CN105373669A - Pholiota adiposa fermentation condition optimization and dynamic model construction method - Google Patents
Pholiota adiposa fermentation condition optimization and dynamic model construction method Download PDFInfo
- Publication number
- CN105373669A CN105373669A CN201510854621.0A CN201510854621A CN105373669A CN 105373669 A CN105373669 A CN 105373669A CN 201510854621 A CN201510854621 A CN 201510854621A CN 105373669 A CN105373669 A CN 105373669A
- Authority
- CN
- China
- Prior art keywords
- fermentation
- yellow
- agaric
- condition
- genetic algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention discloses a genetic algorithm based Pholiota adiposa fermentation condition optimization and dynamic model construction method. The construction method comprises the steps of determining factors influencing the Pholiota adiposa polysaccharide fermentation condition and the value range of the factors in a single factor experiment and an orthogonal design experiment under a laboratory flask-shaking condition; performing neural network modeling and genetic algorithm optimization on fermentation culture medium components and the fermentation conditions, wherein the genetic objective function does not need specific mathematical and derivative expressions, so that the genetic objective function can be used for calculating the optimization to work out the optimal Pholiota adiposa fermentation culture medium component proportion and the optimal combination of the fermentation conditions; performing a Pholiota adiposa liquid deep culture experience by adopting the optimized culture medium formula and the fermentation conditions, drawing a progress curve on the basis of the experimental data, performing simulation on the Pholiota adiposa fermentation dynamics by adopting the genetic algorithm, comparing the advantages and disadvantages of an Monod equation and an Logistic equation in describing the Pholiota adiposa growth dynamics, and determining the parameters of the fermentation dynamic model based on the algorithm.
Description
Technical field
The invention belongs to the yellow agaric fermentation condition technical field of genetic algorithm, particularly relate to the construction method of yellow agaric fermentation condition optimization based on genetic algorithm and kinetic model.
Background technology
Yellow umbrella (Pholiotaadiposa), has another name called willow mushroom, yellow mushroom, Pholiota adiposa, is a kind of food medicine dual-purpose fungi.Yellow umbrella is distributed in the ground such as Europe, the U.S., Japan abroad, is distributed in multiple areas such as Shandong, Hebei, Shanxi, Jilin, Zhejiang, Henan in China.Yellow umbrella is rich in protein, carbohydrates, vitamin and multi mineral prime element, food stick smooth mouth, delicious flavour, unique flavor, nutritious, be among the peoplely used for the treatment of tumour and lung disease [2].Through By consulting literatures, find that people mainly concentrate on yellow destroying angel and mycelial polysaccharose substance to the pharmacodynamic study of yellow umbrella, research shows that pholiota adiosapose polysaccharide has the effects such as develop immunitypty, Tumor suppression, prevention infection, adjusting blood lipid.
The available sources of pholiota adiosapose polysaccharide mainly contains following three kinds: 1. extract from natural yellow destroying angel; 2. extract from artificial cultivation yellow destroying angel; 3. extract from the mycelium of fermented and cultured.The yellow destroying angel of nature is produced comparatively slow, and not easily obtains due to limited conditions; The yellow destroying angel growth cycle of artificial cultivation is grown, is yielded poorly, and cost is higher, does not thus obtain full-scale development.Current yellow agaric effective constituent development & application main path is liquid fermentation method, from yellow umbrella Submerged cultivated mycelium, extract polysaccharide.For this reason, be extremely necessary to study the Fermentations conditions of yellow umbrella, to replace fructification as the raw material of food, health products and medicine with the mycelium of fermentation.Adopt deep liquid fermentation process to cultivate yellow umbrella, extract with fermentation liquor mycelium the inexorable trend that active substance is research and development from now on.
In order to obtain more mycelium polysaccharides, must be optimized yellow agaric deep liquid fermentation process condition.Yellow agaric sweat is non-linear, the non-structured complication system of height, and relate to many influence factors, the output of selection on pholiota adiposa mycelium of fermentation condition has important impact.The classical algorithm of fermentation condition uses orthogonal design method, but it has the shortcomings such as precision is not high, workload is large, makes the result obtained by this method often can not obtain satisfactory result.Research fermentation dynamics is the precondition realizing sweat optimum control, is also the theoretical foundation that research sweat amplifies and is transitioned into fed-batch cultivation from batch fermentation, continuously ferments.The foundation of kinetic model, be unable to do without the estimation of model parameter.For remarkable nonlinear fermentation kinetics model, the optimized algorithm of traditional " point-to-point " is often more difficult for the determination of initial point, and the selection of initial point directly has influence on convergence of algorithm.
Over nearly 20 years, a kind of genetic algorithm (GeneticAlgorithms is called for short GA) becoming study hotspot is efficient with it, self-adaptation and benefit the advantage of global search, is applied in many fields such as fermentation condition optimization and kinetic model foundation.Genetic algorithm (GA) is a kind of random search algorithm based on biological natural selection and Genetic Mechanisms, is a kind of method solving complex systems optimization problem.There are some researches show genetic algorithm in the process problem such as fermentation condition optimization and kinetic model foundation comparatively classic method there is advantage.This research is attempted to utilize said method solve the optimization of yellow umbrella Fermentations conditions and set up the problems such as kinetic model, parameter optimization for sweat provides one method more accurately and effectively, thus for yellow agaric sweat technology controlling and process, improve product yield and creating conditions with the control of computing machine to sweat.
Summary of the invention
The object of the embodiment of the present invention is to provide the construction method of yellow agaric fermentation condition optimization based on genetic algorithm and kinetic model, to solve existing problem.
The embodiment of the present invention is achieved in that the construction method of yellow agaric fermentation condition optimization based on genetic algorithm and kinetic model, and the foundation of this model comprises following three parts:
Under laboratory shake flask condition, determine factor and its span of affecting yellow agaric polysaccharide fermentation condition with experiment of single factor and orthonormal design of experiments, this partial content is decomposed into following four tasks:
(1), with the mycelia scale of construction or mycelium polysaccharides output for index application experiment of single factor determines the formula (carbon source, nitrogenous source, production factor, inorganic salts etc.) of yellow agaric liquid fermentation medium and each component span;
(2), each component optimum proportioning of yellow agaric fermentation medium is determined with orthonormal design of experiments method;
(3), with the mycelia scale of construction or mycelium polysaccharides output for index application experiment of single factor determines yellow agaric liquid fermentation and culture condition (inoculum concentration, shaking speed, shaking flask liquid amount) span;
(4), determine to affect the best value of yellow agaric liquid fermentation and culture condition with orthonormal design of experiments method.
Carry out neural network (ANN) modeling and genetic algorithm optimizing to fermentation medium component and fermentation condition, this part research contents is decomposed into following two tasks:
(1), neural network (ANN) modeling
MATLAB software is adopted to carry out the structure of neural network.With to the initial mass concentration of the larger medium component of yellow agaric fermentation polysaccharides yield effect for input value, with " cost performance " for output valve, adopt ANN method to build the mathematical model of this system.
(2), genetic algorithm (GA) is optimized
The above-mentioned neural network completing training is exported, as solving target function value.Because the objective function of heredity does not need clear and definite mathematics and derivative expressions, therefore it can be utilized to calculate optimizing, in the hope of the yellow proportioning of agaric fermentation medium component and the best of breed of fermentation condition of the best;
The culture medium prescription of optimization and fermentation condition is adopted to carry out the experiment of yellow agaric Submerged liquid culturation, progress curve is drawn on experimental data basis, genetic algorithm is utilized to simulate yellow agaric fermentation dynamics, contrast Monod equation and Logistic equation in the quality describing yellow agaric growth power class hour, and utilize the parameter of this algorithm determination fermentation kinetics model.
technique effect:
Genetic algorithm is creatively applied in the optimizing process of yellow agaric fermentation condition by the present invention, obtain the fermentation medium proportioning of yellow agaric optimum and the environmental baseline combination of the best, overcome the shortcoming that classical algorithm labour intensity is large, precision is low, for yellow agaric amplification test lays the foundation.At present, mainly concentrate on the conventional mathematic curve approximating method of application to the dynamic (dynamical) research of fungi fermentation, this method also exist that precision is low, fitting result and the larger shortcoming of experimental result gap.The present invention utilizes the advantage of the distinctive adaptivity of GA, Global optimization and implict parallelism, GA is utilized to carry out research and inquirement to yellow agaric sweat and dynamics thereof, obtain dynamics mathematical model and model parameter, for the yellow agaric of suitability for industrialized production provides theoretical foundation.Pass through the present invention, first dynamics research is carried out to the yellow agaric of food medicine dual-purpose fungi, applied dynamics model can predict mycelial growth conditions, for optimizing fermentation controls to lay the foundation, on the basis of forefathers' research, introduce genetic algorithm to be first optimized yellow agaric fermentation medium and fermentation condition, improve the output of exocellular polysaccharide, the present invention uses genetic algorithm to study yellow agaric fermentation dynamics first, optimize the parameter of kinetic model, the further large scale fermentation for yellow umbrella is produced and is provided theoretical foundation.
Accompanying drawing explanation
Fig. 1 is the fermentation medium based on the yellow agaric fermentation condition optimization of genetic algorithm and the foundation of kinetic model that provides of the embodiment of the present invention and training systern Technology Roadmap;
Fig. 2 is the genetic algorithm process flow diagram based on the yellow agaric fermentation condition optimization of genetic algorithm and the foundation of kinetic model that the embodiment of the present invention provides.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearly understand, below in conjunction with embodiment, the present invention is further elaborated.Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.
Below in conjunction with drawings and the specific embodiments, application principle of the present invention is further described.
Based on the yellow agaric fermentation condition optimization of genetic algorithm and the construction method of kinetic model, the foundation of this model comprises following three parts:
Under laboratory shake flask condition, determine factor and its span of affecting yellow agaric polysaccharide fermentation condition with experiment of single factor and orthonormal design of experiments, this partial content is decomposed into following four tasks:
(1), with the mycelia scale of construction or mycelium polysaccharides output for index application experiment of single factor determines the formula (carbon source, nitrogenous source, production factor, inorganic salts etc.) of yellow agaric liquid fermentation medium and each component span;
(2), each component optimum proportioning of yellow agaric fermentation medium is determined with orthonormal design of experiments method;
(3), with the mycelia scale of construction or mycelium polysaccharides output for index application experiment of single factor determines yellow agaric liquid fermentation and culture condition (inoculum concentration, shaking speed, shaking flask liquid amount) span;
(4), determine to affect the best value of yellow agaric liquid fermentation and culture condition with orthonormal design of experiments method.
Carry out neural network (ANN) modeling and genetic algorithm optimizing to fermentation medium component and fermentation condition, this part research contents is decomposed into following two tasks:
(1), neural network (ANN) modeling
MATLAB software is adopted to carry out the structure of neural network.With to the initial mass concentration of the larger medium component of yellow agaric fermentation polysaccharides yield effect for input value, with " cost performance " for output valve, adopt ANN method to build the mathematical model of this system.
(2), genetic algorithm (GA) is optimized
The above-mentioned neural network completing training is exported, as solving target function value.Because the objective function of heredity does not need clear and definite mathematics and derivative expressions, therefore it can be utilized to calculate optimizing, in the hope of the yellow proportioning of agaric fermentation medium component and the best of breed of fermentation condition of the best;
The culture medium prescription of optimization and fermentation condition is adopted to carry out the experiment of yellow agaric Submerged liquid culturation, progress curve is drawn on experimental data basis, genetic algorithm is utilized to simulate yellow agaric fermentation dynamics, contrast Monod equation and Logistic equation in the quality describing yellow agaric growth power class hour, and utilize the parameter of this algorithm determination fermentation kinetics model.
The research method that the present invention adopts:
(1), first the present invention takes single factor test and orthonormal design of experiments to obtain the key component of the yellow agaric liquid fermentation medium of impact, and with single factor test and orthogonal experiment data for sample, set up the BP neural network model of fermentation condition and polysaccharide yield corresponding relation, and use genetic algorithm to carry out model optimizing, obtain optimal conditions of fermentation;
(2), to yellow agaric thalli growth kinetic model adopt Monod equation and Logistic equation to describe, polysaccharide synthetic model adopts Luedeking-Piret equation to describe.Under Matlab platform, application genetic algorithm carries out matching to two group models and experimental data respectively, carries out parameter estimation.
The experimental technique that the present invention adopts: experimental technique of the present invention is divided into following three parts:
(1), with the yellow agaric liquid fermentation medium formula of genetic algorithm optimization;
(2), with genetic algorithm optimization yellow agaric yeasting condition;
(3), with genetic algorithm, yellow agaric liquid fermentation dynamics is studied.
Part I: with the yellow agaric liquid fermentation medium formula of genetic algorithm optimization
(1), fermentation liquor preparation and polysaccharide determination:
3. yellow agaric bacterial classification
Yellow umbrella is the resourceful fungus resource in Mount Taishan, and wild yellow destroying angel is adopted in Mount Taishan.Adopt tissue isolation to obtain mycelium, and be transferred on PDA slant medium.
3. first order seed liquid culture medium: peptone 1.0%, glucose 2.0%, yeast extract 0.2%, KH2PO40.1%, MgSO4.7H2O0.1%, pH nature, 0.1MPa, 121 DEG C of sterilizing 20min.
3. yellow agaric Liquid Culture basal medium: with primary seed solution nutrient culture media.
3. cultural method
250mL shaking flask liquid amount 100mL basal medium, the primary seed solution of access 10%, on rotary shaker, rotating speed is 200r/min, cultivates 5-6d under 28 DEG C of conditions, is yellow agaric Liquid Culture fermentation liquor.
3. the mensuration of mycelia yield
By the filter paper suction filtration that fermentation liquor is dried, mycelium is together put into 60 DEG C of baking ovens with filter paper and dries to constant weight, weigh mycelium dry weight with electronic analytical balance, calculate mycelia yield.
3. mycelium polysaccharides extracting
Get dry mycelium to grind, precision takes 0.1g, adds 50 times of volume distilled water, at 85 DEG C of water bath with thermostatic control heating 2h, filters.Filter residue heats 2h as stated above again, merging filtrate, adds 3 times of volume 95% ethanol, and low temperature (4 DEG C) precipitates, and spends the night.Under 4000r/min, centrifugal 20min, abandons supernatant, and precipitation absolute ethanol washing 2 times, often wash once all by centrifugal segregation organic solvent, and precipitation is polysaccharide material, constant volume.
3. mycelium polysaccharides assay
Carry out according to list of references of the present invention [13].
(2), fermentation medium optimization
3. carbon source impact that yellow umbrella is fermented: use corn flour (to boil 20min in advance respectively, four layers of filtered through gauze, discard filter residue), sucrose, maltose, soluble starch be the glucose that carbon source replaces in basal medium, other components unchanged, carry out yellow agaric cultivation and determination of polysaccharide as stated above.
3. nitrogenous source impact that yellow umbrella is fermented: use beancake powder (to boil 20min in advance respectively, four layers of filtered through gauze, discard filter residue), sodium nitrate, ammonium nitrate, ammonium sulfate is the peptone that nitrogenous source replaces in basal medium, other components unchanged, carry out yellow agaric cultivation and determination of polysaccharide as stated above.
3. with the Carbon and nitrogen sources that experiment of single factor has been optimized, add that conventional potassium dihydrogen phosphate and magnesium sulfate are inorganic salts, carry out the orthogonal experiment of four factor three levels, determine the proportioning combination of best carbon and nitrogen sources.
(3) result, with experiment of single factor and orthogonal experiment obtained, for sample, is used genetic algorithm to carry out model optimizing, is optimized fermentation medium.
3. BP neural net model establishing: using the orthogonal experiment data result of fermentation medium as the learning sample of BP neural network.Design the structure of neural network according to the number of medium component and the number of optimizing index, then by experimental data, neural network is trained.This research carries out fermenting experiment with carbon source, nitrogenous source, potassium dihydrogen phosphate, magnesium sulfate for orthogonal test factor, gets some groups of experimental datas as training sample.
3. on the basis of neural network model, genetic algorithm is utilized to carry out optimizing to fermentation condition, under Matlab platform, be that index is written as M file as fitness function with polysaccharide yield, through the genetic optimization process in too much generation, fitness tends towards stability, and draws yellow agaric fermentation optimal medium condition.
Part II: with the yellow agaric fermentation condition of genetic algorithm optimization
(1), determine with experiment of single factor the condition of culture span affecting the fermentation of yellow agaric: fermentation pH value, inoculum concentration, liquid amount and shaking speed.
(2), on experiment of single factor basis the orthogonal experiment of 4 factor 3 levels is carried out to fermentation pH value, inoculum concentration, shaking speed and charge, to cultivate the polysaccharide yield of 5d for index, obtain the result of orthogonal experiment.
(3), use genetic algorithm to be optimized yellow agaric fermentation condition, fermentation condition optimization method is similar with medium optimization method.
Part III: set up the yellow agaric liquid deep layer fermenting kinetic model based on genetic algorithm
(1), yellow agaric growth kinetics, exocellular polysaccharide generation theorem and substrate consumption kinetic model
3. conk dynamics commonly uses Monod equation and the description of Logistic equation, also can apply this two equation models based on the yellow agaric growth course of above hypothesis.This research, by contrasting the fit solution of two equations and test figure, finally determines yellow agaric growth kinetics model.Monod equation form is as follows:
In formula: Cx-mycelial biomass, g/L; Max-maximum specific growth rate, h-1; Cs-growth limiting nutrients concentration, g/L; Ks-saturation constant, g/L; The t-time, h.
Logistic equation form is as follows:
In formula: Cx-mycelial biomass, g/L; Max-maximum specific growth rate, h-1; The maximum hypha biomass of Cxmax-, g/L; The t-time, h.
3. yellow agaric exocellular polysaccharide generation model: adopt Luedeking-Piret equation to describe the generation theorem of yellow agaric exocellular polysaccharide, form is as follows:
In formula: Cp-exocellular polysaccharide concentration, g/L; ,-model parameter, changes with fermentation condition.
3. yellow agaric fermentation substrate consumption models: yellow agaric the consumption of growth course mesostroma mainly generate with the growth of thalline, product and the metabolism of thalline relevant, can be represented by the formula:
In formula: Y
x/s-generate mycelial dry weight and the matrix mass ratio being consumed in mycelial growth completely; m
0the maintenance coefficient of-cell, h-1; The t-time, h.
(2) each parameter metabolic alterations of yellow agaric liquid deep layer fermenting process, is determined
The fermentative medium formula optimized before employing and fermentation condition carry out yellow agaric Submerged liquid culturation, draw yellow agaric mycelial biomass, yield of extracellular polysaccharide and the substrate consumption amount change curve with fermentation time.On the basis of this experimental data, utilize genetic algorithm to simulate yellow agaric dynamics, contrast Monod equation and Logistic equation in the quality describing yellow agaric growth power class hour, and utilize the parameter of this algorithm determination fermentation kinetics model.
(3), genetic algorithm is used to carry out parameter estimation to yellow agaric fermentation kinetics model
3. under Matlab platform, application genetic algorithm carries out matching to two group models and experimental data respectively, day scalar functions is the error sum of squares of the simulated data of experimental data and model, be written as M file, value returns as scalar, and the solution of the differential equation selects quadravalence Runge-Kutta method, and genetic algorithm initial population number is 40, genetic algebra was 100 generations, the evolution situation that contrast Monod equation and Logistic equation grow for describing yellow agaric.
3. after determining yellow agaric growth kinetics model, experimentally data separate genetic algorithm carries out parameter estimation to polysaccharide generation model Luedeking-Piret and substrate consumption model again, and genetic algorithm initial population number is 40, and genetic algebra was 100 generations, hand over adopted probability 0.7, mutation probability 0.06.
Genetic algorithm is creatively applied in the optimizing process of yellow agaric fermentation condition by the present invention, obtain the fermentation medium proportioning of yellow agaric optimum and the environmental baseline combination of the best, overcome the shortcoming that classical algorithm labour intensity is large, precision is low, for yellow agaric amplification test lays the foundation.At present, mainly concentrate on the conventional mathematic curve approximating method of application to the dynamic (dynamical) research of fungi fermentation, this method also exist that precision is low, fitting result and the larger shortcoming of experimental result gap.The present invention utilizes the advantage of the distinctive adaptivity of GA, Global optimization and implict parallelism, GA is utilized to carry out research and inquirement to yellow agaric sweat and dynamics thereof, obtain dynamics mathematical model and model parameter, for the yellow agaric of suitability for industrialized production provides theoretical foundation.Pass through the present invention, first dynamics research is carried out to the yellow agaric of food medicine dual-purpose fungi, applied dynamics model can predict mycelial growth conditions, for optimizing fermentation controls to lay the foundation, on the basis of forefathers' research, introduce genetic algorithm to be first optimized yellow agaric fermentation medium and fermentation condition, improve the output of exocellular polysaccharide, the present invention uses genetic algorithm to study yellow agaric fermentation dynamics first, optimize the parameter of kinetic model, the further large scale fermentation for yellow umbrella is produced and is provided theoretical foundation.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any amendments done within the spirit and principles in the present invention, equivalent replacement and improvement etc., all should be included within protection scope of the present invention.
Claims (5)
1. a construction method for yellow agaric fermentation condition optimization and kinetic model, is characterized in that the foundation of this model comprises:
Determine with experiment of single factor and orthonormal design of experiments factor and its span of affecting yellow agaric polysaccharide fermentation condition under laboratory shake flask condition;
Fermentation medium component and fermentation condition carry out neural network ANN modeling and genetic algorithm optimizing;
The culture medium prescription of optimization and fermentation condition is adopted to carry out the experiment of yellow agaric Submerged liquid culturation, progress curve is drawn on experimental data basis, genetic algorithm is utilized to simulate yellow agaric fermentation dynamics, contrast Monod equation and Logistic equation in the quality describing yellow agaric growth power class hour, and utilize the parameter of this algorithm determination fermentation kinetics model.
2. the construction method of yellow agaric fermentation condition optimization as claimed in claim 1 and kinetic model, it is characterized in that, under laboratory shake flask condition, determine with experiment of single factor and orthonormal design of experiments factor and its span of affecting yellow agaric polysaccharide fermentation condition, specifically comprise:
With the mycelia scale of construction or mycelium polysaccharides output for index application experiment of single factor determines the formula of yellow agaric liquid fermentation medium and each component span;
The each component optimum proportioning of yellow agaric fermentation medium is determined with orthonormal design of experiments method;
With the mycelia scale of construction or mycelium polysaccharides output for index application experiment of single factor determines yellow agaric liquid fermentation and culture condition span;
Determine to affect the best value of yellow agaric liquid fermentation and culture condition with orthonormal design of experiments method.
3. the construction method of yellow agaric fermentation condition optimization as claimed in claim 1 and kinetic model, is characterized in that, carries out neural network ANN modeling and genetic algorithm optimizing, specifically comprise fermentation medium component and fermentation condition:
Neural network ANN modeling: adopt MATLAB software to carry out the structure of neural network; With to the initial mass concentration of the larger medium component of yellow agaric fermentation polysaccharides yield effect for input value, with " cost performance " for output valve, adopt ANN method to build the mathematical model of this system;
Genetic Algorithms is optimized: export, the above-mentioned neural network completing training as solving target function value; Because the objective function of heredity does not need clear and definite mathematics and derivative expressions, therefore it can be utilized to calculate optimizing, in the hope of the yellow proportioning of agaric fermentation medium component and the best of breed of fermentation condition of the best.
4. the construction method of yellow agaric fermentation condition optimization as claimed in claim 1 and kinetic model, it is characterized in that, first single factor test and orthonormal design of experiments is taked to obtain the key component of the yellow agaric liquid fermentation medium of impact, and with single factor test and orthogonal experiment data for sample, set up the BP neural network model of fermentation condition and polysaccharide yield corresponding relation, and use genetic algorithm to carry out model optimizing, obtain optimal conditions of fermentation;
Adopt Monod equation and Logistic equation to describe to yellow agaric thalli growth kinetic model, polysaccharide synthetic model adopts Luedeking-Piret equation to describe; Under Matlab platform, application genetic algorithm carries out matching to two group models and experimental data respectively, carries out parameter estimation.
5. the construction method of yellow agaric fermentation condition optimization as claimed in claim 1 and kinetic model, is characterized in that, the experimental technique that the present invention adopts is divided into following three parts:
(1) with the yellow agaric liquid fermentation medium formula of genetic algorithm optimization;
(2) with genetic algorithm optimization yellow agaric yeasting condition;
(3) with genetic algorithm, yellow agaric liquid fermentation dynamics is studied.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510854621.0A CN105373669A (en) | 2015-11-28 | 2015-11-28 | Pholiota adiposa fermentation condition optimization and dynamic model construction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510854621.0A CN105373669A (en) | 2015-11-28 | 2015-11-28 | Pholiota adiposa fermentation condition optimization and dynamic model construction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105373669A true CN105373669A (en) | 2016-03-02 |
Family
ID=55375864
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510854621.0A Pending CN105373669A (en) | 2015-11-28 | 2015-11-28 | Pholiota adiposa fermentation condition optimization and dynamic model construction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105373669A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503856A (en) * | 2016-10-26 | 2017-03-15 | 中国石油大学(华东) | Test design method for artificial neural network method Optimal Medium |
| CN109486898A (en) * | 2018-12-06 | 2019-03-19 | 浙江大学 | Method based on aspergillus fungi upgrowth situation in electronic nose quick predict rice |
| CN117285382A (en) * | 2023-11-22 | 2023-12-26 | 海南热带海洋学院 | Method for multi-strain fermentation of fish manure and waste low-odor fertilizer based on neural network |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002033400A1 (en) * | 2000-10-18 | 2002-04-25 | Bayer Aktiengesellschaft | Method for characterizing, identifying and designating microbial mixtures by comparing ir, ft-ir, raman, ft-raman and gc analysis data with data from a reference database |
| CN103793543A (en) * | 2012-11-02 | 2014-05-14 | 江南大学 | Rice wine fermentation dynamical model |
| CN105069220A (en) * | 2015-08-04 | 2015-11-18 | 莆田学院 | Back-propagation (BP) neural network immune genetic algorithm based microbial fermentation optimization method |
| CN105095587A (en) * | 2015-08-04 | 2015-11-25 | 莆田学院 | Microbial fermentation optimizing method based on bacterium foraging algorithm |
-
2015
- 2015-11-28 CN CN201510854621.0A patent/CN105373669A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2002033400A1 (en) * | 2000-10-18 | 2002-04-25 | Bayer Aktiengesellschaft | Method for characterizing, identifying and designating microbial mixtures by comparing ir, ft-ir, raman, ft-raman and gc analysis data with data from a reference database |
| CN103793543A (en) * | 2012-11-02 | 2014-05-14 | 江南大学 | Rice wine fermentation dynamical model |
| CN105069220A (en) * | 2015-08-04 | 2015-11-18 | 莆田学院 | Back-propagation (BP) neural network immune genetic algorithm based microbial fermentation optimization method |
| CN105095587A (en) * | 2015-08-04 | 2015-11-25 | 莆田学院 | Microbial fermentation optimizing method based on bacterium foraging algorithm |
Non-Patent Citations (6)
| Title |
|---|
| 李海亮等: "基于人工神经网络和遗传算法的黑木耳糙米醋发酵条件优化", 《中国酿造》 * |
| 洒荣波等: "黄伞多糖的研究进展", 《中国酿造》 * |
| 王莹: "羊肚菌深层发酵及生长动力学研究", 《中国优秀博硕士学位论文全文数据库（硕士）工程科技I辑》 * |
| 王莹等: "基于神经网络和遗传算法的岩藻多糖酶发酵培养基优化", 《青岛农业大学学报（自然科学版）》 * |
| 王莹等: "基于遗传算法的羊肚菌液体发酵动力学模型的建立", 《生物工程学报》 * |
| 罗剑飞等: "基于神经网络和遗传算法培养基优化的发酵经济学", 《食品与生物技术学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106503856A (en) * | 2016-10-26 | 2017-03-15 | 中国石油大学(华东) | Test design method for artificial neural network method Optimal Medium |
| CN109486898A (en) * | 2018-12-06 | 2019-03-19 | 浙江大学 | Method based on aspergillus fungi upgrowth situation in electronic nose quick predict rice |
| CN109486898B (en) * | 2018-12-06 | 2022-06-21 | 浙江大学 | Method for rapidly predicting growth condition of aspergillus fungi in rice based on electronic nose |
| CN117285382A (en) * | 2023-11-22 | 2023-12-26 | 海南热带海洋学院 | Method for multi-strain fermentation of fish manure and waste low-odor fertilizer based on neural network |
| CN117285382B (en) * | 2023-11-22 | 2024-04-05 | 海南热带海洋学院 | Method for multi-strain fermentation of fish manure and waste low-odor fertilizer based on neural network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Feng et al. | Statistical optimization of media for mycelial growth and exo-polysaccharide production by Lentinus edodes and a kinetic model study of two growth morphologies | |
| Barceló-Villalobos et al. | Variations of culture parameters in a pilot-scale thin-layer reactor and their influence on the performance of Scenedesmus almeriensis culture | |
| Amini et al. | Effects of harvesting cell density, medium depth and environmental factors on biomass and lipid productivities of Chlorella vulgaris grown in swine wastewater | |
| CN102119631B (en) | Grifola frondosa strain for producing polysaccharide with composite raw material of rice bran and wheat bran | |
| CN102771314A (en) | Method for culturing selenium-enriched cordyceps militaris | |
| CN105373669A (en) | Pholiota adiposa fermentation condition optimization and dynamic model construction method | |
| CN104911109A (en) | High-yield paecilomyces hepiali mutant strain and cultivation method | |
| CN102342218B (en) | Method for producing cordyceps sinensis hyphae by virtue of solid-state fermentation | |
| CN103416313B (en) | Grifola frondosa strain produced through rice bran and wheat bran complete feed liquid fermentation | |
| CN103627620A (en) | Method and apparatus for producing lipids through microalgae culture | |
| ZHANG et al. | Biological characteristics and cultivation of fruit body of wild edible mushroom Auricularia villosula | |
| CN105695530A (en) | Liquid fermentation medium for high yielding of Qaidam agaricus bitorguis polysaccharide and application | |
| Wang et al. | Soft-sensing modeling based on ABC-MLSSVM inversion for marine low-temperature alkaline protease MP fermentation process | |
| CN102146355A (en) | Method for preparing selenium-enriched yeasts by using Candida utilis | |
| CN104206173A (en) | Method for cultivating by using wild hericium erinacrum bags | |
| CN107164297A (en) | A kind of method for promoting Antrodia camphorata mycelial growth and activated product to synthesize | |
| CN102550294B (en) | Method for liquid fermentation cultivation of Pleurotus cornucopiae strain | |
| Supriyanto et al. | A decision tree approach to estimate the microalgae production in open raceway pond | |
| CN103756950B (en) | Rose dark brown Isaria SCAU-IFCF02 strain liquid yeasting condition optimizing technique | |
| Hu et al. | Construction of closed integrative system for gases robust stabilization employing microalgae peculiarity and computer experiment | |
| CN108062602B (en) | A method of prediction greenhouse solanaceous vegetables crop assimilation products yield | |
| CN101724564B (en) | Method for producing truffle active mycelia and truffle polysaccharide by intermediate feed supplementing and fermentation | |
| Archambault et al. | Nannochloropsis sp. algae for use as biofuel: Analyzing a translog production function using data from multiple sites in the southwestern United States | |
| CN104130949B (en) | Liquid submerged fermentation medium and culture method for iron-rich cordyceps militaris | |
| CN104651423A (en) | Method for fermentation production of arachidonic acid by adopting two-stage pH control |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160302 |
|
| RJ01 | Rejection of invention patent application after publication |