CN108564222B - Optimization algorithm and method for optimizing production process of medicinal pearl nucleus - Google Patents
Optimization algorithm and method for optimizing production process of medicinal pearl nucleus Download PDFInfo
- Publication number
- CN108564222B CN108564222B CN201810366048.2A CN201810366048A CN108564222B CN 108564222 B CN108564222 B CN 108564222B CN 201810366048 A CN201810366048 A CN 201810366048A CN 108564222 B CN108564222 B CN 108564222B
- Authority
- CN
- China
- Prior art keywords
- optimizing
- experimental
- adopting
- production process
- medicinal
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000005457 optimization Methods 0.000 title claims abstract description 25
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 19
- 238000013528 artificial neural network Methods 0.000 claims abstract description 27
- 210000002569 neuron Anatomy 0.000 claims abstract description 24
- 238000002474 experimental method Methods 0.000 claims abstract description 18
- 230000002068 genetic effect Effects 0.000 claims abstract description 13
- 230000003385 bacteriostatic effect Effects 0.000 claims abstract description 8
- 238000012360 testing method Methods 0.000 claims abstract description 6
- 238000002790 cross-validation Methods 0.000 claims abstract description 5
- 230000005764 inhibitory process Effects 0.000 claims description 24
- 239000000243 solution Substances 0.000 claims description 22
- 229920001817 Agar Polymers 0.000 claims description 16
- 239000008272 agar Substances 0.000 claims description 16
- 239000001963 growth medium Substances 0.000 claims description 10
- 239000004181 Flavomycin Substances 0.000 claims description 9
- PERZMHJGZKHNGU-JGYWJTCASA-N bambermycin Chemical compound O([C@H]1[C@H](NC(C)=O)[C@@H](O)[C@@H]([C@H](O1)CO[C@H]1[C@@H]([C@@H](O)[C@H](O)[C@@H](CO)O1)O)O[C@@H]1O[C@@H]([C@H]([C@H](O)[C@H]1NC(C)=O)O[C@H]1[C@@H]([C@@H](O)[C@@H](O)[C@H](O1)C(=O)NC=1C(CCC=1O)=O)O)C)[C@H]1[C@@H](OP(O)(=O)OC[C@@H](OC\C=C(/C)CC\C=C\C(C)(C)CCC(=C)C\C=C(/C)CCC=C(C)C)C(O)=O)O[C@H](C(O)=O)[C@@](C)(O)[C@@H]1OC(N)=O PERZMHJGZKHNGU-JGYWJTCASA-N 0.000 claims description 9
- 235000019374 flavomycin Nutrition 0.000 claims description 9
- 238000001035 drying Methods 0.000 claims description 8
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 6
- 239000004100 Oxytetracycline Substances 0.000 claims description 5
- 238000007598 dipping method Methods 0.000 claims description 5
- 238000004090 dissolution Methods 0.000 claims description 5
- IWVCMVBTMGNXQD-PXOLEDIWSA-N oxytetracycline Chemical compound C1=CC=C2[C@](O)(C)[C@H]3[C@H](O)[C@H]4[C@H](N(C)C)C(O)=C(C(N)=O)C(=O)[C@@]4(O)C(O)=C3C(=O)C2=C1O IWVCMVBTMGNXQD-PXOLEDIWSA-N 0.000 claims description 5
- 235000019366 oxytetracycline Nutrition 0.000 claims description 5
- 229960000625 oxytetracycline Drugs 0.000 claims description 5
- IWVCMVBTMGNXQD-UHFFFAOYSA-N terramycin dehydrate Natural products C1=CC=C2C(O)(C)C3C(O)C4C(N(C)C)C(O)=C(C(N)=O)C(=O)C4(O)C(O)=C3C(=O)C2=C1O IWVCMVBTMGNXQD-UHFFFAOYSA-N 0.000 claims description 5
- 239000011521 glass Substances 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 239000011259 mixed solution Substances 0.000 claims description 3
- 239000008223 sterile water Substances 0.000 claims description 3
- 239000000725 suspension Substances 0.000 claims description 3
- 229910021642 ultra pure water Inorganic materials 0.000 claims description 3
- 239000012498 ultrapure water Substances 0.000 claims description 3
- 239000002609 medium Substances 0.000 claims 1
- 239000011049 pearl Substances 0.000 abstract description 59
- 239000013505 freshwater Substances 0.000 description 9
- FAPWRFPIFSIZLT-UHFFFAOYSA-M Sodium chloride Chemical compound [Na+].[Cl-] FAPWRFPIFSIZLT-UHFFFAOYSA-M 0.000 description 6
- KIPLYOUQVMMOHB-MXWBXKMOSA-L [Ca++].CN(C)[C@H]1[C@@H]2[C@@H](O)[C@H]3C(=C([O-])[C@]2(O)C(=O)C(C(N)=O)=C1O)C(=O)c1c(O)cccc1[C@@]3(C)O.CN(C)[C@H]1[C@@H]2[C@@H](O)[C@H]3C(=C([O-])[C@]2(O)C(=O)C(C(N)=O)=C1O)C(=O)c1c(O)cccc1[C@@]3(C)O Chemical compound [Ca++].CN(C)[C@H]1[C@@H]2[C@@H](O)[C@H]3C(=C([O-])[C@]2(O)C(=O)C(C(N)=O)=C1O)C(=O)c1c(O)cccc1[C@@]3(C)O.CN(C)[C@H]1[C@@H]2[C@@H](O)[C@H]3C(=C([O-])[C@]2(O)C(=O)C(C(N)=O)=C1O)C(=O)c1c(O)cccc1[C@@]3(C)O KIPLYOUQVMMOHB-MXWBXKMOSA-L 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 239000000843 powder Substances 0.000 description 4
- 229940063650 terramycin Drugs 0.000 description 4
- 240000004808 Saccharomyces cerevisiae Species 0.000 description 3
- 230000001580 bacterial effect Effects 0.000 description 3
- 238000009630 liquid culture Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 239000011780 sodium chloride Substances 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 241000237536 Mytilus edulis Species 0.000 description 2
- 239000001888 Peptone Substances 0.000 description 2
- 108010080698 Peptones Proteins 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 235000020638 mussel Nutrition 0.000 description 2
- 235000019319 peptone Nutrition 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241000894006 Bacteria Species 0.000 description 1
- 241000588724 Escherichia coli Species 0.000 description 1
- 241000607142 Salmonella Species 0.000 description 1
- 241000233667 Saprolegnia Species 0.000 description 1
- 230000000844 anti-bacterial effect Effects 0.000 description 1
- 230000003110 anti-inflammatory effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 239000011248 coating agent Substances 0.000 description 1
- 238000000576 coating method Methods 0.000 description 1
- 210000002808 connective tissue Anatomy 0.000 description 1
- 239000010984 cultured pearl Substances 0.000 description 1
- 238000012258 culturing Methods 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000035876 healing Effects 0.000 description 1
- 239000007943 implant Substances 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000002791 soaking Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000009278 visceral effect Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Computational Linguistics (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention relates to an optimization algorithm and a method for optimizing a production process of a medicinal pearl nucleus, wherein the optimization algorithm comprises the following steps: (1) experiment: determining the number of factors required by the experiment, and obtaining orthogonal experimental data by adopting an orthogonal experimental method; (2) modeling: modeling by adopting a BP (back propagation) neural network, setting a factor node number and a target node number, and performing cross validation on the orthogonal experimental data to train neurons of the BP neural network; (3) optimizing: and (4) combining a real number coding program of the R language, and performing target optimization on the target node number by adopting a genetic algorithm and marking. The method for optimizing the production process of the medicinal pearl nuclei combines an optimization algorithm to test the bacteriostatic effect of the medicinal pearl nuclei so as to find the bacteriostatic effect under the optimal condition and produce high-quality pearls. The optimization algorithm of the invention provides a stable and reliable model to find the optimal result, and has simple steps and convenient operation.
Description
Technical Field
The invention relates to an optimization algorithm and a method for optimizing a production process of a medicinal pearl nucleus.
Background
The fresh water pearl culture is mainly to implant pallium cell slices into connective tissues of the pallium of the freshwater mussel to culture the seedless pearl, the pearl culture period is as long as 5 years, the cultured pearl particles are small, the pearl rate is low (5%), most of the shapes are irregular, and the economic value is low. China is a large country for producing fresh water pearls, the yield of the fresh water pearls accounts for 95% of the world yield, Zhejiang province and city are the largest bases for cultivating, processing and selling fresh water pearls in China, the total yield accounts for more than half of the total yield of the whole country, and the fresh water pearls are known as 'country of Chinese pearls', but the sales amount is only 3.8 hundred million dollars and only accounts for 8 percent of 45 hundred million dollars of the total sales amount of the world pearls. The reason is mainly that the quality of the freshwater pearls is poor, and the proportion of high-quality and high-grade pearls is low in China. Therefore, in order to improve the value of the freshwater pearl, a great deal of research and development is carried out, and at present, success is achieved, for example, shells are ground to form pearl nuclei, and the pearl nuclei are inserted into nucleus sites of visceral sac or mantle of the freshwater mussel, and the produced pearl is a full-nacre nucleated pearl. As the mother pearl is surgically seeded, the healing quality of the wound of the mother pearl is directly related to the quality of the pearl, and the influence of the anti-inflammatory and antibacterial effects of the pearl on the quality of the pearl is very important. Therefore, how to optimize the production process conditions of the medicinal pearl nucleus has become an important problem which needs to be solved urgently.
The R language is a programming language with the strongest statistical function, has the characteristics of platform independence, free source opening, extremely strong expansibility and the like, has the functions of powerful mathematical statistical analysis and scientific data visualization, can expand the conventional R language through a programming function, and is simple to operate and powerful in floating point operation function. Most people in China are unfamiliar with the R language, and the technical conditions of the production of the medicinal pearl nucleus are analyzed and verified by applying a BP neural network and a genetic algorithm under the R language environment. The BP neural network is a multilayer feedforward network of an error back propagation algorithm, and the weight and the threshold of the network are continuously adjusted through back propagation, so that the BP neural network is one of the most widely applied network models at present. However, the BP neural network model also has some limitations, such as slow algorithm convergence speed, redundancy of the network model, and trapping of the algorithm into local extrema.
Disclosure of Invention
The invention aims to provide an optimization algorithm which has simple steps and convenient operation and combines a plurality of algorithms under the R language environment and finds the optimal solution and a method for optimizing the production process of the medicinal pearl nucleus.
In order to achieve the purpose, the invention provides the following technical scheme: an optimization algorithm, comprising the steps of:
experiment: determining the number of factors required by the experiment, and obtaining orthogonal experimental data by adopting an orthogonal experimental method;
modeling: modeling by adopting a BP (back propagation) neural network, setting a factor node number and a target node number, and performing cross validation on the orthogonal experimental data to train neurons of the BP neural network;
optimizing: and (4) combining a real number coding program of the R language, and performing target optimization on the target node number by adopting a genetic algorithm and marking.
Further, the number of factor nodes is equal to the number of factor nodes.
Further, in the step of modeling, the BP neural network is of a 3-layer structure.
Further, the step of "modeling" further comprises:
the neurons comprise hidden layer neurons, the fitting error data and the prediction error data are used as selection bases of the hidden layer neurons, and the optimal number of the hidden layer neurons is selected to determine the stability and the reliability of the BP neural network.
Further, in the step of modeling, the output node number is subjected to cross validation by a leave-one-out method.
The invention also provides a method for optimizing the production process of the medicinal pearl nuclei, which adopts the optimization algorithm and comprises the following steps:
s1: providing a plurality of groups of pearl nuclei, setting factor numbers, and preparing the medicinal pearl nuclei by adopting an orthogonal test;
s2: carrying out ultrasonic-assisted dissolution on the prepared medicinal pearl nuclei to form a plurality of groups of solutions, taking filter paper, putting the filter paper into the solutions of different groups for dipping, observing experimental inhibition zones formed on the filter paper of each group, and measuring diameter data of the experimental inhibition zones;
s3: optimizing the factors and the diameter data of the experimental bacteriostatic circle by adopting a genetic algorithm to obtain the maximum value of the diameter data of the experimental bacteriostatic circle and a factor value corresponding to the maximum value;
s4: preparing the medicinal pearl nuclei under the condition of the factor value corresponding to the maximum value, repeating the step S2 to obtain the final inhibition zone, and measuring the diameter data of the final inhibition zone to be compared with the diameter data of the experimental inhibition zone.
In the step "S1", the number of factors is 4, and the factors are the baking temperature, the oxytetracycline concentration, the flavomycin concentration, and the agar concentration.
Further, the step "S2" is specifically:
carrying out ultrasonic-assisted dissolution on the prepared medicinal pearl nuclei by using ultrapure water to form a plurality of groups of solutions, picking strains by using inoculating loops, placing the strains in sterile water with glass water, oscillating for several minutes to disperse spores, filtering to prepare spore suspension, adding a molten agar culture medium, adding the mixed solutions into the solutions of different groups, taking filter paper, placing the filter paper into the solutions of different groups for dipping, observing experimental inhibition zones formed on the filter paper of each group, and measuring diameter data of the experimental inhibition zones.
Furthermore, the volume range of the melting agar culture medium is 15-20 ml.
The invention has the beneficial effects that: in the R language environment, an orthogonal experiment method and a BP neural network are combined for modeling, a genetic algorithm is adopted for optimization, data obtained by the orthogonal experiment are fully utilized for analysis and processing, an optimal value solution is quickly obtained, and the method is simple, direct and convenient;
the production process of the medicinal pearl nucleus is combined with an optimization algorithm, an optimal value solution is quickly and accurately found, and corresponding verification is carried out, so that the optimal result of bacteriostasis of the medicinal pearl nucleus is obtained, and the effect of improving the quality of the pearl is achieved.
The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical solutions of the present invention more clearly understood and to implement them in accordance with the contents of the description, the following detailed description is given with reference to the preferred embodiments of the present invention and the accompanying drawings.
Drawings
FIG. 1 is a flow chart of the optimization algorithm of the present invention.
FIG. 2 is a flow chart of the method for optimizing the production process of the medicinal pearl nucleus of the invention.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
Referring to fig. 1, the optimization algorithm in a preferred embodiment of the present invention includes the following steps:
experiment: determining the number of factors required by the experiment, and obtaining orthogonal experimental data by adopting an orthogonal experimental method;
modeling: modeling by adopting a BP (back propagation) neural network, setting a factor node number and a target node number, and performing cross validation on the orthogonal experimental data to train neurons of the BP neural network; the neurons comprise hidden layer neurons, the fitting error data and the prediction error data are used as selection bases of the hidden layer neurons, and the optimal number of the hidden layer neurons is selected to determine the stability and the reliability of the BP neural network. In this embodiment, the BP neural network used is a 3-layer structure, and the number of nodes after output is cross-validated by a leave-one-out method.
Optimizing: and (4) combining a real number coding program of the R language, and performing target optimization on the target node number by adopting a genetic algorithm and marking.
In this embodiment, the number of factor nodes is equal to the number of factor nodes. Establishing 3-layer BP neural network under R language environment, setting initial random weight to 0.5, and making parameter weight decay to 1 × 10-5The maximum number of iterations is set to 1000, and the other parameters are default values. And (3) carrying out verification training on the BP neural network under the conditions, taking the fitting error data and the prediction error data as the selection basis of the hidden layer neurons, and selecting the number of the optimal hidden layer neurons to determine the stability and reliability of the BP neural network.
Referring to fig. 2, the present invention also provides a method for optimizing the production process of pharmaceutical pearl nuclei, which adopts the optimization algorithm as described above, but needs some preparation.
(1) Providing a strain: saprolegnia, salmonella and escherichia coli; providing drugs and reagents: terramycin, flavomycin, agar, sodium chloride and yeast powder; providing instruments and supplies: a shaking table, an incubator, an oven, a culture dish (diameter is 90mm), glass test paper, filter paper, a triangular flask (250ml) and a vernier caliper; providing a liquid culture medium: peptone 12g/L, yeast powder 6g/L, sodium chloride 11g/L, pH7.6; providing a plate culture medium: peptone 12g/L, yeast powder 6g/L, sodium chloride 11g/L, agar powder 25g/L, pH7.6.
(2) And inoculating each frozen colony to 100ml of liquid culture medium, and placing the liquid culture medium at 37 ℃ for shaking culture at 200r/min overnight to obtain bacterial liquid for later use.
(3) And inoculating 0.6ml of bacterial liquid into the sterilized flat plate, pouring about 15-20 ml of molten agar culture medium, uniformly mixing (the concentration of the mixed bacteria is 107cfu/ml) at the real-time temperature of about 45 ℃, and horizontally standing and solidifying for later use.
The method for optimizing the production process of the medicinal pearl nucleus comprises the following steps:
s1: providing a plurality of groups of pearl nuclei, setting factor numbers, and preparing the medicinal pearl nuclei by adopting an orthogonal test; wherein the number of the factors is 4, and the factors are respectively drying temperature, terramycin concentration, flavomycin concentration and agar concentration. According to an orthogonal L9(34) The method comprises the steps of coating the pearl nuclei with the drying temperature, the oxytetracycline concentration, the flavomycin concentration and the agar concentration, then placing the pearl nuclei in an oven for drying, and preparing the medicinal pearl nuclei as shown in table 1.
Table 1
| Level of | Drying temperature | Oxytetracycline concentration | Concentration of flavomycin | Concentration of agar |
| 1 | 20 | 10 | 20 | 500 |
| 2 | 30 | 20 | 30 | 600 |
| 3 | 40 | 30 | 40 | 700 |
S2: carrying out ultrasonic-assisted dissolution on the prepared medicinal pearl nuclei to form a plurality of groups of solutions, taking filter paper, putting the filter paper into the solutions of different groups for dipping, observing experimental inhibition zones formed on the filter paper of each group, and measuring diameter data of the experimental inhibition zones; the method specifically comprises the following steps: ultrasonic-assisted dissolving the prepared medicinal pearl nuclei with ultrapure water to form a plurality of groups of solutions, picking strains by using inoculating loops, placing the strains in sterile water with glass water, oscillating for a plurality of minutes to disperse spores, filtering to prepare spore suspension, adding molten agar culture medium, adding the mixed solutions into the solutions of different groups, taking filter paper, placing the filter paper in the solutions of different groups for soaking for a moment, taking out the filter paper, placing the filter paper in the center of a flat plate with the bacterial culture medium, and covering the flat plate with a cover. And (3) culturing in an incubator at a proper temperature (33 ℃) for 2-3 d, observing experimental inhibition zones formed on each group of filter paper, and measuring the diameter data of the experimental inhibition zones by adopting a cross method, wherein the diameter data are shown in a table 2.
Table 2
S3: optimizing the factors and the diameter data of the experimental bacteriostatic circle by adopting a genetic algorithm to obtain the maximum value of the diameter data of the experimental bacteriostatic circle and a factor value corresponding to the maximum value;
s4: preparing the medicinal pearl nuclei under the condition of the factor value corresponding to the maximum value, repeating the step S2 to obtain the final inhibition zone, and measuring the diameter data of the final inhibition zone to be compared with the diameter data of the experimental inhibition zone.
Combining the optimization algorithm, establishing a BP neural network with a 3-layer structure under the R language environment, setting the initial random weights to be 0.5, and attenuating the weight of the parameters to be 1 multiplied by 10-5The maximum number of iterations is set to 1000, whichHis parameters are default values. The BP neural network is verified and trained under the above conditions, the fitting error data and the prediction error data are used as the selection basis of the hidden layer neurons, and the number of the optimal hidden layer neurons is selected to determine the stability and reliability of the BP neural network, as shown in table 3.
Table 3
As can be seen from table 1, when the hidden layer neurons are 0, 1, 2, 3, 4, and 5, the average fitting data error and the average prediction data error are less than 5%, which are significant. The test training of the model was performed on different numbers of hidden layer neurons, and the results are shown in table 4.
Table 4
| Hidden layer neuron (size) | Error of fit (%) |
| 0 | 0.48 |
| 1 | 0.67 |
| 2 | 0.23 |
| 3 | 0.04 |
| 4 | 4.29 |
| 5 | 0.36 |
As shown in table 4, when the number of hidden layer neurons in the BP neural network increases to a certain number, an over-fitting phenomenon may occur. With the increase of the number of the hidden layer neurons, the fitting error is firstly reduced, then increased and then reduced, and when the number of the hidden layer neurons is judged to be 3, the phenomenon of overfitting in statistics can occur by increasing and decreasing the number of the neurons afterwards. Therefore, the number of hidden layer neurons of the BP neural network in the experiment is 3, and the BP neural network is stable and reliable at the moment. Then, according to the basic idea of genetic algorithm, a real number coding mode is adopted, the population size is set to be 200, the maximum algebra is 100, the maximum invariable algebra is 10, and the convergence tolerance is 5 multiplied by 10-4And other parameters are set as default values. The R language code is used for programming, the result obtained by the genetic algorithm is that the total generation is 25 generations, the running time is 8s, the maximum value of the size of the inhibition zone is found to be 32.96mm when the genetic algorithm is run to the 21 st generation, and the process conditions are that the drying temperature is 36 ℃, the terramycin concentration is 27g/kg, the flavomycin concentration is 34g/kg and the agar concentration is 580 g/kg.
Experiments show that the optimal value of the inhibition zone is 32.96mm, the factors at the optimal value are the drying temperature of 36 ℃, the oxytetracycline concentration of 27g/kg, the flavomycin concentration of 34g/kg and the agar concentration of 580g/kg, and then the result is verified. Weighing 5kg of pearl nuclei with uniform size, and dividing the pearl nuclei into 5 groups, wherein each group contains 1kg of pearl nuclei. Under the conditions of drying temperature of 36 ℃, terramycin concentration of 27g/kg, flavomycin concentration of 34g/kg and agar concentration of 580g/kg, medicinal pearl nuclei are prepared, the diameters of inhibition zones of the medicinal pearl nuclei are measured to be 31.60 mm, 32.10 mm, 31.65 mm, 32.02 mm and 31.53mm respectively, and the average extraction amount is 31.78 mm. The relative error between the actual measured value and the network predicted value (32.96mm) is 3.6%, and less than 5% indicates that the optimized experimental measurement is more consistent with the network prediction, and the mathematical model has better network prediction.
In summary, the following steps: in the R language environment, an orthogonal experiment method and a BP neural network are combined for modeling, a genetic algorithm is adopted for optimization, data obtained by the orthogonal experiment are fully utilized for analysis and processing, an optimal value solution is quickly obtained, and the method is simple, direct and convenient;
the production process of the medicinal pearl nucleus is combined with an optimization algorithm, an optimal value solution is quickly and accurately found, and corresponding verification is carried out, so that the optimal result of bacteriostasis of the medicinal pearl nucleus is obtained, and the effect of improving the quality of the pearl is achieved.
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (4)
1. A method for optimizing a production process of medicinal pearl nuclei is characterized by adopting an optimization algorithm, wherein the optimization algorithm specifically comprises the following steps:
experiment: determining the number of factors required by the experiment, and obtaining orthogonal experimental data by adopting an orthogonal experimental method;
modeling: modeling by adopting a BP (back propagation) neural network, setting a factor node number and a target node number, and performing cross validation on the orthogonal experimental data to train neurons of the BP neural network;
optimizing: performing target optimization on the target node number by adopting a genetic algorithm in combination with a real number coding program of an R language and marking out the target node number;
the real number encoding program combined with the R language is specifically: establishing 3-layer BP neural network under R language environment, setting initial random weight to 0.5, and making parameter weight decay to 1 × 10-5At the mostThe large iteration number is set to 1000, and other parameters are default values;
according to an optimization algorithm, the method for optimizing the production process of the medicinal pearl nucleus comprises the following steps:
s1: providing a plurality of groups of pearl nuclei, setting factor numbers, and preparing the medicinal pearl nuclei by adopting an orthogonal test;
s2: carrying out ultrasonic-assisted dissolution on the prepared medicinal pearl nuclei to form a plurality of groups of solutions, taking filter paper, putting the filter paper into the solutions of different groups for dipping, observing experimental inhibition zones formed on the filter paper of each group, and measuring diameter data of the experimental inhibition zones;
s3: optimizing the factors and the diameter data of the experimental bacteriostatic circle by adopting a genetic algorithm to obtain the maximum value of the diameter data of the experimental bacteriostatic circle and a factor value corresponding to the maximum value;
s4: preparing the medicinal pearl nuclei under the condition of the factor value corresponding to the maximum value, repeating the step S2 to obtain the final inhibition zone, and measuring the diameter data of the final inhibition zone to be compared with the diameter data of the experimental inhibition zone.
2. The method for optimizing the production process of the pharmaceutical pearl nucleus according to claim 1, wherein in the step "S1", the number of the factors is 4, which are respectively the drying temperature, the oxytetracycline concentration, the flavomycin concentration and the agar concentration.
3. The method for optimizing the production process of the pharmaceutical pearl nucleus according to claim 2, wherein the step "S2" is specifically:
carrying out ultrasonic-assisted dissolution on the prepared medicinal pearl nuclei by using ultrapure water to form a plurality of groups of solutions, picking strains by using inoculating loops, placing the strains in sterile water with glass water, oscillating for several minutes to disperse spores, filtering to prepare spore suspension, adding a molten agar culture medium, adding the mixed solutions into the solutions of different groups, taking filter paper, placing the filter paper into the solutions of different groups for dipping, observing experimental inhibition zones formed on the filter paper of each group, and measuring diameter data of the experimental inhibition zones.
4. The method for optimizing the production process of the medicinal pearl nuclei according to claim 3, wherein the volume of the molten agar medium is 15 to 20 ml.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810366048.2A CN108564222B (en) | 2018-04-23 | 2018-04-23 | Optimization algorithm and method for optimizing production process of medicinal pearl nucleus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810366048.2A CN108564222B (en) | 2018-04-23 | 2018-04-23 | Optimization algorithm and method for optimizing production process of medicinal pearl nucleus |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108564222A CN108564222A (en) | 2018-09-21 |
| CN108564222B true CN108564222B (en) | 2022-03-01 |
Family
ID=63536409
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810366048.2A Active CN108564222B (en) | 2018-04-23 | 2018-04-23 | Optimization algorithm and method for optimizing production process of medicinal pearl nucleus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108564222B (en) |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010509933A (en) * | 2006-11-22 | 2010-04-02 | インディアン カウンシル オブ アグリカルチュラル リサーチ | In-vitro pearl production method using marine organisms |
| CN100448347C (en) * | 2007-04-24 | 2009-01-07 | 詹伟建 | Pearl sacs processing method for cultivating nucleated pearls |
| CN101356901B (en) * | 2008-09-12 | 2011-01-26 | 海南大学 | Method for pearl core treatment by medicament |
| CN101654699A (en) * | 2008-12-31 | 2010-02-24 | 中国人民解放军第三○二医院 | Method for testing antibacterial activity of indigowoad root Chinese medicinal material |
| FR2964014B1 (en) * | 2010-08-31 | 2013-04-05 | Ifremer | NUCLEUS COATED WITH A FILMOGENEOUS COATING WITH ANTIBACTERIAL AND CICATRISANT PROPERTIES AND METHOD OF OBTAINING THE SAME |
| CN102257973B (en) * | 2011-04-28 | 2012-12-26 | 广东海洋大学 | Method for preparing antibacterial nuclei |
| CN103636533B (en) * | 2013-12-02 | 2015-10-07 | 浙江海洋学院 | The breeding method of fresh water genuine pearl with pearl |
| CN106749495A (en) * | 2016-11-18 | 2017-05-31 | 浙江中医药大学 | R language combinations orthogonal experiment optimizes the process for extracting of tanshinone IIA |
-
2018
- 2018-04-23 CN CN201810366048.2A patent/CN108564222B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN108564222A (en) | 2018-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Edelstein-Keshet | Mathematical models in biology | |
| Lederberg | Cell genetics and hereditary symbiosis | |
| Horton et al. | The cortical column: a structure without a function | |
| CN109584337A (en) | A kind of image generating method generating confrontation network based on condition capsule | |
| Dworkin et al. | The myxobacteria: new directions in studies of procaryotic development | |
| CN106202984B (en) | It is a kind of based on multilayer complex network to the screening technique of tumour miRNA marker | |
| CN105701280B (en) | Penaeus Vannmei encloses pool cultivation water prediction technique | |
| Aplin et al. | Growth analysis of circular lichen thalli | |
| CN107038475A (en) | A kind of self-adapting random resonant system and method based on artificial fish-swarm algorithm | |
| CN108564222B (en) | Optimization algorithm and method for optimizing production process of medicinal pearl nucleus | |
| Pan et al. | A hybrid clustering algorithm combining cloud model iwo and k-means | |
| CN110289987A (en) | Multi-agent system network resilience appraisal procedure based on representative learning | |
| CN110322077A (en) | Cement raw material Vertical Mill raw material fineness index prediction technique based on convolutional neural networks | |
| Nokkaew et al. | Mathematical modeling of infectious disease transmission in macroalgae | |
| CN109686399A (en) | A kind of gene data collection confluence analysis method | |
| Li et al. | A computational method for optimizing experimental environments for Phellinus igniarius via genetic algorithm and BP neural network | |
| CN107182900B (en) | Method for researching growth and development rules of breeding hens based on maximum qualified egg number | |
| CN115010232A (en) | Drinking water plant coagulation dosing prediction method based on weak time-lag neural network model | |
| CN110018201B (en) | Rapid identification method for resistance of corn variety fusarium ear rot | |
| Mallick et al. | Application of nature inspired optimization algorithms in bioimpedance spectroscopy: simulation and experiment. | |
| CN109858692A (en) | A kind of Land ecological warning grade assessment method | |
| CN105063011A (en) | Mutagenesis method for improving mutation probability of active streptomycete producing nosiheptide | |
| CN107875374A (en) | The method that Caenorhabditis elegans infection model is precisely quickly established based on orthogonal optimization | |
| CN106538437A (en) | Penaeus vannamei leukoderma monitoring early-warning system and method based on rough set theory | |
| CN103210855A (en) | Mantle piece treatment liquid for improving seawater pearl quality and treatment method |
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 | ||
| CB03 | Change of inventor or designer information |
Inventor after: Yu Jiaying Inventor after: Zhan Yi Inventor after: Jin Weifeng Inventor after: Li Xiaohong Inventor before: Zhan Yi Inventor before: Jin Weifeng |
|
| CB03 | Change of inventor or designer information | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220208 Address after: Hangzhou City, Zhejiang province Binjiang District 310053 shore road 548 Applicant after: ZHEJIANG CHINESE MEDICAL University Address before: 247100 1314, building Z2, Tonghui City Plaza, Guichi District, Chizhou City, Anhui Province Applicant before: ANHUI XINBEI ECOLOGICAL AGRICULTURAL DEVELOPMENT CO.,LTD. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |