CN114038512B - Catalytic condition optimization method and system for synthesizing acrylic acid - Google Patents
Catalytic condition optimization method and system for synthesizing acrylic acid Download PDFInfo
- Publication number
- CN114038512B CN114038512B CN202111292181.6A CN202111292181A CN114038512B CN 114038512 B CN114038512 B CN 114038512B CN 202111292181 A CN202111292181 A CN 202111292181A CN 114038512 B CN114038512 B CN 114038512B
- Authority
- CN
- China
- Prior art keywords
- information
- result
- catalyst
- selection
- model
- 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
- SMZOUWXMTYCWNB-UHFFFAOYSA-N 2-(2-methoxy-5-methylphenyl)ethanamine Chemical compound COC1=CC=C(C)C=C1CCN SMZOUWXMTYCWNB-UHFFFAOYSA-N 0.000 title claims abstract description 114
- NIXOWILDQLNWCW-UHFFFAOYSA-N 2-Propenoic acid Natural products OC(=O)C=C NIXOWILDQLNWCW-UHFFFAOYSA-N 0.000 title claims abstract description 114
- 238000000034 method Methods 0.000 title claims abstract description 59
- 230000003197 catalytic effect Effects 0.000 title claims abstract description 56
- 230000002194 synthesizing effect Effects 0.000 title claims abstract description 28
- 238000005457 optimization Methods 0.000 title claims abstract description 24
- 239000003054 catalyst Substances 0.000 claims abstract description 151
- 238000013507 mapping Methods 0.000 claims abstract description 64
- 238000006243 chemical reaction Methods 0.000 claims description 46
- 108091026890 Coding region Proteins 0.000 claims description 40
- 238000012986 modification Methods 0.000 claims description 31
- 230000004048 modification Effects 0.000 claims description 31
- 238000012549 training Methods 0.000 claims description 23
- 238000006555 catalytic reaction Methods 0.000 claims description 20
- 239000013078 crystal Substances 0.000 claims description 20
- 230000000694 effects Effects 0.000 claims description 18
- 239000011148 porous material Substances 0.000 claims description 18
- 239000002253 acid Substances 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 11
- 230000010354 integration Effects 0.000 claims description 9
- 238000012217 deletion Methods 0.000 claims description 5
- 230000037430 deletion Effects 0.000 claims description 5
- 239000007795 chemical reaction product Substances 0.000 claims description 3
- 238000002474 experimental method Methods 0.000 abstract description 11
- 238000004519 manufacturing process Methods 0.000 description 28
- HGINCPLSRVDWNT-UHFFFAOYSA-N Acrolein Chemical compound C=CC=O HGINCPLSRVDWNT-UHFFFAOYSA-N 0.000 description 20
- 238000003860 storage Methods 0.000 description 14
- 239000003377 acid catalyst Substances 0.000 description 12
- 230000008569 process Effects 0.000 description 12
- 230000015572 biosynthetic process Effects 0.000 description 9
- 238000012545 processing Methods 0.000 description 9
- 238000003786 synthesis reaction Methods 0.000 description 9
- 238000000605 extraction Methods 0.000 description 7
- 239000000047 product Substances 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 239000000203 mixture Substances 0.000 description 5
- QQONPFPTGQHPMA-UHFFFAOYSA-N propylene Natural products CC=C QQONPFPTGQHPMA-UHFFFAOYSA-N 0.000 description 5
- 125000004805 propylene group Chemical group [H]C([H])([H])C([H])([*:1])C([H])([H])[*:2] 0.000 description 5
- 238000012216 screening Methods 0.000 description 5
- 239000012752 auxiliary agent Substances 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 238000007254 oxidation reaction Methods 0.000 description 4
- 238000002360 preparation method Methods 0.000 description 4
- 239000002131 composite material Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000003647 oxidation Effects 0.000 description 3
- -1 papermaking Substances 0.000 description 3
- 239000002994 raw material Substances 0.000 description 3
- 238000001878 scanning electron micrograph Methods 0.000 description 3
- 239000002002 slurry Substances 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- LYCAIKOWRPUZTN-UHFFFAOYSA-N Ethylene glycol Chemical compound OCCO LYCAIKOWRPUZTN-UHFFFAOYSA-N 0.000 description 2
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 2
- 238000007171 acid catalysis Methods 0.000 description 2
- 230000002378 acidificating effect Effects 0.000 description 2
- 239000000853 adhesive Substances 0.000 description 2
- 230000001070 adhesive effect Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 239000004566 building material Substances 0.000 description 2
- 239000007809 chemical reaction catalyst Substances 0.000 description 2
- 239000011248 coating agent Substances 0.000 description 2
- 238000000576 coating method Methods 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 150000002148 esters Chemical class 0.000 description 2
- 239000012847 fine chemical Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000010985 leather Substances 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 239000004753 textile Substances 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- VHUUQVKOLVNVRT-UHFFFAOYSA-N Ammonium hydroxide Chemical compound [NH4+].[OH-] VHUUQVKOLVNVRT-UHFFFAOYSA-N 0.000 description 1
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 1
- VGGSQFUCUMXWEO-UHFFFAOYSA-N Ethene Chemical compound C=C VGGSQFUCUMXWEO-UHFFFAOYSA-N 0.000 description 1
- 239000005977 Ethylene Substances 0.000 description 1
- 229910002651 NO3 Inorganic materials 0.000 description 1
- NHNBFGGVMKEFGY-UHFFFAOYSA-N Nitrate Chemical compound [O-][N+]([O-])=O NHNBFGGVMKEFGY-UHFFFAOYSA-N 0.000 description 1
- 239000004698 Polyethylene Substances 0.000 description 1
- IKHGUXGNUITLKF-XPULMUKRSA-N acetaldehyde Chemical compound [14CH]([14CH3])=O IKHGUXGNUITLKF-XPULMUKRSA-N 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 235000011114 ammonium hydroxide Nutrition 0.000 description 1
- APUPEJJSWDHEBO-UHFFFAOYSA-P ammonium molybdate Chemical compound [NH4+].[NH4+].[O-][Mo]([O-])(=O)=O APUPEJJSWDHEBO-UHFFFAOYSA-P 0.000 description 1
- 229940010552 ammonium molybdate Drugs 0.000 description 1
- 235000018660 ammonium molybdate Nutrition 0.000 description 1
- 239000011609 ammonium molybdate Substances 0.000 description 1
- 239000006227 byproduct Substances 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 229910002091 carbon monoxide Inorganic materials 0.000 description 1
- 238000007036 catalytic synthesis reaction Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 235000011187 glycerol Nutrition 0.000 description 1
- WGCNASOHLSPBMP-UHFFFAOYSA-N hydroxyacetaldehyde Natural products OCC=O WGCNASOHLSPBMP-UHFFFAOYSA-N 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005502 peroxidation Methods 0.000 description 1
- 229920000573 polyethylene Polymers 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 230000009257 reactivity Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000007086 side reaction Methods 0.000 description 1
- 238000001179 sorption measurement Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000007039 two-step reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/10—Analysis or design of chemical reactions, syntheses or processes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C60/00—Computational materials science, i.e. ICT specially adapted for investigating the physical or chemical properties of materials or phenomena associated with their design, synthesis, processing, characterisation or utilisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Molecular Biology (AREA)
- General Engineering & Computer Science (AREA)
- Analytical Chemistry (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Crystallography & Structural Chemistry (AREA)
- Organic Low-Molecular-Weight Compounds And Preparation Thereof (AREA)
Abstract
The invention provides a catalytic condition optimization method and a catalytic condition optimization system for synthesizing acrylic acid, wherein the method comprises the following steps: obtaining first characteristic information according to the basic information of the first catalyst; according to the catalytic result of the first catalyst, first phenotype information is obtained, wherein the first phenotype information and the first characteristic information have a first mapping relation, the first characteristic information is encoded, and a first encoding result is obtained; constructing a first fitness scoring model, and inputting a first coding result into the first fitness scoring model to obtain a first scoring result; a first selection model is built, a first scoring result is input into the first selection model, a first selection result is obtained, and if a first preset characteristic threshold is met, a first catalyst is prepared according to the first characteristic information corresponding to the first selection result. Solves the technical problems of low selection efficiency and weak stability caused by the fact that a large amount of experiments prove that the catalyst is required to be selected when acrylic acid is produced in the prior art.
Description
Technical Field
The invention relates to the technical field of intelligent manufacturing, in particular to a catalytic condition optimization method and a catalytic condition optimization system for synthesizing acrylic acid.
Background
Acrylic acid is one of important fine chemical raw materials and is widely used in the fields of coating, building materials, adhesives, textiles, leather, papermaking, oil extraction, water treatment and the like. The consumption of acrylic acid and esters thereof in China is rapidly increased, and the rapid development of the domestic acrylic acid industry is accelerated.
Along with the increase of the demand of the acrylic acid, the preparation process is also continuously developed, wherein the selection of the catalyst has great influence on the yield and purity of the acrylic acid, the catalyst is selected, the catalytic condition can be optimized, and the production efficiency of the acrylic acid is improved.
However, in the process of implementing the technical scheme of the embodiment of the application, the inventor discovers that the above technology has at least the following technical problems:
In the prior art, a large number of experiments prove that the selection of the catalyst in the process of producing the acrylic acid is too low in selection efficiency and poor in stability.
Disclosure of Invention
The embodiment of the application solves the technical problems of low selection efficiency and low stability caused by a large amount of experimental verification on the selection of a catalyst in the production of acrylic acid in the prior art by providing the method and the system for optimizing the catalytic condition of the synthesis of the acrylic acid. The method comprises the steps of constructing a mapping relation by collecting intrinsic characteristic information of an acrylic acid catalyst and catalytic effect information expressed by used synthetic acrylic acid, coding the characteristic information based on the mapping relation, scoring a coding sequence according to the catalytic effect expressed by the corresponding synthetic acrylic acid, selecting a preferable characteristic coding sequence according to a scoring result, selecting a corresponding group of acrylic acid catalysts meeting a preset ideal characteristic threshold, and preparing according to the characteristic information. The coding sequence is utilized to sign the intrinsic characteristic information of the acrylic acid catalyst, and the acrylic acid synthesis catalyst meeting the requirements can be rapidly selected according to the screening result, so that the technical effects of optimizing the catalysis condition of synthesizing acrylic acid and improving the reaction efficiency are achieved.
In view of the above problems, the embodiments of the present application provide a method and a system for optimizing catalytic conditions for synthesizing acrylic acid.
In a first aspect, an embodiment of the present application provides a catalytic condition optimization method for synthesizing acrylic acid, where the method is applied to a catalytic condition optimization system, and the method includes: obtaining first characteristic information according to basic information of a first catalyst, wherein the first characteristic information is used for representing attribute information of the first catalyst; obtaining first phenotype information according to a catalysis result of the first catalyst, wherein the first phenotype information is used for representing catalysis effect information of the first catalyst, and the first phenotype information and the first characteristic information have a first mapping relation; encoding the first characteristic information according to the first mapping relation to obtain a first encoding result; constructing a first fitness scoring model, and inputting the first coding result into the first fitness scoring model to obtain a first scoring result; constructing a first selection model, and inputting the first scoring result into the first selection model to obtain a first selection result; judging whether the first selection result meets the first preset characteristic threshold value or not; and if the first selection result meets the first preset characteristic threshold, preparing the first catalyst according to the first characteristic information corresponding to the first selection result.
In another aspect, embodiments of the present application provide a catalytic condition optimization system for synthesizing acrylic acid, wherein the system comprises: the first obtaining unit is used for obtaining first characteristic information according to basic information of a first catalyst, wherein the first characteristic information is used for representing attribute information of the first catalyst; the second obtaining unit is used for obtaining first phenotype information according to the catalysis result of the first catalyst, wherein the first phenotype information is used for representing catalysis effect information of the first catalyst, and the first phenotype information and the first characteristic information have a first mapping relation; the first coding unit is used for coding the first characteristic information according to the first mapping relation to obtain a first coding result; the first scoring unit is used for constructing a first fitness scoring model, inputting the first coding result into the first fitness scoring model and obtaining a first scoring result; the first selection unit is used for constructing a first selection model, inputting the first scoring result into the first selection model and obtaining a first selection result; the first judging unit is used for judging whether the first selection result meets the first preset characteristic threshold value or not; and the first execution unit is used for preparing the first catalyst according to the first characteristic information corresponding to the first selection result if the first selection result meets the first preset characteristic threshold value.
In a third aspect, embodiments of the present application provide a catalytic condition optimization system for synthesizing acrylic acid, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any one of the first aspects when the processor executes the program.
One or more technical solutions provided in the embodiments of the present application at least have the following technical effects or advantages:
Obtaining first characteristic information by adopting basic information according to a first catalyst, wherein the first characteristic information is used for representing attribute information of the first catalyst; obtaining first phenotype information according to a catalysis result of the first catalyst, wherein the first phenotype information is used for representing catalysis effect information of the first catalyst, and the first phenotype information and the first characteristic information have a first mapping relation; encoding the first characteristic information according to the first mapping relation to obtain a first encoding result; constructing a first fitness scoring model, and inputting the first coding result into the first fitness scoring model to obtain a first scoring result; constructing a first selection model, and inputting the first scoring result into the first selection model to obtain a first selection result; judging whether the first selection result meets the first preset characteristic threshold value or not; if the first selection result meets the first preset feature threshold, preparing the first catalyst according to the first feature information corresponding to the first selection result, constructing a mapping relation by collecting the intrinsic feature information of the acrylic acid catalyst and the catalytic effect information of the used synthesized acrylic acid, coding the feature information based on the mapping relation, scoring the coding sequence according to the catalytic effect of the corresponding synthesized acrylic acid, selecting a more preferable feature coding sequence according to the scoring result, selecting a corresponding group of acrylic acid catalysts meeting the preset ideal feature threshold, and preparing according to the feature information. The coding sequence is utilized to sign the intrinsic characteristic information of the acrylic acid catalyst, and the acrylic acid synthesis catalyst meeting the requirements can be rapidly selected by screening according to the scoring result, so that the technical effects of optimizing the catalysis condition of synthesizing the acrylic acid and improving the reaction efficiency are achieved.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
FIG. 1 is a schematic flow chart of a catalytic condition optimization method for synthesizing acrylic acid according to an embodiment of the application;
FIG. 2 is a schematic flow chart of a processing method in which a selected result does not satisfy a preset feature threshold;
FIG. 3 is a schematic diagram of a catalytic condition optimizing system for synthesizing acrylic acid according to an embodiment of the present application;
Fig. 4 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Reference numerals illustrate: the device comprises a first obtaining unit 11, a second obtaining unit 12, a first encoding unit 13, a first scoring unit 14, a first selecting unit 15, a first judging unit 16, a first executing unit 17, an electronic device 300, a memory 301, a processor 302, a communication interface 303 and a bus architecture 304.
Detailed Description
The embodiment of the application solves the technical problems of low selection efficiency and low stability caused by a large amount of experimental verification on the selection of the catalyst in the prior art by providing the method and the system for optimizing the catalytic conditions for synthesizing the acrylic acid. The method comprises the steps of constructing a mapping relation by collecting intrinsic characteristic information of an acrylic acid catalyst and catalytic effect information expressed by used synthetic acrylic acid, coding the characteristic information based on the mapping relation, scoring a coding sequence according to the catalytic effect expressed by the corresponding synthetic acrylic acid, selecting a preferable characteristic coding sequence according to a scoring result, selecting a corresponding group of acrylic acid catalysts meeting a preset ideal characteristic threshold, and preparing according to the characteristic information. The coding sequence is utilized to sign the intrinsic characteristic information of the acrylic acid catalyst, and the acrylic acid synthesis catalyst meeting the requirements can be rapidly selected by screening according to the scoring result, so that the technical effects of optimizing the catalysis condition of synthesizing the acrylic acid and improving the reaction efficiency are achieved.
Summary of the application
Acrylic acid is one of important fine chemical raw materials and is widely used in the fields of coating, building materials, adhesives, textiles, leather, papermaking, oil extraction, water treatment and the like. The consumption of acrylic acid and esters thereof in China is rapidly increased, and the rapid development of the domestic acrylic acid industry is accelerated. Along with the increase of the demand of the acrylic acid, the preparation process is also continuously developed, wherein the selection of the catalyst has great influence on the yield and purity of the acrylic acid, the catalyst is selected, the catalytic condition can be optimized, and the production efficiency of the acrylic acid is improved. However, in the prior art, a large number of experiments prove that the selection of the catalyst has the technical problems of low selection efficiency and poor stability.
Aiming at the technical problems, the technical scheme provided by the application has the following overall thought:
The embodiment of the application provides a catalytic condition optimization method for synthesizing acrylic acid, wherein the method is applied to a catalytic condition optimization system, and comprises the following steps: obtaining first characteristic information according to basic information of a first catalyst, wherein the first characteristic information is used for representing attribute information of the first catalyst; obtaining first phenotype information according to a catalysis result of the first catalyst, wherein the first phenotype information is used for representing catalysis effect information of the first catalyst, and the first phenotype information and the first characteristic information have a first mapping relation; encoding the first characteristic information according to the first mapping relation to obtain a first encoding result; constructing a first fitness scoring model, and inputting the first coding result into the first fitness scoring model to obtain a first scoring result; constructing a first selection model, and inputting the first scoring result into the first selection model to obtain a first selection result; judging whether the first selection result meets the first preset characteristic threshold value or not; and if the first selection result meets the first preset characteristic threshold, preparing the first catalyst according to the first characteristic information corresponding to the first selection result.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Example 1
As shown in fig. 1, an embodiment of the present application provides a catalytic condition optimization method for synthesizing acrylic acid, wherein the method is applied to a catalytic condition optimization system, and the method includes:
S100: obtaining first characteristic information according to basic information of a first catalyst, wherein the first characteristic information is used for representing attribute information of the first catalyst;
specifically, the most common industrial process for producing acrylic acid: by way of example, the two-step oxidation method of propylene is adopted, the first-stage reaction is mainly to synthesize acrolein by propylene, the currently used catalyst is mainly Mo-Bi catalyst, and then the catalyst is catalyzed by adding Fe, co, ni, mn, mg and other multi-element metal elements as auxiliary agents. The second-stage reaction is mainly to synthesize acrylic acid by acrolein, the currently used catalyst is mainly Mo-V catalyst, and W, cu, ce, sb and other elements are added as auxiliary agents for catalysis. The two-step reaction can produce various byproducts, such as products of ethylene, acetaldehyde, carbon monoxide, carbon dioxide, polyethylene and the like, and the selection of the catalyst with proper properties is significant in reducing side reactions, improving yield and accelerating reaction efficiency.
Further, the basic information of the first catalyst is basic data of a catalyst used for synthesizing acrylic acid, which is not limited to a few examples: such as Mo-Bi-based catalyst and Mo-V-based catalyst composition and ratio information, SEM image information, XRD image information, microscopic image information, and other attribute information. The first characteristic information is obtained by carrying out characteristic extraction on basic information of the first catalyst by preferably utilizing an unsupervised model trained based on a convolutional neural network, and the convolutional can be used as a characteristic extractor in machine learning, so that the extracted characteristic information has a concentration and a representativeness, further, the convolutional characteristic of the first characteristic information is obtained, and the convolutional neural network is one of the neural networks and has higher recognition performance on characteristic extraction.
S200: obtaining first phenotype information according to a catalysis result of the first catalyst, wherein the first phenotype information is used for representing catalysis effect information of the first catalyst, and the first phenotype information and the first characteristic information have a first mapping relation;
Specifically, the catalytic result of the first catalyst is information representing catalytic effects of the first catalyst after use under different attributes based on big data historical data, and the first phenotype information is obtained by characterizing the information. The preferable determination mode is to acquire experimental data and theoretical data through big data to obtain the catalytic effect of catalysts with different properties, such as data of the yield of the acrylic acid, the proportion of the acrylic acid in the product, the reaction time data, the reaction temperature, the reaction pressure and the like, which are obtained by the Mo-Bi catalyst and the Mo-V catalyst with different component proportions. Further, the first mapping relation is used for representing the relation between catalysts with different attributes and corresponding catalytic effects, namely representing the mapping relation between the first phenotype information and the first characteristic information. And the first characteristic information is evaluated according to different first phenotype information conveniently by combining the first catalyst intrinsic attribute and the corresponding extrinsic expression form through the first mapping relation, so that the first characteristic information is optimized.
S300: encoding the first characteristic information according to the first mapping relation to obtain a first encoding result;
Specifically, the first encoding result is a result of encoding the first feature information according to the first mapping relationship, and in order to convert specific first feature information into data that can be identified by a computer, the first feature information is encoded in an encoding manner, where a preferred encoding manner is: using a special symbol for each kind of characteristic information of the first catalyst: the digits, the capital letters and other symbols are identified, further, the digits, the capital letters and the other symbols are characterized by binary codes to obtain corresponding coding sequences, and different digits, the capital letters and the other symbols can be connected to the first phenotype information through the first mapping relation, so that the first coding result is determined. The specific actual problem can be converted into an abstract mathematical problem through the first coding result, so that the processing efficiency and the quantized processing process are improved.
S400: constructing a first fitness scoring model, and inputting the first coding result into the first fitness scoring model to obtain a first scoring result;
Specifically, the first fitness scoring model is an intelligent scoring model trained based on a neural network according to the first phenotype information, that is, corresponding scoring criteria are determined based on different first phenotype interval information, the scoring criteria are established based on the practical application fitness of acrylic acid products, the higher the fitness is, the higher the corresponding score is, the preferred score is 100 minutes at the highest, when the first phenotype information corresponding to the scoring result lower than 50 minutes and the first catalyst information are directly screened out, and the method is not suitable for catalytic synthesis of corresponding acrylic acid production scenes, and is exemplified: the two-stage oxidation of propylene to acrylic acid is not limited: in a certain historical production experiment, propylene is subjected to primary oxidation reaction to generate acrolein, and two kinds of catalysts are used: the first attribute is that a Mo-Bi composite oxide catalyst is used, fe, co and K are introduced as auxiliary agents, and the purity of the generated acrolein is 95%; the second is Mo-Bi composite oxide catalyst, fe, co and K are introduced as auxiliary agents, but glycol and glycerin are added as additives in the preparation process, and the purity of the produced acrolein is 98%. The results of the subsequent acrolein production show that the selectivity of the catalyst of the second nature towards acrolein is greatly enhanced, whereas the purity ratio of acrolein is required to be greater than 96% in the workshops at that time, while the purity ratio of acrolein of the first nature is not greater than 96%, and the first nature is not adapted to the production scenario at that time, and is then screened out. It should be noted that the data standard herein is merely an example for illustrating the principle of system operation, and is not limited to an acrylic acid production factory collection, but can be constructed by big data or historical production data collection; the first scoring result refers to a result obtained by inputting the first coding result into the first fitness scoring model, reading the corresponding first phenotype information according to the first mapping relation, and scoring. The first catalysts with different attributes can be distinguished through the first scoring result, quantization standards are provided for the first catalysts with poor rejection adaptability in the later step, and the accuracy of the treatment process is improved.
S500: constructing a first selection model, and inputting the first scoring result into the first selection model to obtain a first selection result;
Specifically, the first selection model is an intelligent model constructed based on data provided by a multipartite acrylic acid production enterprise and a factory, the intelligent model is updated by applying encryption model parameters which are provided by the acrylic acid production factory of the system and are trained based on the first scoring result information and then combining encryption model parameters provided by other acrylic acid production factories, the first scoring result is processed through the updated model, the first catalyst corresponding to the non-satisfactory scoring result is screened out, and a batch of first catalysts with higher fitness are left. Because the first selection model is a model trained by data of multiparty acrylic acid production enterprises, the problem of fewer historical data samples in the traditional acrylic acid production factories is solved, the basic data volume of the training model is increased, and the accuracy of the processing result is improved; the encryption mode of the model parameters ensures that all the acrylic acid production factories can not obtain the secret of the acrylic acid production process in the opposite enterprises only by updating the model through the aggregated model parameters, thereby improving the privacy among the parties of large data interaction.
S600: judging whether the first selection result meets the first preset characteristic threshold value or not;
S700: and if the first selection result meets the first preset characteristic threshold, preparing the first catalyst according to the first characteristic information corresponding to the first selection result.
Specifically, the first preset feature threshold refers to a preset optimal attribute data interval in which the first catalyst can be obtained under actual acrylic acid production conditions, which is exemplified by: the crystal phase structure of the pre-set one-stage reaction catalyst of the acrylic acid is mainly CoMoO 4、Bi2Mo3O12 and Bi 2MoO6, and the crystal phase particle size is 200nm-400nm, so that the non-conforming catalyst is screened out in the first selection result, all the first pre-set characteristic threshold values are in a logical and relation, and only the first catalyst which is fully satisfied can be selected; sequentially comparing the first characteristic information corresponding to the obtained first selection result with the first preset characteristic threshold, and marking the first preset characteristic threshold as the first selection result meeting the first preset characteristic threshold; further, it is described that the first catalyst corresponding to the first selection result satisfying the first preset feature threshold is the most suitable selection under the actual acrylic acid production condition of the corresponding acrylic acid production factory, the first catalyst is prepared according to the first feature information corresponding to the first catalyst, so as to achieve the technical effect of optimizing the acrylic acid catalysis condition.
Further, as shown in fig. 2, the method further includes step S800:
S810: if the first selection result does not meet the first preset characteristic threshold, a first arrangement instruction is obtained, wherein the first arrangement instruction comprises a first random modification instruction and a first random addition and deletion instruction;
s820: modifying the first coding result in the first selection result according to the first random modification instruction to obtain a first modification result;
s830: performing coding adding or deleting operation on the first coding result in the first selection result according to the first random adding or deleting instruction to obtain a second modification result;
s840: and inputting the first modification result and/or the second modification result into the first selection model to obtain a second selection result.
Specifically, when the first selection result does not have the information meeting the first preset characteristic threshold value, the first coding result is adjusted through the first randomly generated arrangement instruction; the first orchestration instruction includes the first random modification instruction: the instruction for modifying the first coding result corresponding to the first selection result includes the following two embodiments:
embodiment one: using a new code to replace the original code for the first code result corresponding to the first selection result;
embodiment two: adjusting the coding sequence of the first coding result corresponding to the first selection result; and obtaining the first modification result after modification. Wherein the first and second embodiments may be performed simultaneously or only one of them may be performed, and the first encoding result is again screened when the first encoding result is identical to the first encoding result which has been screened
The first arrangement instruction includes the first random addition/deletion instruction, and the following two adjustment modes can be performed on the first coding result in the first selection result through the first random addition/deletion instruction:
embodiment one: the first coding result in the first selection result can be added with codes or deleted with codes through the first random adding and deleting instruction;
Embodiment two: the first coding result in the first selection result can be subjected to coding adding and coding deleting through the first random adding and deleting instruction; and obtaining the second modification result after adjustment. Wherein the first and second embodiments may be implemented simultaneously or only one of them may be implemented, and the first encoding result is screened out again when the first encoding result is identical to the first encoding result which has been screened out.
Further, the first modification result and the second modification result or the first modification result or the second modification result may be input into the first selection model, the second selection result after the code update is further obtained, the second selection result is processed the same as the first selection result, if the first preset feature threshold is still not met, modification of the coding result corresponding to the second selection result is continued, and a third selection result is obtained, until the first catalyst meeting the first preset feature threshold is obtained, stopping outputting the first catalyst. The first catalyst with the attribute value which is not used actually can be verified by changing the coding result to process the catalytic experiment corresponding to the adjustment of the attribute value of the first catalyst, but the characteristic experiment amount is far larger than the verification content of the actual experiment, so that the decision efficiency of obtaining the optimized acrylic acid catalytic condition is improved.
Further, based on the basic information according to the first catalyst, first feature information is obtained, and step S1000 includes:
S110: extracting features of microscopic image information of the first catalyst to obtain first crystal phase structure feature information;
s120: extracting the characteristics of the macroscopic image information of the first catalyst to obtain first pore characteristic information;
S130: detecting the acid-base characteristic on the first catalyst to obtain first acid site quantity characteristic information;
S140: and taking the first crystal phase structure characteristic information, the first pore characteristic information and the first acid site quantity characteristic information as the first characteristic information.
Specifically, the microscopic image information of the first catalyst is image data representing the structure information and the component information of the finished product of the first catalyst, and the microscopic image information comprises: the method comprises the steps of carrying out feature extraction on microscopic image information of a first catalyst to obtain first crystal phase structural feature information representing component information and structural information of the first catalyst, wherein a certain Mo-Bi-Ni-Fe-Co-K-O composite oxide catalyst acquired through historical data is obtained by taking ammonium molybdate and Fe, co, ni, bi, K nitrate as raw materials, obtaining a mixture slurry through a hydrothermal precipitation method, regulating the pH value of the slurry through ammonia water, drying, roasting and forming to obtain the mixture slurry, and obtaining the first crystal phase structural feature information corresponding to the catalyst through XRD and SEM image feature acquisition, wherein the crystal phase composition of the mixture is mainly CoMoO 4、Bi2Mo3O12 and Bi 2MoO6, and the crystal phase particle size is 200-400 nm; further, the macroscopic image information of the first catalyst is characteristic data characterizing the integral structure of the first catalyst, including: microscopic image information and other information, which is macroscopic with respect to an SEM image, wherein the macroscopic image information of the first catalyst can be used for obtaining the first pore characteristic information representing the data such as pore shape, size, quantity and the like on the first catalyst, and generally, a proper amount of pores can improve the reactivity of the first catalyst and improve the selectivity to acrylic acid; further, the acid-base characteristic of the first catalyst is a result obtained by detecting the number of acid-base sites on the surface of the first catalyst, and in the synthesis of acrylic acid, the selectivity of acrylic acid is advantageously improved by adjusting the number of acid-base sites on the first catalyst, for example: in the two-step oxidation method, the number of acid sites on the first-stage reaction catalyst is reduced, namely the adsorption of propylene on the catalyst can be weakened, the peroxidation is inhibited, the selectivity to acrolein is improved, and the acid-base site number information on the surface of the first catalyst is represented by the first acid site number characteristic information. And finally, integrating the first crystal phase structure characteristic information, the first pore characteristic information and the first acid site quantity characteristic information to obtain the first characteristic information, wherein the first characteristic information can represent basic attribute information of the first catalyst. And quantifying the catalyst attribute through the first characteristic information, so that the subsequent processing is facilitated.
Further, based on the catalytic result according to the first catalyst, first phenotype information is obtained, and step S200 includes:
s210: obtaining historical reaction information of the first catalyst, and obtaining first reaction process information and first reaction result information according to the historical reaction information;
s220: obtaining first reaction duration information and first catalyst dosage information according to the first reaction process information;
S230: obtaining first purity information and first yield information according to the first reaction result information, wherein the first purity information represents the proportion of acrylic acid in a reaction product;
s240: and using the first reaction duration information, the first catalyst usage information, the first purity information and the first yield information as the first phenotype information.
Specifically, the historical reaction information of the first catalyst refers to catalytic effect data generated by acrylic acid production after the first catalyst is used under various attributes based on big data acquisition. If the first characteristic information of the first catalyst is characterized by data which is not put into experiments or produced, theoretical acrylic acid catalysis result data can be obtained through expert reasoning according to theory; further, decomposing the historical reaction information into the first reaction process information representing the acrylic acid generation reaction process and the first reaction result information representing the acrylic acid generation reaction result; still further, the first reaction duration information and the first catalyst amount information are collected based on the first reaction process information, and the first purity information and the first yield information of acrylic acid yield of the reaction acrylic acid in the product are collected based on the first reaction result information, by way of example: . And finally, integrating the first reaction duration information, the first catalyst dosage information, the first purity information and the first yield information to obtain the first phenotype information of the acrylic acid product corresponding to different attributes. And quantifying the catalytic effect of the acrylic acid synthesizing catalyst through the first phenotype information, so that the subsequent treatment is facilitated.
Further, based on the encoding the first feature information according to the first mapping relationship, a first encoding result is obtained, and step S300 includes:
S310: obtaining a first mapping coefficient according to the influence of the first crystal phase structural feature information on the first phenotype information;
S320: encoding the first crystal phase structural feature information according to the first mapping coefficient to obtain a first encoding sequence;
s330: obtaining a second mapping coefficient according to the influence of the first pore characteristic information on the first phenotype information;
s340: encoding the first pore characteristic information according to the second mapping coefficient to obtain a second encoding sequence;
s350: obtaining a third mapping coefficient according to the influence of the first acid site quantity characteristic information on the first phenotype information;
S360: coding the first acid site quantity characteristic information according to the third mapping coefficient to obtain a third coding sequence;
And S370, merging the first coding sequence, the second coding sequence and the third coding sequence to obtain a first coding sequence group, and taking the first coding sequence group as the first coding result.
Specifically, the first mapping relation includes the second mapping coefficient: a process for characterizing the effect of the first crystalline phase structural feature information on the first phenotype information; the second mapping coefficient: a process for characterizing the effect of the first pore characterization information on the first phenotype information; the third mapping coefficient: the method is used for representing the influence of the first acid site quantity characteristic information on the first phenotype information, and in the actual reaction process, the optimized catalyst in the modes of preparation conditions, roasting conditions, addition of auxiliaries and the like of the acrylic acid synthesis catalyst can be finally summarized into the first characteristic information. Further, the first crystal phase structural feature information is encoded according to the first mapping coefficient to obtain the first encoding sequence; encoding the first pore characteristic information according to the second mapping coefficient to obtain the second coding sequence; coding the first acid site quantity characteristic information according to the third mapping coefficient to obtain a third coding sequence, unifying coding standards, and ensuring operational generality; further, the first coding sequence, the second coding sequence and the third coding sequence are obtained into a three-dimensional first coding sequence group, and the first coding result is recorded as the first characteristic information and the first mapping relation between the first characteristic information and the first phenotype. And quantizing the specific first characteristic information through the first coding result to obtain an abstract coding result, wherein the first coding result can represent the diversified attribute of the first catalyst for synthesizing the acrylic acid, and the selection range is improved.
Further, based on the constructing the first fitness scoring model, step S400 includes:
s410: obtaining a first preset scoring standard according to the first phenotype information;
s420: constructing the first fitness function through the first mapping relation and the first preset scoring standard;
S430: and training the first fitness scoring model through the first fitness function.
Specifically, the first preset scoring standard is a scoring standard constructed in combination with the acrylic acid production process in big data, and the first phenotype information reaches a corresponding value, namely, the corresponding score is assessed; the first fitness function is a function representing the degree of fitness between the actual environment of acrylic acid production of the acrylic acid factory combined with the application of the system and the first catalyst with corresponding attributes, and the first fitness scoring model is trained based on a neural network model by combining the first preset scoring standard. The training data is a plurality of sets of data, each set of data comprising: the first coding result information and the identification information identifying the scoring result. Stopping until the output of the first fitness scoring model reaches convergence, and then processing the first coding result to obtain a more accurate scoring result.
Further, based on the constructing the first selection model, step S500 includes:
s510: downloading a first initial model through a first collaboration system;
S520: training the first initial model by using the first scoring result to obtain a first training model;
S530: reading model parameters of the first training model, and encrypting the model parameters to obtain a first encryption result;
S540: feeding the first encryption result back to the first cooperation system, and obtaining a first integration parameter through the first cooperation system, wherein the first integration parameter is obtained after the first cooperation system integrates N encryption results, the N encryption results comprise the first encryption result, and N is a positive integer greater than 1;
S550: and updating the first initial model through the first integration parameters to obtain the first selection model.
Specifically, step S510-step S550 are the process of constructing the first selection model, where the first collaboration system is involved, that is, a third party assisting multiple participants in training an update model; multiple participants, i.e., participants who provide data and use a model. The following describes the process of constructing the model from the first collaboration system side and from the factory side respectively:
Embodiment one:
The first collaboration system distributes an original model, namely the first initial model, to each acrylic acid-producing chemical plant, each acrylic acid-producing plant carries out model training, the model parameter encryption result of the first training model after training transmitted from the first plant, the second plant and the third plant to the N th plant is received, and the first encryption result is obtained.
Embodiment two:
The method comprises the steps of downloading an original model, namely a first initial model, from a first collaboration system by a first factory, a second factory and a third factory until an N-th factory for producing acrylic acid, training the first initial model by using a plurality of groups of first grading results until the first initial model reaches convergence to obtain the first training model, extracting model parameters of the first training model and encrypting the model parameters, sending the model parameters to the first collaboration system as a first encryption result, and after receiving information that the first collaboration system is updated by aggregating a plurality of N training parameter models similar to that sent by the first factory, namely the first selection model is updated, sending request information to the first collaboration system when the first initial model needs to be called, and cooperatively calling and processing data. The intelligent model can be used for integrating multiple data, increasing the data quantity and achieving the technical effect of improving the accuracy of the processing result.
In summary, the form page design method and system for user-defined metadata provided by the embodiment of the application have the following technical effects:
1. The method comprises the steps of constructing a mapping relation by collecting intrinsic characteristic information of a catalyst and catalytic effect information after use, coding the characteristic information based on the mapping relation, scoring a coding sequence according to a corresponding catalytic effect, selecting a more preferable characteristic coding sequence according to a scoring result, selecting a corresponding group of catalysts meeting a preset ideal characteristic threshold, and manufacturing according to the characteristic information. The intrinsic characteristic information of the catalyst is characterized by utilizing the coding sequence, and the catalyst meeting the requirements can be rapidly selected by screening according to the scoring result, so that the technical effects of optimizing the catalytic conditions of acrylic acid synthesis and improving the reaction efficiency are achieved.
2. Because the first selection model is a model trained by multiparty enterprise data, the problem of fewer historical data samples in the traditional factory is solved, the basic data volume of the training model is increased, and the accuracy of a processing result is improved; the encryption mode of the model parameters ensures that each factory can not obtain the production process secret in the opposite enterprise only by updating the model through the aggregated model parameters, and the privacy among the parties of large data interaction is improved.
3. The process of carrying out the catalytic experiment by changing the coding result to process the attribute value corresponding to the first catalyst is adjusted, however, the characteristic experiment amount is far larger than the content which can be verified by the actual experiment, the first catalyst with the attribute value which is not used actually can be verified until the first preset characteristic threshold is met, the obtained catalyst is ensured to be most suitable for the actual acrylic acid production environment corresponding to the acrylic acid production factory, and the decision efficiency of obtaining the optimized acrylic acid synthesis catalysis condition is improved.
Example two
Based on the same inventive concept as the catalytic condition optimization method for synthesizing acrylic acid in the previous embodiment, as shown in fig. 3, an embodiment of the present application provides a catalytic condition optimization system for synthesizing acrylic acid, wherein the system includes:
A first obtaining unit 11, where the first obtaining unit 11 is configured to obtain first feature information according to basic information of a first catalyst, where the first feature information is used to characterize attribute information of the first catalyst;
A second obtaining unit 12, where the second obtaining unit 12 is configured to obtain first phenotype information according to a catalytic result of the first catalyst, where the first phenotype information is used to characterize catalytic effect information of the first catalyst, and the first phenotype information and the first feature information have a first mapping relationship;
The first coding unit 13 is configured to code the first feature information according to the first mapping relationship, so as to obtain a first coding result;
the first scoring unit 14 is configured to construct a first fitness scoring model, and input the first encoding result into the first fitness scoring model to obtain a first scoring result;
the first selection unit 15 is configured to construct a first selection model, and input the first scoring result into the first selection model to obtain a first selection result;
A first judging unit 16, where the first judging unit 16 is configured to judge whether the first selection result meets the first preset feature threshold;
the first execution unit 17 is configured to prepare the first catalyst according to the first feature information corresponding to the first selection result if the first selection result meets the first preset feature threshold.
Further, the system further comprises:
The third obtaining unit is used for obtaining a first arrangement instruction if the first selection result does not meet the first preset characteristic threshold value, wherein the first arrangement instruction comprises a first random modification instruction and a first random addition/deletion instruction;
A fourth obtaining unit, configured to modify the first encoding result in the first selection result according to the first random modification instruction, to obtain a first modification result;
a fifth obtaining unit, configured to perform an encoding adding operation or an encoding deleting operation on the first encoding result in the first selection result according to the first random adding/deleting instruction, to obtain a second modification result;
and the sixth obtaining unit is used for inputting the first modification result and/or the second modification result into the first selection model to obtain a second selection result.
Further, the system further comprises:
A seventh obtaining unit, configured to perform feature extraction on microscopic image information of the first catalyst, to obtain first crystal phase structural feature information;
an eighth obtaining unit, configured to perform feature extraction on macroscopic image information of the first catalyst, to obtain first pore feature information;
a ninth obtaining unit, configured to detect an acid-base characteristic on the first catalyst, and obtain first acid site number characteristic information;
The first setting unit is used for taking the first crystal phase structure characteristic information, the first pore characteristic information and the first acid site quantity characteristic information as the first characteristic information.
Further, the system further comprises:
A tenth obtaining unit configured to obtain historical reaction information of the first catalyst, and obtain first reaction process information and first reaction result information according to the historical reaction information;
An eleventh obtaining unit configured to obtain first reaction duration information and the first catalyst usage information according to the first reaction process information;
A twelfth obtaining unit for obtaining first purity information and first yield information according to the first reaction result information, wherein the first purity information characterizes a ratio of acrylic acid in a reaction product;
And a second setting unit configured to take the first reaction duration information, the first catalyst usage information, the first purity information, and the first yield information as the first phenotype information.
Further, the system further comprises:
A thirteenth obtaining unit configured to obtain a first mapping coefficient according to an influence of the first crystal phase structural feature information on the first phenotype information;
A fourteenth obtaining unit, configured to encode the first crystal phase structural feature information according to the first mapping coefficient, to obtain a first encoding sequence;
A fifteenth obtaining unit configured to obtain a second mapping coefficient according to an influence of the first pore characteristic information on the first phenotype information;
A sixteenth obtaining unit, configured to encode the first pore characteristic information according to the second mapping coefficient, to obtain a second encoding sequence;
a seventeenth obtaining unit configured to obtain a third mapping coefficient according to an influence of the first acidic site number feature information on the first phenotype information;
An eighteenth obtaining unit, configured to encode the first acidic site number feature information according to the third mapping coefficient, to obtain a third coding sequence;
and the third setting unit is used for combining the first coding sequence, the second coding sequence and the third coding sequence to obtain a first coding sequence group, and taking the first coding sequence group as the first coding result.
Further, the system further comprises:
a nineteenth obtaining unit configured to obtain a first preset scoring criterion according to the first phenotype information;
A twentieth obtaining unit, configured to construct the first fitness function according to the first mapping relationship and the first preset scoring criterion;
The first training unit is used for training the first fitness scoring model through the first fitness function.
Further, the system further comprises:
The first downloading unit is used for downloading the first initial model through the first collaboration system;
a twenty-first obtaining unit, configured to train the first initial model using the first scoring result, and obtain a first training model;
The first encryption unit is used for reading the model parameters of the first training model and encrypting the model parameters to obtain a first encryption result;
A twenty-second obtaining unit, configured to feed back the first encryption result to the first collaboration system, and obtain a first integration parameter through the first collaboration system, where the first integration parameter is obtained after the first collaboration system integrates N encryption results, where the N encryption results include the first encryption result, and N is a positive integer greater than 1;
And a twenty-third obtaining unit, configured to update the first initial model with the first integration parameter, and obtain the first selection model.
Exemplary electronic device
An electronic device of an embodiment of the application is described below with reference to figure 4,
Based on the same inventive concept as the catalytic condition optimization method for synthesizing acrylic acid in the previous embodiment, the embodiment of the application further provides a catalytic condition optimization system for synthesizing acrylic acid, which comprises: a processor coupled to a memory for storing a program that, when executed by the processor, causes the system to perform the method of any of the first aspects.
The electronic device 300 includes: a processor 302, a communication interface 303, a memory 301. Optionally, the electronic device 300 may also include a bus architecture 304. Wherein the communication interface 303, the processor 302 and the memory 301 may be interconnected by a bus architecture 304; the bus architecture 304 may be a peripheral component interconnect (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus, or an extended industry standard architecture (extended industry Standard architecture, EISA) bus, among others. The bus architecture 304 may be divided into address buses, data buses, control buses, and the like. For ease of illustration, only one thick line is shown in fig. 4, but not only one bus or one type of bus.
Processor 302 may be a CPU, microprocessor, ASIC, or one or more integrated circuits for controlling the execution of the programs of the present application.
The communication interface 303 uses any transceiver-like system for communicating with other devices or communication networks, such as ethernet, radio access network (radio access network, RAN), wireless local area network (wireless local area networks, WLAN), wired access network, etc.
The memory 301 may be, but is not limited to, ROM or other type of static storage device that may store static information and instructions, RAM or other type of dynamic storage device that may store information and instructions, or may be an electrically erasable programmable read-only memory (EEPROM), a compact disk read-only memory (compact disc read-only memory) or other optical disk storage, optical disk storage (including compact disk, laser disk, optical disk, digital versatile disk, blu-ray disk, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. The memory may be self-contained and coupled to the processor through bus architecture 304. The memory may also be integrated with the processor.
The memory 301 is used for storing computer-executable instructions for executing the inventive arrangements, and is controlled by the processor 302 for execution. The processor 302 is configured to execute computer-executable instructions stored in the memory 301, thereby implementing a catalytic condition optimization method for synthesizing acrylic acid according to the above embodiment of the present application.
Alternatively, the computer-executable instructions in the embodiments of the present application may be referred to as application program codes, which are not particularly limited in the embodiments of the present application.
The embodiment of the application provides a method for optimizing the catalytic condition of synthesized acrylic acid, which constructs a mapping relation by collecting the intrinsic characteristic information of an acrylic acid catalyst and the catalytic effect information expressed by the synthesized acrylic acid after use, codes the characteristic information based on the mapping relation, scores a coding sequence according to the catalytic effect expressed by the corresponding synthesized acrylic acid, selects a preferable characteristic coding sequence according to a scoring result, selects a corresponding group of acrylic acid catalysts meeting a preset ideal characteristic threshold, and prepares according to the characteristic information. The coding sequence is utilized to sign the intrinsic characteristic information of the acrylic acid catalyst, and the acrylic acid synthesis catalyst meeting the requirements can be rapidly selected by screening according to the scoring result, so that the technical effects of optimizing the catalysis condition of synthesizing the acrylic acid and improving the reaction efficiency are achieved.
Those of ordinary skill in the art will appreciate that: the first, second, etc. numbers referred to in the present application are merely for convenience of description and are not intended to limit the scope of the embodiments of the present application, nor represent the sequence. "and/or", describes an association relationship of an association object, and indicates that there may be three relationships, for example, a and/or B, and may indicate: a exists alone, A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. "at least one" means one or more. At least two means two or more. "at least one," "any one," or the like, refers to any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one of a, b, or c (species ) may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable system. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device including one or more servers, data centers, etc. that can be integrated with the available medium. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (Solid STATE DISK, SSD)), etc.
The various illustrative logical blocks and circuits described in connection with the embodiments of the present application may be implemented or performed with a general purpose processor, a digital signal processor, an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic system, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the general purpose processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing systems, e.g., a digital signal processor and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a digital signal processor core, or any other similar configuration.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software unit executed by a processor, or in a combination of the two. The software elements may be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. In an example, a storage medium may be coupled to the processor such that the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an ASIC, which may reside in a terminal. In the alternative, the processor and the storage medium may reside in different components in a terminal. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Although the application has been described in connection with specific features and embodiments thereof, it will be apparent that various modifications and combinations can be made without departing from the spirit and scope of the application. Accordingly, the specification and drawings are merely exemplary illustrations of the present application as defined in the appended claims and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, it is intended that the present application cover the modifications and variations of this application provided they come within the scope of the appended claims and their equivalents.
Claims (9)
1. A catalytic condition optimization method for synthesizing acrylic acid, wherein the method is applied to a catalytic condition optimization system, the method comprising:
Obtaining first characteristic information according to basic information of a first catalyst, wherein the first characteristic information is used for representing attribute information of the first catalyst;
obtaining first phenotype information according to a catalysis result of the first catalyst, wherein the first phenotype information is used for representing catalysis effect information of the first catalyst, and the first phenotype information and the first characteristic information have a first mapping relation;
encoding the first characteristic information according to the first mapping relation to obtain a first encoding result;
constructing a first fitness scoring model, and inputting the first coding result into the first fitness scoring model to obtain a first scoring result;
Constructing a first selection model, and inputting the first scoring result into the first selection model to obtain a first selection result;
judging whether the first selection result meets a first preset characteristic threshold value or not;
And if the first selection result meets the first preset characteristic threshold, preparing the first catalyst according to the first characteristic information corresponding to the first selection result.
2. The method of claim 1, wherein the method further comprises:
If the first selection result does not meet the first preset characteristic threshold, a first arrangement instruction is obtained, wherein the first arrangement instruction comprises a first random modification instruction and a first random addition and deletion instruction;
Modifying the first coding result in the first selection result according to the first random modification instruction to obtain a first modification result;
performing coding adding or deleting operation on the first coding result in the first selection result according to the first random adding or deleting instruction to obtain a second modification result;
And inputting the first modification result and/or the second modification result into the first selection model to obtain a second selection result.
3. The method of claim 1, wherein the obtaining the first characteristic information based on the basic information of the first catalyst comprises:
extracting features of microscopic image information of the first catalyst to obtain first crystal phase structure feature information;
extracting the characteristics of the macroscopic image information of the first catalyst to obtain first pore characteristic information;
detecting the acid-base characteristic on the first catalyst to obtain first acid site quantity characteristic information;
And taking the first crystal phase structure characteristic information, the first pore characteristic information and the first acid site quantity characteristic information as the first characteristic information.
4. The method of claim 1, wherein said obtaining first phenotype information based on the catalytic result of the first catalyst comprises:
obtaining historical reaction information of the first catalyst, and obtaining first reaction process information and first reaction result information according to the historical reaction information;
obtaining first reaction duration information and first catalyst dosage information according to the first reaction process information;
Obtaining first purity information and first yield information according to the first reaction result information, wherein the first purity information represents the proportion of acrylic acid in a reaction product;
And using the first reaction duration information, the first catalyst usage information, the first purity information and the first yield information as the first phenotype information.
5. The method of claim 3, wherein the encoding the first feature information according to the first mapping relationship to obtain a first encoding result includes:
obtaining a first mapping coefficient according to the influence of the first crystal phase structural feature information on the first phenotype information;
Encoding the first crystal phase structural feature information according to the first mapping coefficient to obtain a first encoding sequence;
Obtaining a second mapping coefficient according to the influence of the first pore characteristic information on the first phenotype information;
Encoding the first pore characteristic information according to the second mapping coefficient to obtain a second encoding sequence;
Obtaining a third mapping coefficient according to the influence of the first acid site quantity characteristic information on the first phenotype information;
Coding the first acid site quantity characteristic information according to the third mapping coefficient to obtain a third coding sequence;
And combining the first coding sequence, the second coding sequence and the third coding sequence to obtain a first coding sequence group, and taking the first coding sequence group as the first coding result.
6. The method of claim 1, wherein the constructing a first fitness scoring model comprises:
obtaining a first preset scoring standard according to the first phenotype information;
Constructing the first fitness function through the first mapping relation and the first preset scoring standard;
and training the first fitness scoring model through the first fitness function.
7. The method of claim 1, wherein the constructing a first selection model comprises:
downloading a first initial model through a first collaboration system;
Training the first initial model by using the first scoring result to obtain a first training model;
Reading model parameters of the first training model, and encrypting the model parameters to obtain a first encryption result;
Feeding the first encryption result back to the first cooperation system, and obtaining a first integration parameter through the first cooperation system, wherein the first integration parameter is obtained after the first cooperation system integrates N encryption results, the N encryption results comprise the first encryption result, and N is a positive integer greater than 1;
And updating the first initial model through the first integration parameters to obtain the first selection model.
8. A catalytic condition optimization system for synthesizing acrylic acid, wherein the system comprises:
the first obtaining unit is used for obtaining first characteristic information according to basic information of a first catalyst, wherein the first characteristic information is used for representing attribute information of the first catalyst;
the second obtaining unit is used for obtaining first phenotype information according to the catalysis result of the first catalyst, wherein the first phenotype information is used for representing catalysis effect information of the first catalyst, and the first phenotype information and the first characteristic information have a first mapping relation;
The first coding unit is used for coding the first characteristic information according to the first mapping relation to obtain a first coding result;
The first scoring unit is used for constructing a first fitness scoring model, inputting the first coding result into the first fitness scoring model and obtaining a first scoring result;
the first selection unit is used for constructing a first selection model, inputting the first scoring result into the first selection model and obtaining a first selection result;
The first judging unit is used for judging whether the first selection result meets a first preset characteristic threshold value or not;
And the first execution unit is used for preparing the first catalyst according to the first characteristic information corresponding to the first selection result if the first selection result meets the first preset characteristic threshold value.
9. A catalytic condition optimization system for synthesizing acrylic acid, comprising: a processor coupled to a memory for storing a program that, when executed by the processor, causes the system to perform the method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111292181.6A CN114038512B (en) | 2021-11-02 | 2021-11-02 | Catalytic condition optimization method and system for synthesizing acrylic acid |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111292181.6A CN114038512B (en) | 2021-11-02 | 2021-11-02 | Catalytic condition optimization method and system for synthesizing acrylic acid |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114038512A CN114038512A (en) | 2022-02-11 |
CN114038512B true CN114038512B (en) | 2024-04-30 |
Family
ID=80136104
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111292181.6A Active CN114038512B (en) | 2021-11-02 | 2021-11-02 | Catalytic condition optimization method and system for synthesizing acrylic acid |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114038512B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115064206B (en) * | 2022-06-07 | 2023-08-08 | 浙江高裕家居科技股份有限公司 | Polyurethane elastomer optimization method and system based on performance evaluation |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3264344A1 (en) * | 2016-07-01 | 2018-01-03 | Siemens Aktiengesellschaft | Mapping rule updating method, device and system |
CN111128311A (en) * | 2019-12-25 | 2020-05-08 | 北京化工大学 | Catalytic material screening method and system based on high-throughput experiment and calculation |
CN113360780A (en) * | 2021-08-10 | 2021-09-07 | 北京黑马企服科技有限公司 | Big data based information recommendation method and system |
-
2021
- 2021-11-02 CN CN202111292181.6A patent/CN114038512B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3264344A1 (en) * | 2016-07-01 | 2018-01-03 | Siemens Aktiengesellschaft | Mapping rule updating method, device and system |
CN111128311A (en) * | 2019-12-25 | 2020-05-08 | 北京化工大学 | Catalytic material screening method and system based on high-throughput experiment and calculation |
CN113360780A (en) * | 2021-08-10 | 2021-09-07 | 北京黑马企服科技有限公司 | Big data based information recommendation method and system |
Also Published As
Publication number | Publication date |
---|---|
CN114038512A (en) | 2022-02-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Alquier et al. | Estimation bounds and sharp oracle inequalities of regularized procedures with Lipschitz loss functions | |
CN114038512B (en) | Catalytic condition optimization method and system for synthesizing acrylic acid | |
CN112131272B (en) | Method, device, equipment and storage medium for detecting multi-element KPI time sequence | |
CN112669905B (en) | RNA sequence coding potential prediction method and system based on data enhancement | |
CN107483059B (en) | Multi-channel data coding and decoding method and device based on dynamic Huffman tree | |
CN108108829A (en) | A kind of job-shop scheduling method based on improvement drosophila algorithm | |
CN105718943A (en) | Character selection method based on particle swarm optimization algorithm | |
CN113627479B (en) | Graph data anomaly detection method based on semi-supervised learning | |
US20200410285A1 (en) | Anomaly Augmented Generative Adversarial Network | |
CN112634992A (en) | Molecular property prediction method, training method of model thereof, and related device and equipment | |
CN103310027B (en) | Rules extraction method for map template coupling | |
CN103577900A (en) | Blocking flow shop scheduling method based on scatter variable neighborhood search | |
CN113642679B (en) | Multi-type data identification method | |
CN115169366A (en) | Session recommendation method based on sampling convolution and interaction strategy | |
CN114185956A (en) | Data mining method based on canty and k-means algorithm | |
CN114692888A (en) | System parameter processing method, device, equipment and storage medium | |
CN113989567A (en) | Garbage picture classification method and device | |
Andrews et al. | A perspective on future research directions in information theory | |
CN117560016B (en) | College recruitment information management method based on big data | |
CN115099356B (en) | Industrial unbalanced data classification method, device, electronic equipment and storage medium | |
CN108124283A (en) | A kind of radio frequency data transmission method and system | |
KR102068241B1 (en) | Method for quantum entanglement transformation using machine learning and Quantum system using thereof | |
AU2021105155A4 (en) | Task-based sampling network for Point Cloud Classification | |
Shang et al. | Tuning parameter selection rules for nuclear norm regularized multivariate linear regression | |
CN113011472B (en) | Multi-section electric power quotation curve similarity judging method and device |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |