CN108827910A - The method for building up of fruit processed safely time prediction model - Google Patents
The method for building up of fruit processed safely time prediction model Download PDFInfo
- Publication number
- CN108827910A CN108827910A CN201810606610.4A CN201810606610A CN108827910A CN 108827910 A CN108827910 A CN 108827910A CN 201810606610 A CN201810606610 A CN 201810606610A CN 108827910 A CN108827910 A CN 108827910A
- Authority
- CN
- China
- Prior art keywords
- fruit
- time
- processed safely
- prediction model
- absorbing wavelength
- 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.)
- Withdrawn
Links
- 235000013399 edible fruits Nutrition 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000004611 spectroscopical analysis Methods 0.000 claims abstract description 16
- 238000011156 evaluation Methods 0.000 claims abstract description 9
- 238000001514 detection method Methods 0.000 claims abstract description 4
- 238000005286 illumination Methods 0.000 claims abstract description 4
- 238000010801 machine learning Methods 0.000 claims abstract description 4
- 238000012360 testing method Methods 0.000 claims abstract description 4
- 238000002835 absorbance Methods 0.000 claims description 34
- 230000008859 change Effects 0.000 claims description 15
- 230000008033 biological extinction Effects 0.000 claims description 3
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 2
- 238000012706 support-vector machine Methods 0.000 claims description 2
- 241000132456 Haplocarpha Species 0.000 claims 1
- 235000006040 Prunus persica var persica Nutrition 0.000 description 13
- 240000005809 Prunus persica Species 0.000 description 10
- 235000010987 pectin Nutrition 0.000 description 6
- 229920001277 pectin Polymers 0.000 description 6
- 239000001814 pectin Substances 0.000 description 6
- 238000002329 infrared spectrum Methods 0.000 description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 5
- 238000003306 harvesting Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 244000144730 Amygdalus persica Species 0.000 description 3
- 230000001066 destructive effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 241000283690 Bos taurus Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 229930002875 chlorophyll Natural products 0.000 description 1
- 235000019804 chlorophyll Nutrition 0.000 description 1
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000004345 fruit ripening Effects 0.000 description 1
- 230000003301 hydrolyzing effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000009659 non-destructive testing Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The present invention relates to a kind of method for building up of fruit processed safely time prediction model, include the following steps：A fruit sample is selected, the processed safely time of the sample is assessed according to artificial evaluation criterion, a time series is established according to the processed safely time, illumination is carried out to the fruit as evaluation object according to the time series；Transmitted light or reflected light to the fruit carry out light splitting detection and will test the spectroscopic data output of result；The spectroscopic data is analyzed, establishes fruit processed safely time prediction model using unitary bearing calibration or machine learning algorithm.
Description
Technical field
The present invention relates to fruit quality technical field of nondestructive testing more particularly to a kind of fruit processed safely time prediction moulds
The method for building up of type.
Background technique
Pericarp absorbance difference index (IAD) be based on fruit maturation pericarp early period greenery element degrade and its with maturity
Substantial connection and a kind of index established, it utilizes near-infrared spectrum technique, poor by the absorbance for reading 670nm and 720nm
Value forms IAD index, directly reflects the actual content of chlorophyll.The non-destructive determination of IAD is not disruptive to fruit, and reading is fast
Victory is convenient, and carrying out fruit quality estimation to the fruit supply end of the chain has preferable effect.
Based on the above technology, application No. is 201710168443.5 documents to disclose a kind of Peach fruits maturity for the patent No.
The method for building up of prediction model, step include：
(1) veraison is harvested respectively and reaches the Peach fruits of harvesting ripe degree, and is respectively labeled as maturity I and maturity
II；Peach fruits substantially 7 are mature when veraison, pericarp cyan, and color starts to change to red；The fruit for reaching harvest maturity is big
8.5 maturations are caused, the cyan of pericarp background color is gradually taken off, and red colored degree is high；
(2) pericarp absorbance difference IAD is measured to the Peach fruits picked, measures the hardness of Peach fruits；
(3) maturity I, the hardness of maturity II fruit and IAD value are fitted, establish Peach fruits maturity prediction side
Journey y=ax2+bx+c, wherein y is hardness, and x is IAD value, and a, b, c are the quadratic polynomial coefficient that regression analysis fits.
Above-mentioned technical proposal establishes Peach fruits based on the fruit rind absorbance difference IAD of near infrared technology non-destructive determination
Maturity prediction model, through regression forecasting, estimated value and actual observation value difference be not different significant, illustrates that prediction model is with higher
Accuracy, measurement, calculation method are simple, it can be achieved that Peach fruits timely collecting.
The inventors discovered that the fruit after harvesting, it is difficult to evaluate the difference of taste.Such as even if pol is identical, but
In the real and mature soft fruit of immature xylocarp, taste is also very different.At present, practician can only pass through appearance
(color, size) and hardness carry out subjective assessment to the maturity of fruit, are not based on physics and the quantitatively non-of chemical characteristic is broken
The method of bad Fast Evaluation fruit maturity.
The visible and near infrared spectrum acquisition of fruit sample is carried out in fruit equator position；Visible and near infrared spectrum instrument is miniature light
Optical fiber spectrograph, in-built CCD detector array for receiving the signal that diffuses of fruit sample, and spectral signal are changed into
Electric signal, then by A/D transitions be that digital signal by USB interface is input to computer, apple it is visible-near infrared
Spectrogram as shown in Figure 1, the inventors discovered that, in Fig. 1, wavelength be 670nm absorbance highest, wavelength be 710nm extinction
It spends minimum.
Summary of the invention
The purpose of the present invention is to provide a kind of method for building up of fruit processed safely time prediction model, accurately control
Best safety process time or best safety edible time after fruit harvesting improve fruit processing efficiency and processing quality.
Technical scheme is as follows, a kind of method for building up of fruit processed safely time prediction model, including as follows
Step：A fruit sample is selected, the processed safely time of the sample is assessed according to artificial evaluation criterion, is added according to the safety
A time series is established between working hour, and illumination is carried out to the fruit as evaluation object according to the time series；To the fruit
Real transmitted light or reflected light carries out light splitting detection and will test the spectroscopic data output of result；The spectroscopic data is analyzed, is returned
Receive out the fruit at any time sequence variation and change the smallest absorbance absorbing wavelength I, and at any time sequence variation and become
Change maximum absorbance absorbing wavelength II；The absorbance data A that absorbing wavelength is I is extracted from the spectroscopic data, from described
The absorbance data B that absorbing wavelength is II is extracted in spectroscopic data, the absorbance for calculating the every time in the time series is poor
Value C=A-B；In conjunction with absorbance difference C and time series, fruit safety is established using unitary bearing calibration or machine learning algorithm
Process time prediction model.
Further, the unitary bearing calibration establishes fruit processed safely time prediction model and includes：If processed safely
Time is dependent variable, is denoted as Y；Absorbance difference is independent variable, is denoted as X, establishes following linear relationship：Y=A+BX+ §；Formula
In：A and B is undetermined parameter, and A is the intercept of regression straight line；B is the slope of regression straight line, when indicating that X changes a unit, Y's
Mean change situation；§ is stochastic error.
Further, the absorbing wavelength I is 960nm, and the absorbing wavelength II is 810nm.Because in fruit (peach)
Ripe period is chased after, water soluble pectin extracted amount increases as time increases；By comparison spectroscopic data discovery, in absorbing wavelength
Absorbance at 810nm reaches minimum, and changes over time that absorbance change is little, and the extinction at absorbing wavelength 960nm
Sequence variation is larger at any time for degree.
Further, the absorbing wavelength I is 720nm, and the absorbing wavelength II is 670nm.Because at fruit (apple)
Chase after ripe period, water soluble pectin extracted amount increases as time increases, by comparison spectroscopic data discovery, absorb wave
Absorbance at long 670nm reaches minimum, and changes over time that absorbance change is little, and the suction at absorbing wavelength 720nm
Sequence variation is larger at any time for luminosity.
Further, the machine learning algorithm is one or more of artificial neural network, support vector machines.
The beneficial effects of the present invention are：In the ripe period that chases after of fruit, water soluble pectin extracted amount is as time increases
And increase, therefore in the hydrolytic process of pectin, it can use near-infrared spectrum technique, by the suction for reading different absorbing wavelengths
Luminosity difference forms absorbance difference index, the actual content of water soluble pectin directly in reflection fruit, so as to quantify
Then the maturity of fruit evaluates the best safety process time of fruit by quantifying the maturity of fruit or best safety is eaten
Use the time.
Detailed description of the invention
Fig. 1 is the visible and near infrared spectrum figure of apple.
Fig. 2 is the variation diagram that the absorbance of peach changes over time.
Specific embodiment
It elaborates below in conjunction with attached drawing and embodiment to technical solution of the present invention.
As shown in Fig. 2, the inventors discovered that, in the ripe period that chases after of fruit (peach), water soluble pectin extracted amount is with the time
Increase and increase, by comparison spectroscopic data discovery, the absorbance at absorbing wavelength 810nm reaches minimum, and at any time
It is little to change absorbance change, and sequence variation is larger at any time for the absorbance at absorbing wavelength 960nm.
A kind of method for building up of fruit processed safely time prediction model, includes the following steps：A fruit sample is selected,
The processed safely time that the sample is assessed according to artificial evaluation criterion establishes a time sequence according to the processed safely time
Column, if the artificial estimation processed safely time of the sample is 6 days, then establishing an overall length is 6 days, is divided into 60min's between each
Time series carries out illumination to the Peach fruits as evaluation object according to the time series, that is, every 60min；To institute
The transmitted light or reflected light for stating Peach fruits carry out light splitting detection and will test the spectroscopic data output of result；Analyze the spectrum number
According to, summarize the fruit at any time sequence variation and to change the smallest absorbance absorbing wavelength I be 810nm, and at any time
Sequence variation and change maximum absorbance absorbing wavelength II be 960nm；It is I's that absorbing wavelength is extracted from the spectroscopic data
Absorbance data A extracts the absorbance data B that absorbing wavelength is II from the spectroscopic data, calculates in the time series
The absorbance difference C=A-B of every 60min；In conjunction with absorbance difference C and time series, using unitary bearing calibration or engineering
It practises algorithm and establishes fruit processed safely time prediction model.
Further, the unitary bearing calibration establishes fruit processed safely time prediction model and includes：If processed safely
Time is dependent variable, is denoted as Y；Absorbance difference is independent variable, is denoted as X, establishes following linear relationship：Y=A+BX+ §；Formula
In：A and B is undetermined parameter, and A is the intercept of regression straight line；B is the slope of regression straight line, when indicating that X changes a unit, Y's
Mean change situation；§ is stochastic error.
Above description merely relates to certain specific embodiments of the invention, and any those skilled in the art is based on this
The replacement or improvement that the spirit of invention is done should be protection scope of the present invention and covered, protection scope of the present invention Ying Yiquan
Subject to sharp claim.
Claims (5)
1. a kind of method for building up of fruit processed safely time prediction model, includes the following steps：A fruit sample is selected, is pressed
The processed safely time that the sample is assessed according to artificial evaluation criterion establishes a time series according to the processed safely time,
Illumination is carried out to the fruit as evaluation object according to the time series；The transmitted light or reflected light of the fruit are divided
Light detection and the spectroscopic data output that will test result；The spectroscopic data is analyzed, summarizing the fruit, sequence becomes at any time
Change and change the smallest absorbance absorbing wavelength I, and at any time sequence variation and change maximum absorbance absorbing wavelength II；
The absorbance data A that absorbing wavelength is I is extracted from the spectroscopic data, it is II that absorbing wavelength is extracted from the spectroscopic data
Absorbance data B, calculate the absorbance difference C=A-B of every time in the time series；In conjunction with absorbance difference C and
Time series establishes fruit processed safely time prediction model using unitary bearing calibration or machine learning algorithm.
2. the method for building up of fruit processed safely time prediction model according to claim 1, which is characterized in that described one
Fruit processed safely time prediction model is established in first bearing calibration：If the processed safely time is dependent variable, it is denoted as Y；Extinction
Degree difference is independent variable, is denoted as X, establishes following linear relationship：Y=A+BX+ §；In formula：A and B is undetermined parameter, and A is to return
The intercept of straight line；B is the slope of regression straight line, when indicating that X changes a unit, the mean change situation of Y；§ is random error
?.
3. the method for building up of fruit processed safely time prediction model according to claim 1 or 2, which is characterized in that its
It is characterized in that, the absorbing wavelength I is 960nm, and the absorbing wavelength II is 810nm.
4. the method for building up of fruit processed safely time prediction model according to claim 1 or 2, which is characterized in that institute
Stating absorbing wavelength I is 720nm, and the absorbing wavelength II is 670nm.
5. the method for building up of fruit processed safely time prediction model according to claim 1, which is characterized in that the machine
Device learning algorithm is one or more of artificial neural network, support vector machines.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810606610.4A CN108827910A (en) | 2018-06-13 | 2018-06-13 | The method for building up of fruit processed safely time prediction model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810606610.4A CN108827910A (en) | 2018-06-13 | 2018-06-13 | The method for building up of fruit processed safely time prediction model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108827910A true CN108827910A (en) | 2018-11-16 |
Family
ID=64144898
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810606610.4A Withdrawn CN108827910A (en) | 2018-06-13 | 2018-06-13 | The method for building up of fruit processed safely time prediction model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108827910A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112461782A (en) * | 2019-10-17 | 2021-03-09 | 山东金璋隆祥智能科技有限责任公司 | Spectrum correction technology based on GSA near-infrared spectrometer |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06186159A (en) * | 1991-10-04 | 1994-07-08 | Natl Food Res Inst | Non-destructive measurement method for fruits sugar degree with near-infrared transmission spectrum |
| JPH1144638A (en) * | 1997-07-25 | 1999-02-16 | Ishikawajima Harima Heavy Ind Co Ltd | Method for measuring fruit sugar level and fruit sugar level meter |
| JP2002048709A (en) * | 2000-07-31 | 2002-02-15 | Mitsui Mining & Smelting Co Ltd | Internal quality measuring method for vegetable and fruit internal quality evaluating device |
| CN204989006U (en) * | 2015-06-16 | 2016-01-20 | 江西农业大学 | Quick nondestructive test device of navel orange sugar degree |
| CN105738311A (en) * | 2015-12-01 | 2016-07-06 | 昆明睿意铂科技股份有限公司 | Apple sweetness non-damage quick detection method based on near-infrared spectrum technology |
| CN106872370A (en) * | 2017-02-23 | 2017-06-20 | 浙江大学 | Anthocyanin content method for measuring in a kind of red bayberry based on EO-1 hyperion |
-
2018
- 2018-06-13 CN CN201810606610.4A patent/CN108827910A/en not_active Withdrawn
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06186159A (en) * | 1991-10-04 | 1994-07-08 | Natl Food Res Inst | Non-destructive measurement method for fruits sugar degree with near-infrared transmission spectrum |
| JPH1144638A (en) * | 1997-07-25 | 1999-02-16 | Ishikawajima Harima Heavy Ind Co Ltd | Method for measuring fruit sugar level and fruit sugar level meter |
| JP2002048709A (en) * | 2000-07-31 | 2002-02-15 | Mitsui Mining & Smelting Co Ltd | Internal quality measuring method for vegetable and fruit internal quality evaluating device |
| CN204989006U (en) * | 2015-06-16 | 2016-01-20 | 江西农业大学 | Quick nondestructive test device of navel orange sugar degree |
| CN105738311A (en) * | 2015-12-01 | 2016-07-06 | 昆明睿意铂科技股份有限公司 | Apple sweetness non-damage quick detection method based on near-infrared spectrum technology |
| CN106872370A (en) * | 2017-02-23 | 2017-06-20 | 浙江大学 | Anthocyanin content method for measuring in a kind of red bayberry based on EO-1 hyperion |
Non-Patent Citations (3)
| Title |
|---|
| D. STEFANELLI: "Modelling peach and nectarine ripening during storage using the IAD maturity index", 《ACTA HORTICULTURAE》 * |
| JULIANA NYASORDZI: "Utilizing the IAD index to determine internal quality attributes of apples at harvest and after storage", 《POSTHARVEST BIOLOGY AND TECHNOLOGY》 * |
| V. ZIOSI: "A new index based on vis spectroscopy to characterize the progression of ripening in peach fruit", 《POSTHARVEST BIOLOGY AND TECHNOLOGY》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112461782A (en) * | 2019-10-17 | 2021-03-09 | 山东金璋隆祥智能科技有限责任公司 | Spectrum correction technology based on GSA near-infrared spectrometer |
| CN112461782B (en) * | 2019-10-17 | 2022-11-01 | 山东金璋隆祥智能科技有限责任公司 | Spectrum correction technology based on GSA near-infrared spectrometer |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| McGlone et al. | Internal quality assessment of mandarin fruit by vis/NIR spectroscopy | |
| CN102818777B (en) | Fruit maturity degree evaluation method based on spectrum and color measurement | |
| Zou et al. | Selection of the efficient wavelength regions in FT-NIR spectroscopy for determination of SSC of ‘Fuji’apple based on BiPLS and FiPLS models | |
| Xiaobo et al. | Use of FT-NIR spectrometry in non-invasive measurements of soluble solid contents (SSC) of ‘Fuji’apple based on different PLS models | |
| Sun et al. | Simultaneous measurement of brown core and soluble solids content in pear by on-line visible and near infrared spectroscopy | |
| Sun et al. | Achieving robustness to temperature change of a NIRS-PLSR model for intact mango fruit dry matter content | |
| CN108846203A (en) | The method and device of fruit non-destructive testing | |
| Cruz et al. | Nondestructive simultaneous prediction of internal browning disorder and quality attributes in ‘Rocha’pear (Pyrus communis L.) using VIS-NIR spectroscopy | |
| Piazzolla et al. | Spectra evolution over on-vine holding of Italia table grapes: prediction of maturity and discrimination for harvest times using a Vis-NIR hyperspectral device | |
| Shah et al. | Mango maturity classification instead of maturity index estimation: A new approach towards handheld NIR spectroscopy | |
| Subedi et al. | Assessment of potato dry matter concentration using short-wave near-infrared spectroscopy | |
| CN108535250A (en) | ' Fuji ' ripe apples degree lossless detection method based on Streif indexes | |
| JP2002122540A (en) | Fresh product evaluating device and method | |
| Wang et al. | Development of near‐infrared online grading device for long jujube | |
| CN109946246A (en) | A kind of detection method and device of apple soluble solid | |
| Yao et al. | Non-destructive determination of soluble solids content in intact apples using a self-made portable NIR diffuse reflectance instrument | |
| Lu et al. | Nondestructive determination of soluble solids and firmness in mix-cultivar melon using near-infrared CCD spectroscopy | |
| Qi et al. | Rapid and non-destructive determination of soluble solid content of crown pear by visible/near-infrared spectroscopy with deep learning regression | |
| CN108827910A (en) | The method for building up of fruit processed safely time prediction model | |
| Semyalo et al. | Nondestructive online measurement of pineapple maturity and soluble solids content using visible and near-infrared spectral analysis | |
| Hu et al. | Modelling postharvest quality of blueberry affected by biological variability using image and spectral data | |
| CN105158178A (en) | Rapid modeling method for detecting sugar content of navel orange based on spectral peak area in high spectral transmission technology | |
| Wang et al. | Influence of the peel on predicting soluble solids content of navel oranges using visible and near-infrared spectroscopy | |
| JP7360649B2 (en) | Method for measuring chlorophyll content and method for determining ripeness of fruit | |
| Cayuela | Prediction of intact nectarine quality using a Vis/NIR portable spectrometer |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181116 |
|
| WW01 | Invention patent application withdrawn after publication |