Preparation method and device of carbon dioxide adsorption material and electronic equipment

Abstract

The invention provides a preparation method and device of a carbon dioxide adsorption material and electronic equipment, and the method comprises the following steps: obtaining material property data of a plurality of candidate materials, the plurality of candidate materials comprising a plurality of metal organic framework materials and a plurality of porous carbon materials; screening the material property data by using a performance prediction model and a multi-objective optimization algorithm to select an optimal composite material combination from the plurality of candidate materials, the optimal composite material combination being a combination of a metal organic framework material and a porous carbon material; and synthesizing the optimal composite material combination by using a preset preparation method to obtain the carbon dioxide adsorption material. By adopting the preparation method and device of the carbon dioxide adsorption material and the electronic equipment, the problems of low material selection efficiency and high research and development cost of the carbon dioxide adsorption material in the prior art are solved.

Description

Technical Field

[0001] The present application relates to the technical field of carbon dioxide processing, and in particular to a method, device and electronic equipment for preparing carbon dioxide adsorption material. Background Art

[0002] With the intensification of global warming, carbon dioxide capture and storage (CCS) technology has become a current research hotspot. In CCS technology, metal organic framework materials are usually used. Metal organic framework materials MOFs have high specific surface area, adjustable pore size and chemical stability, which makes them show great potential in the field of carbon dioxide adsorption. However, MOFs often face problems such as limited adsorption capacity and high cost in practical applications. Porous carbon materials have the characteristics of high specific surface area, good conductivity and low cost, and have become an ideal adsorption material. Therefore, combining MOFs with porous carbon materials and utilizing the high specific surface area and excellent conductivity of porous carbon materials can significantly improve the carbon dioxide adsorption performance and economy of composite materials.

[0003] However, there are many types of MOFs and porous carbon materials. How to quickly screen out materials with high adsorption performance from a large number of materials is crucial to the adsorption performance and R&D efficiency of carbon dioxide adsorption materials. In the existing technology, experiments and theoretical analysis are usually used to select the types of MOFs and porous carbon materials used, which not only has low efficiency in material selection, but also increases the R&D cost of carbon dioxide adsorption materials. Summary of the invention

[0004] In view of this, the purpose of the present application is to provide a method, device and electronic device for preparing a carbon dioxide adsorbent material, so as to solve the problems of low material selection efficiency and high R&D cost of carbon dioxide adsorbent materials in the prior art.

[0005] In a first aspect, an embodiment of the present application provides a method for preparing a carbon dioxide adsorbent material, comprising:

[0006] Obtaining material property data of a plurality of candidate materials, the plurality of candidate materials including a plurality of metal organic framework materials and a plurality of porous carbon materials;

[0007] Using performance prediction models and multi-objective optimization algorithms, material property data are screened to select the best composite material combination from multiple candidate materials. The best composite material combination is a combination of metal organic framework materials and porous carbon materials.

[0008] The optimal composite material combination was synthesized using the preset preparation method to obtain carbon dioxide adsorption materials.

[0009] Optionally, the target optimization algorithm is a genetic algorithm, which uses a performance prediction model and a multi-objective optimization algorithm to screen material property data, including: using a multi-objective optimization algorithm to generate multiple candidate composite material combinations; using a performance prediction model to predict the adsorption performance of each candidate composite material combination, and selecting the best composite material combination from multiple candidate composite material combinations based on the prediction results.

[0010] Optionally, a multi-objective optimization algorithm is used to generate multiple candidate composite material combinations, including: using the performance prediction model as the fitness evaluation function of the multi-objective optimization algorithm, using carbon dioxide adsorption capacity and selectivity as optimization targets, using material synthesis feasibility as a constraint, and using a multi-objective genetic algorithm to obtain multiple candidate composite material combinations.

[0011] Optionally, obtaining material property data of multiple candidate materials includes: obtaining initial material property data of multiple candidate materials, cleaning and standardizing the initial material property data to obtain standardized data; and performing feature engineering on the standardized data to obtain descriptors.

[0012] Optionally, the performance prediction model includes a three-dimensional convolutional neural network, a graph neural network and a fully connected layer, and the performance prediction model is used to predict the adsorption performance of each candidate composite material combination, including: using a three-dimensional convolutional neural network and a graph neural network to extract features from standardized data to obtain structural features; using a fully connected layer to fuse the structural features with descriptors to obtain the predicted results of the adsorption performance of the candidate composite material combination.

[0013] Optionally, the standardized data includes a three-dimensional voxel grid and a graph structure, and the structural features include spatial structure features and topological structure features. A three-dimensional convolutional neural network and a graph neural network are used to perform feature extraction on the standardized data to obtain structural features, including: inputting the three-dimensional voxel grid into the three-dimensional convolutional neural network to extract spatial structure features; inputting the graph structure into the graph neural network to extract topological structure features.

[0014] Optionally, the method also includes: using a preset loss function to determine the gradient of each parameter in the performance prediction model; based on the gradient, using an optimizer to update the parameters of the performance prediction model to train the performance prediction model.

[0015] Optionally, the method further includes: performing actual synthesis on the top-ranked candidate composite material combinations, and performing cyclic testing on the carbon dioxide adsorption materials obtained by the actual synthesis; and optimizing the performance prediction model according to the cyclic testing results.

[0016] In a second aspect, an embodiment of the present application further provides a device for preparing a carbon dioxide adsorption material, the device comprising:

[0017] A data processing module, used to obtain material property data of a plurality of candidate materials, wherein the plurality of candidate materials include a plurality of metal organic framework materials and a plurality of porous carbon materials;

[0018] A material combination selection module is used to screen material property data using a performance prediction model and a multi-objective optimization algorithm to select the best composite material combination from multiple candidate materials. The best composite material combination is a combination of a metal organic framework material and a porous carbon material.

[0019] The adsorption material preparation module is used to synthesize the best composite material combination using a preset preparation method to obtain carbon dioxide adsorption materials.

[0020] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the method for preparing carbon dioxide adsorption material as described above are performed.

[0021] The embodiments of the present application bring the following beneficial effects:

[0022] The carbon dioxide adsorption material preparation method, device and electronic device provided in the embodiment of the present application can use the performance prediction model and multi-objective optimization algorithm to screen the material property data, improve the material design and screening efficiency, reduce the experimental workload, and accelerate the discovery process of high-performance materials. At the same time, through the performance prediction model and multi-objective optimization algorithm, it is possible to more accurately predict and design the structure and performance of the composite material, optimize the mass ratio between MOFs and porous carbon materials, reduce material costs, and improve economic feasibility. Compared with the carbon dioxide adsorption material preparation method in the prior art, it solves the problems of low material selection efficiency and high R&D cost of carbon dioxide adsorption materials in the prior art.

[0023] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1A flow chart showing a method for preparing a carbon dioxide adsorbent material provided in an embodiment of the present application is shown;

[0026] Figure 2 A flow chart showing a composite material determination method provided in an embodiment of the present application is shown;

[0027] Figure 3 A schematic diagram of the structure of a device for preparing a carbon dioxide adsorption material provided in an embodiment of the present application is shown;

[0028] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0029] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, each other embodiment obtained by those skilled in the art without making creative work belongs to the scope of protection of the present application.

[0030] It is worth noting that before the present application was filed, with the intensification of global warming, carbon dioxide capture and storage (CCS) technology has become a current research hotspot. Carbon dioxide, as the main component of greenhouse gases, has become an important cause of global warming due to its excessive emissions. Traditional carbon dioxide capture and storage technologies mainly include chemical absorption, physical adsorption, membrane separation and other methods. Physical adsorption has attracted much attention due to its simple operation, low energy consumption and strong renewability. Metal organic framework materials MOFs have high specific surface area, adjustable pore size and chemical stability, which makes them show great potential in the field of carbon dioxide adsorption. However, MOFs often face problems such as limited adsorption capacity and high cost in practical applications. Porous carbon materials have the characteristics of high specific surface area, good conductivity and low cost, and have become an ideal adsorption material. Therefore, combining MOFs with porous carbon materials and utilizing the high specific surface area and excellent conductivity of porous carbon materials can significantly improve the carbon dioxide adsorption performance and economy of composite materials. However, there are many types of MOFs and porous carbon materials. How to quickly screen out materials with high adsorption performance from a large number of materials is crucial to the adsorption performance and R&D efficiency of carbon dioxide adsorption materials. In the existing technology, experiments and theoretical analysis are usually used to select the types of MOFs and porous carbon materials used, which not only has low efficiency in material selection, but also increases the R&D cost of carbon dioxide adsorption materials.

[0031] Based on this, an embodiment of the present application provides a method for preparing a carbon dioxide adsorbent material to improve the material selection efficiency and reduce the research and development cost of the carbon dioxide adsorbent material.

[0032] See also Figure 1 , Figure 1 This is a flow chart of a method for preparing a carbon dioxide adsorbent material provided in an embodiment of the present application. Figure 1 As shown, the method for preparing the carbon dioxide adsorbent material provided in the embodiment of the present application comprises:

[0033] Step S101, obtaining material property data of a plurality of candidate materials;

[0034] Step S102, using a performance prediction model and a multi-objective optimization algorithm to screen material property data to select the best composite material combination from multiple candidate materials;

[0035] Step S103, synthesizing the optimal composite material combination using a preset preparation method to obtain a carbon dioxide adsorption material.

[0036] The method for preparing carbon dioxide adsorbent materials provided in the embodiment of the present application can use the performance prediction model and multi-objective optimization algorithm to screen the material property data, improve the efficiency of material design and screening, reduce the experimental workload, and accelerate the discovery process of high-performance materials. At the same time, through the performance prediction model and multi-objective optimization algorithm, it is possible to more accurately predict and design the structure and performance of the composite material, optimize the mass ratio between MOFs and porous carbon materials, reduce material costs, improve economic feasibility, and solve the problems of low material selection efficiency and high R&D costs of carbon dioxide adsorbent materials in the prior art.

[0037] To facilitate understanding of this embodiment, each of the above exemplary steps provided in the embodiment of the present application is described below.

[0038] In step S101 , material property data of a plurality of candidate materials are obtained.

[0039] In this step, the plurality of candidate materials include a plurality of metal organic framework materials and a plurality of porous carbon materials.

[0040] As examples, various metal organic framework materials include but are not limited to: Zn-MOF-74, Mg-MOF-74, Ni-MOF-74, UiO-66, UiO-66-NH2, UiO-67, HKUST-1, ZIF-8, ZIF-67, MIL-101 (Cr), MIL-101 (Fe).

[0041] Various porous carbon materials include but are not limited to: activated carbon, carbon nanotubes, graphene, porous carbon aerogels, and MOFs pyrolytic carbon.

[0042] In an embodiment of the present application, the physicochemical property data of multiple candidate materials are collected from public databases, including Materials Project, CoRE MOF, and Carbon Materials Database, and these physicochemical property data are the initial material property data of multiple candidate materials. The initial material property data include, but are not limited to, crystal structure, chemical composition, specific surface area, pore size range, skeleton density, and carbon dioxide adsorption capacity. Then, the initial material property data is cleaned and standardized to obtain standardized data, for example: during the data cleaning process, the 3σ principle can be used to detect and process outliers, and the actual initial material property data can be filled based on the mean of similar structural materials, duplicate data entries are deleted, and the data units are unified. During the standardization process, the cleaned initial material property data can be divided into numerical data, chemical composition data, and crystal structure data, and the numerical data is standardized using the Z-score standardization method to map the numerical data to the [0,1] interval; at the same time, the chemical composition data is converted into one-hot encoding, and the crystal structure data is converted into a three-dimensional voxel grid.

[0043] In one example, after the initial material property data is cleaned and standardized, feature engineering can be performed on the standardized data to obtain descriptors, for example: structural descriptors representing the coordination number and bond length distribution of the material, geometric descriptors representing porosity and accessible pore volume, and chemical descriptors are calculated based on a 3D voxel grid through material simulation software or a self-programming algorithm.

[0044] In step S102, the material property data is screened using a performance prediction model and a multi-objective optimization algorithm to select the best composite material combination from a plurality of candidate materials.

[0045] In this step, the performance prediction model may refer to a trained deep learning model, and the performance prediction model is used to predict the adsorption performance of the carbon dioxide adsorption material. The output of the performance prediction model is CO 2 Adsorption capacity and CO 2 / N 2 Selective.

[0046] The multi-objective optimization algorithm may refer to an algorithm for determining an optimal composite material combination from a plurality of candidate materials. As an example, the multi-objective optimization algorithm may be a multi-objective genetic algorithm, such as the NSGA-II algorithm.

[0047] The best composite material combination is a combination of metal-organic framework materials and porous carbon materials.

[0048] Refer to the following Figure 2Let's introduce the process of determining the best composite material combination.

[0049] Figure 2 A flow chart of a composite material determination method provided in an embodiment of the present application is shown. Figure 2 As shown, the composite material determination method comprises:

[0050] Step S1021: Generate multiple candidate composite material combinations using a multi-objective optimization algorithm.

[0051] In one example, the trained performance prediction model can be used as the fitness evaluation function of the multi-objective optimization algorithm to use the CO output by the performance prediction model. 2 Adsorption capacity and CO 2 / N 2 Selectivity is used to guide the optimization process of the NSGA-II algorithm. At the same time, the carbon dioxide adsorption capacity is greater than the first preset target value and the selectivity (CO 2 / N 2 ) is greater than the second preset target value as the optimization target, the material synthesis feasibility is used as the constraint condition, and a multi-objective genetic algorithm or a combination of multiple candidate composite materials is used.

[0052] The first preset target value is 5mmol / g, and the second preset target value is 20. The feasibility of material synthesis can refer to the pore size distribution being within the first preset range, such as 0.3-2nm, and the specific surface area being within the second preset range, such as 500-8000m 2 / g.

[0053] The standardized data is input into the NSGA-II algorithm. In each generation, the NSGA-II algorithm continuously generates new composite material combination schemes through crossover and mutation operations, and selects the excellent individuals of this generation from the new composite material combination schemes based on non-dominated sorting and crowding distance. After multiple generations of iterative optimization, until the convergence condition is reached or the preset performance index is reached, the composite material combination selected at this time is taken as the best composite material combination. Among them, the Pareto optimal solution must be retained in each generation of population, and the set size of each generation of population is 100. The convergence condition can refer to no significant improvement in the optimal solution for 10 consecutive generations.

[0054] Step S1022: predict the adsorption performance of each candidate composite material combination using the performance prediction model, and select the best composite material combination from multiple candidate composite material combinations according to the prediction results.

[0055] The performance prediction model includes 3 layers of three-dimensional convolutional neural networks (3DCNN), 2 layers of graph neural networks (GNN) and 3 layers of fully connected layers. Each layer of 3DCNN includes 64 filters, each layer of GNN includes 128 hidden units, and each fully connected layer includes multiple neurons.

[0056] In one example, before using the performance prediction model to predict the adsorption performance of each candidate composite material combination, the performance prediction model needs to be trained. For example: the Adam optimizer can be used to train the performance prediction model. At this time, the initial learning rate is set to 0.001 (β1 = 0.9, β2 = 0.999), and the training data set is forward propagated through a network architecture including 3 layers of 3DCNN (64 filters per layer), 2 layers of GNN (128 hidden units per layer) and 3 layers of fully connected layers. The loss function is used to determine the gradient of each parameter in the performance prediction model, for example: the loss function is derived with respect to the parameters of the performance prediction model (including weights and biases), and the Adam optimizer algorithm is used to update the weights and biases of the initial performance prediction model. When the number of training rounds reaches the preset number or the loss value of the verification data set has not improved for 5 consecutive rounds, the model training is stopped to ensure that the performance prediction model meets the prediction accuracy requirements, that is, R 2 >0.95 and MAE<0.2mmol / g, where the weights include the convolution kernel weights, graph neural network weights, and fully connected layer weights in the performance prediction model, R 2 It indicates the degree to which the performance prediction model explains the change in carbon dioxide adsorption capacity. MAE is the calculation result of the loss function. MAE represents the mean absolute error of carbon dioxide adsorption capacity between the predicted value and the true value. The smaller the loss value, the higher the prediction accuracy of the performance prediction model.

[0057] In one example, each time a new composite material combination is obtained, the new composite material combination is used as a candidate composite material combination, and the performance prediction model is used to obtain the prediction result of the adsorption performance of the candidate composite material combination. Specifically, 3DCNN and GNN can be used to extract features from the standardized data to obtain structural features, and then the structural features and descriptors are fused together using a fully connected layer to obtain the prediction result of the adsorption performance of each candidate composite material combination.

[0058] For example: the standardized data includes a three-dimensional voxel grid and a graph structure. The three-dimensional voxel grid is input into 3DCNN to extract the spatial structure features, so that the spatial structure features such as the atomic arrangement and pore distribution of the material can be extracted through 3DCNN. The graph structure is input into GNN to extract the topological structure features, so that the network characteristics such as the connection relationship between atoms and the coordination environment of the material can be extracted through GNN. Finally, the spatial structure features, topological structure features and descriptors are fused together in the fully connected layer to obtain the prediction results of the adsorption performance of the candidate composite material combination.

[0059] In one example, in order to further optimize the performance prediction model, a preset number of candidate composite material combinations with high rankings can be selected from multiple candidate composite material combinations output by the multi-objective optimization algorithm, the selected preset number of candidate composite material combinations can be actually synthesized, and the carbon dioxide adsorption material actually synthesized can be subjected to a cycle test to determine the actual adsorption performance, and the prediction accuracy of the performance prediction model can be evaluated and optimized based on the cycle test results.

[0060] For example, the top 20 selected candidate composite material combinations were actually synthesized using an in-situ growth method (reaction temperature of 80 to 150°C and time of 1248 h) or a solution impregnation method (impregnation time of 424 h).

[0061] For each carbon dioxide adsorbent material obtained by actual synthesis, it is evaluated from three aspects: structural characteristics, adsorption performance and stability. Among them, for structural characteristics, XRD can be used to analyze the physical phase and crystal structure integrity of each carbon dioxide adsorbent material, SEM or TEM can be used to observe the morphology and composite interface characteristics of each carbon dioxide adsorbent material, and the specific surface area and pore size distribution of each carbon dioxide adsorbent material can be determined by N2 adsorption and desorption test; for adsorption performance, the static adsorption isotherm and fixed bed breakthrough curve of carbon dioxide in the range of 0-1bar at 298K can be obtained by volumetric method, and the separation coefficient can be calculated by IAST method; for stability, 20 adsorption-desorption cycle tests, water stability tests at 75% relative humidity, as well as compression tests and particle strength tests can be carried out. Through the above methods, multiple experimental test results of the carbon dioxide adsorbent material can be obtained.

[0062] Determine whether the performance prediction model meets the prediction accuracy requirements. For example, compare the predicted results of the adsorption performance of 20 candidate composite materials with the actual experimental test results. If the comparison results meet the R 2 >0.95, MAE<0.2mmol / g, it is determined to meet the prediction accuracy requirements. If the comparison result is R 2 ≤0.95, MAE≥0.2mmol / g, it is determined that it does not meet the prediction accuracy requirements. 2 It indicates the degree to which the performance prediction model explains the changes in carbon dioxide adsorption capacity, and MAE represents the mean absolute error of carbon dioxide adsorption capacity between the predicted value and the experimental test results.

[0063] If the prediction accuracy requirements are not met, the transfer learning method is used to integrate multiple experimental test results corresponding to each candidate composite material combination into the performance prediction model, so as to use multiple experimental test results to retrain the performance prediction model and update the weights in the performance prediction model to achieve model optimization. For example: in the process of updating the performance prediction model, the weights of the 3DCNN and GNN layers can be retained, the last three fully connected layers can be unfrozen, the domain adaptation layer can be introduced, and the maximum mean difference (MMD) can be used as the loss function. At the same time, in the process of updating the performance prediction model, the learning rate can be set to 0.0001, and the small batch training strategy can be used to divide the training data set into multiple small batches. Each training uses a small batch of data instead of the entire training data set to improve the efficiency of training. In addition, in the process of updating the performance prediction model, the L2 regularization method is also used to prevent overfitting and improve the generalization ability of the model.

[0064] In step S103, the optimal composite material combination is synthesized using a preset preparation method to obtain a carbon dioxide adsorption material.

[0065] In this step, MOFs form a stable composite structure with the porous carbon material through coordination bonds or π-π interactions, and the stable composite structure is the carbon dioxide adsorption material.

[0066] Among them, the carbon dioxide adsorption material has the following microstructure parameters: specific surface area is 1000-3500m 2 / g, preferably 1500-3000m 2 / g; total pore volume is 0.5-2.5cm 3 / g, preferably 0.8-2.0cm 3 / g; micropores (<2nm) account for 40-80%, mesopores (2-50nm) account for 20-60%, and the main pore size range is 0.8±0.2nm; the characteristic diffraction peaks of MOFs remain intact, and the intensity is not less than 80% of that of single-substance MOFs.

[0067] In addition, the CO2 adsorption capacity of the carbon dioxide adsorbent material at 298K and 1 bar is not less than 5mmol / g, and the selectivity (CO 2 / N 2 ) is not less than 100, and the adsorption capacity retention rate is not less than 95% after 20 adsorption-desorption cycles; after storage for 7 days under a relative humidity of 75%, CO 2 The retention rate of adsorption capacity and selectivity is not less than 90%; the bulk density of the material is 0.35-0.85g / cm 3 , the particle crushing strength is not less than 40N.

[0068] In one example, the preset preparation method includes at least one of the following items: in-situ growth method, solution impregnation method. Taking the optimal composite material combination of Mg-MOF-74 and activated carbon as an example, the in-situ growth method can be used to prepare the carbon dioxide adsorbent material. For example, 3.0 g of activated carbon can be dispersed in 150 mL DMF and ultrasonically treated for 30 minutes, and 6.16 g of Mg(NO 3 ) 2 6H 2 O and 2.52 g of dihydroxyterephthalic acid were transferred to a 250 mL polytetrafluoroethylene-lined stainless steel reactor, reacted at 120 ° C for 24 hours, and then the product was washed with DMF and methanol and dried under vacuum at 80 ° C for 12 hours to obtain the final carbon dioxide adsorption material.

[0069] Finally, the performance of the final synthesized carbon dioxide adsorption material can be tested, for example, using Micromeritics ASAP2020 for nitrogen adsorption and desorption testing, and using Micromeritics 3Flex for carbon dioxide adsorption testing. At the same time, using a homemade gravimetric adsorption device, 20 cycles of adsorption and desorption tests were performed to obtain the retention rate of the adsorption capacity of the carbon dioxide adsorption material after 20 cycles.

[0070] Based on the same inventive concept, an apparatus for preparing carbon dioxide adsorbent material corresponding to the method for preparing carbon dioxide adsorbent material is also provided in an embodiment of the present application. Since the principle of solving the problem by the apparatus in the embodiment of the present application is similar to the method for preparing carbon dioxide adsorbent material in the embodiment of the present application, the implementation of the apparatus can refer to the implementation of the method, and the repeated parts will not be repeated.

[0071] See also Figure 3 , Figure 3 This is a schematic diagram of the structure of a carbon dioxide adsorption material preparation device provided in an embodiment of the present application. Figure 3 As shown in , the carbon dioxide adsorption material preparation device 200 includes:

[0072] A data processing module 201 is used to obtain material property data of a plurality of candidate materials, wherein the plurality of candidate materials include a plurality of metal organic framework materials and a plurality of porous carbon materials;

[0073] The material combination selection module 202 is used to screen the material property data by using the performance prediction model and the multi-objective optimization algorithm to select the best composite material combination from multiple candidate materials, and the best composite material combination is a combination of metal organic framework material and porous carbon material;

[0074] The adsorption material preparation module 203 is used to synthesize the optimal composite material combination using a preset preparation method to obtain a carbon dioxide adsorption material.

[0075] See also Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 4 As shown in , the electronic device 300 includes a processor 310 , a memory 320 and a bus 330 .

[0076] The memory 320 stores machine-readable instructions executable by the processor 310. When the electronic device 300 is running, the processor 310 communicates with the memory 320 via the bus 330. When the machine-readable instructions are executed by the processor 310, the above-mentioned Figure 1 The steps of the method for preparing the carbon dioxide adsorbent material in the method embodiment shown, and the specific implementation methods can be found in the method embodiment, which will not be repeated here.

[0077] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the computer program can execute the above-mentioned Figure 1 The steps of the method for preparing the carbon dioxide adsorbent material in the method embodiment shown, and the specific implementation methods can be found in the method embodiment, which will not be repeated here.

[0078] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0079] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0080] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0081] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0082] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application can essentially be embodied in the form of a software product, or in other words, the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0083] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for preparing a carbon dioxide adsorbent material, characterized in that: include: Acquiring material property data of a plurality of candidate materials, wherein the plurality of candidate materials include a plurality of metal organic framework materials and a plurality of porous carbon materials; Using a performance prediction model and a multi-objective optimization algorithm, the material property data is screened to select an optimal composite material combination from a plurality of candidate materials, wherein the optimal composite material combination is a combination of a metal organic framework material and a porous carbon material; The optimal composite material combination is synthesized using a preset preparation method to obtain a carbon dioxide adsorption material.

2. The method according to claim 1, characterized in that: The target optimization algorithm is a genetic algorithm, and the material property data is screened using a performance prediction model and a multi-objective optimization algorithm, including: generating a plurality of candidate composite material combinations using the multi-objective optimization algorithm; The performance prediction model is used to predict the adsorption performance of each candidate composite material combination, and the best composite material combination is selected from multiple candidate composite material combinations according to the prediction results.

3. The method according to claim 2, characterized in that The method of generating a plurality of candidate composite material combinations by using the multi-objective optimization algorithm comprises: The performance prediction model is used as the fitness evaluation function of the multi-objective optimization algorithm, the carbon dioxide adsorption capacity and selectivity are used as optimization targets, the material synthesis feasibility is used as a constraint condition, and a multi-objective genetic algorithm is used to obtain multiple candidate composite material combinations.

4. The method according to claim 2, characterized in that: The obtaining of material property data of a plurality of candidate materials comprises: Acquire initial material property data of a plurality of candidate materials, and clean and standardize the initial material property data to obtain standardized data; Feature engineering is performed on the standardized data to obtain descriptors.

5. The method according to claim 4, characterized in that The performance prediction model includes a three-dimensional convolutional neural network, a graph neural network and a fully connected layer. The performance prediction model is used to predict the adsorption performance of each candidate composite material combination, including: Using the three-dimensional convolutional neural network and the graph neural network, extracting features from the standardized data to obtain structural features; The structural features are fused with the descriptors using the fully connected layer to obtain a prediction result of the adsorption performance of the candidate composite material combination.

6. The method according to claim 5, characterized in that The standardized data includes a three-dimensional voxel grid and a graph structure, the structural features include a spatial structural feature and a topological structural feature, and the three-dimensional convolutional neural network and the graph neural network are used to extract features from the standardized data to obtain structural features, including: Inputting the three-dimensional voxel grid into a three-dimensional convolutional neural network to extract spatial structural features; The graph structure is input into a graph neural network to extract topological structure features.

7. The method according to claim 1, characterized in that The method further comprises: Determining the gradient of each parameter in the performance prediction model using a preset loss function; Based on the gradient, an optimizer is used to update the parameters of the performance prediction model to train the performance prediction model.

8. The method according to claim 1, characterized in that: The method further comprises: Performing actual synthesis of multiple candidate composite material combinations that are ranked high, and performing cyclic testing on the carbon dioxide adsorbent materials obtained by the actual synthesis; The performance prediction model is optimized according to the cycle test results.

9. A device for preparing carbon dioxide adsorbent material, characterized in that: include: A data processing module, used to obtain material property data of a plurality of candidate materials, wherein the plurality of candidate materials include a plurality of metal organic framework materials and a plurality of porous carbon materials; A material combination selection module, for screening the material property data by using a performance prediction model and a multi-objective optimization algorithm, so as to select an optimal composite material combination from a plurality of candidate materials, wherein the optimal composite material combination is a combination of a metal organic framework material and a porous carbon material; The adsorption material preparation module is used to synthesize the optimal composite material combination using a preset preparation method to obtain a carbon dioxide adsorption material.

10. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and the processor executes the machine-readable instructions to perform the steps of the method for preparing a carbon dioxide adsorbent material as claimed in any one of claims 1 to 8.

Images