CN111292006A

CN111292006A - Method and device for obtaining raw material quality range based on quality range of yellow rice wine product

Info

Publication number: CN111292006A
Application number: CN202010118101.4A
Authority: CN
Inventors: 尹明君; 周康; 周坚; 杨华; 刘朔; 刘江蓉; 高婧; 周胜玲
Original assignee: Wuhan Polytechnic University
Current assignee: Hefei Wisdom Dragon Machinery Design Co ltd
Priority date: 2020-02-25
Filing date: 2020-02-25
Publication date: 2020-06-16
Anticipated expiration: 2040-02-25
Also published as: CN111292006B

Abstract

The invention relates to the technical field of yellow wine processing, and discloses a method and a device for acquiring a raw material quality range based on a yellow wine product quality range, wherein the method comprises the following steps: acquiring yellow wine quality research data and yellow wine quality research data, acquiring a yellow wine raw material sample set and a yellow wine product sample set according to the data, performing stepwise regression processing, predicting the quality index of the yellow wine product, and constructing a yellow wine raw material quality standard optimization model according to the calculation data in the prediction process to determine the yellow wine raw material quality index range. Therefore, the yellow wine raw material sample set and the yellow wine product sample set are obtained firstly, the yellow wine raw material quality standard optimization model is further constructed, the yellow wine raw material quality index range is determined according to the model, and the technical problem that the yellow wine raw material can produce qualified yellow wine products under the given production process conditions by determining the optimal range of the yellow wine raw material quality index is solved.

Description

Method and device for obtaining raw material quality range based on quality range of yellow rice wine product

Technical Field

The invention relates to the technical field of yellow wine processing, in particular to a method and a device for acquiring a raw material quality range based on a yellow wine product quality range.

Background

In the field of yellow wine processing, the requirements of diversified yellow wine products on the quality of yellow wine raw materials are different, the yellow wine products meeting national standards, provincial standards, marketing standards and enterprise standards are required to be manufactured, the optimal quality range of the yellow wine raw materials is predicted according to the quality of the yellow wine products, so that the basis can be provided for enterprises to adopt raw materials, the appropriate raw materials are adopted, qualified target products are produced under the given production process conditions, the qualification rate is improved, the waste is reduced, the loss of the enterprises is reduced, and the profits of the enterprises are improved.

At present, enterprises have a plurality of methods for determining production raw materials of yellow wine products, and can roughly judge what kind of yellow wine raw materials are put into production to obtain what kind of yellow wine products according to production experiences or simple comparison tests. For the production planning of enterprises, how to scientifically find the most suitable quality range of yellow wine raw materials for producing target yellow wine products is a big problem.

The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.

Disclosure of Invention

The invention mainly aims to provide a method and a device for acquiring a raw material quality range based on a yellow wine product quality range, and aims to solve the technical problem of how to determine the optimal range of yellow wine raw material quality indexes so that the yellow wine raw materials can produce qualified yellow wine products under given production process conditions.

In order to achieve the purpose, the invention provides a method for obtaining a raw material quality range based on a yellow wine product quality range, which comprises the following steps of:

acquiring yellow wine quality research data and yellow wine quality research data;

constructing an index system of the yellow wine raw material and the yellow wine product according to the yellow wine quality research data and the yellow wine quality research data;

extracting a yellow wine making process from the yellow wine quality research data, and selecting a target yellow wine making process from the yellow wine making process;

determining a yellow wine raw material sample set and a yellow wine product sample set according to the index system and the target yellow wine making process;

respectively carrying out standardization treatment on the yellow wine raw material sample set and the yellow wine product sample set to obtain a standardized yellow wine raw material sample set and a standardized yellow wine product sample set;

performing stepwise regression treatment on the quality indexes of the yellow wine raw materials based on the standardized yellow wine raw material sample set to obtain a regression equation;

predicting the quality index of the yellow wine product according to the regression equation, and acquiring calculation data in the prediction process;

building a yellow wine raw material quality standard optimization model according to the calculation data and a preset optimization target;

and determining the quality index range of the yellow wine raw material according to the yellow wine raw material quality standard optimization model.

Preferably, the determining a yellow wine raw material sample set and a yellow wine product sample set according to the index system and the target yellow wine making process specifically comprises:

determining the indexes of the yellow wine raw materials and the indexes of the yellow wine products according to the index system;

extracting the variety and basic information of the yellow wine raw material from the research data;

selecting a target yellow wine raw material variety from the yellow wine raw material varieties according to the basic information of the yellow wine raw materials;

searching a target sample yellow rice wine raw material index corresponding to the target yellow rice wine raw material variety according to the yellow rice wine raw material index;

constructing a yellow wine raw material sample set according to the target sample yellow wine raw material indexes;

processing the yellow wine raw materials corresponding to the target yellow wine raw material variety according to the target yellow wine making process to obtain a target yellow wine product;

and constructing a yellow wine product sample set according to the yellow wine product index and the target yellow wine product.

Preferably, before the step-by-step regression processing is performed on the quality index of the yellow wine raw material based on the standardized yellow wine raw material sample set to obtain the regression equation, the method further includes:

extracting target yellow wine raw material indexes from the standardized yellow wine raw material sample set, and extracting target yellow wine product indexes from the standardized yellow wine product sample set;

performing multiple collinear analysis processing on the target yellow wine raw material index to obtain a variance expansion coefficient corresponding to the target yellow wine raw material index;

comparing the coefficient of variance expansion with a preset coefficient threshold;

and if the variance expansion coefficient is larger than the preset coefficient threshold value, executing the step of performing stepwise regression processing on the quality index of the yellow wine raw material based on the standardized yellow wine raw material sample set to obtain a regression equation.

Preferably, the step-by-step regression processing is performed on the quality index of the yellow wine raw material based on the standardized yellow wine raw material sample set to obtain a regression equation, which specifically includes:

establishing a regression model according to the target yellow wine raw material index and the target yellow wine product index;

extracting yellow wine raw material sample set dimensions from the standardized yellow wine raw material sample set, and extracting yellow wine product sample set dimensions from the standardized yellow wine product sample set;

and determining a regression equation according to the dimensions of the yellow wine raw material sample set, the dimensions of the yellow wine product sample set and the regression model.

Preferably, the predicting the quality index of the yellow wine product according to the regression equation and obtaining the calculation data in the prediction process specifically include:

generating a multiple linear regression model corresponding to the quality index of the yellow rice wine product;

training the multiple linear regression model according to the regression equation to obtain a prediction model corresponding to the quality index of the yellow rice wine product;

extracting a target yellow wine product index from the standardized yellow wine product sample set, and determining a regression function corresponding to the target yellow wine product index;

determining goodness of fit according to the regression function;

and taking the prediction model and the goodness of fit as calculation data.

Preferably, the building of the yellow wine raw material quality standard optimization model according to the calculation data and the preset optimization target specifically comprises:

searching physical and chemical property data of the quality of the yellow wine raw material corresponding to the quality index of the yellow wine raw material, and determining the limitation constraint of the yellow wine raw material based on the physical and chemical property data;

determining the limit constraint of the yellow wine product based on the prediction model and the quality requirement of the preset target yellow wine product;

correcting the limit constraint of the yellow wine product according to the goodness-of-fit to obtain a target limit constraint of the yellow wine product;

constructing a high-dimensional target space according to a plurality of target yellow wine raw material indexes, and setting diffusion factors in the high-dimensional target space;

determining diffusion factor constraint according to the diffusion factors and the requirements of a preset target area;

taking the limit constraint of the yellow wine raw material, the limit constraint of the target yellow wine product and the diffusion factor constraint as constraint conditions;

and constructing a yellow wine raw material quality standard optimization model according to the constraint conditions and a preset optimization target.

Preferably, the determining of the quality index range of the yellow rice wine raw material according to the yellow rice wine raw material quality standard optimization model specifically comprises:

converting the yellow rice wine raw material quality standard model into a single-target quality standard optimization model;

acquiring result data of the single target quality standard optimization model;

optimizing the diffusion factor constraint according to the result data to obtain a target diffusion factor constraint;

regulating and controlling the yellow wine raw material quality standard optimization model according to the target diffusion factor constraint to obtain a regulation and control model;

and determining the quality index range of the yellow wine raw material according to the regulation and control model.

Preferably, the determining the quality index range of the yellow wine raw material according to the regulation and control model specifically comprises the following steps:

calculating a lower bound value of the quality index of the yellow rice wine raw material and an upper bound value of the quality index of the yellow rice wine raw material according to the regulation and control model;

performing anti-standardization treatment on the lower bound value of the yellow wine raw material quality index and the upper bound value of the yellow wine raw material quality index;

determining the quality index range of the yellow wine raw material according to the processing result.

In addition, in order to achieve the above object, the present invention further provides a device for obtaining a quality range of a raw material based on a quality range of a yellow wine product, wherein the device for obtaining the quality range of the raw material based on the quality range of the yellow wine product comprises:

the data acquisition module is used for acquiring yellow wine quality research data and yellow wine quality research data;

the system construction module is used for constructing an index system of the yellow wine raw materials and the yellow wine products according to the yellow wine quality research data and the yellow wine quality research data;

the making process module is used for extracting a yellow wine making process from the yellow wine quality research data and selecting a target yellow wine making process from the yellow wine making process;

the sample set determining module is used for determining a yellow wine raw material sample set and a yellow wine product sample set according to the index system and the target yellow wine making process;

the data processing module is used for respectively carrying out standardized processing on the yellow wine raw material sample set and the yellow wine product sample set to obtain a standardized yellow wine raw material sample set and a standardized yellow wine product sample set;

the stepwise regression module is used for performing stepwise regression treatment on the quality indexes of the yellow wine raw materials based on the standardized yellow wine raw material sample set to obtain a regression equation;

the index prediction module is used for predicting the quality index of the yellow wine product according to the regression equation and acquiring the calculation data in the prediction process;

the model building module is used for building a yellow wine raw material quality standard optimization model according to the calculation data and a preset optimization target;

and the range determining module is used for determining the quality index range of the yellow wine raw material according to the yellow wine raw material quality standard optimization model.

Preferably, the index prediction module is further configured to generate a multiple linear regression model corresponding to the quality index of the yellow wine product;

the index prediction module is further used for training the multiple linear regression model according to the regression equation to obtain a prediction model corresponding to the quality index of the yellow rice wine product;

the index prediction module is also used for extracting a target yellow wine product index from the standardized yellow wine product sample set and determining a regression function corresponding to the target yellow wine product index;

the index prediction module is further used for determining goodness of fit according to the regression function;

and the index prediction module is also used for taking the prediction model and the goodness of fit as calculation data.

The method for acquiring the quality range of the raw materials based on the quality range of the yellow wine product, provided by the invention, comprises the steps of acquiring yellow wine quality research data and yellow wine quality research data; constructing an index system of the yellow wine raw material and the yellow wine product according to the yellow wine quality research data and the yellow wine quality research data; extracting a yellow wine making process from the yellow wine quality research data, and selecting a target yellow wine making process from the yellow wine making process; determining a yellow wine raw material sample set and a yellow wine product sample set according to the index system and the target yellow wine making process; respectively carrying out standardization treatment on the yellow wine raw material sample set and the yellow wine product sample set to obtain a standardized yellow wine raw material sample set and a standardized yellow wine product sample set; performing stepwise regression treatment on the quality indexes of the yellow wine raw materials based on the standardized yellow wine raw material sample set to obtain a regression equation; predicting the quality index of the yellow wine product according to the regression equation, and acquiring calculation data in the prediction process; building a yellow wine raw material quality standard optimization model according to the calculation data and a preset optimization target; and determining the quality index range of the yellow wine raw material according to the yellow wine raw material quality standard optimization model. Therefore, the yellow wine raw material sample set and the yellow wine product sample set are obtained firstly, the yellow wine raw material quality standard optimization model is further constructed, the yellow wine raw material quality index range is determined according to the model, and the technical problem that the yellow wine raw material can produce qualified yellow wine products under the given production process conditions by determining the optimal range of the yellow wine raw material quality index is solved.

Drawings

FIG. 1 is a schematic flow chart of a first embodiment of the method for obtaining a quality range of a raw material based on a quality range of a yellow rice wine product according to the present invention;

FIG. 2 is a schematic flow chart of a second embodiment of the method for obtaining a quality range of a raw material based on a quality range of a yellow rice wine product according to the present invention;

FIG. 3 is a schematic flow chart of a third embodiment of the method for obtaining a quality range of a raw material based on a quality range of a yellow rice wine product according to the present invention;

fig. 4 is a functional module diagram of a first embodiment of the device for obtaining the quality range of the raw material based on the quality range of the yellow wine product.

The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.

Detailed Description

It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

Referring to fig. 1, fig. 1 is a schematic flow chart of a first embodiment of the method for obtaining the quality range of raw materials based on the quality range of yellow wine products.

In a first embodiment, the method for obtaining the quality range of the raw materials based on the quality range of the yellow rice wine product comprises the following steps:

and step S10, obtaining yellow wine quality research data and yellow wine quality research data.

It should be noted that the executing main body of the embodiment may be a computing service device with data processing, program running and network communication functions, such as a smart phone, a tablet computer, a personal computer, etc., and may also be other devices that can achieve the same or similar functions and obtain the quality range of the raw material based on the quality range of the yellow wine product.

It should be understood that the yellow wine quality research data is various data collected on the basis of big data about the yellow wine raw materials and the yellow wine products, and the yellow wine quality research data is data collected during research and test on the yellow wine raw materials and the yellow wine products.

It should be understood that the yellow wine raw material indexes comprise: region, rice variety, rice moisture, protein, fat, crude starch, amylose, amylopectin, rice sensory score, rice output, peak viscosity, minimum viscosity, final viscosity, attenuation value, retrogradation value, gelatinization temperature.

The indexes of the yellow wine product comprise: yellow wine type, total sugar, PH, total acid, amino acid nitrogen, CaO, alcohol content, non-sugar solid content, appearance, aroma, taste, style and total score.

And step S20, constructing an index system of the yellow wine raw materials and the yellow wine products according to the yellow wine quality research data and the yellow wine quality research data.

It should be noted that, according to various data in the yellow wine quality research data and the yellow wine quality research data, including but not limited to the above listed data, an index system of the yellow wine raw material and the yellow wine product can be constructed, and the index system contains the yellow wine raw material index capable of evaluating the yellow wine raw material and the yellow wine product index capable of evaluating the yellow wine product.

And step S30, extracting a yellow wine making process from the yellow wine quality research data, and selecting a target yellow wine making process from the yellow wine making process.

It should be understood that various yellow wine making processes can be extracted from yellow wine quality research data, and the most typical yellow wine making process is used as the target yellow wine making process by screening the universality and the advancement of the yellow wine making process.

the preparation method of the yellow wine comprises the following steps of crushing polished glutinous rice, sieving with a 40-mesh sieve, weighing 215g in a 1000mL beaker or a conical flask, adding 538mL of distilled water according to the material-water ratio of 1:2.5, uniformly mixing, adding 15U/g of dry glutinous rice into high-temperature-resistant alpha-amylase, treating in a 95 ℃ water bath kettle for 90min, cooling, adjusting the pH to 4.5-5.0 with lactic acid, adding 150U/g of dry glutinous rice into saccharifying enzyme, treating in a 65 ℃ water bath kettle for 30min while continuously stirring, filling the saccharifying mash into a fermentation bottle while hot, cooling, inoculating yeast, fermenting, filtering, canning, pasteurizing to prepare a yellow wine finished product, inoculating 1.0X 107 active dry yeast into a 1.0X 107 dry rice wine/mL biochemical culture tank, fermenting for 3 days at 25 ℃, measuring the number of yeast in the fermented mash, then cooling to 20 ℃, measuring the content of yeast in the yellow wine and measuring the alcohol content of the yellow wine.

And step S40, determining a yellow wine raw material sample set and a yellow wine product sample set according to the index system and the target yellow wine making process.

Further, the step S40 includes:

determining the indexes of the yellow wine raw materials and the indexes of the yellow wine products according to the index system; extracting yellow wine raw material varieties and basic information of the yellow wine raw materials from the research data, wherein the basic information of the yellow wine raw materials comprises quality information of the yellow wine raw materials; selecting a target yellow wine raw material variety from the yellow wine raw material varieties according to the basic information of the yellow wine raw materials; searching a target sample yellow rice wine raw material index corresponding to the target yellow rice wine raw material variety according to the yellow rice wine raw material index; constructing a yellow wine raw material sample set according to the target sample yellow wine raw material indexes; processing the yellow wine raw materials corresponding to the target yellow wine raw material variety according to the target yellow wine making process to obtain a target yellow wine product; and constructing a yellow wine product sample set according to the yellow wine product index and the target yellow wine product.

The method comprises the steps of extracting yellow wine raw material varieties and basic yellow wine raw material information from research data, wherein the basic yellow wine raw material information comprises but is not limited to yellow wine raw material quality information, selecting the most suitable yellow wine raw material variety as a target yellow wine raw material variety according to the information, and taking the yellow wine raw material corresponding to the target yellow wine raw material variety as a sample, so that t types of sample yellow wine raw materials can be obtained, and indexes corresponding to the sample yellow wine raw materials are indexes of the target sample yellow wine raw materials.

The method comprises the following steps of:

the method comprises the following steps of obtaining all varieties and quality information of yellow wine raw materials in a determined region according to needs, wherein the variety range of the yellow wine raw materials is nationwide for national standards, the variety range of the yellow wine raw materials is the range of provinces and surrounding provinces thereof for provincial standards, and the variety range of the yellow wine raw materials is the range of frequent purchase and potential raw material supply of an enterprise for enterprise standards.

secondly, setting weight according to factors such as quality difference of the raw materials, and determining a sampling and purchasing scheme of the yellow wine raw materials by adopting a hierarchical sampling method.

thirdly, sampling varieties of the yellow wine raw materials according to a layered sampling method to obtain 5 kinds of yellow wine raw materials, namely glutinous rice, polished round-grained rice, long-grained rice, husked millet and millet, and collecting a plurality of samples of each variety to perform subsequent experiments.

fourthly, counting basic information of the yellow wine raw materials:

wherein A is₁Is a number, A₁₁1 st basic attribute of 1 st yellow wine raw material, namely, region of glutinous rice, A_5mIs the mth basic attribute of millet, m corresponds to the sequence of yellow wine raw material quality index, 1 is region, if m is 4, then A_5mRepresents the protein of millet. It should be noted that the indexes in the quality indexes of yellow wine raw materials are not applicable to the records of some yellow wine raw material varieties.

fifthly, carrying out measurement experiments on a plurality of samples of 5 kinds of yellow wine raw materials, collecting index values of various quality standards, and obtaining a yellow wine raw material quality data set D of the plurality of samples_M：

Wherein x₁₁Is the index value of the 1 st index of the 1 st yellow wine raw material, such as the first sample of glutinous rice. x is the number of_tmIs the index value of the mth index of the t kinds of yellow rice wine raw materials, such as the 3 rd sample of the japonica rice.

Carrying out production experiments on t yellow wine raw material samples according to the selected target yellow wine making process to obtain t portions of yellow wine products, and acquiring quality index values of the t portions of yellow wine products to obtain a yellow wine product sample set D_NComprises the following steps:

wherein y is₁₁The index value of 1 st index of 1 st yellow wine product, such as yellow wine type of yellow wine produced from the first sample of glutinous rice product, y_tmThe index value of the mth index of the t type yellow rice wine product, such as the alcoholic strength of the yellow rice wine produced by the second sample of the japonica rice.

According to basic information D of yellow rice wine raw materials_AYellow rice wine raw material quality data set D_MAnd yellow wine product sample set D_NBuilding a databaseD is as follows:

wherein, the matrix D_A ^*Is D_AThe row vector of (a) is copied and the result of the column vector dimension is increased, and D is guaranteed_A ^*And D_MThe same yellow wine raw material variety can be understood as D in the row vector table with the same number of rows_A ^*Is given to D_MIs tagged.

And then, carrying out simple data processing on the data in the database, and checking whether the data in the database has data omission, data repetition, obvious data errors and the like.

And step S50, respectively carrying out standardization treatment on the yellow wine raw material sample set and the yellow wine product sample set to obtain a standardized yellow wine raw material sample set and a standardized yellow wine product sample set.

It should be noted that, the yellow wine raw material sample set D_MAnd yellow wine product sample set D_NThe calculation formula for the normalization process is:

wherein x is_i＝(x_1i；x_2i；…；x_ti) (i-1, 2, …,8) is a sample set of yellow wine starting materials, y_j＝(y_1j；x_2j；…；y_tj) (j ═ 1,2, …,7) is a sample set of yellow wine products, t kinds of yellow wine raw materials, mean value

Standard deviation of

The standardized sample set of the yellow wine raw materials and the standardized sample set of the yellow wine products are still recorded as D_M、D_N。

And step S60, performing stepwise regression processing on the quality indexes of the yellow wine raw materials based on the standardized yellow wine raw material sample set to obtain a regression equation.

It should be noted that, by acquiring the yellow wine raw material sample set and the yellow wine product sample set in the sample database, setting the indexes in the yellow wine product sample set as response variables and setting the indexes in the yellow wine raw material sample set as prediction variables, the constraint on the yellow wine product standard can be converted into the constraint on the yellow wine raw material standard.

It should be understood that the step-by-step regression processing of the quality index of the yellow wine raw material based on the standardized yellow wine raw material sample set specifically comprises the following steps:

establishing a regression model according to the target yellow wine raw material index and the target yellow wine product index; extracting yellow wine raw material sample set dimensions from the standardized yellow wine raw material sample set, and extracting yellow wine product sample set dimensions from the standardized yellow wine product sample set; and determining a regression equation according to the dimensions of the yellow wine raw material sample set, the dimensions of the yellow wine product sample set and the regression model.

It can be understood that by stepwise regression, the data can be screened so that the explanatory variables retained in the model are both important and have no severe multicollinearity, which makes the subsequent steps more accurate.

And step S70, predicting the quality index of the yellow wine product according to the regression equation, and acquiring the calculation data in the prediction process.

The step of predicting the quality index of the yellow wine product based on the target data is specifically as follows:

firstly, generating a training set of a multiple linear regression model according to target yellow wine raw material sample data and a standard yellow wine product sample set, then training the multiple linear regression model according to the training set to obtain a prediction model corresponding to the quality index of the yellow wine product, wherein the prediction model is used for predicting the quality index of the yellow wine product according to the quality index of the yellow wine raw material, and in the subsequent steps, determining the limit constraint of the yellow wine product through the prediction model.

And then, extracting the target yellow wine product index from the standardized yellow wine product sample set, determining a regression function corresponding to the target yellow wine product index based on a preset coefficient matrix, and determining the goodness of fit according to the regression function.

And finally, taking the prediction model and the goodness of fit obtained in the prediction step process as calculation data for subsequent calculation and use, namely the calculation data comprises the prediction model and the goodness of fit.

It should be understood that, in order to solve the accuracy problem, a correction factor based on regression prediction accuracy is introduced for constraint of the yellow wine raw material standard to reform constraint conditions, so that the optimized yellow wine raw material can maximally ensure that a product meeting the yellow wine quality standard is obtained, and the reliability of optimization decision is improved.

And step S80, constructing a yellow wine raw material quality standard optimization model according to the calculation data and a preset optimization target.

It should be noted that the preset optimization target is set to optimize the raw material quality index standard.

It should be noted that the constraint conditions of the yellow wine raw material quality standard optimization model include:

a first type of constraint: and (5) limiting and restricting the yellow wine raw materials. The constraint limits the solving range according to the reasonable range of the index values of the yellow wine raw materials.

The second type of constraint: and (5) limiting and restricting the yellow wine product. The constraint is realized by transferring the limit of the yellow wine product to the limit of the yellow wine raw material through the transmission of a relationship model of the yellow wine raw material and the yellow wine product, wherein the precision correction problem of the relationship model is also considered. The principle of constructing the limit constraint of the yellow wine product is researched by taking two yellow wine raw material indexes and two yellow wine product indexes as examples, and the principle can be popularized to the situation of higher dimensional space.

Constraint of the third type: and (4) diffusion factor constraint. And constructing a yellow wine raw material quality standard optimization model according to the constraint conditions.

And step S90, determining the quality index range of the yellow wine raw material according to the yellow wine raw material quality standard optimization model.

It should be noted that the yellow wine raw material quality standard optimization model may be optimized to obtain a regulation and control model, and then the yellow wine raw material quality index range is determined according to the regulation and control model, and it should be understood that the index range, i.e., the index standard, represents the same meaning in this embodiment.

It should be understood that the purpose of optimizing the yellow wine raw material quality standard optimization model is to make the obtained conclusion include the yellow wine raw material quality index range of more varieties of yellow wine raw materials.

In the embodiment, yellow wine quality research data and yellow wine quality research data are obtained; constructing an index system of the yellow wine raw material and the yellow wine product according to the yellow wine quality research data and the yellow wine quality research data; extracting a yellow wine making process from the yellow wine quality research data, and selecting a target yellow wine making process from the yellow wine making process; determining a yellow wine raw material sample set and a yellow wine product sample set according to the index system and the target yellow wine making process; respectively carrying out standardization treatment on the yellow wine raw material sample set and the yellow wine product sample set to obtain a standardized yellow wine raw material sample set and a standardized yellow wine product sample set; performing stepwise regression treatment on the quality indexes of the yellow wine raw materials based on the standardized yellow wine raw material sample set to obtain a regression equation; predicting the quality index of the yellow wine product according to the regression equation, and acquiring calculation data in the prediction process; building a yellow wine raw material quality standard optimization model according to the calculation data and a preset optimization target; and determining the quality index range of the yellow wine raw material according to the yellow wine raw material quality standard optimization model. Therefore, the yellow wine raw material sample set and the yellow wine product sample set are obtained firstly, the yellow wine raw material quality standard optimization model is further constructed, the yellow wine raw material quality index range is determined according to the model, and the technical problem that the yellow wine raw material can produce qualified yellow wine products under the given production process conditions by determining the optimal range of the yellow wine raw material quality index is solved.

In an embodiment, as shown in fig. 2, a second embodiment of the method for obtaining a quality range of a raw material based on a quality range of a yellow wine product is provided based on the first embodiment, before the step S60, the method further includes:

and step S501, extracting a target yellow wine raw material index from the standardized yellow wine raw material sample set, and extracting a target yellow wine product index from the standardized yellow wine product sample set.

And step S502, carrying out multiple collinear analysis processing on the target yellow wine raw material index to obtain a variance expansion coefficient corresponding to the target yellow wine raw material index.

Step S503, comparing the variance expansion coefficient with a preset coefficient threshold.

And step S504, if the variance expansion coefficient is larger than the preset coefficient threshold value, executing the step of performing stepwise regression processing on the quality index of the yellow wine raw material based on the standardized yellow wine raw material sample set to obtain a regression equation.

Before stepwise regression processing, whether stepwise regression processing is needed or not needs to be judged, a target yellow wine raw material index is extracted from a standard yellow wine raw material sample set, multiple collinear analysis processing is carried out on the target yellow wine raw material index, a variance expansion coefficient VIF corresponding to the target yellow wine raw material index is obtained, the variance expansion coefficient is compared with a preset coefficient threshold, and stepwise regression processing is carried out if the variance expansion coefficient is larger than the preset coefficient threshold.

In a specific implementation, the preset coefficient threshold may be 10, based on SPSS multiple collinear analysis, if VIF between target yellow wine raw material indexes is greater than 10, stepwise regression processing is performed for the quality of yellow wine products in a given scene, and the multiple collinear analysis is performed on each target yellow wine raw material index to obtain a result:

wherein amylose and yield VIF are both more than 10, and multiple collinearity exists.

Further, the step S60 includes:

It should be noted that the basic idea of stepwise regression is as follows: and introducing the variables into the model one by one, performing F test after introducing each explanatory variable, performing t test on the selected explanatory variables one by one, and deleting the originally introduced explanatory variables when the originally introduced explanatory variables become unnoticeable due to introduction of the explained variables later. To ensure that only significant variables are contained in the regression equation before each new variable is introduced. This is an iterative process until neither significant explanatory variables are selected into the regression equation, nor insignificant explanatory variables are removed from the regression equation. To ensure that the resulting set of interpretation variables is optimal. And meanwhile, stepwise regression is carried out, so that the interpretation variables finally retained in the model are important and have no serious multiple collinearity.

In a specific implementation, the step-by-step regression specifically includes:

(1) establishing regression model according to the indexes of yellow wine raw materials and yellow wine products

y_j＝ω₀+ωx^T+ε

Wherein ω is (ω)₁，ω₂，…，ω_m)，x^T＝(x₁，x₂，…，x_m) J is 1,2, … n, m is the dimension of the yellow wine raw material sample set, and n is the dimension of the yellow wine product sample set. And taking the value of the F-test statistic, recording as

Taking the maximum value therein

Namely, it is

for a given level of significance α, the correspondingHas a critical value of F⁽¹⁾，

Then will be

Introducing a regression model, recording I₁Is selected into the variable index set.

(2) Establishing yellow wine product Y and raw material subset

The number of the binary regression model (2) is m-1. The statistical value of regression coefficient Ftest of the calculated variable is recorded as

Choose the largest one, record as

Namely, it is

for a given significance level α, the corresponding threshold value is denoted as F⁽²⁾，

Then will be

A regression model was introduced. Otherwise, the variable import process is terminated.

(3) According to the index subset of yellow rice wine raw materials

And training the product to obtain a stepwise regression equation.

In the embodiment, the data can be screened by stepwise regression processing, so that the interpretation variables retained in the model are important and have no serious multiple collinearity, the subsequent steps can be more accurate, and the calculation accuracy is improved.

In an embodiment, as shown in fig. 3, a third embodiment of the method for obtaining a quality range of a raw material based on a quality range of a yellow wine product according to the present invention is provided based on the first embodiment or the second embodiment, in this embodiment, the step S70 includes:

and step S701, generating a multiple linear regression model corresponding to the quality index of the yellow wine product.

And step S702, training the multiple linear regression model according to the regression equation to obtain a prediction model corresponding to the quality index of the yellow wine product.

And step S703, extracting a target yellow wine product index from the standardized yellow wine product sample set, and determining a regression function corresponding to the target yellow wine product index.

Step S704, determining the goodness of fit according to the regression function.

Step S705, using the prediction model and the goodness of fit as calculation data.

It should be noted that a multiple linear regression model corresponding to the quality index of the yellow wine product is generated, and the multiple linear regression model is trained according to a regression equation to obtain a prediction model corresponding to the quality index of each yellow wine product. Regression function of each target yellow wine product index:

wherein i is 1,2, …, m; j is 1,2, …, n. Theta is coefficient, f of multiple linear regression function_i(x) Goodness of fit R_i ²Value of [0,1 ]]。

Further, the step S80 includes:

step S801, searching physicochemical property data of the quality of the yellow wine raw material corresponding to the quality index of the yellow wine raw material, and determining limitation constraint of the yellow wine raw material based on the physicochemical property data.

In addition, the raw materials of yellow wine are determinedLower bound value and upper bound value x of each quality index standard^low、x^upIs a vector of decision variables, wherein

It should be understood that physicochemical property data of the quality of the yellow wine raw material corresponding to the quality index of the yellow wine raw material are searched, and a first type constraint is determined based on the physicochemical property data: and (5) limiting and restricting the yellow wine raw materials.

The restriction of the yellow wine raw material is the index range of the yellow wine raw material which is put into practical production and meets the requirements, and the expressed vector space is as follows:

X_limit＝{x|l_α≤x_α≤u_α，α＝1，2，…，m}

and S802, determining the limit constraint of the yellow wine product based on the prediction model and the quality requirement of the preset target yellow wine product.

It should be noted that the preset target quality requirement of the yellow wine product is also set by the user according to the actual situation, and this embodiment does not limit this.

Determining a second type of constraint based on the prediction model and the quality requirement of the preset target yellow wine product: and (5) limiting and restricting the yellow wine product.

Assuming that the feasible range of the quality index of the yellow rice wine is L ═ L (L)₁，L₂，…，L_n)，U＝(U₁，U₂，…，U_n) Respectively representing the lower and upper bounds of the quality index of the yellow wine.

And S803, correcting the limit constraint of the yellow wine product according to the goodness-of-fit to obtain the target limit constraint of the yellow wine product.

It should be noted that, in order to improve the accuracy of the yellow wine product limit constraint, the yellow wine product limit constraint is corrected according to the goodness of fit to obtain the target yellow wine product limit constraint.

Goodness of fit obtained for the prediction stage

The specific correction method comprises the following steps:

a calculating Δ_k＝L_k-U_k，Δ_kIs the initial value of the range.

b calculating goodness of fit R of each regression function_i ²"correction factor":

c, calculating the upper and lower limits of the quality index of the yellow wine product to reduce and increase the same size according to the correction quantity of the upper and lower limits:

[L′_j，U′_j]＝[L_j+0.5*Δ_j*∈_j，U_j-0.5*Δ_j*∈_j]

where j is 1,2, …, n, which represents the quality standard in the k-th product index, and 0.5 represents the sharing of the upper and lower limit correction amounts in the upper and lower limits.

Setting yellow wine product limit constraint:

wherein k is 1,2, …, n, X_process.The feasible domain limited by the restriction of the yellow wine product.

Step S804, a high-dimensional target space is constructed according to a plurality of target yellow wine raw material indexes, and diffusion factors are set in the high-dimensional target space.

And step S805, determining diffusion factor constraint according to the diffusion factor and the requirement of a preset target area.

It should be noted that the preset target area requirement may be a target area maximization, and based on the target area maximization requirement, a third type of constraint is determined: and (4) diffusion factor constraint.

Setting a diffusion factor in a high-dimensional target space consisting of a plurality of yellow wine raw material indexes, and substituting the diffusion factor into a linear weighting method target to meet the following requirements:

(1) the range is reasonable, so that the obtained range of the yellow wine raw materials is a high-reliability range solution given under the condition of comprehensively considering prediction errors of various products.

(2) The range is the widest, and the coverage degree which is finally solved in the restriction of yellow wine raw materials and the restriction of yellow wine products is sought to be as large as possible.

Let x^low、x^upThe lower and upper bound of final solution for each yellow wine raw material, delta is "diffusion factor", there are 9 such indexes, then there are

And step S806, taking the yellow wine raw material limit constraint, the yellow wine product limit constraint and the diffusion factor constraint as constraint conditions.

And S807, constructing a yellow wine raw material quality standard optimization model according to the constraint conditions and a preset optimization target.

It should be noted that, an objective function is set, and the food raw material quality index range solved by the multi-objective optimization model covers a wider range on the premise of satisfying the constraint condition, and firstly, δ is maximized, which is a primary objective:

maxf₁＝δ

and the final solution upper and lower bounds are to satisfy the maximum and minimum, respectively, with the following secondary objectives:

in conclusion, the yellow rice wine raw material quality standard optimization model is a multi-objective optimization mathematical model and is specifically expressed as follows:

P₁max f₁＝δ

further, the step S90 includes:

and step S901, converting the yellow wine raw material quality standardized model into a single-target quality standard optimized model.

It should be noted that, by using a linear weighting method, a weight value with magnitude difference is set according to the priority of a target and the importance of a target at the same level, and the raw material quality standard optimization model is converted into a single-target raw material quality standard optimization model:

wherein, beta_αAre the weights of the indexes, each weight is equal and

β' is the weight of diffusion factor, and the general ratio β is obtained when the proper solution is obtained_αOne or two orders of magnitude larger.

In a high dimensional space constructed from the overall material index variables, X_limitLimiting the basic value range of the variable of each dimension of the space to form a hypercube space, wherein X is_processA super-dimensional space with an irregular shape is constructed by the dimensional variables and the linear function of L, U. The two spaces are included or partially overlapped in the high-dimensional space. The objective function is set to find a hypercube with 2 in the overlapping region of the two high dimensional spaces^mA vertex in which two points have respective coordinates of

And

the two coordinates already contain the vertex coordinate information of the hypercube, so that only the two coordinates need to be determinedAnd determining the quality standard range of all food raw materials.

And S902, acquiring result data of the single target quality standard optimization model.

And step S903, optimizing the diffusion factor constraint according to the result data to obtain a target diffusion factor constraint.

And step S904, regulating and controlling the yellow wine raw material quality standard optimization model according to the target diffusion factor constraint to obtain a regulation and control model.

It should be noted that the regulation phase is divided into three parts: determining the size of a regulation and control range, determining a regulation and control model, and obtaining the quality standard of the special yellow wine raw material. The specific implementation steps of the regulation and control stage are as follows.

Step 1: and determining the size of the regulation and control range.

(1) And (4) calculating the quartile of the raw material standardized data, namely arranging all numerical values from small to large by the quartile, dividing the numerical values into four equal parts and setting the numerical values at the positions of three dividing points.

(2) The value at the 25% position (called the lower quartile) and the value at the 75% position (called the upper quartile) are chosen and the difference R (R) is calculated₁，r₂，…，r_α)。

(3) Calculating new solving weight and constraint weight of each decision variable by a min-max standardization method:

β_α＝r_α/∑_αr_α

at this time, the weights still satisfy

But not equal.

(4) According to the diffusion factor delta₀Adjusting constraints of the third kind

It is modified into

Where p is the "relaxation factor" used to connect the thirdThe diffusion factor obtained in stages is reduced so that the coordinates of the final solution space (hypercube) are δ₀ρ, in which each vertex can adjust for variations. Gamma is a 'floating variable' used for controlling the final solution of each index to float according to the discrete characteristics of each quality index of the actual food raw material so as to obtain different solution ranges.

Step 2: and determining a regulation and control model.

The regulated and controlled double-layer multi-objective optimization model comprises the following steps:

P1：max f₁＝γ

wherein P1 is far larger than P2, the value range of 'relaxation factor' rho is [0,0.05], namely the value of maximum half of diffusion factor is used as the floating range of hypercube coordinate at most, the step length of 0.05 being rho is set, 10 times of solving is carried out, and the result is compared to obtain the most reasonable solution range.

And step 3: and calculating a regulation and control model.

When a linear weighting method is used for solving, solving weights of all new decision variables are substituted, and multi-objective is achieved as a single objective:

wherein, beta_αfor updated optimization weights, the order of magnitude of β' is greater than β_αIs high.

And step S905, determining the quality index range of the yellow wine raw material according to the regulation and control model.

Further, the step S905 includes:

calculating a lower bound value of the quality index of the yellow rice wine raw material and an upper bound value of the quality index of the yellow rice wine raw material according to the regulation and control model; performing anti-standardization treatment on the lower bound value of the yellow wine raw material quality index and the upper bound value of the yellow wine raw material quality index; determining the quality index range of the yellow wine raw material according to the processing result.

It should be noted that the quality index range of the yellow wine raw material is determined by adopting a conclusion denormalization mode. Standard deviation sigma according to data standardization process_iAnd mean value

i represents the quality index of the first raw material, and the solving result x^low、x^up(lower bound value of quality index of yellow wine raw material and upper bound value of quality index of yellow wine raw material) are subjected to anti-standardization treatment to obtain the optimization range of each raw material index

The denormalization formula is:

it should be understood that, by using a data-driven model analysis method formulated by yellow wine raw material quality indexes, the yellow wine raw material indexes corresponding to the indexes of each yellow wine product and the range values of each raw material index are summarized (the yellow wine raw material indexes capable of guiding production are selected from a yellow wine raw material sample set and the optimal ranges of the indexes are determined), so as to obtain the quality index range of the yellow wine raw material, the yellow wine raw material is controlled by the quality standard of the yellow wine raw material, and yellow wine meeting the yellow wine product standard can be obtained by production and processing under the same production process.

In the embodiment, the quality index range of the yellow wine raw material is determined by constructing a yellow wine raw material quality standardized optimization model, and in order to contain as many raw material varieties as possible in the variation range of the specified yellow wine raw material quality index, the structure and parameters of the raw material quality index model are optimized and adjusted, the yellow wine raw material quality standardized optimization model is improved to obtain a regulation and control model, and the shape of a hypercube is optimized, so that the most suitable yellow wine raw material quality index range of a target product is obtained.

In addition, referring to fig. 4, an embodiment of the present invention further provides a device for obtaining a quality range of a raw material based on a quality range of a yellow wine product, where the device for obtaining the quality range of the raw material based on the quality range of the yellow wine product includes:

the data acquisition module 10 is used for acquiring yellow wine quality research data and yellow wine quality research data;

the system construction module 20 is used for constructing an index system of the yellow wine raw materials and the yellow wine products according to the yellow wine quality research data and the yellow wine quality research data;

a making process module 30 for extracting a yellow wine making process from the yellow wine quality research data and selecting a target yellow wine making process from the yellow wine making process;

a sample set determining module 40, configured to determine a yellow wine raw material sample set and a yellow wine product sample set according to the index system and the target yellow wine making process;

the data processing module 50 is used for respectively carrying out standardized processing on the yellow wine raw material sample set and the yellow wine product sample set to obtain a standardized yellow wine raw material sample set and a standardized yellow wine product sample set;

a stepwise regression module 60, configured to perform stepwise regression processing on the quality index of the yellow wine raw material based on the standardized yellow wine raw material sample set to obtain a regression equation;

the index prediction module 70 is used for predicting the quality index of the yellow wine product according to the regression equation and acquiring the calculation data in the prediction process;

the model building module 80 is used for building a yellow wine raw material quality standard optimization model according to the calculation data and a preset optimization target;

and the range determining module 90 is used for determining the quality index range of the yellow wine raw material according to the yellow wine raw material quality standard optimization model.

In an embodiment, the sample set determining module 40 is further configured to determine yellow wine raw material indexes and yellow wine product indexes according to the index system; extracting the variety and basic information of the yellow wine raw material from the research data; selecting a target yellow wine raw material variety from the yellow wine raw material varieties according to the basic information of the yellow wine raw materials; searching a target sample yellow rice wine raw material index corresponding to the target yellow rice wine raw material variety according to the yellow rice wine raw material index; constructing a yellow wine raw material sample set according to the target sample yellow wine raw material indexes; processing the yellow wine raw materials corresponding to the target yellow wine raw material variety according to the target yellow wine making process to obtain a target yellow wine product; and constructing a yellow wine product sample set according to the yellow wine product index and the target yellow wine product.

In an embodiment, the device for obtaining the raw material quality range based on the yellow wine product quality range further includes a regression validation module, configured to extract a target yellow wine raw material index from the standardized yellow wine raw material sample set, and extract a target yellow wine product index from the standardized yellow wine product sample set; performing multiple collinear analysis processing on the target yellow wine raw material index to obtain a variance expansion coefficient corresponding to the target yellow wine raw material index; comparing the coefficient of variance expansion with a preset coefficient threshold; and if the variance expansion coefficient is larger than the preset coefficient threshold value, executing the step of performing stepwise regression processing on the quality index of the yellow wine raw material based on the standardized yellow wine raw material sample set to obtain a regression equation.

In an embodiment, the stepwise regression module 60 is further configured to construct a regression model according to the target yellow wine raw material index and the target yellow wine product index; extracting yellow wine raw material sample set dimensions from the standardized yellow wine raw material sample set, and extracting yellow wine product sample set dimensions from the standardized yellow wine product sample set; and determining a regression equation according to the dimensions of the yellow wine raw material sample set, the dimensions of the yellow wine product sample set and the regression model.

In an embodiment, the index prediction module 70 is further configured to generate a multiple linear regression model corresponding to the quality index of the yellow wine product; training the multiple linear regression model according to the regression equation to obtain a prediction model corresponding to the quality index of the yellow rice wine product; extracting a target yellow wine product index from the standardized yellow wine product sample set, and determining a regression function corresponding to the target yellow wine product index; determining goodness of fit according to the regression function; and taking the prediction model and the goodness of fit as calculation data.

In an embodiment, the model building module 80 is further configured to search physicochemical property data of the quality of the yellow wine raw material corresponding to the yellow wine raw material quality index, and determine a yellow wine raw material limit constraint based on the physicochemical property data; determining the limit constraint of the yellow wine product based on the prediction model and the quality requirement of the preset target yellow wine product; correcting the limit constraint of the yellow wine product according to the goodness-of-fit to obtain a target limit constraint of the yellow wine product; constructing a high-dimensional target space according to a plurality of target yellow wine raw material indexes, and setting diffusion factors in the high-dimensional target space; determining diffusion factor constraint according to the diffusion factors and the requirements of a preset target area; taking the limit constraint of the yellow wine raw material, the limit constraint of the target yellow wine product and the diffusion factor constraint as constraint conditions; and constructing a yellow wine raw material quality standard optimization model according to the constraint conditions and a preset optimization target.

In an embodiment, the range determining module 90 is further configured to convert the standard quality model of yellow rice wine raw materials into a single target quality standard optimization model; acquiring result data of the single target quality standard optimization model; optimizing the diffusion factor constraint according to the result data to obtain a target diffusion factor constraint; regulating and controlling the yellow wine raw material quality standard optimization model according to the target diffusion factor constraint to obtain a regulation and control model; and determining the quality index range of the yellow wine raw material according to the regulation and control model.

In an embodiment, the range determining module 90 is further configured to calculate a lower bound value of a yellow wine raw material quality index and an upper bound value of the yellow wine raw material quality index according to the regulation and control model; performing anti-standardization treatment on the lower bound value of the yellow wine raw material quality index and the upper bound value of the yellow wine raw material quality index; determining the quality index range of the yellow wine raw material according to the processing result.

Other embodiments or specific implementation methods of the device for obtaining the quality range of the raw material based on the quality range of the yellow wine product can refer to the embodiments of the methods, and are not described herein again.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in an estimator readable storage medium (such as ROM/RAM, magnetic disk, optical disk) as described above, and includes instructions for enabling an intelligent device (such as a mobile phone, an estimator, a device for acquiring quality range of raw material based on quality range of yellow wine product, an air conditioner, or a device for acquiring quality range of raw material based on quality range of yellow wine product in network) to execute the method according to the embodiments of the present invention.

The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims

1. A method for obtaining a raw material quality range based on a yellow wine product quality range is characterized by comprising the following steps of:

2. The method for obtaining a quality range of a raw material based on a quality range of a yellow rice wine product according to claim 1, wherein the determining a yellow rice wine raw material sample set and a yellow rice wine product sample set according to the index system and the target yellow rice wine making process specifically comprises:

3. The method for obtaining a quality range of a raw material based on a quality range of a yellow rice wine product according to claim 1, wherein the step-by-step regression of the quality index of a yellow rice wine raw material based on the standardized sample set of yellow rice wine raw materials further comprises, before obtaining a regression equation:

4. The method for obtaining a quality range of a raw material based on a quality range of a yellow rice wine product according to claim 3, wherein the step-by-step regression processing is performed on the quality index of the yellow rice wine raw material based on the standardized sample set of yellow rice wine raw material to obtain a regression equation, which specifically comprises:

5. The method for obtaining a quality range of a raw material based on a quality range of a yellow rice wine product according to claim 1, wherein the predicting the quality index of the yellow rice wine product according to the regression equation and obtaining the calculation data in the prediction process specifically comprise:

determining goodness of fit according to the regression function;

and taking the prediction model and the goodness of fit as calculation data.

6. The method for obtaining the quality range of the raw materials based on the quality range of the yellow rice wine product according to claim 5, wherein the constructing of the yellow rice wine raw material quality standard optimization model according to the calculation data and the preset optimization target specifically comprises:

7. The method for obtaining a quality range of a raw material based on a quality range of a yellow rice wine product according to claim 6, wherein determining a quality index range of a yellow rice wine raw material according to the yellow rice wine raw material quality standard optimization model specifically comprises:

acquiring result data of the single target quality standard optimization model;

8. The method for obtaining a quality range of a raw material based on a quality range of a yellow rice wine product according to claim 7, wherein determining the quality index range of the yellow rice wine raw material according to the regulation and control model specifically comprises:

9. The device for obtaining the quality range of the raw materials based on the quality range of the yellow wine products is characterized by comprising the following components:

10. The device for obtaining a raw material quality range based on a yellow rice wine product quality range according to claim 9, wherein the index prediction module is further configured to generate a multiple linear regression model corresponding to a yellow rice wine product quality index;