CN110487746A - A method of baby cabbage quality is detected based near infrared spectrum - Google Patents
A method of baby cabbage quality is detected based near infrared spectrum Download PDFInfo
- Publication number
- CN110487746A CN110487746A CN201910830792.8A CN201910830792A CN110487746A CN 110487746 A CN110487746 A CN 110487746A CN 201910830792 A CN201910830792 A CN 201910830792A CN 110487746 A CN110487746 A CN 110487746A
- Authority
- CN
- China
- Prior art keywords
- quality
- near infrared
- baby cabbage
- infrared spectrum
- index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 240000007124 Brassica oleracea Species 0.000 title claims abstract description 69
- 235000003899 Brassica oleracea var acephala Nutrition 0.000 title claims abstract description 69
- 235000011301 Brassica oleracea var capitata Nutrition 0.000 title claims abstract description 69
- 235000001169 Brassica oleracea var oleracea Nutrition 0.000 title claims abstract description 69
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 35
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000001514 detection method Methods 0.000 claims abstract description 25
- 238000001228 spectrum Methods 0.000 claims abstract description 13
- 238000010561 standard procedure Methods 0.000 claims abstract description 5
- 238000005259 measurement Methods 0.000 claims abstract description 4
- 238000012706 support-vector machine Methods 0.000 claims description 19
- 238000003860 storage Methods 0.000 claims description 10
- 230000007547 defect Effects 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 4
- CJOBVZJTOIVNNF-UHFFFAOYSA-N cadmium sulfide Chemical compound [Cd]=S CJOBVZJTOIVNNF-UHFFFAOYSA-N 0.000 claims description 3
- 238000012856 packing Methods 0.000 claims description 3
- 230000003595 spectral effect Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 244000174681 Michelia champaca Species 0.000 claims description 2
- 239000006229 carbon black Substances 0.000 claims description 2
- 238000012937 correction Methods 0.000 claims description 2
- 238000009795 derivation Methods 0.000 claims description 2
- 238000009499 grossing Methods 0.000 claims description 2
- 238000005303 weighing Methods 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims 1
- 239000000126 substance Substances 0.000 abstract description 5
- 238000011160 research Methods 0.000 abstract description 4
- 238000005457 optimization Methods 0.000 abstract 1
- 238000004445 quantitative analysis Methods 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 10
- 235000013311 vegetables Nutrition 0.000 description 6
- 238000004806 packaging method and process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 235000010149 Brassica rapa subsp chinensis Nutrition 0.000 description 2
- 235000000536 Brassica rapa subsp pekinensis Nutrition 0.000 description 2
- 241000499436 Brassica rapa subsp. pekinensis Species 0.000 description 2
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 239000004698 Polyethylene Substances 0.000 description 2
- 150000001720 carbohydrates Chemical class 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000035515 penetration Effects 0.000 description 2
- -1 polyethylene Polymers 0.000 description 2
- 229920000573 polyethylene Polymers 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000003908 quality control method Methods 0.000 description 2
- 239000011782 vitamin Substances 0.000 description 2
- 235000013343 vitamin Nutrition 0.000 description 2
- 229940088594 vitamin Drugs 0.000 description 2
- 229930003231 vitamin Natural products 0.000 description 2
- 150000003722 vitamin derivatives Chemical class 0.000 description 2
- 235000005637 Brassica campestris Nutrition 0.000 description 1
- 241001301148 Brassica rapa subsp. oleifera Species 0.000 description 1
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 1
- 102000015781 Dietary Proteins Human genes 0.000 description 1
- 108010010256 Dietary Proteins Proteins 0.000 description 1
- 206010022998 Irritability Diseases 0.000 description 1
- 238000004497 NIR spectroscopy Methods 0.000 description 1
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 1
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 description 1
- 238000000862 absorption spectrum Methods 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000011575 calcium Substances 0.000 description 1
- 229910052791 calcium Inorganic materials 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 235000013325 dietary fiber Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000003925 fat Substances 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000000796 flavoring agent Substances 0.000 description 1
- 235000019634 flavors Nutrition 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 235000021384 green leafy vegetables Nutrition 0.000 description 1
- 230000005283 ground state Effects 0.000 description 1
- 238000001727 in vivo Methods 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 239000003041 laboratory chemical Substances 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 230000004060 metabolic process Effects 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000009659 non-destructive testing Methods 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 230000000050 nutritive effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 150000002894 organic compounds Chemical class 0.000 description 1
- 239000011574 phosphorus Substances 0.000 description 1
- 229910052698 phosphorus Inorganic materials 0.000 description 1
- 239000011591 potassium Substances 0.000 description 1
- 229910052700 potassium Inorganic materials 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 208000007442 rickets Diseases 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000001845 vibrational spectrum Methods 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
- G01N21/3563—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
-
- 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
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/02—Food
- G01N33/025—Fruits or vegetables
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2201/00—Features of devices classified in G01N21/00
- G01N2201/12—Circuits of general importance; Signal processing
- G01N2201/129—Using chemometrical methods
Abstract
The invention discloses a kind of methods based near infrared spectrum detection baby cabbage quality, by collecting the near infrared spectrum data of baby cabbage sample and being fitted using the chemical score that standard method measures, and establish model with Partial Least Squares (PLS) optimization；Optimal Pretreated spectra method is selected, by comparing the coefficient of determination (R of model2) and root-mean-square error (RMSECV) measurement model quality, construct the Quantitative Analysis Model of the baby cabbage near infrared spectrum of high quality.This method can rapidly and accurately predict surface color, mass loss rate, hardness, VC content and the judgement that grade is carried out to baby cabbage quality of baby cabbage, it lays a good foundation for quick, lossless baby cabbage Quality Detection research, there is very strong practicability and wide applicability.
Description
Technical field
The present invention relates to a kind of detection methods of baby cabbage quality, and in particular to one kind detects doll based near infrared spectrum
The method of vegetable matter.
Background technique
Baby cabbage (Brassica campestris), brassicaceous vegetable, also known as miniature Chinese cabbage are in recent years from day
A New Vegetable Varieties of this introduction, receive favor at home.The medical value and nutritive value of baby cabbage are high, Major Nutrient at
It is divided into carbohydrate, protein, dietary fiber, fat, vitamin, calcium, iron, phosphorus etc..Wherein, baby cabbage institute calcic, potassium content compared with
Height is the reason for maintaining nervomuscular irritability and normal function and preventing and treating rickets no better than 2~3 times of Chinese cabbage content
Think vegetables.
The quality of baby cabbage includes marketing quality, nutritional quality and flavor quality.Baby cabbage belongs to leaf vegetables, is adopting
Be metabolized in vivo after plucking it is vigorous, leaf-shrinkage decay, be easy to tarnish；Vitamin and mineral easily aoxidizes or is dissolved in water.It adopts
The metabolism of moisture, protein, carbohydrate will also result in the loss of nutriment afterwards, cause the decline of edible quality.
The detection of these physical and chemical indexes of baby cabbage mainly relies on traditional laboratory chemical detection method, can not apply
The large batch of quality of vegetable monitoring in reality production.Therefore, the Fast Detection Technique to baby cabbage quality is developed, and with whole
Baby cabbage is research object, has weight in multiple link Quality Detections such as baby cabbage production, marketing, food processing and control
The meaning wanted.
Near infrared light be wavelength between visible light and in it is infrared between electromagnetic wave (780~2526nm).Near infrared spectrum
Belong to the frequency multiplication and dominant frequency absorption spectrum of molecular vibration spectrum, the anharmonicity of mainly molecular vibration makes molecular vibration from ground state
To what is generated when high energy order transition, there is stronger penetration capacity.Currently, predicting baby cabbage in storage using near-infrared
The research of quality comparison be rarely reported.
Summary of the invention
To solve the deficiencies in the prior art, the purpose of the present invention is to provide a kind of lossless quick detection baby cabbage qualities
Near infrared spectrum detection method.
In order to achieve the above objectives, the present invention adopts the following technical scheme that:
A method of baby cabbage quality is detected based near infrared spectrum, comprising the following steps:
S1, to the baby cabbage sample stored at a certain temperature, carry out near infrared ray by certain storage number of days,
Collect spectral information；
S2, Pretreated spectra is carried out to the near infrared spectrum of collection；
S3, according to standard method, measure the index of quality of baby cabbage sample respectively, including mass loss rate, color (L*,
B*), VC content, hardness；And quality grade is established according to the variation of the index of quality in storage；
L* value indicates brightness, and value variation range 100~0, brightness is from pure white to black；B* value represents champac, and positive value is
Yellow, negative value are blue.
S4, step S2 pretreated near infrared spectrum is associated with the corresponding index of quality in step S3, is utilized
Software establishes near infrared prediction model；
S5, it brings the near infrared spectrum of baby cabbage to be measured into established prediction model, exports the prediction of baby cabbage to be measured
As a result, including mass loss rate, color, VC content, hardness and quality grade.
The parameter of near infrared ray in above-mentioned steps S1 are as follows: scan the range 4000-10000cm that sets a song to music-1(corresponding wavelength
It is 1000-2500nm), scanning times 32 times, resolution ratio 4cm-1, using diffusing reflection acquisition mode, using carbon black as background.
Pretreated spectra in above-mentioned steps S2, including single order and second order derivation, standard normal variable is used to convert, is polynary
Scatter correction, smoothing denoising go to trend processing, mean value center etc..
The standard method of the index of quality is measured in above-mentioned steps S3, comprising: use weighing method quality measurement loss late, use is portable
Formula color difference meter measures color, VC content is measured with spectrophotometer method, with instrumental test hardness.
The quality grade divided in above-mentioned steps S3, comprising:
1 grade is excellent, the variation of the index of quality are as follows: mass loss rate 0-30%, L* value > 71, Vc content > 59mg/100g；I.e.
Blades integrity is good, and blade is bright orange tender crisp, and tissue tight, toughness are big, zero defect and peculiar smell；
2 grades are good, the variation of the index of quality are as follows: mass loss rate 30%-50%, L* value 68-71, Vc content 47-59mg/
100g；That is leaf color cadmium yellow, integrality is preferable, and tissue is closer, slightly defect, free from extraneous odour；
3 grades are inedible, the variation of the index of quality: for mass loss rate>50%, L* value<68, Vc content<47mg/
100g；That is the micro- Huang of blade, hardness is small, slight to rot.
The software that prediction model is established in above-mentioned steps S4, including the use of MATLAB2010b (The Mathworks, beauty
State) Partial Least Squares (PLS), support vector machines (SVM) establish model in software.
The prediction model established in above-mentioned steps S4, further include filtered out by precision index it is corresponding with the index of quality most
Good prediction model；
The precision index, comprising: coefficient of determination R, forecast set root-mean-square error RMSEP, forecast set standard deviation and
The ratio R PD of square error；
By comparing the coefficient of determination R of model2, forecast set root-mean-square error RMSEP and forecast set standard deviation with it is square
The ratio R PD of root error measures the quality of model, filters out optimum prediction model.
The baby cabbage sample stored under room temperature in above-mentioned steps S1, further include based on being stored under different manner of packings,
Manner of packing includes unpackaged, polyethylene packaging, nano-packaging.
The invention has the beneficial effects that:
(1), the present invention obtains the optical response signals of the baby cabbage under Different Package using near-infrared spectrum technique, uses
Offset minimum binary scheduling algorithm constructs the main quality (such as mass loss rate, color (L*, b*), VC content, hardness) of vegetables
Non-destructive testing and detection model and technology.Prediction model under the conditions of the room temperature storage of foundation, involves a wide range of knowledge, and the scope of application is big；
Wherein, mass loss rate, VC, L*, b* this four indexs prediction result it is preferable, mass loss rate and VC content the two
The prediction R of index2Reach 0.9 or more, provides new technological means for quality testing in baby cabbage process.
(2), the invention proposes the Quality Detection based on baby cabbage near infrared spectrum, the nothing to baby cabbage quality is realized
Damage detection.The Quality Detection of traditional baby cabbage needs the pre-treatment of various chemical reagent, damages to baby cabbage, influences to examine
Survey result；Near infrared spectrum identification can detect baby cabbage, easy to operate, do not cause the features such as any pollution to environment,
Do not need have professional knowledge to tester, using convenient.
Near infrared spectroscopy of the invention is mainly the information for reflecting the chemical bonds such as hydric group, can be covered almost all of
Organic compound and mixture.Since near infrared spectrum has stronger penetration power ability, it can detecte the liquid of sample, consolidate
A variety of states of matters such as body, powder, fiber；Detection method is simple.Sample does not need to be pre-processed when measuring, and has analysis speed
Fastly, analysis efficiency is high, and analysis cost is low, repeatability, favorable reproducibility.
(3), detection method of the invention is the qualitatively and quantitatively side of a set of reliable, practical baby cabbage quality
Method and system can carry out quality control, assortment, convenient for formulating satisfactory examination criteria, to protect to baby cabbage
The quality and safety and stability for demonstrate,proving final baby cabbage product achieve the purpose that quick, efficient quality control.Meanwhile according to preceding
Phase, which tests, establishes the classification standard of baby cabbage, using near-infrared spectrum technique to quality grade of the baby cabbage in storage into
Row prediction, provides certain reference value for the purchase of consumer.
Detailed description of the invention
Fig. 1 is the flow chart of the method for detection baby cabbage quality of the invention.
Fig. 2 is the near-infrared primary light spectrogram of baby cabbage sample of the invention.
Fig. 3 is near infrared spectrometer device figure used in the present invention.
Fig. 4 is the optimum prediction model scatter plot that baby cabbage mass loss rate of the invention detects.
Fig. 5 is the optimum prediction model scatter plot that baby cabbage L* value of the invention detects.
Fig. 6 is the optimum prediction model scatter plot that baby cabbage b* value of the invention detects.
Fig. 7 is the optimum prediction model scatter plot of baby cabbage VC content detection of the invention.
Fig. 8 is the optimum prediction model scatter plot of baby cabbage hardness determination of the invention.
Specific embodiment
Specific introduce is made to the present invention below in conjunction with the drawings and specific embodiments.
Used in the present invention is Antaris II (Thermo, the U.S.) near infrared spectrometer.
Near infrared spectrum by acquiring the baby cabbage of Different Package is established one kind and is based in conjunction with chemometrics algorithm
Baby cabbage quartile length (prediction) model of near infrared spectrum, comprising the following steps:
S1, baby cabbage is selected, is grouped, using whole baby cabbage as research object, every group selection maturity is almost the same,
Baby cabbage of uniform size packs it.Unpackaged (control), polyethylene packaging, nano-packaging these three groups are set,
(temperature is 20 ± 0.5 DEG C, and relative humidity is 85%~90%) storage (also favorable low temperature storage) is placed under room temperature.Often
It is measured every 3 days progress spectra collections and index of correlation.
Every group of processing sample size is 60, and the sample size of three groups of packages groups in total is 180.
Near infrared spectrum is carried out every 3 days to sample using Antaris II (Thermo, the U.S.) near infrared spectrometer
Acquisition.
It is 4000-10000cm that sweep parameter, which is set as spectral scanning range,-1(corresponding wavelength is 1000-2500nm), scanning
Resolution ratio 4cm-1, using diffusing reflection acquisition mode, the averaged spectrum that scanning is 32 times is denoted as sample spectra.
Process are as follows: test sample after booting preheating 30min.Per background of acquisition every other hour.10 babies are chosen daily
Baby's dish is uniformly chosen three faces (3) in every baby cabbage, and every on piece is chosen four parts and is measured.
S2, to the near infrared spectrum of all acquisitions, using in MATLAB2010b (The Mathworks, the U.S.) software
First derivative (1st-derivative) and standard normal transformation (SNV) are pre-processed, to play smooth spectrogram, improve letter
Make an uproar ratio, reduce noise, improve the purpose of accuracy rate.
S3, to all samples collection, using traditional chemical gauging mass loss rate, color (L*, b*), hardness, VC
Content.
S4, by the pretreated near infrared spectrum of each sample respectively with the mass loss rate of measurement, color, hardness,
VC content is associated, using Partial Least Squares (PLS) in MATLAB2010b (The Mathworks, the U.S.) software and supports
Vector machine (SVM) establishes prediction model, with the ratio of 3:1 carry out modeling collection and forecast set division (modeling collection: forecast set=
135:45)。
In mass loss rate PLS prediction model based on all band establishment of spectrum, Rc 2Between 0.82-0.95, Rp 2In
Between 0.80-0.92；In SVM model, Rc 2Between 0.83-0.89, Rp 2In 0.79-0.87.The result shows that with PLS
The model overall effect that algorithm is established is significantly better than SVM model.In PLS model, resulting mould after being pre-processed with SNV
Type prediction effect is best, Rp 2, RMSEP and RPD be respectively 0.96,1.432 and 4.31；In SVM model, pre-processed with 1-st
Obtained prediction model is best, Rp 2, RMSEP and RPD be respectively 0.87,1.359 and 4.10.
In the PLS prediction model of L* value based on all band establishment of spectrum, Rc 2Between 0.65-0.77, Rp2In 0.60-
Between 0.72；In SVM model, Rc 2Between 0.68-0.84, Rp 2In 0.60-0.82.The result shows that with SVM algorithm
The model overall effect of foundation is significantly better than PLS model.And in PLS model, resulting model after being pre-processed with MSC
Prediction effect is best, Rp 2, RMSEP and RPD be respectively 0.72,2.051 and 2.83；In SVM model, institute is pre-processed with MSC
Obtained prediction model is best, Rp 2, RMSEP and RPD be respectively 0.82,2.0131 and 3.15.
In the PLS prediction model of b* value based on all band establishment of spectrum, Rc 2Between 0.68-0.85, Rp 2In 0.67-
Between 0.84；In SVM model, Rc 2Between 0.73-0.80, Rp2 in 0.70-0.75.The result shows that with SVM algorithm
The model overall effect of foundation is significantly better than PLS model.And in PLS model, resulting mould after being pre-processed with 1-st
Type prediction effect is best, Rp 2, RMSEP and RPD be respectively 0.85,1.264 and 3.43；In SVM model, pre-processed with MSC
Obtained prediction model is best, Rp 2, RMSEP and RPD be respectively 0.74,1.310 and 3.06.
In the PLS prediction model of VC based on all band establishment of spectrum, Rc 2Between 0.81-0.85, Rp 2In 0.78-
Between 0.93；In SVM model, Rc 2Between 0.82-0.90, Rp 2In 0.79-0.87.The result shows that with SVM algorithm
The model overall effect of foundation is significantly better than PLS model.And in PLS model, resulting model after being pre-processed with MSC
Prediction effect is best, Rp 2, RMSEP and RPD be respectively 0.95,3.192 and 4.75；It is pre- with Autoscale in SVM model
It is best to handle obtained prediction model, Rp 2, RMSEP and RPD be respectively 0.82,3.315 and 4.01.
In the PLS prediction model of hardness based on all band establishment of spectrum, Rc 2Between 0.45-0.60, Rp 2In 0.40-
Between 0.58；In SVM model, Rc2 is between 0.55-0.60, Rp 2In 0.49-0.60.The result shows that with SVM algorithm
The model overall effect of foundation is significantly better than PLS model.And in PLS model, resulting model after being pre-processed with SNV
Prediction effect is best, Rp 2, RMSEP and RPD be respectively 0.57,2.606 and 2.45；It is pre- with Autoscale in SVM model
It is best to handle obtained prediction model, Rp 2, RMSEP and RPD be respectively 0.60,2.453 and 2.63.
The prediction model of the baby cabbage index of quality of the table 1 based on all band near infrared spectrum
According to the Change Law of Quality of baby cabbage under the conditions of room temperature storage, according to integrality, freshness, the uniformity, appearance
Color carries out quality grade division (1~3 grade) to fresh baby cabbage:
1 grade to be excellent, i.e., blades integrity is good, and blade is bright orange tender crisp, and tissue tight, toughness are big, zero defect and peculiar smell, specifically
Index value is mass loss rate 0-30%, L* value > 71, Vc content > 59mg/100g；
2 grades to be good, i.e. leaf color cadmium yellow, integrality is preferable, organizes closer, slightly defect, free from extraneous odour, specific targets
Value is mass loss rate 30%-50%, value 68-71, Vc content 47-59mg/100g；
3 grades to be inedible, i.e. the micro- Huang of blade, hardness is small, slightly rotten (for commodity boundary), and referring specifically to scale value is quality
Loss late>50%, L* value<68, Vc content<47mg/100g.
According to above-mentioned standard, the corresponding physical and chemical index quality table of grading of sample is shown, utilizes prediction model, prediction prediction
The quality grade of baby cabbage sample in collecting, the results are shown in Table 2:
Table 2 is determined based on the baby cabbage quality grade of near-infrared spectrum technique
The basic principles, main features and advantages of the invention have been shown and described above.The technical staff of the industry should
Understand, the above embodiments do not limit the invention in any form, all obtained by the way of equivalent substitution or equivalent transformation
Technical solution is fallen within the scope of protection of the present invention.
Claims (8)
1. a kind of method based near infrared spectrum detection baby cabbage quality, which comprises the following steps:
S1, the baby cabbage sample stored at a certain temperature is collected by certain storage number of days progress near infrared ray
Spectral information；
S2, Pretreated spectra is carried out to the near infrared spectrum of collection；
S3, according to standard method, measure the index of quality of baby cabbage sample respectively, including mass loss rate, color, VC content,
Hardness；And quality grade is established according to the variation of the index of quality in storage；
S4, step S2 pretreated near infrared spectrum is associated with the corresponding index of quality in step S3, utilizes software
Establish near infrared prediction model；
S5, it brings the near infrared spectrum of baby cabbage to be measured into established prediction model, exports the prediction result of baby cabbage to be measured,
Including mass loss rate, color, VC content, hardness and quality grade；
The color includes L*, b*；
L* value indicates brightness, and value variation range 100~0, brightness is from pure white to black；B* value represents champac, and positive value is yellow,
Negative value is blue.
2. a kind of method based near infrared spectrum detection baby cabbage quality according to claim 1, which is characterized in that institute
State the parameter of near infrared ray in step S1 are as follows: scan the range 4000-10000cm that sets a song to music-1, scanning times 32 times, differentiate
Rate 4cm-1, using carbon black as background.
3. a kind of method based near infrared spectrum detection baby cabbage quality according to claim 1, which is characterized in that institute
State the Pretreated spectra in step S2, including using single order and second order derivation, standard normal variable transformation, multiplicative scatter correction,
Smoothing denoising goes trend to handle.
4. a kind of method based near infrared spectrum detection baby cabbage quality according to claim 1, which is characterized in that institute
State the standard method that the index of quality is measured in step S3, comprising: use weighing method quality measurement loss late, surveyed with portable colorimeter
Determine color, VC content is measured with spectrophotometer method, with instrumental test hardness.
5. a kind of method based near infrared spectrum detection baby cabbage quality according to claim 1, which is characterized in that institute
State the quality grade divided in step S3, comprising:
1 grade is excellent, the variation of the index of quality are as follows: mass loss rate 0-30%, L* value > 71, Vc content > 59mg/100g；That is blade
Integrality is good, and blade is bright orange tender crisp, and tissue tight, toughness are big, zero defect and peculiar smell；
2 grades are good, the variation of the index of quality are as follows: mass loss rate 30%-50%, L* value 68-71, Vc content 47-59mg/100g；
That is leaf color cadmium yellow, integrality is preferable, and tissue is closer, slightly defect, free from extraneous odour；
3 grades are inedible, the variation of the index of quality: for mass loss rate>50%, L* value<68, Vc content<47mg/100g；
That is the micro- Huang of blade, hardness is small, slight to rot.
6. a kind of method based near infrared spectrum detection baby cabbage quality according to claim 1, which is characterized in that institute
State the software that prediction model is established in step S4, including Partial Least Squares, support vector machines.
7. a kind of method based near infrared spectrum detection baby cabbage quality according to claim 1, which is characterized in that institute
The prediction model established in step S4 is stated, further includes filtering out optimum prediction mould corresponding with the index of quality by precision index
Type；
The precision index, comprising: the standard deviation and root mean square of coefficient of determination R, forecast set root-mean-square error RMSEP, forecast set
The ratio R PD of error.
8. a kind of method based near infrared spectrum detection baby cabbage quality according to claim 1, which is characterized in that institute
The baby cabbage sample stored under the room temperature in step S1 is stated, further includes based on being stored under different manner of packings.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910830792.8A CN110487746A (en) | 2019-09-04 | 2019-09-04 | A method of baby cabbage quality is detected based near infrared spectrum |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910830792.8A CN110487746A (en) | 2019-09-04 | 2019-09-04 | A method of baby cabbage quality is detected based near infrared spectrum |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110487746A true CN110487746A (en) | 2019-11-22 |
Family
ID=68556390
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910830792.8A Pending CN110487746A (en) | 2019-09-04 | 2019-09-04 | A method of baby cabbage quality is detected based near infrared spectrum |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110487746A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111624317A (en) * | 2020-06-22 | 2020-09-04 | 南京农业大学 | Nondestructive testing method for judging freshness of baby cabbage |
| CN112098357A (en) * | 2020-08-21 | 2020-12-18 | 南京农业大学 | Strawberry sensory quality grade evaluation method based on near infrared spectrum |
| CN112179871A (en) * | 2020-10-22 | 2021-01-05 | 南京农业大学 | Method for nondestructive detection of caprolactam content in sauce food |
| CN113109290A (en) * | 2021-04-08 | 2021-07-13 | 晨光生物科技集团股份有限公司 | Method for rapidly predicting attenuation speed of natural pigment |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105076361A (en) * | 2014-05-21 | 2015-11-25 | 刘静兵 | Method for preventing decomposition of baby cabbage |
| CN208897745U (en) * | 2018-09-01 | 2019-05-24 | 云南神创蔬菜种植有限公司 | Vegetable preservation device |
-
2019
- 2019-09-04 CN CN201910830792.8A patent/CN110487746A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105076361A (en) * | 2014-05-21 | 2015-11-25 | 刘静兵 | Method for preventing decomposition of baby cabbage |
| CN208897745U (en) * | 2018-09-01 | 2019-05-24 | 云南神创蔬菜种植有限公司 | Vegetable preservation device |
Non-Patent Citations (4)
| Title |
|---|
| ROBERTO BEGHI等: "Application of visible/near infrared spectroscopy to quality control of fresh fruits and vegetables in large‐scale mass distribution channels: a preliminary test on carrots and tomatoes", 《SOCIETY OF CHEMICAL INDUSTRY》 * |
| VALENTINA GIOVENZANA等: "Monitoring of fresh-cut Valerianella locusta Laterr. shelf life by electronic nose and VIS–NIR spectroscopy", 《TALANTA》 * |
| 张哲等: "冷藏车温度场不均匀度对蔬菜保鲜效果的影响", 《农业工程学报》 * |
| 金同铭等: "用近红外光谱法测定大白菜的营养成分", 《华北农学院》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111624317A (en) * | 2020-06-22 | 2020-09-04 | 南京农业大学 | Nondestructive testing method for judging freshness of baby cabbage |
| CN112098357A (en) * | 2020-08-21 | 2020-12-18 | 南京农业大学 | Strawberry sensory quality grade evaluation method based on near infrared spectrum |
| CN112098357B (en) * | 2020-08-21 | 2021-12-10 | 南京农业大学 | Strawberry sensory quality grade evaluation method based on near infrared spectrum |
| CN112179871A (en) * | 2020-10-22 | 2021-01-05 | 南京农业大学 | Method for nondestructive detection of caprolactam content in sauce food |
| CN113109290A (en) * | 2021-04-08 | 2021-07-13 | 晨光生物科技集团股份有限公司 | Method for rapidly predicting attenuation speed of natural pigment |
| CN113109290B (en) * | 2021-04-08 | 2023-03-03 | 晨光生物科技集团股份有限公司 | Method for rapidly predicting attenuation speed of natural pigment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110487746A (en) | A method of baby cabbage quality is detected based near infrared spectrum | |
| Zude et al. | Non-destructive tests on the prediction of apple fruit flesh firmness and soluble solids content on tree and in shelf life | |
| McGlone et al. | Vis/NIR estimation at harvest of pre-and post-storage quality indices for ‘Royal Gala’apple | |
| Jha et al. | Non-destructive determination of firmness and yellowness of mango during growth and storage using visual spectroscopy | |
| CN102507480B (en) | Method for nondestructively and quickly measuring moisture content of tea leaf based on 12 characteristic wavelengths | |
| CN102279168A (en) | Near-infrared spectroscopic technology-based method for fast and undamaged analysis of nutritional quality of whole cottonseed | |
| CN102507459A (en) | Method and system for quick lossless evaluation on freshness of fresh beef | |
| CN104977258B (en) | The quality detecting methods such as tealeaves/cosmetics based on two-dimensional correlation spectra | |
| CN105136737A (en) | Method for fast measuring content of potato flour in steamed buns based on near infrared spectrums | |
| KR100921914B1 (en) | Component measuring apparatus for grain and measuring method using the same | |
| CN106950192A (en) | A kind of method of Contents of Main Components quick detection in vegetable protein beverage based on near-infrared spectral analysis technology | |
| CN103344597B (en) | Anti-flavored-interference near infrared non-destructive testing method for internal components of lotus roots | |
| CN104778349B (en) | One kind is used for rice table soil nitrogen application Classified Protection | |
| CN104237138A (en) | Near infrared determination method for potato reducing sugar | |
| CN109211829A (en) | A method of moisture content in the near infrared spectroscopy measurement rice based on SiPLS | |
| Wang et al. | General model of multi-quality detection for apple from different origins by Vis/NIR transmittance spectroscopy | |
| Xu et al. | Nondestructive detection of internal flavor in ‘Shatian’pomelo fruit based on visible/near infrared spectroscopy | |
| CN110231302A (en) | A kind of method of the odd sub- seed crude fat content of quick measurement | |
| CN109406447A (en) | A kind of near infrared detection method of tannin in sorghum | |
| CN106198423B (en) | A method of ham sausage grade is identified based on visible-near-infrared spectrum analytical technology | |
| CN102519903B (en) | Method for measuring whiteness value of Agaricus bisporus by using near infrared spectrum | |
| CN105158178B (en) | Navel orange pol detection rapid modeling method based on EO-1 hyperion through-transmission technique spectral peak area | |
| CN104914068B (en) | The spectrum rapid detection method of content of trans fatty acids in a kind of grease | |
| CN106124447A (en) | A kind of based on the method for soluble solid content in near-infrared spectral analysis technology detection Fructus Fragariae Ananssae | |
| CN113049526B (en) | Corn seed moisture content determination method based on terahertz attenuated total reflection |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191122 |