CN109192247B - Method for generating yellow wine sterilized microorganism content curve - Google Patents
Method for generating yellow wine sterilized microorganism content curve Download PDFInfo
- Publication number
- CN109192247B CN109192247B CN201811142506.0A CN201811142506A CN109192247B CN 109192247 B CN109192247 B CN 109192247B CN 201811142506 A CN201811142506 A CN 201811142506A CN 109192247 B CN109192247 B CN 109192247B
- Authority
- CN
- China
- Prior art keywords
- curve
- yellow wine
- microorganism
- weight coefficient
- microorganisms
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Distillation Of Fermentation Liquor, Processing Of Alcohols, Vinegar And Beer (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
- Food Preservation Except Freezing, Refrigeration, And Drying (AREA)
- Alcoholic Beverages (AREA)
Abstract
A method for generating a yellow wine sterilized microorganism content curve comprises the following steps: determining the influence of sugar, alcohol, acid, etc. generated under the action of microorganism on the flavor of yellow wine and the heat resistance of microorganism according to the components of yellow wine; sterilizing microorganisms in the yellow wine by adopting high-temperature and sealing measures, and detecting the content of the microorganisms in the sterilization process; establishing a microorganism content rule curve model, discretizing the curve model, and changing the weight coefficient of curve type value points to obtain a target curve; training a target curve through an artificial neural network, and adaptively learning weight coefficient value, thereby controlling the shape of the curve and generating a yellow wine sterilized microorganism content curve. The method has good controllability and adaptability, and the artificial neural network self-adaptation training controls the whole and local shape of the microorganism content curve, so that the sterilization effect of different temperatures and time on microorganisms in the yellow wine can be known in real time, the influence on the flavor of the yellow wine can be reduced, and the yellow wine is more mellow under the condition of ensuring the quality safety of the yellow wine.
Description
Technical Field
The invention relates to a method for generating a yellow wine sterilized microorganism content curve, and belongs to the fields of food generation, microorganisms and geometric curves.
Background
Sterilization is one of the key processes of yellow wine production, and if not strictly controlled, the flavor of the yellow wine can be damaged and even the yellow wine can deteriorate. The existing yellow wine sterilization method has insufficient temperature control in the sterilization process, because the fermentation process of the yellow wine is open, some yeast, lactobacillus and the like with higher heat resistance remain after fermentation, the due flavor of the yellow wine is damaged due to overhigh temperature, and the yellow wine is deteriorated and even can not be drunk due to insufficient sterilization due to low temperature, and the content curve of microorganisms in the sterilization process is difficult to measure due to randomness and is difficult to accurately draw.
Disclosure of Invention
In order to solve the problems, the invention aims to provide a yellow wine sterilization microorganism content curve generation method with better controllability and self-adaptability.
The technical scheme adopted by the invention for solving the problems comprises the following steps:
A. determining the influence of sugar, alcohol, acid, etc. generated under the action of microorganism on the flavor of yellow wine and the heat resistance of microorganism according to the components of yellow wine;
B. sterilizing microorganisms in the yellow wine by adopting measures such as high temperature, sealing and the like, and detecting the content of the microorganisms in the sterilization process;
C. establishing a microorganism content rule curve model, discretizing the curve model, and changing the weight coefficient of curve type value points to obtain a target curve;
D. training a target curve through an artificial neural network, and adaptively learning the value of a weight coefficient, thereby controlling the shape of the curve and generating a yellow wine sterilized microorganism content curve.
Further, the step C includes:
(1) in the sterilization process, the content of microorganisms is approximately exponentially reduced along with the rise of temperature, and a microorganism content rule curve model is established:
wherein D isi(i-0, 1.., n) is the type point of the curve, n is the number of type points, x is time, f (x) -axlna is a combination function of the type points, a is a survival parameter for different microorganisms, and therefore the model becomes:
(2) discretizing the model, changing the weight coefficient of the curve model value point to obtain an objective function:
wherein, ω isiIs the weight coefficient for each type point.
Further, the step D includes:
(1) using the weight coefficient of the type value point as the connection weight of the artificial neural network, initializing the connection weight, and taking f (x) as-axlna as the input signal of the artificial neural network, the weight coefficient as the output of the network, the number of hidden layer nodes is:
wherein n is the number of input neurons, m is the number of output neurons, k is a constant, the actual output and the expected output of the network are compared, the square sum minimum of the difference between the actual output and the expected output is an optimization target, the network weight converges to the optimal weight after training the target curve for a plurality of times, and then the weight coefficient adjustment function is:
wherein, ω isk(x) Is the value of the kth iteration weight coefficient, alpha is the learning interval coefficient, delta is the error value, k is the iteration number, fk(x) As a combined function of the kth iteration, Fk(x) Is the target discrete function of the kth iteration;
(2) different objective function values are obtained through different settings of the connection weight, initial values of the connection weight are given, values of other connection weights are changed, and the local shape of the curve is controlled, so that the shape of the whole body is controlled, the output value is dynamically changed, the curvature and fluctuation of the curve are controlled, the time is used as the abscissa, the microorganism content is used as the ordinate, and the yellow wine sterilization microorganism content curve is obtained.
The invention has the beneficial effects that:
under the condition that the requirements on the flavor and the quality of the yellow wine are higher and higher, the method has better controllability and self-adaptability, the artificial neural network self-adaptation training controls the whole and local shape of the microorganism content curve, the sterilization effect of different temperatures and time on the microorganisms in the yellow wine is known in real time, the influence on the flavor of the yellow wine is reduced, and the yellow wine is more mellow under the condition of ensuring the quality safety of the yellow wine.
Drawings
FIG. 1 is an overall flow chart of a method for generating a curve of the content of sterilized microorganisms in yellow wine;
FIG. 2 is a diagram showing the result of the generation of the main components of yellow wine;
FIG. 3 is a graph of the content of yellow wine-sterilized microorganisms.
Detailed Description
Referring to fig. 1, the method of the present invention comprises the steps of:
A. determining the influence of sugar, alcohol, acid, etc. generated under the action of microorganism on the flavor of yellow wine and the heat resistance of microorganism according to the components of yellow wine;
(1) the yellow wine comprises the following main components: sugar, alcohol, acid, etc. as shown in fig. 2, these substances produced by the microorganisms will have certain influence on the flavor of the yellow wine. The fungi in yellow wine yeast can generate glucose, maltose, etc., and give sweet taste to yellow wine. Sugar is metabolized to generate organic acid, which forms the sour taste of yellow wine, but if lactic acid is too much, the yellow wine is rancid. The acetic acid and alcohol react to generate ester, the ester is decomposed into glycerin and fatty acid under the action of lipase, and the yellow wine is rich in mellow fragrance. The protein is degraded to generate amino acid, and the yellow wine is sour, sweet, bitter, spicy, salty and astringent … … taste feeling with multiple tastes.
(2) The yellow wine contains some heat-resistant lactobacillus, lactobacillus and the like, the sterilization temperature of the heat-resistant lactobacillus and lactobacillus reaches about 70 ℃, and the heat-resistant lactobacillus and lactobacillus are main microorganisms for rancidity of the yellow wine. The mold with very small amount still has activity after fermentation, and the sterilization temperature is about 80 ℃. A small amount of enzyme needs 70-90 ℃ to be inactivated. However, too high temperature may affect the flavor of yellow wine, so that an appropriate temperature for sterilization needs to be found.
B. Sterilizing microorganisms in the yellow wine by adopting measures such as high temperature, sealing and the like, and detecting the content of the microorganisms in the sterilization process;
(1) the empty bottle needs to be sterilized before bottling, the sterilization temperature and time of the yellow wine are strictly controlled, the yellow wine needs to be cooled rapidly after sterilization, the seal needs to be rapid and compact to prevent microorganisms from entering the wine, the bottle mouth of the wine bottle needs to be prevented from loosening in the transportation process, and the storage warehouse needs to be dry and sanitary to prevent the yellow wine from being polluted by mass propagation of the microorganisms in the warehouse.
(2) And (3) taking 5ml of liquor by using a sterile pipette under the sterile condition every 2 hours in the yellow wine sterilization process, placing the liquor on a culture medium for dilution, respectively placing the liquor on constant temperature shaking culture at 30 and 37 ℃, and detecting a light absorption value so as to judge the content of the microorganisms.
C. Establishing a microorganism content rule curve model, discretizing the curve model, and changing the weight coefficient of curve type value points to obtain a target curve;
(1) in the sterilization process, the content of microorganisms is approximately exponentially reduced along with the rise of temperature, and a microorganism content rule curve model is established:
wherein D isi(i ═ 0, 1., n) is the type point of the curve, n is the number of type points, x is time, f (x) ═ axlna is a combination function of the type points, a is the survival parameter of different microorganisms. Thus, the model becomes:
(2) discretizing the model, changing the weight coefficient of the curve model value point to obtain an objective function:
wherein, ω isiIs the weight coefficient for each type point.
D. Training a target curve through an artificial neural network, and adaptively learning the value of a weight coefficient, thereby controlling the shape of the curve and generating a yellow wine sterilized microorganism content curve.
(1) Using the weight coefficient of the type value point as the connection weight of the artificial neural network, initializing the connection weight, and taking f (x) as-axlna as the input signal of the artificial neural network, the weight coefficient as the output of the network, the number of hidden layer nodes is:
where n is the number of input neurons, m is the number of output neurons, and k is a constant. Comparing the actual output and the expected output of the network, taking the square sum minimum of the difference between the actual output and the expected output as an optimization target, training the target curve for many times, and converging the network weight to the optimal weight, wherein the weight coefficient adjustment function is as follows:
wherein, ω isk(x) Is the value of the kth iteration weight coefficient, alpha is the learning interval coefficient, delta is the error value, k is the iteration number, fk(x) As a combined function of the kth iteration, Fk(x) Is the target discrete function of the kth iteration.
(2) Different objective function values are obtained through different settings of the connection weight, initial values of the connection weight are given, values of other connection weights are changed, and the local shape of the curve is controlled, so that the overall shape is controlled. And the output value is dynamically changed, and the curvature and the fluctuation of the curve are controlled. Taking time as abscissa and microorganism content as ordinate, the curve of sterilized microorganism content of yellow wine (as shown in FIG. 3) is obtained.
In conclusion, the method for generating the yellow wine sterilized microorganism content curve is completed. The method has good controllability and adaptability, and the artificial neural network self-adaptation training controls the whole and local shape of the microorganism content curve, so that the sterilization effect of different temperatures and time on microorganisms in the yellow wine can be known in real time, the influence on the flavor of the yellow wine can be reduced, and the yellow wine is more mellow under the condition of ensuring the quality safety of the yellow wine.
Claims (2)
1. A method for generating a yellow wine sterilized microorganism content curve is characterized by comprising the following steps: the method comprises the following steps:
A. determining the influence of sugar, alcohol, acid, etc. generated under the action of microorganism on the flavor of yellow wine and the heat resistance of microorganism according to the components of yellow wine;
B. sterilizing microorganisms in the yellow wine by adopting high-temperature and sealing measures, and detecting the content of the microorganisms in the sterilization process;
C. establishing a microorganism content rule curve model, discretizing the curve model, and changing the weight coefficient of curve type value points to obtain a target curve;
D. training a target curve through an artificial neural network, and adaptively learning the value of a weight coefficient, thereby controlling the shape of the curve and generating a yellow wine sterilized microorganism content curve;
the step C comprises the following steps:
(1) in the sterilization process, the content of microorganisms is approximately exponentially reduced along with the rise of temperature, and a microorganism content rule curve model is established:
wherein D isi(i ═ 0, 1, …, n) is the norm point of the curve, n is the number of norm points, x is time, f (x) ═ -axlna is a combination function of the type points, a is a survival parameter for different microorganisms, and therefore the model becomes:
(2) discretizing the model, changing the weight coefficient of the curve model value point to obtain an objective function:
wherein, ω isiIs the weight coefficient for each type point.
2. The method for generating a yellow wine sterilized microorganism content curve according to claim 1, which is characterized by comprising the following steps: the step D comprises the following steps:
(1) using the weight coefficient of the type value point as the connection weight of the artificial neural network, initializing the connection weight, and taking f (x) as-axlna as the input signal of the artificial neural network, the weight coefficient as the output of the network, the number of hidden layer nodes is:
wherein n is the number of input neurons, m is the number of output neurons, k is a constant, the actual output and the expected output of the network are compared, the square sum minimum of the difference between the actual output and the expected output is an optimization target, the network weight converges to the optimal weight after training the target curve for a plurality of times, and then the weight coefficient adjustment function is:
wherein, ω isk(x) Is the value of the kth iteration weight coefficient, alpha is the learning interval coefficient, delta is the error value, k is the iteration number, fk(x) As a combined function of the kth iteration, Fk(x) Is the target discrete function of the kth iteration;
(2) different objective function values are obtained through different settings of the connection weight, initial values of the connection weight are given, values of other connection weights are changed, and the local shape of the curve is controlled, so that the shape of the whole body is controlled, the output value is dynamically changed, the curvature and fluctuation of the curve are controlled, the time is used as the abscissa, the microorganism content is used as the ordinate, and the yellow wine sterilization microorganism content curve is obtained.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811142506.0A CN109192247B (en) | 2018-09-28 | 2018-09-28 | Method for generating yellow wine sterilized microorganism content curve |
| CN202210001820.7A CN114267415A (en) | 2018-09-28 | 2018-09-28 | Method for detecting content of sterilized microorganisms in yellow wine and generating curve |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811142506.0A CN109192247B (en) | 2018-09-28 | 2018-09-28 | Method for generating yellow wine sterilized microorganism content curve |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210001820.7A Division CN114267415A (en) | 2018-09-28 | 2018-09-28 | Method for detecting content of sterilized microorganisms in yellow wine and generating curve |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109192247A CN109192247A (en) | 2019-01-11 |
| CN109192247B true CN109192247B (en) | 2022-03-29 |
Family
ID=64907753
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811142506.0A Expired - Fee Related CN109192247B (en) | 2018-09-28 | 2018-09-28 | Method for generating yellow wine sterilized microorganism content curve |
| CN202210001820.7A Withdrawn CN114267415A (en) | 2018-09-28 | 2018-09-28 | Method for detecting content of sterilized microorganisms in yellow wine and generating curve |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210001820.7A Withdrawn CN114267415A (en) | 2018-09-28 | 2018-09-28 | Method for detecting content of sterilized microorganisms in yellow wine and generating curve |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN109192247B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101630376A (en) * | 2009-08-12 | 2010-01-20 | 江苏大学 | Soft-sensing modeling method and soft meter of multi-model neural network in biological fermentation process |
| CN107238638A (en) * | 2017-06-28 | 2017-10-10 | 四川理工学院 | The assay method contacted based on each composition physical and chemical index of Daqu and liquor output and vinosity |
| CN107641644A (en) * | 2016-07-20 | 2018-01-30 | 江南大学 | A kind of method for detecting yellow rice wine putrefactive microorganisms |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170028005A1 (en) * | 2014-01-30 | 2017-02-02 | NatGood IP, LLC | Natural sweetener |
-
2018
- 2018-09-28 CN CN201811142506.0A patent/CN109192247B/en not_active Expired - Fee Related
- 2018-09-28 CN CN202210001820.7A patent/CN114267415A/en not_active Withdrawn
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101630376A (en) * | 2009-08-12 | 2010-01-20 | 江苏大学 | Soft-sensing modeling method and soft meter of multi-model neural network in biological fermentation process |
| CN107641644A (en) * | 2016-07-20 | 2018-01-30 | 江南大学 | A kind of method for detecting yellow rice wine putrefactive microorganisms |
| CN107238638A (en) * | 2017-06-28 | 2017-10-10 | 四川理工学院 | The assay method contacted based on each composition physical and chemical index of Daqu and liquor output and vinosity |
Non-Patent Citations (2)
| Title |
|---|
| 一类随机曲线的控制生成;莫灿林;《计算机学报》;20010712;第24卷(第7期);摘要，第749页第左栏第2节 * |
| 红曲黄酒酿造关键技术的研究;左楠楠;《中国优秀硕士学位论文全文数据库.工程科技Ⅰ辑》;20140315(第03期);第7、30、35页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114267415A (en) | 2022-04-01 |
| CN109192247A (en) | 2019-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wu et al. | Can we control microbiota in spontaneous food fermentation?–Chinese liquor as a case example | |
| Senkarcinova et al. | Probiotic alcohol-free beer made with Saccharomyces cerevisiae var. boulardii | |
| Mukisa et al. | Production of organic flavor compounds by dominant lactic acid bacteria and yeasts from Obushera, a traditional sorghum malt fermented beverage | |
| Sudheer Kumar et al. | Optimisation of fermentation conditions for mango (Mangifera indica L.) wine production by employing response surface methodology | |
| KR102183170B1 (en) | Alcohol fermentation system with complex neural network algorithm | |
| Sanchez | Philippine fermented foods: principles and technology | |
| Mukisa et al. | Application of starter cultures in the production of Enturire–a traditional sorghum‐based alcoholic beverage | |
| Moreno-Zambrano et al. | A mathematical model of cocoa bean fermentation | |
| Morales‐Oyervides et al. | Selection of best conditions of inoculum preparation for optimum performance of the pigment production process by Talaromyces spp. using the Taguchi method | |
| CN109192247B (en) | Method for generating yellow wine sterilized microorganism content curve | |
| Maryam et al. | Screening of fermentative potency of yeast isolates from indigenous sources for dough leavening | |
| Mawonike et al. | Process improvement of opaque beer (chibuku) based on multivariate cumulative sum control chart | |
| Timmermans et al. | Evaluation of the Gauss-Eyring model to predict thermal inactivation of micro-organisms at short holding times | |
| Liu et al. | Production of an innovative mixed Qu (fermentation starter) for waxy maize brewing and comparison of the quality of different waxy maize wines | |
| Kabuo et al. | The microorganisms and compounds influencing the organoleptic properties of Ugba (fermented Pentaclethra macrophylla Benth. seeds) | |
| Xubin et al. | Mango wine making process optimization based on artificial intelligence deep learning technology | |
| Satora et al. | The Influence of Fermentation Vessels on Yeast Microbiota and Main Parameters of Sauerkraut | |
| Ataç et al. | The use of yeast‐rich kefir grain as a starter culture in bread making | |
| Mazutti et al. | Mathematical modeling of Kluyveromyces marxianus growth in solid-state fermentation using a packed-bed bioreactor | |
| Owusu-Apenten et al. | Food microbes, quality and fermentation | |
| CN112036618B (en) | Method for predicting roast duck shelf time by combining electronic nose with partial least square regression | |
| Nomura et al. | High hydrostatic pressure pasteurization of a draft sake brewed using a Niigata-sake yeast | |
| CN116825176A (en) | Method for predicting and controlling metabolite spectrum based on process flora structure and application | |
| CN107541505A (en) | A kind of method of acidifying low temperature lactic acid bacteria mutant strain after seed selection is weak | |
| Jummai et al. | Comparative studies of the dough raising capacity of local yeast strains isolated from different sources |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220309 Address after: 710300 middle section of huazhan street, Fuyi District, Xi'an City, Shaanxi Province Applicant after: Xi'an Gyeonggi Rice Wine Research Institute Applicant after: Xi'an Qinyu Liquor Co.,Ltd. Address before: No. 3203, block C, Range Rover mansion, No. 588, Gangcheng East Street, Laishan District, Yantai City, Shandong Province, 264003 Applicant before: SHANDONG HENGHAO INFORMATION TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220329 |