CN109409580A - Method based on apple feedstock specifications prediction fruit juice turbidity - Google Patents
Method based on apple feedstock specifications prediction fruit juice turbidity Download PDFInfo
- Publication number
- CN109409580A CN109409580A CN201811148007.2A CN201811148007A CN109409580A CN 109409580 A CN109409580 A CN 109409580A CN 201811148007 A CN201811148007 A CN 201811148007A CN 109409580 A CN109409580 A CN 109409580A
- Authority
- CN
- China
- Prior art keywords
- apple
- fruit juice
- feedstock specifications
- data
- cider
- 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
- 235000015203 fruit juice Nutrition 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 34
- 239000002994 raw material Substances 0.000 claims abstract description 38
- 235000019987 cider Nutrition 0.000 claims abstract description 36
- 238000013528 artificial neural network Methods 0.000 claims abstract description 26
- 238000012549 training Methods 0.000 claims abstract description 23
- 235000013399 edible fruits Nutrition 0.000 claims description 9
- 238000010219 correlation analysis Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 235000016709 nutrition Nutrition 0.000 claims description 3
- 230000035764 nutrition Effects 0.000 claims description 3
- 210000000697 sensory organ Anatomy 0.000 claims description 2
- 235000015197 apple juice Nutrition 0.000 abstract description 8
- 238000011161 development Methods 0.000 abstract description 4
- 238000001514 detection method Methods 0.000 abstract 1
- 241000220225 Malus Species 0.000 description 100
- 235000011389 fruit/vegetable juice Nutrition 0.000 description 19
- KRKNYBCHXYNGOX-UHFFFAOYSA-N citric acid Chemical compound OC(=O)CC(O)(C(O)=O)CC(O)=O KRKNYBCHXYNGOX-UHFFFAOYSA-N 0.000 description 12
- 238000004519 manufacturing process Methods 0.000 description 8
- 235000021016 apples Nutrition 0.000 description 6
- 238000005070 sampling Methods 0.000 description 6
- 238000011160 research Methods 0.000 description 5
- 238000012216 screening Methods 0.000 description 4
- 235000000346 sugar Nutrition 0.000 description 4
- 241000607479 Yersinia pestis Species 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- JVTAAEKCZFNVCJ-UHFFFAOYSA-N lactic acid Chemical group CC(O)C(O)=O JVTAAEKCZFNVCJ-UHFFFAOYSA-N 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- HNDVDQJCIGZPNO-UHFFFAOYSA-N histidine Natural products OC(=O)C(N)CC1=CN=CN1 HNDVDQJCIGZPNO-UHFFFAOYSA-N 0.000 description 2
- 235000014304 histidine Nutrition 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 235000005976 Citrus sinensis Nutrition 0.000 description 1
- 240000002319 Citrus sinensis Species 0.000 description 1
- 240000003604 Dillenia indica Species 0.000 description 1
- HNDVDQJCIGZPNO-YFKPBYRVSA-N L-histidine Chemical compound OC(=O)[C@@H](N)CC1=CN=CN1 HNDVDQJCIGZPNO-YFKPBYRVSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000796 flavoring agent Substances 0.000 description 1
- 235000019634 flavors Nutrition 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 235000021581 juice product Nutrition 0.000 description 1
- 239000004310 lactic acid Substances 0.000 description 1
- 235000014655 lactic acid Nutrition 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000015277 pork Nutrition 0.000 description 1
- 239000002244 precipitate Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 239000003381 stabilizer Substances 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
Classifications
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Primary Health Care (AREA)
- Non-Alcoholic Beverages (AREA)
Abstract
The invention discloses the methods based on apple feedstock specifications prediction fruit juice turbidity, comprising: chooses apple sample, determines apple feedstock specifications, and obtain apple feedstock specifications data and cider haze numbers evidence;Establish the correlativity of apple feedstock specifications data Yu cider haze numbers evidence;Determination is to cider haze numbers according in significant relevant apple raw material core index data;Training sample is chosen from apple sample, obtains the apple feedstock specifications data of training sample, and using the apple raw material core index data of training sample as input layer, using cider turbidity as output layer, training obtains neural-network learning model;Using the raw material core index data of neural-network learning model and apple to be measured, the fruit juice turbidity of apple to be measured is predicted.The present invention can quickly judge fruit juice turbidity, and then understand the stability of fruit juice, solve that the detection of fruit juice stability indicator is cumbersome, and used time longer problem meets the demand of fresh apple juice industry fast development.
Description
Technical field
The present invention relates to a kind of methods for predicting fruit juice turbidity.It is more particularly related to be based on apple raw material
The method of index prediction fruit juice turbidity.
Background technique
Apple occupies first of the big fruit in the world four, and China is maximum apple production state and country of consumption in the world, China's apple
Plantation is extensively and kind is also relatively abundant.Apple is mainly to be squeezed into juice to eat in addition to being used as fresh food.Fruit juice according to processing method not
Normal juice and non-concentrated also Normal juice are gone back with concentration can be divided into.The non-concentrated also Normal juice of fresh apple juice, i.e. apple, adds without numerous
Engineering sequence, mouthfeel is fresh, flavor is natural, full of nutrition, favor of the quality closer to fresh apple, by numerous consumers.
Fresh apple juice is turbid succulent fruits juice, therefore stability is bad, easily precipitates during shelf, affects fresh squeezing apple
Quality of the turbid juice in shelf life, intermediate links.It, can be with currently, to keep the stability in fruit juice and fruit drink shelf life
Alleviated by addition stabilizer, but it solves fruit juice stability problem not from source.The existing research to product property
The methods of step analysis, grey correlation independent analysis, such as Wu Houjiu et al. is mostly used to differentiate that sweet orange kind adds with percentage
The quantitative evaluation method of work suitability, Song Jie et al. handle achievement data with range transformation method, obtain the quality that pork rinses food
Evaluation result, such method can only evaluate the processing characteristics of studied kind, the processing performance of unpredictable unknown sample.
Turbidity and the variation of shelf life internal haze degree are the important indicators for measuring turbid succulent fruits juice stability, if there is a kind of side
Method can predict that apple raw material is prepared into the fresh stability indicator for squeezing turbid juice, and then determine whether this apple variety is suitable for that fresh squeezing is turbid
Juice processing strictly screens the apple variety that the turbid juice of high stability is processed from raw material angle, that will be from the source of fruit juice production
The determining juice customizations apple variety offer effective ways processed of industry, promotion secondary industry raw material standard and juice product quality
It is promoted, promotes the development of China's apple Fresh Juice industry.
Summary of the invention
The object of the present invention is to provide the methods based on apple feedstock specifications prediction fruit juice turbidity, by with artificial mind
Through network, quick predict is fresh to squeeze turbid juice turbidity, and then determines the fresh stability for squeezing turbid juice, solves the inspection of fruit juice stability indicator
Cumbersome, used time longer problem is surveyed, prediction fruit juice product quality is reached, the apple of the turbid juice processing of directed screening high stability is former
The purpose of item kind meets the demand of fresh apple juice industry fast development.
In order to realize these purposes and other advantages according to the present invention, provides and predict fruit juice based on apple feedstock specifications
The method of turbidity, comprising:
Step 1: choosing apple sample, apple feedstock specifications are determined, and it is mixed to obtain apple feedstock specifications data and cider
Turbidity data;
Step 2: establishing the correlativity of the apple feedstock specifications data Yu the cider haze numbers evidence;
Step 3: determination is to the cider haze numbers according in significant relevant apple raw material core index data;
Step 4: choosing training sample from apple sample, the apple feedstock specifications data of training sample are obtained, with training
The apple raw material core index data of sample are input layer, and using cider turbidity as output layer, training obtains Neural Network Science
Practise model;
Step 5: being predicted to be measured using the raw material core index data of the neural-network learning model and apple to be measured
The fruit juice turbidity of apple.
Preferably, in the method based on apple feedstock specifications prediction fruit juice turbidity, the apple raw material refers to
Mark includes physics class index, sense organ class index, processing class index and nutrition class index.
Preferably, it in the method based on apple feedstock specifications prediction fruit juice turbidity, in the step 2, builds
Found the correlativity of the apple feedstock specifications data and the cider haze numbers evidence method particularly includes: to apple raw material
Achievement data and the cider haze numbers according to carrying out correlation analysis, with establish the apple feedstock specifications data with it is described
The correlativity of cider haze numbers evidence.
Preferably, in the method based on apple feedstock specifications prediction fruit juice turbidity, in the step 3, really
Determine to the cider haze numbers according in significant relevant apple raw material core index data method particularly includes: to apple original
Achievement data and the cider haze numbers are expected according to correlation analysis is carried out, and choosing relative coefficient is in the relevant original of conspicuousness
Expect that index as apple raw material core index, determines apple raw material core index data by apple raw material core index.
Preferably, in the method based on apple feedstock specifications prediction fruit juice turbidity, after the step 4,
It is further comprising the steps of before step 5:
It chooses apple and verifies sample, obtain the apple raw material core index data and cider haze numbers of verifying sample
According to, it utilizes the neural-network learning model and verifies the apple raw material core index data of sample, the fruit of acquisition verifying sample
Juice turbidity, if the accuracy of the fruit juice turbidity of the verifying sample obtained by neural-network learning model is lower than 90%,
Increase the quantity of training sample, and update neural-network learning model, or improve setting value, more new apple raw material core refers to
Mark, and re -training obtains neural-network learning model.
Preferably, in the method based on apple feedstock specifications prediction fruit juice turbidity, the Neural Network Science
Practise model training parameter it is as follows: maximum cycle be 1000~20000, learning rate be 0.1~1, factor of momentum be 0.1~
0.5, error amount is 0.00005~0.1.
Preferably, in the method based on apple feedstock specifications prediction fruit juice turbidity, the selection of training sample
Number is 25~40.
Preferably, in the method based on apple feedstock specifications prediction fruit juice turbidity, the apple raw material core
The quantity of heart achievement data is 4~10.
The present invention is include at least the following beneficial effects:
The present invention establishes the quick predict model of cider turbidity with artificial neural network, can determine that the mixed of cider
Turbid stability, and then the apple variety of the turbid juice processing of high stability is screened, the cider of high-quality is produced, is greatly promoted
The development of fresh apple juice industry.
Further advantage, target and feature of the invention will be partially reflected by the following instructions, and part will also be by this
The research and practice of invention and be understood by the person skilled in the art.
Detailed description of the invention
Fig. 1 is according to embodiments of the present invention 1 BP neural network structure chart;
Fig. 2 is according to embodiments of the present invention 2 BP neural network structure chart;
Fig. 3 is according to embodiments of the present invention 3 BP neural network structure chart.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples, to enable those skilled in the art's reference
Specification word can be implemented accordingly.
Embodiment 1
Based on the method for apple feedstock specifications prediction fruit juice turbidity, the specific steps of which are as follows:
(1) apple sample is selected.
41 apple varieties from various parts of the country are chosen as experimental raw, part variety name, the place of production are shown in Table 1.Fruit
Real maturity period sampling, sampling cover early, middle and late ripe three types apple, have no mechanical damage, no disease and pests harm.
1 part apple variety title of table and the place of production
(2) apple feedstock specifications are determined, and obtain apple feedstock specifications data and cider haze numbers evidence.
(3) apple raw material core index is screened.
The correlativity for establishing apple feedstock specifications data Yu cider haze numbers evidence, to apple juice haze numbers evidence
Correlation analysis is carried out with apple feedstock specifications data, the results are shown in Table 2.Obtain core size, pulp L* value, pericarp a* value
Core index with 4 indexs of citric acid as apple raw material.
The correlativity of table 2 apple feedstock specifications data and cider haze numbers evidence
(4) neural-network learning model is constructed.
This research 35 apple samples of random screening from 41 apple samples establish learning model as training sample,
Remaining 6 apple samples carry out the prediction of fruit juice turbidity as forecast sample.As shown in Figure 1, wherein mode input layer is core
4 size, pulp L* value, pericarp a* value and citric acid raw material core index data, model output layer are that Apple is corresponding
Fruit juice haze values, input layer lowest level are model-aided layer, are added automatically by software.The optimal implicit number of plies of model is 5.Its
Remaining each training parameter selection is as follows: maximum cycle 4000, learning rate 0.2, factor of momentum 0.2, error amount 0.001.
(5) forecast sample is verified.
Using neural-network learning model, the results are shown in Table 3 is predicted to the fruit juice turbidity of 6 kind apples,
Wherein, relative error=(the prediction practical turbidity of turbidity -)/practical turbidity × 100%.
3 neural network prediction result of table
As shown in Table 3, the relative error of prediction, which is respectively less than 3%, to be predicted to the fruit juice turbidity of 6 kind apples,
Preset threshold value is that less than 8%, 6 apple sample prediction of absolute relative error is accurate, predictablity rate 100%.
Embodiment 2
A method of fruit juice turbidity is predicted based on apple feedstock specifications, the specific steps of which are as follows:
(1) apple sample is selected.
30 apple varieties from various parts of the country are chosen as experimental raw, part variety name, the place of production are shown in Table 4.Fruit
Real maturity period sampling, sampling cover early, middle and late ripe three types apple, have no mechanical damage, no disease and pests harm.
4 part apple variety title of table and the place of production
(2) apple feedstock specifications are determined, and obtain apple feedstock specifications data and cider haze numbers evidence.
(3) apple raw material core index is screened.
The correlativity for establishing apple feedstock specifications data Yu cider haze numbers evidence, to apple juice haze numbers evidence
Correlation analysis is carried out with apple feedstock specifications data, the results are shown in Table 5.Obtain pulp b* value, reduced sugar, total reducing sugar, lactic acid
Core index with 5 indexs of histidine as apple raw material.
The correlativity of table 5 apple feedstock specifications data and cider haze numbers evidence
(4) learning model is constructed.
This research 25 samples of random screening from 30 apple samples establish learning model, and remaining 5 samples carry out fruit
The prediction of juice turbidity.As shown in Fig. 2, wherein mode input layer is pulp b* value, reduced sugar, 5 total reducing sugar, lactic acid and histidine originals
Expect core index data, model output layer is the corresponding fruit juice haze values of Apple, and input layer lowest level is model-aided
Layer, is added automatically by software.The optimal implicit number of plies of model is 5.Remaining each training parameter selection is as follows: maximum cycle
6000, learning rate 0.2, factor of momentum 0.4, error amount 0.0001.
(5) forecast sample is verified.
Using neural-network learning model, the results are shown in Table 6 is predicted to the fruit juice turbidity of 5 kind apples,
Wherein, relative error=(the prediction practical turbidity of turbidity -)/practical turbidity × 100%.
6 neural network prediction result of table
As shown in Table 6, the relative error of prediction, which is respectively less than 5%, to be predicted to the fruit juice turbidity of 5 kind apples,
Preset threshold value is that less than 8%, 5 apple sample prediction of absolute relative error is accurate, predictablity rate 100%.
Embodiment 3
A method of fruit juice turbidity is predicted based on apple feedstock specifications, the specific steps of which are as follows:
(1) apple sample is selected.
45 apple varieties from various parts of the country are chosen as experimental raw, part variety name, the place of production are shown in Table 7.Fruit
Real maturity period sampling, sampling cover early, middle and late ripe three types apple, have no mechanical damage, no disease and pests harm.
7 part apple variety title of table and the place of production
(2) apple feedstock specifications are determined, and obtain apple feedstock specifications data and cider haze numbers evidence.
(3) apple raw material core index is screened.
The correlativity for establishing apple feedstock specifications data Yu cider haze numbers evidence, to apple juice haze numbers evidence
Correlation analysis is carried out with apple feedstock specifications data, the results are shown in Table 8.Obtain core size, pericarp a* value, pericarp b* and
Core index of 4 indexs of citric acid as apple raw material.
The correlativity of table 8 apple feedstock specifications data and cider haze numbers evidence
(4) learning model is constructed.
This research 40 samples of random screening from 45 apple samples establish learning model, and remaining 5 samples carry out fruit
The prediction of juice turbidity.As shown in figure 3, wherein mode input layer is core size, 4 pericarp a* value, pericarp b* and citric acid originals
Expect core index data, model output layer is the corresponding fruit juice haze values of Apple, and input layer lowest level is model-aided
Layer, is added automatically by software.The optimal implicit number of plies of model is 5.Remaining each training parameter selection is as follows: maximum cycle
10000, learning rate 0.4, factor of momentum 0.5, error amount 0.00001.
(5) forecast sample is verified.
Using neural-network learning model, the results are shown in Table 9 is predicted to the fruit juice turbidity of 5 kind apples,
Wherein, relative error=(the prediction practical turbidity of turbidity -)/practical turbidity × 100%.
9 neural network prediction result of table
As shown in Table 9, the relative error of prediction, which is respectively less than 7%, to be predicted to the fruit juice turbidity of 5 kind apples,
Preset threshold value is that less than 8%, 5 apple sample prediction of absolute relative error is accurate, predictablity rate 100%.
Although the embodiments of the present invention have been disclosed as above, but its is not only in the description and the implementation listed
With it can be fully applied to various fields suitable for the present invention, for those skilled in the art, can be easily
Realize other modification, therefore without departing from the general concept defined in the claims and the equivalent scope, the present invention is simultaneously unlimited
In specific details and legend shown and described herein and embodiment.
Claims (8)
1. the method based on apple feedstock specifications prediction fruit juice turbidity characterized by comprising
Step 1: choosing apple sample, apple feedstock specifications are determined, and obtain apple feedstock specifications data and cider turbidity
Data;
Step 2: establishing the correlativity of the apple feedstock specifications data Yu the cider haze numbers evidence;
Step 3: determination is to the cider haze numbers according in significant relevant apple raw material core index data;
Step 4: choosing training sample from apple sample, the apple feedstock specifications data of training sample are obtained, with training sample
Apple raw material core index data be input layer, using cider turbidity as output layer, training obtain neural network learning mould
Type;
Step 5: predicting apple to be measured using the raw material core index data of the neural-network learning model and apple to be measured
Fruit juice turbidity.
2. the method as described in claim 1 based on apple feedstock specifications prediction fruit juice turbidity, which is characterized in that the apple
Fruit feedstock specifications include physics class index, sense organ class index, processing class index and nutrition class index.
3. the method as described in claim 1 based on apple feedstock specifications prediction fruit juice turbidity, which is characterized in that the step
In rapid two, the correlativity of the apple feedstock specifications data and the cider haze numbers evidence is established method particularly includes:
To apple feedstock specifications data and the cider haze numbers according to correlation analysis is carried out, to establish the apple feedstock specifications
The correlativity of data and the cider haze numbers evidence.
4. the method as described in claim 1 based on apple feedstock specifications prediction fruit juice turbidity, which is characterized in that the step
In rapid three, determination is to the cider haze numbers according to the specific method for being in significant relevant apple raw material core index data
Are as follows: to apple feedstock specifications data and the cider haze numbers according to correlation analysis is carried out, chooses relative coefficient and manifest
The relevant feedstock specifications of work property determine that apple raw material core refers to by apple raw material core index as apple raw material core index
Mark data.
5. the method as described in claim 1 based on apple feedstock specifications prediction fruit juice turbidity, which is characterized in that the step
It is further comprising the steps of before step 5 after rapid four:
It chooses apple and verifies sample, obtain the apple raw material core index data and cider haze numbers evidence of verifying sample, benefit
With the apple raw material core index data of the neural-network learning model and verifying sample, the fruit juice for obtaining verifying sample is muddy
Degree, if the accuracy of the fruit juice turbidity of the verifying sample obtained by neural-network learning model increases instruction lower than 90%
Practice the quantity of sample, and update neural-network learning model, or improve setting value, more new apple raw material core index is laid equal stress on
New training obtains neural-network learning model.
6. the method as described in claim 1 based on apple feedstock specifications prediction fruit juice turbidity, which is characterized in that the mind
Training parameter through network learning model is as follows: maximum cycle be 1000~20000, learning rate be 0.1~1, momentum because
Son is 0.1~0.5, and error amount is 0.00005~0.1.
7. the method as claimed in claim 5 based on apple feedstock specifications prediction fruit juice turbidity, which is characterized in that training sample
This selection number is 25~40.
8. the method as described in claim 1 based on apple feedstock specifications prediction fruit juice turbidity, which is characterized in that the apple
The quantity of fruit raw material core index data is 4~10.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811148007.2A CN109409580A (en) | 2018-09-29 | 2018-09-29 | Method based on apple feedstock specifications prediction fruit juice turbidity |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811148007.2A CN109409580A (en) | 2018-09-29 | 2018-09-29 | Method based on apple feedstock specifications prediction fruit juice turbidity |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109409580A true CN109409580A (en) | 2019-03-01 |
Family
ID=65466564
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811148007.2A Pending CN109409580A (en) | 2018-09-29 | 2018-09-29 | Method based on apple feedstock specifications prediction fruit juice turbidity |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109409580A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114062320A (en) * | 2021-11-17 | 2022-02-18 | 北京市自来水集团有限责任公司技术研究院 | Turbidity determination method and device of desk-top turbidity meter |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107064047A (en) * | 2017-03-02 | 2017-08-18 | 兰州大学 | A kind of Fuji apple quality damage-free detection method based near infrared spectrum |
-
2018
- 2018-09-29 CN CN201811148007.2A patent/CN109409580A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107064047A (en) * | 2017-03-02 | 2017-08-18 | 兰州大学 | A kind of Fuji apple quality damage-free detection method based near infrared spectrum |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114062320A (en) * | 2021-11-17 | 2022-02-18 | 北京市自来水集团有限责任公司技术研究院 | Turbidity determination method and device of desk-top turbidity meter |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Wang et al. | Quality analysis, classification, and authentication of liquid foods by near-infrared spectroscopy: A review of recent research developments | |
Cheng et al. | Marbling analysis for evaluating meat quality: Methods and techniques | |
Zhang et al. | Effects of different varieties and shelf storage conditions of chicory on deteriorative color changes using digital image processing and analysis | |
CN108960315B (en) | Intelligent evaluation system and method for quality of cooked meat product | |
CN109409579A (en) | The method of BP neural network prediction Raw material processing suitability | |
CN109242341A (en) | Method based on apple feedstock specifications prediction fruit juice integrated quality | |
Bavay et al. | Importance of fruit variability in the assessment of apple quality by sensory evaluation | |
CN100421823C (en) | Method for grading pork based on its color and quality | |
Lee et al. | Comparison of marbling fleck characteristics between beef marbling grades and its effect on sensory quality characteristics in high-marbled Hanwoo steer | |
CN109063783A (en) | A kind of salted water goose quality integrated evaluating method and the quality evaluation model using this method building | |
Tang et al. | Magnetic resonance applications in food analysis | |
Huang et al. | Evaluating quality of tomato during storage using fusion information of computer vision and electronic nose | |
CN104597217A (en) | Fruit maturity evaluating method based on maturation rule | |
CN104914223A (en) | Determination method and evaluation method of quality of peanuts for peanut sauce | |
KR100800597B1 (en) | Method for measuring sugar content of fuji apple and it's measuring board | |
CN106290754B (en) | A kind of pork rinses food processing suitability evaluation methods | |
CN101718772A (en) | Method for quantitatively evaluating quality of dairy products | |
CN109409580A (en) | Method based on apple feedstock specifications prediction fruit juice turbidity | |
CN108535250A (en) | ' Fuji ' ripe apples degree lossless detection method based on Streif indexes | |
CN113609647B (en) | Method for predicting aroma intensity change of passion fruit juice | |
Iswari | Fruitylicious: Mobile application for fruit ripeness determination based on fruit image | |
CN112200446A (en) | Method for comprehensively evaluating pork quality | |
CN109409687A (en) | Method based on apple feedstock specifications prediction dried product Color Quality | |
CN104914068B (en) | The spectrum rapid detection method of content of trans fatty acids in a kind of grease | |
CN111838607B (en) | Rice starch jelly with health care function and preparation method thereof |
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 |