.852λ4636.0-90901.481λ4637.9-82541.703λ4703.5-89625.552
λ4707.3-104470.820λ4738.2-105405.841λ4769.0-106029.872λ4786.4-108989.175λ4788.3-
107924.008λ4796.0-104129.292λ4988.9-103529.299λ4990.8-111549.708λ5085.3-115909.981
λ5490.3-106618.822λ5496.1-116337.682λ5498.0+106438.398λ5688.9+96029.676λ5810.4+
115032.826λ5814.3+107935.301λ5957.0-91748.438λ5958.9-88456.837λ5960.8-95833.780λ5962.8+
199904.1549λ5966.6+189393.5788λ5968.6+160175.552λ6190.3+142319.686λ6196.1+126593.009
λ6198.0+116570.457λ7135.3+122100.435λ7225.9+207595.089λ7239.4-83566.187λ7241.3-
67547.235λ7291.5-63108.673λ7293.4-70816.081λ7320.4-89420.384λ7322.3+171940.532λ7357.1+
175047.273λ7359.0-60733.900λ7362.8-91592.019λ7364.8-85493.596λ7386.0-177139.329λ7387.9-
206453.142λ7391.8-115512.261λ8342.5-129283.029λ8572.0-153976.382λ8573.9-150740.715
λ8575.8-117422.490λ8629.8-114922.986λ8631.8-127950.490λ8633.7+54391.231λ8755.2-
105707.858λ8757.1+242191.880λ8826.5+147387.742λ9513.1+80160.282λ9601.8-159513.138
λ9605.6-220245.358λ9744.5+7.124；
Wherein, Y is the estimated value of apple soluble solid content, and unit is ° Brix.λ4078.7It is for wave number
4078.7cm-1It is corresponding through second order spectral value of leading that treated, 56525.898 be λ4078.7Regression coefficient, 7.124 be constant.
In order to verify the precision of prediction and stability of above-mentioned model built, using above-mentioned model to calibration set, and comprising
There is the soluble solid content of the forecast set sample of 3 different parts spectral informations to be detected, and result is evaluated.
Evaluation index lieutenant colonel's positive correlation coefficient (rc), prediction related coefficient (rp) bigger, correction root-mean-square error (RMSEC), prediction are square
Root error more (RMSEP) is small, illustrates that model prediction performance is better.Prediction result is as shown in table 1 below:
Table 1
Related coefficient between calibration set and the predicted value and measured value of forecast set is all larger than 0.95, and root-mean-square error is small
In 0.5 ° of Brix, satisfied precision of prediction is obtained.Meanwhile preferable prediction is achieved to the forecast set of 3 groups of different parts
As a result, illustrating that the model is insensitive for the variation at spectral detection position.
As shown in figure 5, sample has good linear prediction effect close to regression straight line two sides are distributed in.The above results
Illustrate that the variation at spectral detection position can be reduced to apple soluble solid near infrared spectrum using the method for the present embodiment
The influence of detection model.
In order to verify the validity of selected characteristic wavelength in the spectral information obtained by multiple acquisition positions, with equator position
Spectrum be calibration set, establish the apple soluble solid calibration model based on selected characteristic wavelength, still through contain 3
The prediction the set pair analysis model of different parts spectral information is verified.Modeling and prediction result are as shown in table 2 below.Meanwhile in order to say
The validity of bright characteristic wavelength gives the result of the model based on equator position all band establishment of spectrum in table 2.
Table 2
Compare above-mentioned two model, it can be seen that the apple soluble solid established based on all band equator position is close
Infrared spectroscopy detection model can be generated when being different from the position such as soluble solid content at calyx position for detecting
Fairly obvious error.And the model established based on 66 characteristic wavelengths, while the precision of prediction of model is improved, to 3
A forecast set is without there is biggish prediction error.Therefore, by 66 validity feature wavelength of screening, it can reduce spectrum
Detect the influence for the model that change in location establishes the spectral information based on single position such as equator.
Those of ordinary skill in the art will appreciate that: the above embodiments are only used to illustrate the technical solution of the present invention., and
It is non-that it is limited；Although present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art
It is understood that it is still possible to modify the technical solutions described in the foregoing embodiments, either to part of or
All technical features are equivalently replaced；And these are modified or replaceed, it does not separate the essence of the corresponding technical solution this hair
Bright claim limited range.
Claims (6)
1. a kind of apple soluble solid near infrared detection position compensation method, which is characterized in that the described method includes:
Acquire the absorbance spectrum of the predetermined patterns of multiple apples；
Second dervative processing is carried out to the absorbance spectrum of the predetermined patterns of the multiple apple, obtains multiple treated extinctions
Spend spectrum；
Obtain the soluble solid content of the predetermined patterns of the apple；
Binding characteristic wavelength filtering algorithm is selected solid with apple solubility from all band absorbance spectrum of the predetermined patterns
The relevant characteristic wavelength of shape object；
According under the characteristic wavelength of predetermined number apple predetermined patterns absorbance spectrum and its corresponding soluble solid contain
Amount, establishes apple soluble solid near infrared spectrum detection model using partial least squares algorithm；
Wherein, the apple predetermined patterns include carpopodium, equator and the calyx of apple.
2. the method according to claim 1, wherein it is described obtain apple predetermined patterns absorbance spectrum,
Include:
By integrating sphere diffusing reflection method, the absorbance spectrum of the predetermined patterns of the apple in default wave band section is obtained.
3. the method according to claim 1, wherein the apple soluble solid near infrared spectrum detects mould
Type, specifically:
Y=∑ Akλk+B；
Wherein, Y is the estimated value of apple soluble solid content, and k is the characteristic wavelength selected, λkFor the absorbance under k wavelength
Spectrum, AkFor λkRegression coefficient, B is constant.
4. method according to claim 1-3, which is characterized in that the method also includes:
It tests to the apple soluble solid near infrared spectrum detection model.
5. according to the method described in claim 4, it is characterized in that, described to the apple soluble solid near infrared spectrum
Detection model is tested, comprising:
Obtain the measured value of the absorbance spectrum and soluble solid content of examining apple；
According to the absorbance spectrum under the characteristic wavelength for examining apple, the apple soluble solid near infrared light is utilized
Detection model is composed, the estimated value of soluble solid content is obtained；
The estimated value of the measured value of the soluble solid content and the soluble solid content is compared, is obtained
Evaluation index is detected, the detection evaluation index is for judging the apple soluble solid near infrared spectrum detection model
Estimated performance.
6. a kind of apple soluble solid near infrared detection position compensation system, which is characterized in that the system comprises:
First acquisition unit, the absorbance spectrum of the predetermined patterns for obtaining apple；
Second acquisition unit, the soluble solid content of the predetermined patterns for obtaining the apple；
Modeling unit, the absorbance spectrum obtained according to the first acquisition unit and the second acquisition unit obtain solvable
Property solid content, binding characteristic wavelength filtering algorithm establish apple soluble solid near infrared spectrum detection model；
Wherein, the apple predetermined patterns include carpopodium, equator and the calyx of apple；
The first acquisition unit, is specifically used for,
Acquire the absorbance spectrum of the predetermined patterns of multiple apples；
Second dervative processing is carried out to the absorbance spectrum of the predetermined patterns of the multiple apple, obtains multiple treated extinctions
Spend spectrum；
The modeling unit, is specifically used for,
Binding characteristic wavelength filtering algorithm is selected solid with apple solubility from all band absorbance spectrum of the predetermined patterns
The relevant characteristic wavelength of shape object；
According under the characteristic wavelength of predetermined number apple predetermined patterns absorbance spectrum and its corresponding soluble solid contain
Amount, establishes apple soluble solid near infrared spectrum detection model using partial least squares algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511031809.1A CN105548070B (en) | 2015-12-31 | 2015-12-31 | A kind of apple soluble solid near infrared detection position compensation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511031809.1A CN105548070B (en) | 2015-12-31 | 2015-12-31 | A kind of apple soluble solid near infrared detection position compensation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105548070A CN105548070A (en) | 2016-05-04 |
| CN105548070B true CN105548070B (en) | 2019-03-08 |
Family
ID=55827411
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511031809.1A Active CN105548070B (en) | 2015-12-31 | 2015-12-31 | A kind of apple soluble solid near infrared detection position compensation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105548070B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106124447A (en) * | 2016-06-08 | 2016-11-16 | 沈阳农业大学 | A kind of based on the method for soluble solid content in near-infrared spectral analysis technology detection Fructus Fragariae Ananssae |
| CN107462533A (en) * | 2017-08-11 | 2017-12-12 | 宜宾金铁红林业科技有限公司 | Oily camphor tree fruit based on spectral technique adopts instrument |
| CN108333139A (en) * | 2018-01-15 | 2018-07-27 | 深圳市芭田生态工程股份有限公司 | A kind of apple soluble solid rapid detection method |
| CN109238973A (en) * | 2018-07-18 | 2019-01-18 | 中科谱光科技（天津）有限公司 | A method of detection apple soluble solid content and water content |
| CN109946246B (en) * | 2019-02-27 | 2023-03-14 | 北京农业智能装备技术研究中心 | Detection method and device for soluble solid of apple |
| CN110991469B (en) * | 2019-12-30 | 2022-08-12 | 西南大学 | Fruit soluble solid online detection method and system |
| CN111693487A (en) * | 2020-05-28 | 2020-09-22 | 济南大学 | Fruit sugar degree detection method and system based on genetic algorithm and extreme learning machine |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104062258A (en) * | 2013-05-07 | 2014-09-24 | 山东东阿阿胶股份有限公司 | Method for rapid determination of soluble solids in compound ass-hide glue pulp by near infrared spectroscopy |
-
2015
- 2015-12-31 CN CN201511031809.1A patent/CN105548070B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104062258A (en) * | 2013-05-07 | 2014-09-24 | 山东东阿阿胶股份有限公司 | Method for rapid determination of soluble solids in compound ass-hide glue pulp by near infrared spectroscopy |
Non-Patent Citations (5)
| Title |
|---|
| 小型西瓜品质近红外无损检测的光谱信息采集;韩东海等;《农业机械学报》;20130731;第44卷(第7期);174-178 |
| 苹果产地差异对可溶性固形物近红外光谱检测模型影响的研究;樊书祥等;《分析化学研究报告》;20150228;第43卷(第2期);第239-243页，2 实验部分，3 结果与分析 |
| 苹果可溶性固形物近红外在线光谱变量优选;欧阳爱国等;《农业机械学报》;20140430;第45卷(第4期);220-225 |
| 近红外光谱检测苹果可溶性固形物;章海亮等;《农业工程学报》;20091031;第25卷;340-344 |
| 适宜西瓜检测部位提高近红外光谱糖度预测模型精度;介邓飞等;《农业工程学报》;20140531;第30卷(第9期);229-234 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105548070A (en) | 2016-05-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105548070B (en) | A kind of apple soluble solid near infrared detection position compensation method and system | |
| CN104062263B (en) | The near-infrared universal model detection method of light physical property close fruit quality index | |
| Liu et al. | Use of FT-NIR spectrometry in non-invasive measurements of internal quality of ‘Fuji’apples | |
| Leiva-Valenzuela et al. | Assessment of internal quality of blueberries using hyperspectral transmittance and reflectance images with whole spectra or selected wavelengths | |
| Cayuela | Vis/NIR soluble solids prediction in intact oranges (Citrus sinensis L.) cv. Valencia Late by reflectance | |
| CN103776777B (en) | Method for identifying ginsengs with different growth patterns by using near infrared spectrum technology and determining content of components in ginsengs | |
| Ma et al. | Non-destructive and fast method of mapping the distribution of the soluble solids content and pH in kiwifruit using object rotation near-infrared hyperspectral imaging approach | |
| CN108846203A (en) | The method and device of fruit non-destructive testing | |
| CN104020129A (en) | Method for discriminating fermentation quality of congou black tea based on near-infrared-spectroscopy-combined amino acid analysis technology | |
| CN109211829A (en) | A method of moisture content in the near infrared spectroscopy measurement rice based on SiPLS | |
| CN104062258A (en) | Method for rapid determination of soluble solids in compound ass-hide glue pulp by near infrared spectroscopy | |
| CN111537469A (en) | Apple quality rapid nondestructive testing method based on near-infrared technology | |
| CN109946246A (en) | A kind of detection method and device of apple soluble solid | |
| CN110672578A (en) | Model universality and stability verification method for polar component detection of frying oil | |
| Lu et al. | Nondestructive determination of soluble solids and firmness in mix-cultivar melon using near-infrared CCD spectroscopy | |
| CN106872396A (en) | A kind of method that different nir instruments determine grape pol model conversion | |
| Yu et al. | Parameter optimization in soluble solid content prediction of entire bunches of grape based on near infrared spectroscopic technique | |
| Wang et al. | Influence of the peel on predicting soluble solids content of navel oranges using visible and near-infrared spectroscopy | |
| CN109459408A (en) | A kind of Near-Infrared Quantitative Analysis method based on sparse regression LAR algorithm | |
| Sheng | Determination of shearing force by measuring NDF and ADF in tea stems with hyperspectral imaging technique | |
| Liu et al. | Prediction of valid acidity in intact apples with Fourier transform near infrared spectroscopy | |
| CN109164062A (en) | A kind of method of near infrared ray "Hami" melon titratable acid content value | |
| Pan et al. | Nondestructive measuring soluble solid contents and weight of intact pears based on on-line near-infrared spectroscopy | |
| Ying et al. | Application FT-NIR in rapid estimation of soluble solids content of intact kiwifruits by reflectance mode | |
| Jiang et al. | Hyperspectral determination of reducing sugar in potatoes based on CARS |
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 |