CN105548070A - Apple soluble solid near-infrared detection part compensation method and system - Google Patents
Apple soluble solid near-infrared detection part compensation method and system Download PDFInfo
- Publication number
- CN105548070A CN105548070A CN201511031809.1A CN201511031809A CN105548070A CN 105548070 A CN105548070 A CN 105548070A CN 201511031809 A CN201511031809 A CN 201511031809A CN 105548070 A CN105548070 A CN 105548070A
- Authority
- CN
- China
- Prior art keywords
- apple
- soluble solid
- predetermined patterns
- near infrared
- spectrum
- 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.)
- Granted
Links
- 239000007787 solid Substances 0.000 title claims abstract description 139
- 238000001514 detection method Methods 0.000 title claims abstract description 85
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000001228 spectrum Methods 0.000 claims abstract description 18
- 238000000862 absorption spectrum Methods 0.000 claims description 61
- 238000002329 infrared spectrum Methods 0.000 claims description 47
- 238000001914 filtration Methods 0.000 claims description 23
- 241001164374 Calyx Species 0.000 claims description 14
- 238000007689 inspection Methods 0.000 claims description 10
- 238000002835 absorbance Methods 0.000 claims description 8
- 230000036961 partial effect Effects 0.000 claims description 7
- 238000012360 testing method Methods 0.000 claims description 4
- 230000003595 spectral effect Effects 0.000 abstract description 23
- 238000004519 manufacturing process Methods 0.000 abstract description 6
- 238000012216 screening Methods 0.000 abstract description 3
- 241000220225 Malus Species 0.000 description 136
- 238000004458 analytical method Methods 0.000 description 3
- 235000021016 apples Nutrition 0.000 description 3
- 230000001066 destructive effect Effects 0.000 description 3
- 238000004611 spectroscopical analysis Methods 0.000 description 3
- 230000002860 competitive effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 235000011389 fruit/vegetable juice Nutrition 0.000 description 2
- 229910000530 Gallium indium arsenide Inorganic materials 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 238000012512 characterization method Methods 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
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 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
- 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 invention provides an apple soluble solid near-infrared detection part compensation method and system. The method includes the steps an absorbancy spectrum of the preset portion of an apple is obtained; the soluble solid content of the preset portion of the apple is obtained; according to the absorbancy spectrum and the soluble solid content, a characteristic wavelength screening algorithm is applied to select characteristic wavelengths related to the apple soluble solid content in a full-wave band spectral range, and an apple soluble solid near-infrared detection model is set up. Spectral information of multiple portions of the apple is fused, the characteristic wavelength screening algorithm is combined, the apple soluble solid near-infrared detection model is set up, the influence on the apple soluble solid near-infrared detection model by changes of spectrum detection is overcome, the stability of the model is improved, and a theoretical basis is laid for portable detection and online detection of apple soluble solid in practical production.
Description
Technical field
The present invention relates to fruit quality detection field, particularly relate to a kind of apple soluble solid near infrared detection position compensation method and system.
Background technology
Soluble solid refers to all general names being dissolved in the compound of water in liquid or fluid food, comprises sugar, acid, vitamin, mineral matter etc.The soluble solid content of apple is the important indicator of measuring apple internal quality, is also the determinative affecting consumer's purchase intention.
At present, near-infrared spectrum technique is widely applied in apple soluble solid context of detection with the advantage of its quick nondestructive.But the stability of model is often subject to the temperature variation of apple, the impact of the factors such as the place of production, kind, seasonal variation.In addition, the soluble solid content skewness of apple surface, its distribution trend raises along carpopodium gradually to calyx direction, therefore, may cause there are differences between the spectrum of different parts.
In prior art, mostly the research detected about apple soluble solid near infrared spectrum is for position, equator, by gathering the spectral information at position, apple equator, sets up apple soluble solid near infrared spectrum detection model.Therefore, when the soluble solid content going to prediction other positions of apple as carpopodium with this model, its precision of prediction will be affected.
Summary of the invention
For defect of the prior art, the invention provides a kind of apple soluble solid near infrared detection position compensation method and system, by merging the spectral information at the multiple position of apple, in conjunction with characteristic wavelength filtering algorithm, set up apple soluble solid near infrared spectrum detection model, the change overcoming spectral detection position, on the impact of apple soluble solid near infrared spectrum detection model, improves the stability of model.
First aspect, the invention provides a kind of apple soluble solid near infrared detection position compensation method, described method comprises:
Obtain the absorbance spectrum of the predetermined patterns of apple;
Obtain the soluble solid content of the predetermined patterns of described apple;
According to described absorbance spectrum and described soluble solid content, in conjunction with characteristic wavelength filtering algorithm, set up apple soluble solid near infrared spectrum detection model;
Wherein, described apple predetermined patterns comprises the carpopodium of apple, equator and calyx.
Preferably, the absorption spectrum degree of the predetermined patterns of described acquisition apple, comprising:
By integrating sphere diffuse reflection methodology, obtain the absorbance spectrum of the predetermined patterns of the described apple preset in wave band interval.
Preferably, the absorbance spectrum of the predetermined patterns of described acquisition apple, comprising:
Gather the absorbance spectrum of the predetermined patterns of multiple apple;
Second derivative process is carried out to the absorbance spectrum of the predetermined patterns of described multiple apple, obtains the absorbance spectrum after multiple process.
Preferably, described according to described absorbance spectrum and described soluble solid content, in conjunction with characteristic wavelength filtering algorithm, set up apple soluble solid near infrared spectrum detection model, comprising:
In conjunction with characteristic wavelength filtering algorithm, from all band absorbance spectrum of described predetermined patterns, select the characteristic wavelength relevant to apple soluble solid;
According to the soluble solid content of the absorbance spectrum under the characteristic wavelength of described predetermined number apple predetermined patterns and correspondence thereof, partial least squares algorithm is adopted to set up apple soluble solid near infrared spectrum detection model.
Preferably, described apple soluble solid near infrared spectrum detection model, is specially:
Y＝∑A
kλ
k+B；
Wherein, Y is the estimated value of apple soluble solid content, and k is the characteristic wavelength selected, λ
kfor the absorbance spectrum under k wavelength, A
kfor λ
kregression coefficient, B is constant.
Preferably, it is characterized in that, described method also comprises:
Described apple soluble solid near infrared spectrum detection model is tested.
Preferably, described described apple soluble solid near infrared spectrum detection model to be tested, comprising:
Obtain the inspection absorbance log spectrum of apple and the measured value of soluble solid content;
According to the absorbance log spectrum under the characteristic wavelength of described inspection apple, utilize described apple soluble solid near infrared spectrum detection model, obtain the estimated value of soluble solid content;
The estimated value of the measured value of described soluble solid content and described soluble solid content is compared, obtain checking and appraising index, described checking and appraising index is for judging the estimated performance of described apple soluble solid near infrared spectrum detection model.
Second aspect, the invention provides a kind of apple soluble solid near infrared detection position bucking-out system, described system comprises:
First acquiring unit, for obtaining the absorbance spectrum of the predetermined patterns of apple;
Second acquisition unit, for obtaining the soluble solid content of the predetermined patterns of described apple;
Modeling unit, the soluble solid content that the absorbance spectrum obtained according to described first acquiring unit and described second acquisition unit obtain, in conjunction with characteristic wavelength filtering algorithm, sets up apple soluble solid near infrared spectrum detection model;
Wherein, described apple predetermined patterns comprises the carpopodium of apple, equator and calyx.
Preferably, described first acquiring unit, specifically for,
Gather the absorbance spectrum of the predetermined patterns of multiple apple;
Second derivative process is carried out to the absorbance spectrum of the predetermined patterns of described multiple apple, obtains the absorbance spectrum after multiple process.
Preferably, described modeling unit, specifically for,
In conjunction with characteristic wavelength filtering algorithm, from all band absorbance spectrum of described predetermined patterns, select the characteristic wavelength relevant to apple soluble solid;
According to the soluble solid content of the absorbance spectrum under the characteristic wavelength of described predetermined number apple predetermined patterns and correspondence thereof, partial least squares algorithm is adopted to set up apple soluble solid near infrared spectrum detection model.
As shown from the above technical solution, the invention provides a kind of apple soluble solid near infrared detection position compensation method and system, by merging the spectral information of the multiple position of apple as carpopodium, equator and calyx, in conjunction with characteristic wavelength filtering algorithm, set up apple soluble solid near infrared spectrum detection model, overcome the change at spectral detection position to the impact of apple soluble solid near infrared spectrum detection model, improve the stability of model, for the portable detection of apple soluble solid content in actual production and on-line checkingi have established theoretical foundation.
Accompanying drawing explanation
In order to be illustrated more clearly in disclosure embodiment or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only embodiments more of the present disclosure, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these figure.
The schematic flow sheet of a kind of apple soluble solid near infrared detection position compensation method that Fig. 1 provides for one embodiment of the invention;
The schematic flow sheet of a kind of apple soluble solid near infrared detection position compensation method that Fig. 2 provides for another embodiment of the present invention;
The structure intention of a kind of apple soluble solid near infrared detection position compensation method that Fig. 3 provides for one embodiment of the invention;
The apple spectra collection position schematic diagram that Fig. 4 provides for one embodiment of the invention;
The scatter diagram of the forecast set sample predictions result that Fig. 5 provides for one embodiment of the invention.
Embodiment
Below in conjunction with drawings and Examples, the specific embodiment of the present invention is described in further detail.Following examples for illustration of the present invention, but are not used for limiting the scope of the invention.
Fig. 1 shows the schematic flow sheet of a kind of apple soluble solid near infrared detection position compensation method that one embodiment of the invention provides, as shown in Figure 1, a kind of apple soluble solid near infrared detection position compensation method of the present embodiment, described method comprises:
The absorbance spectrum of the predetermined patterns of S11, acquisition apple.
Be understandable that, described apple predetermined patterns comprises the carpopodium of apple, equator and calyx.
Specifically, by AntarisII ft-nir spectrometer, adopt InGaAs detecting device, obtain the absorbance spectrum of the carpopodium of apple, equator and calyx.
S12, obtain the soluble solid content of the predetermined patterns of described apple.
Be understandable that, the mensuration of apple soluble solid content is with reference to adopting the semi-automatic Abbe refractometer (ReichertInc., USA) of Arias500 type.
Specifically, after spectra collection completes, and then utilize traditional destructive test to adopt part from the carpopodium of apple, equator and calyx successively and cut band arillate top layer pulp, be placed on gauze for filtering, extrude juice 1 ~ 2, measure the soluble solid content of apple.
S13, according to described absorbance spectrum and described soluble solid content, in conjunction with characteristic wavelength filtering algorithm, set up apple soluble solid near infrared spectrum detection model.
The present embodiment is by merging the spectral information at the multiple position of apple, in conjunction with characteristic wavelength filtering algorithm, set up apple soluble solid near infrared spectrum detection model, overcome the change at spectral detection position to the impact of apple soluble solid near infrared spectrum detection model, improve the stability of model, for the portable detection of apple soluble solid content in actual production and on-line checkingi have established theoretical foundation.
Fig. 2 shows the schematic flow sheet of a kind of apple soluble solid near infrared detection position compensation method that another embodiment of the present invention provides, as shown in Figure 2, a kind of apple soluble solid near infrared detection position compensation method of the present embodiment, described method comprises:
The absorbance spectrum of the predetermined patterns of S21, acquisition apple.
Be understandable that, by integrating sphere diffuse reflection methodology, obtain the absorbance spectrum of the predetermined patterns of the described apple preset in wave band interval.Wherein, scanning times is 32 times, and resolution is 4cm
-1, described default wave band interval is 10000-4000cm
-1.
Above-mentioned step S21 can be following not shown step S211-S212:
S211, gather the absorbance spectrum of the predetermined patterns of multiple apple.
Being understandable that, in order to improve the accuracy of modeling, the sample of multiple apple as modeling should being chosen.
S212, second derivative process is carried out to the absorbance spectrum of the predetermined patterns of described multiple apple, obtain the absorbance spectrum after multiple process.
Be understandable that, the absorbance spectrum collected, the random noise often containing instrument, in addition, the spuious introducing of the information such as to penetrate of baseline wander, light, also can affect the corresponding relation between near infrared spectrum and soluble solid content, cause the reliability and stability of institute's established model to reduce.
Specifically, in the present embodiment, by carrying out second derivative process to the absorbance spectrum of acquired original, applying and leading the spectroscopic data after process through second order and carry out follow-up modeling analysis.
S22, obtain the soluble solid content of the predetermined patterns of described apple.
Be understandable that, the mensuration of apple soluble solid content is with reference to adopting the semi-automatic Abbe refractometer (ReichertInc., USA) of Arias500 type.
Specifically, after spectra collection completes, and then utilize traditional destructive test to adopt part from the carpopodium of apple, equator and calyx successively and cut band arillate top layer pulp, be placed on gauze for filtering, extrude juice 1 ~ 2, measure the soluble solid content of apple.
S23, according to described absorbance spectrum and described soluble solid content, in conjunction with characteristic wavelength filtering algorithm, set up apple soluble solid near infrared spectrum detection model.
Above-mentioned step S23 can be following not shown step S231-S232:
S231, in conjunction with characteristic wavelength filtering algorithm, from all band absorbance spectrum of described predetermined patterns, select the characteristic wavelength relevant to apple soluble solid.
Be understandable that between spectral variables, to there is a large amount of redundancies and colinearity information, larger interference is created to the extraction of spectral effective information, cause the problems such as model is complicated, calculated amount is large.
Preferably, in the present embodiment, based on the spectroscopic data at above-mentioned multiple detection position, the heavy weighting algorithm of competitive self-adaptation is adopted, from all band 10000-4000cm
-1pick out the characteristic wavelength of apple soluble solid content, for setting up apple soluble solid near infrared spectrum detection model.
S232, soluble solid content according to the absorbance spectrum under the characteristic wavelength of described predetermined number apple predetermined patterns and correspondence thereof, adopt partial least squares algorithm to set up apple soluble solid near infrared spectrum detection model.
Specifically, described apple soluble solid near infrared spectrum detection model is:
Y＝∑A
kλ
k+B；
Wherein, Y is the estimated value of apple soluble solid content, and k is the characteristic wavelength selected, λ
kfor the absorbance spectrum under k wavelength, A
kfor λ
kregression coefficient, B is constant.
S24, described apple soluble solid near infrared spectrum detection model to be tested.
Above-mentioned step S24 can be following not shown step S241-S243:
S241, the acquisition inspection absorbance log spectrum of apple and the measured value of soluble solid content.
Be understandable that, in order to verify precision of prediction and the stability of above-mentioned institute Modling model, modeling apple used and new apple can be chosen respectively as inspection apple, obtain the absorbance log spectrum of inspection apple, and utilize the method for step S22 to obtain the measured value of the soluble solid content of its correspondence.
S242, absorbance log spectrum according to described inspection apple, utilize described apple soluble solid near infrared spectrum detection model, obtains the estimated value of soluble solid content.
Be understandable that, according to the absorbance log spectrum of described inspection apple, utilize model Y=∑ A
kλ
k+ B, obtains the estimated value of soluble solid content.
S243, the estimated value of the measured value of described soluble solid content and described soluble solid content to be compared, obtain checking and appraising index, described checking and appraising index is for judging the estimated performance of described apple soluble solid near infrared spectrum detection model.
Be understandable that, checking and appraising index comprises related coefficient and root-mean-square error.
The present embodiment is by merging the spectral information at the multiple position of apple, in conjunction with characteristic wavelength filtering algorithm, set up apple soluble solid near infrared spectrum detection model, overcome the change at spectral detection position to the impact of apple soluble solid near infrared spectrum detection model, improve the stability of model, for the portable detection of apple soluble solid content in actual production and on-line checkingi have established theoretical foundation.
Fig. 3 shows the structural representation of a kind of apple soluble solid near infrared detection position bucking-out system that another embodiment of the present invention provides, and as shown in Figure 3, a kind of apple soluble solid near infrared detection position bucking-out system 30 of the present embodiment, comprising:
First acquiring unit 31, for obtaining the absorbance spectrum of the predetermined patterns of apple;
Second acquisition unit 32, for obtaining the soluble solid content of the predetermined patterns of described apple;
Modeling unit 33, the soluble solid content that the absorbance spectrum obtained according to described first acquiring unit 31 and described second acquisition unit 32 obtain, in conjunction with characteristic wavelength filtering algorithm, sets up apple soluble solid near infrared spectrum detection model;
Wherein, described apple predetermined patterns comprises the carpopodium of apple, equator and calyx.
In a kind of apple soluble solid near infrared detection position bucking-out system that another embodiment of the present invention provides,
Described first acquiring unit 31, specifically for,
Gather the absorbance spectrum of the predetermined patterns of multiple apple;
Second derivative process is carried out to the absorbance spectrum of the predetermined patterns of described multiple apple, obtains the absorbance spectrum after multiple process.
Described modeling unit 33, specifically for,
In conjunction with characteristic wavelength filtering algorithm, from all band absorbance spectrum of described predetermined patterns, select the characteristic wavelength relevant to apple soluble solid;
According to the soluble solid content of the absorbance spectrum under the characteristic wavelength of described predetermined number apple predetermined patterns and correspondence thereof, partial least squares algorithm is adopted to set up apple soluble solid near infrared spectrum detection model.
The present embodiment is by merging the spectral information at the multiple position of apple, in conjunction with characteristic wavelength filtering algorithm, set up apple soluble solid near infrared spectrum detection model, overcome the change at spectral detection position to the impact of apple soluble solid near infrared spectrum detection model, improve the stability of model, for the portable detection of apple soluble solid content in actual production and on-line checkingi have established theoretical foundation.
In one particular embodiment of the present invention, as described below:
Choose 95 apples as calibration set, for Modling model; Choose 35 apples as forecast set, for the inspection of institute's established model.
At room temperature, as shown in Figure 4, to all 130 apples, absorbance spectrum is gathered from the carpopodium of each apple, equator and calyx 3 parts successively.
After spectra collection completes, and then utilize traditional destructive test to adopt part from the carpopodium of apple sample, equator and calyx successively and cut band arillate top layer pulp, measure the soluble solid content of apple.
Second derivative process is carried out to the absorbance spectrum gathered, applies the spectroscopic data after second derivative process and carry out follow-up modeling analysis.
In conjunction with characteristic wavelength filtering algorithm, in full band range, select the characteristic wavelength relevant to apple soluble solid, especially, in this example, adopt the heavy weighting algorithm of competitive self-adaptation, from all band 10000-4000cm
-1pick out the characteristic wavelength of 66 apple soluble solids, adopt partial least squares algorithm foundation based on the apple soluble solid near infrared spectrum detection model of selected characteristic wavelength.
Model expression is as follows:
Y＝-56525.898λ
4078.7-22856.338λ
4182.8-36943.720λ
4269.6+56956.642λ
4271.5+154815.334λ
4313.9+113330.183λ
4398.8+129408.255λ
4504.8-117514.829λ
4539.6-121295.514λ
4541.5-121564.421λ
4545.3-84672.852λ
4636.0-90901.481λ
4637.9-82541.703λ
4703.5-89625.552λ
4707.3-104470.820λ
4738.2-105405.841λ
4769.0-106029.872λ
4786.4-108989.175λ
4788.3-107924.008λ
4796. 0-104129.292λ
4988.9-103529.299λ
4990.8-111549.708λ
5085.3-115909.981λ
5490.3-106618.822λ
5496.1-116337.682λ
5498.0+106438.398λ
5688.9+96029.676λ
5810.4+115032.826λ
5814.3+107935.301λ
5957.0-91748.438λ
5958.9-88456.837λ
5960.8-95833.780λ
5962.8+199904.1549λ
5966.6+189393.5788λ
5968.6+160175.552λ
6190.3+142319.686λ
6196.1+126593.009λ
6198.0+116570.457λ
713 5.3+122100.435λ
7225.9+207595.089λ
7239.4-83566.187λ
7241.3-67547.235λ
7291.5-63108.673λ
7 293.4-70816.081λ
7320.4-89420.384λ
7322.3+171940.532λ
7357.1+175047.273λ
7359.0-60733.900λ
7362.8-91592.019λ
7364.8-85493.596λ
7386.0-177139.329λ
7387.9-206453.142λ
7391.8-115512.261λ
8342.5-129283.029λ
8572.0-153976.382λ
8573.9-150740.715λ
8575.8-117422.490λ
8629.8-114922.986λ
8631.8-127950.490λ
8633.7+54391.231λ
8755.2-105707.858λ
8757.1+242191.880λ
8826.5+147387.742λ
9513.1+80160.282λ
9601.8-159513.138λ
9605.6-220245.358λ
9744.5+7.124；
Wherein, Y is the estimated value of apple soluble solid content, and unit is a ° Brix.λ
4078.7for wave number is 4078.7cm
-1corresponding leads the spectral value after process through second order, and 56525.898 is λ
4078.7regression coefficient, 7.124 is constant.
In order to verify precision of prediction and the stability of above-mentioned institute established model, utilize above-mentioned model to calibration set, and the soluble solid content of the forecast set sample including 3 different parts spectral informations detecting, and result is evaluated.Evaluation index lieutenant colonel positive correlation coefficient (r
c), prediction related coefficient (r
p) larger, correction root-mean-square error (RMSEC), predicted root mean square error more (RMSEP) are little, illustrate that model prediction performance is better.Predict the outcome as shown in table 1 below:
Table 1
Related coefficient between the predicted value of calibration set and forecast set and measured value is all greater than 0.95, and root-mean-square error is all less than 0.5 ° of Brix, obtains satisfied precision of prediction.Meanwhile, the forecast set of 3 groups of different parts is all achieved and predicts the outcome preferably, illustrate that this model is insensitive for the change at spectral detection position.
As shown in Figure 5, sample, near being distributed in regression straight line both sides, has good linear prediction effect.The method of the above results application the present embodiment can reduce the change at spectral detection position to the impact of apple soluble solid near infrared spectrum detection model.
In order to verify by the validity of characteristic wavelength selected in the spectral information of multiple collection positions acquisition, with the spectrum at position, equator for calibration set, set up the apple soluble solid calibration model based on selected characteristic wavelength, still verified by the prediction the set pair analysis model containing 3 different parts spectral informations.Modeling and predict the outcome as shown in table 2 below.Meanwhile, in order to the validity of characterization wavelength, in table 2, give the result of the model based on position, equator all band establishment of spectrum.
Table 2
Contrast above-mentioned two models, can find out, based on the apple soluble solid near infrared spectrum detection model that position, all band equator is set up, when soluble solid content for detecting with its different parts as calyx position, fairly obvious error can be produced.And based on the model that 66 characteristic wavelengths are set up, while the precision of prediction of model is improved, all larger predicated error is not occurred to 3 forecast sets.Therefore, by 66 validity feature wavelength of screening, the impact of spectral detection change in location on the model set up as the spectral information in equator based on single position can be reduced.
One of ordinary skill in the art will appreciate that: above each embodiment, only in order to technical scheme of the present invention to be described, is not intended to limit; Although with reference to foregoing embodiments to invention has been detailed description, those of ordinary skill in the art is to be understood that: it still can be modified to the technical scheme described in foregoing embodiments, or carries out equivalent replacement to wherein some or all of technical characteristic; And these amendments or replacement, do not make the essence of appropriate technical solution depart from the scope of the claims in the present invention.
Claims (10)
1. an apple soluble solid near infrared detection position compensation method, is characterized in that, described method comprises:
Obtain the absorbance spectrum of the predetermined patterns of apple;
Obtain the soluble solid content of the predetermined patterns of described apple;
According to described absorbance spectrum and described soluble solid content, in conjunction with characteristic wavelength filtering algorithm, set up apple soluble solid near infrared spectrum detection model;
Wherein, described apple predetermined patterns comprises the carpopodium of apple, equator and calyx.
2. method according to claim 1, is characterized in that, the absorption spectrum degree of the predetermined patterns of described acquisition apple, comprising:
By integrating sphere diffuse reflection methodology, obtain the absorbance spectrum of the predetermined patterns of the described apple preset in wave band interval.
3. method according to claim 1, is characterized in that, the absorbance spectrum of the predetermined patterns of described acquisition apple, comprising:
Gather the absorbance spectrum of the predetermined patterns of multiple apple;
Second derivative process is carried out to the absorbance spectrum of the predetermined patterns of described multiple apple, obtains the absorbance spectrum after multiple process.
4. method according to claim 3, is characterized in that, described according to described absorbance spectrum and described soluble solid content, in conjunction with characteristic wavelength filtering algorithm, sets up apple soluble solid near infrared spectrum detection model, comprising:
In conjunction with characteristic wavelength filtering algorithm, from all band absorbance spectrum of described predetermined patterns, select the characteristic wavelength relevant to apple soluble solid;
According to the soluble solid content of the absorbance spectrum under the characteristic wavelength of described predetermined number apple predetermined patterns and correspondence thereof, partial least squares algorithm is adopted to set up apple soluble solid near infrared spectrum detection model.
5. method according to claim 4, is characterized in that, described apple soluble solid near infrared spectrum detection model, is specially:
Y＝∑A
kλ
k+B；
Wherein, Y is the estimated value of apple soluble solid content, and k is the characteristic wavelength selected, λ
kfor the absorbance spectrum under k wavelength, A
kfor λ
kregression coefficient, B is constant.
6. the method according to any one of claim 1-5, is characterized in that, described method also comprises:
Described apple soluble solid near infrared spectrum detection model is tested.
7. method according to claim 6, is characterized in that, describedly tests to described apple soluble solid near infrared spectrum detection model, comprising:
Obtain the inspection absorbance log spectrum of apple and the measured value of soluble solid content;
According to the absorbance log spectrum under the characteristic wavelength of described inspection apple, utilize described apple soluble solid near infrared spectrum detection model, obtain the estimated value of soluble solid content;
The estimated value of the measured value of described soluble solid content and described soluble solid content is compared, obtain checking and appraising index, described checking and appraising index is for judging the estimated performance of described apple soluble solid near infrared spectrum detection model.
8. an apple soluble solid near infrared detection position bucking-out system, is characterized in that, described system comprises:
First acquiring unit, for obtaining the absorbance spectrum of the predetermined patterns of apple;
Second acquisition unit, for obtaining the soluble solid content of the predetermined patterns of described apple;
Modeling unit, the soluble solid content that the absorbance spectrum obtained according to described first acquiring unit and described second acquisition unit obtain, in conjunction with characteristic wavelength filtering algorithm, sets up apple soluble solid near infrared spectrum detection model;
Wherein, described apple predetermined patterns comprises the carpopodium of apple, equator and calyx.
9. system according to claim 8, is characterized in that, described first acquiring unit, specifically for,
Gather the absorbance spectrum of the predetermined patterns of multiple apple;
Second derivative process is carried out to the absorbance spectrum of the predetermined patterns of described multiple apple, obtains the absorbance spectrum after multiple process.
10. system according to claim 8, is characterized in that, described modeling unit, specifically for,
In conjunction with characteristic wavelength filtering algorithm, from all band absorbance spectrum of described predetermined patterns, select the characteristic wavelength relevant to apple soluble solid;
According to the soluble solid content of the absorbance spectrum under the characteristic wavelength of described predetermined number apple predetermined patterns and correspondence thereof, partial least squares algorithm is adopted to set up apple soluble solid near infrared spectrum detection model.
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 true CN105548070A (en) | 2016-05-04 |
| CN105548070B 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) |
Cited By (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 |
| CN109946246A (en) * | 2019-02-27 | 2019-06-28 | 北京农业智能装备技术研究中心 | A kind of detection method and device of apple soluble solid |
| CN110991469A (en) * | 2019-12-30 | 2020-04-10 | 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 |
|---|
| 介邓飞等: "适宜西瓜检测部位提高近红外光谱糖度预测模型精度", 《农业工程学报》 * |
| 樊书祥等: "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", 《分析化学研究报告》 * |
| 欧阳爱国等: "苹果可溶性固形物近红外在线光谱变量优选", 《农业机械学报》 * |
| 章海亮等: "近红外光谱检测苹果可溶性固形物", 《农业工程学报》 * |
| 韩东海等: "小型西瓜品质近红外无损检测的光谱信息采集", 《农业机械学报》 * |
Cited By (9)
| 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 |
| CN109946246A (en) * | 2019-02-27 | 2019-06-28 | 北京农业智能装备技术研究中心 | A kind of detection method and device of apple soluble solid |
| 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 |
| CN110991469A (en) * | 2019-12-30 | 2020-04-10 | 西南大学 | Fruit soluble solid online detection method and system |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105548070B (en) | 2019-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105548070A (en) | Apple soluble solid near-infrared detection part compensation method and system | |
| Liu et al. | Nondestructive measurement of soluble solid content of navel orange fruit by visible–NIR spectrometric technique with PLSR and PCA-BPNN | |
| JP5441703B2 (en) | Visible / Near-Infrared Spectroscopy and Grape Brewing Method | |
| CN101413885A (en) | Near-infrared spectrum method for rapidly quantifying honey quality | |
| CN103278473B (en) | The mensuration of pipering and moisture and method for evaluating quality in white pepper | |
| CN104062256A (en) | Soft measurement method based on near infrared spectroscopy | |
| CN105891147A (en) | Near infrared spectrum information extraction method based on canonical correlation coefficients | |
| CN104020129A (en) | Method for discriminating fermentation quality of congou black tea based on near-infrared-spectroscopy-combined amino acid analysis technology | |
| CN101929951A (en) | Method for distinguishing milk doped with ewe's milk by near infrared spectrum | |
| CN104062258A (en) | Method for rapid determination of soluble solids in compound ass-hide glue pulp by near infrared spectroscopy | |
| CN109211829A (en) | A method of moisture content in the near infrared spectroscopy measurement rice based on SiPLS | |
| JP2007171196A (en) | Method for determining dimensional stability of wooden product from simple algebraic function of moisture, shrinkage factor and woodgrain angle | |
| Beghi et al. | Rapid monitoring of grape withering using visible near‐infrared spectroscopy | |
| CN107703097A (en) | Utilize the method and its application of decay total reflection probe and the model of near infrared spectrometer structure fast prediction oil property | |
| CN104062259A (en) | Method for rapid determination of total saponin content in compound ass-hide glue pulp by near infrared spectroscopy | |
| CN111044469A (en) | Fruit soluble solid detection method and equipment based on single integrating sphere | |
| CN108037084A (en) | A kind of anti-jamming measurement methods suitable for photometry principle water quality automatic analyzer | |
| CN103344597A (en) | Anti-flavored-interference near infrared non-destructive testing method for internal components of lotus roots | |
| CN107860743A (en) | Utilize the method and its application of the model of reflective near infrared fibre-optical probe structure fast prediction oil property | |
| CN104596979A (en) | Method for measuring cellulose of reconstituted tobacco by virtue of near infrared reflectance spectroscopy technique | |
| CN105738311A (en) | Apple sweetness non-damage quick detection method based on near-infrared spectrum technology | |
| CN109946246B (en) | Detection method and device for soluble solid of apple | |
| CN110672578A (en) | Model universality and stability verification method for polar component detection of frying oil | |
| CN104596976A (en) | Method for determining protein of paper-making reconstituted tobacco through ear infrared reflectance spectroscopy technique | |
| CN110376154A (en) | Fruit online test method and system based on spectrum correction |
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 |