Porous material preparation process optimization method

Abstract

The invention relates to the technical field of porous material preparation process optimization, in particular to a porous material preparation process optimization method. The method comprises the steps of obtaining microscopic pore distribution characteristic data to generate preliminary design parameters, constructing a microstructure model to optimize pore sizes, adjusting key element distribution to generate an improved scheme, determining an optimal process parameter combination through simulation testing, detecting pore uniformity in real time and dynamically adjusting parameters. And monitoring the element utilization rate to generate a dynamic adjustment scheme and verifying the performance index to generate an optimization record. Intelligent control over preparation of the porous material can be achieved, the surface area, the pore uniformity and the key element utilization rate are remarkably increased, and reliable technical support is provided for application in the fields of catalysis, environmental protection and the like.

Description

Technical Field

[0001] The present invention belongs to the technical field of porous material preparation process optimization, and in particular relates to a porous material preparation process optimization method. Background Art

[0002] In the field of chemical catalysis and environmental protection equipment, the research on porous materials is of great significance. Their performance directly affects the catalytic efficiency and resource utilization rate, and plays a key role in promoting the green industrial process and energy conservation and emission reduction. However, the current preparation methods of porous materials have many shortcomings, such as insufficient material surface area, low resource utilization efficiency and complex preparation process. These problems seriously limit the further improvement of their performance. Specifically, traditional preparation processes are difficult to accurately control the pore structure at the microscale, resulting in a low surface area of ​​the material, thereby limiting the number of active sites for catalytic reactions. At the same time, the uneven distribution and low utilization rate of key elements in the material further aggravate resource waste and cost increases. These problems are interrelated. The defects of the pore structure directly lead to a decrease in element utilization efficiency, and the inefficient element utilization, in turn, limits the optimization space of material performance, forming a technical bottleneck that needs to be solved urgently.

[0003] In addition, the existing porous material preparation technology also has obvious deficiencies in process parameter optimization and real-time monitoring. Traditional methods often rely on experience or simple experimental designs, lack of systematic and intelligent means, and it is difficult to achieve precise control of pore uniformity and element distribution. At the same time, there is a lack of dynamic feedback mechanism in the preparation process, and it is impossible to adjust the process parameters according to real-time data, resulting in the final material performance being difficult to achieve the expected goals. Therefore, how to construct a porous structure with a high surface area and significantly improve the utilization efficiency of key elements has become a core issue that urgently needs to be solved. The solution to this problem will directly determine the performance of porous materials in catalytic reactions and provide an important foundation for technological breakthroughs in related fields.

[0004] The present invention aims to solve the above-mentioned technical problems by optimizing the preparation process of porous materials through intelligent methods. Specifically, the present invention obtains the microscopic pore distribution characteristic data of porous materials, combines numerical simulation and optimization algorithms to generate preliminary design parameters, and constructs a microstructure model on this basis to optimize the pore size and element distribution. At the same time, the present invention determines the optimal combination of process parameters through simulation tests, and introduces a real-time monitoring and feedback mechanism in the preparation process to dynamically adjust the process parameters to ensure the optimization of pore uniformity and element distribution. Finally, through a comprehensive analysis of the surface area and element utilization, it is verified whether the material performance meets the preset indicators, and an optimization record is generated as a guide for subsequent preparation. This method realizes the intelligent control of the porous material preparation process, significantly improves the material performance and preparation efficiency, and provides an innovative solution for the technological development of related fields. Summary of the Invention

[0005] This paper addresses the challenges of existing porous material preparation processes, such as insufficient surface area, low utilization of key elements, and limited microstructural control. By doing so, it proposes an intelligently-based method for optimizing porous material preparation processes. This method obtains microscopic pore distribution data and generates preliminary design parameters. It then constructs a microstructural model to optimize pore size parameters, analyzes the distribution of key elements and adjusts their positions. The method then combines virtual parameter configuration and simulation testing to determine the optimal process parameter combination. The method then dynamically adjusts the process parameters through real-time detection and feedback mechanisms, ultimately achieving precise control of the porous material's performance.

[0006] The technical solution of the present invention is: A method for optimizing the preparation process of porous materials, first extracting the microscopic pore distribution characteristic data of the target porous material from a pre-established structural database. Specifically, a data processing tool is used to classify and organize the microscopic pore distribution characteristic data to obtain a preliminary distribution characteristic set. Furthermore, based on the preliminary distribution characteristic set, the correspondence data between the pore size and the surface area value is extracted, and the support vector machine algorithm is used to analyze the correspondence data to determine the key size and surface area matching pattern. For the key size and surface area matching pattern, the pore structure range that meets the conditions is screened to obtain an optimized initial pore data set. If the data points in the optimized initial pore data set deviate from the preset threshold range, the abnormal data is eliminated by a data cleaning tool to obtain an adjusted pore structure data set. Finally, based on the adjusted pore structure data set, the pore characteristic parameters within the optimization range are extracted to determine the design parameter set that matches the target porous material.

[0007] In particular, the above-mentioned method for optimizing the preparation process of porous materials uses a numerical simulation method to construct a microstructure model of the porous material based on the preliminary pore design parameters. Specifically, the initial microstructure model data of the porous material is obtained by numerical simulation technology, and modeling is performed on the preliminary pore design parameters to generate a preliminary structural model. Furthermore, the pore distribution characteristic data is extracted based on the preliminary structural model, and the uniformity and connectivity of the pore distribution are quantitatively evaluated using analysis tools to obtain distribution characteristic indicators. The surface area value is calculated for the distribution characteristic indicator and compared with a preset threshold. If the surface area value is lower than the preset threshold, the deviation of the current size parameter is recorded. The pore size parameters are iteratively optimized using a genetic algorithm to generate an adjusted parameter data set. The microstructure model is updated using the adjusted parameter data set, and the optimized structure model is reconstructed to obtain new pore distribution characteristic data.

[0008] Furthermore, the above-mentioned method for optimizing the preparation process of porous materials uses the optimized structural model data to analyze the distribution of key elements and adjust the element positions using a uniform distribution optimization algorithm to generate improved solution data. Specifically, it includes: obtaining the initial distribution information of key elements through the optimized structural model data, and performing preliminary processing on the distribution characteristics within the pores to obtain the original data set of element distribution. According to the original data set, the degree of aggregation of key elements in the pores is analyzed, and the distribution density is quantified using statistical tools to determine the high and low distribution areas of the aggregation degree. If the aggregation degree exceeds a preset threshold, the key element position in the high aggregation area is marked, and the element position data to be adjusted is extracted. The element position data to be adjusted is redistributed by a uniform distribution optimization algorithm to obtain the adjusted position distribution information. Based on the adjusted position distribution information, the improved element distribution solution data is generated, and it is determined whether the uniform distribution requirements are met.

[0009] Furthermore, the above-mentioned method for optimizing the preparation process of porous materials constructs a virtual parameter configuration of the preparation process based on the improved solution data, and determines the optimal process parameter combination through simulation testing. Specifically, a virtual parameter configuration model of the porous material preparation process is constructed through the improved solution data to obtain the initial process conditions and parameter set. Based on the initial process conditions and parameter set, a multi-round simulation method is used to generate operating data under different parameter combinations to obtain a simulation result data set. For the simulation result data set, the change trend between the process parameters and the pore surface area is analyzed to obtain preliminary correlation data. If there is a significant correlation pattern in the correlation data, the mapping relationship between the process parameters and the pore surface area is quantified by a regression analysis method to determine the key influencing factors. According to the key influencing factors, the process conditions in the virtual parameter configuration are adjusted to generate a new parameter combination data set, and the simulation test process is repeated to obtain the pore surface area prediction data.

[0010] Furthermore, the above-mentioned method for optimizing the preparation process of porous materials obtains real-time pore data during the preparation process through the optimal process parameter combination, detects pore uniformity, and adjusts the process parameters through a feedback mechanism to obtain corrected parameter values. Specifically, real-time pore data during the preparation process is obtained through a sensor system, and preliminary processing is performed on the real-time pore data to obtain structured pore distribution information. Based on the structured pore distribution information, image processing technology is used to analyze the pore uniformity and determine the uniformity index value. If the uniformity index value is lower than a preset threshold, the process parameters are evaluated through a pre-established feedback mechanism to determine the deviation range of the current parameters. Based on the deviation range, a support vector machine model is used to optimize and calculate the process parameters to obtain adjusted parameter recommended values. The adjusted parameter recommended values ​​are transmitted to the control system through the information feedback mechanism to obtain an updated process parameter configuration.

[0011] Furthermore, the above-mentioned method for optimizing the preparation process of porous materials generates dynamic control instructions and monitors element utilization based on the corrected parameter values, and determines a dynamic adjustment plan for element distribution. Specifically, it includes: by collecting parameter adjustment data during the preparation process, constructing an initial dynamic control model, and obtaining a preliminary basis for generating preparation instructions. According to the preparation instructions output by the dynamic control model, the changes in element utilization are monitored in real time, the utilization fluctuation data is recorded, and the distribution state of the fluctuation characteristics is obtained. According to the distribution state of the utilization fluctuation data, a data analysis method is used to extract the key indicators of the change trend and determine the main influencing factors of the trend. If the key indicators of the change trend exceed the preset threshold, a new control instruction is generated by adjusting the dynamic strategy of the element distribution to obtain the adjusted operating parameters. The dynamic control model is updated according to the adjusted operating parameters, and the element utilization is predicted using the support vector machine algorithm to judge the stability of the prediction results.

[0012] Furthermore, the above-mentioned method for optimizing the preparation process of porous materials obtains the surface area and element utilization test data after preparation through the dynamic adjustment scheme, uses the data comparison method to determine whether the preset performance indicators are met, and generates the final performance verification result. Specifically, the preparation scheme of the porous material is dynamically adjusted by the automation system to obtain the initial surface area value and the test data related to the element utilization. Based on the test data, the surface area value and the element utilization data are pre-processed using a standardized processing method to obtain a normalized first data set. For the first data set, the support vector machine algorithm is used to extract the features of the surface area value and the element utilization to determine the key performance feature set. By performing a comprehensive analysis on the key performance feature set, the correlation distribution between the features is obtained to determine whether the feature distribution conforms to the preset distribution model. If the feature distribution conforms to the preset distribution model, the feature set is compared with the preset standard to obtain a preliminary performance matching result. Based on the preliminary performance matching result, the matching result is secondary verified using a logistic regression algorithm to determine whether the final performance indicator meets the preset standard.

[0013] Finally, based on the final performance verification results, an optimized record of the porous material preparation process is generated. Key parameters in the record are archived, a reference dataset for process improvement is obtained, and a guiding basis for subsequent preparation is determined. Specifically, by collecting performance verification results, various indicators related to the preparation process are extracted from the raw data. Data cleaning methods are used to remove outliers, resulting in a preliminary performance dataset. Based on this preliminary performance dataset, key parameters in the preparation process are classified and labeled. A support vector machine algorithm is used to model the correlation between parameters and performance, and the influence weights of key parameters are determined. From the influence weights of key parameters, parameter combinations directly related to process improvement are obtained. These combinations are subjected to multi-dimensional comparative analysis to determine the direction of parameter adjustment and obtain an optimized parameter configuration scheme. The optimized parameter configuration scheme is then matched against historical optimization records. If the match exceeds a preset threshold, the scheme is included in the reference dataset and identified as a candidate basis for subsequent preparation. The candidate basis in the reference dataset is simulated and verified for the subsequent preparation process. If the deviation between the simulation results and the expected performance is below a preset threshold, the basis is archived as a guiding basis, resulting in the final process guidance scheme. Based on the final process guidance plan, key parameters are digitally archived and structured using a database management system. This creates a parameter library that can be accessed in real time, establishing the foundation for subsequent production. This real-time access to the parameter library allows for comparison and analysis of dynamic data during the subsequent production process. If performance data deviates from the preset guidance range, a parameter adjustment mechanism is triggered, resulting in real-time optimized process parameters.

[0014] Advantages and beneficial effects of the present invention: The present invention obtains the microscopic pore distribution characteristics of the target material through a pre-established database, uses numerical simulation to generate a structural model and optimize the pore size parameters to achieve precise control of the surface area; at the same time, the present invention uses a uniform distribution optimization algorithm to adjust the position of key elements and determine an element distribution improvement plan. During the preparation process, the present invention dynamically adjusts the process parameters by real-time monitoring of pore formation data and element utilization to ensure the optimization of pore uniformity and element distribution; finally, the present invention verifies whether the material performance meets the preset indicators through comprehensive analysis of surface area and element utilization detection data, and generates optimization records as a guide for subsequent preparation. This method realizes intelligent control of the porous material preparation process, significantly improves the surface area, pore uniformity and key element utilization of the material, solves the problems of insufficient material performance and resource waste in traditional preparation processes, and provides reliable technical support for the application of porous materials in catalysis, environmental protection and other fields. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The overall process optimization flow chart of the present invention is as follows; Figure 2 A specific flow chart for obtaining microscopic pore distribution characteristic data of the present invention; Figure 3 A specific flow chart for constructing a microstructure model for the present invention; Figure 4 A specific flow chart for analyzing the distribution of key elements for the present invention; Figure 5 A specific flow chart of constructing virtual parameter configuration for the present invention. DETAILED DESCRIPTION

[0016] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0017] A porous material preparation process optimization method, by combining intelligent means and data analysis technology, realizes the optimization of the whole process from microstructure design to dynamic adjustment of process parameters. The flow chart is as follows Figure 1 As shown, the method includes obtaining microscopic pore distribution characteristic data and generating preliminary design parameters; Construct microstructure models and optimize pore size parameters; Analyze the distribution of key elements and adjust the element positions; Build virtual parameter configurations and determine the optimal process parameter combination through simulation testing; Real-time detection of pore uniformity and adjustment of process parameters through feedback mechanism; Generate dynamic control instructions and monitor element utilization; Comprehensively analyze test data and generate final performance verification results.

[0018] In a specific embodiment, the optimization method is as follows: like Figure 1 、 2 As shown, in step S101, microscopic pore distribution characteristic data of the target material is first obtained from a pre-established porous material structure database. This database contains pore sizes, surface area values, and other key parameters related to material properties for a variety of porous materials. For example, when preparing a porous ceramic material for gas adsorption, distribution data for pore diameters ranging from 1 nanometer to 50 nanometers can be extracted from the database, and the corresponding surface area values ​​can be recorded. This data is then sorted and organized to form a preliminary distribution characteristic set. Furthermore, data on the correspondence between pore size and surface area values ​​is extracted from this preliminary distribution characteristic set. This data is then analyzed using a support vector machine algorithm to identify key size-surface area matching patterns. Assuming the analysis results show that the surface area peaks at a pore diameter of 12 nanometers, this pattern becomes an important basis for subsequent optimization. If any data points deviate from a preset threshold range, such as abnormally low pore surface areas, these abnormal data are removed using a data cleaning tool to obtain an adjusted pore structure dataset. Finally, pore characteristic parameters within the optimization range are extracted from the adjusted pore structure dataset to generate a set of design parameters that match the target porous material. For example, the optimal pore diameter was determined to be 12.5 nanometers and the surface area was determined to be 200 square meters per gram, which served as the basis for subsequent modeling and optimization.

[0019] like Figure 1 、 3As shown, in step S102, a numerical simulation method is used to construct a microstructure model of the porous material based on the preliminary pore design parameters generated in step S101. Specifically, initial microstructure model data of the porous material is obtained through numerical simulation technology, and modeling is performed based on the preliminary pore design parameters to generate a preliminary structural model. For example, the initial pore size range is set to 2 nanometers to 10 nanometers, and a three-dimensional grid model is constructed using simulation software to simulate the random distribution of pores. Based on this, pore distribution characteristic data is extracted, including indicators such as the mean and standard deviation of the pore spacing, and analytical tools are used to quantitatively evaluate the uniformity and connectivity of the pore distribution. Assume that the evaluation results show that the mean value of the pore spacing is 5 nanometers, the standard deviation is 1.2 nanometers, and the connectivity ratio is 80%. The surface area value is calculated based on these distribution characteristic indicators and compared with a preset threshold. If the surface area value is lower than the preset threshold, for example, the calculated result is 300 square meters per gram and the preset threshold is 400 square meters per gram, the deviation of the current size parameter is recorded. A genetic algorithm is used to iteratively optimize the pore size parameters. Each iteration selects the top 20% of pores with the highest surface area values ​​for crossover mutation, gradually approaching the target value. For example, after multiple iterations, the pore size is adjusted to 6 nanometers, the 3D model is regenerated, and the pore distribution is observed to see if it becomes more uniform. If the surface area value remains below the preset threshold, the adjustment process is repeated until the target is met. Finally, the microstructure model is updated with the adjusted parameter data set, and the optimized structural model is rebuilt to obtain new pore distribution characteristic data.

[0020] like Figure 1 、 4As shown, in step S103, the optimized structural model data generated in step S102 is used to analyze the distribution of key elements and adjust element positions using a uniform distribution optimization algorithm to generate improved solution data. Specifically, initial key element distribution information is first obtained from the optimized structural model data and preliminarily processed based on the distribution characteristics within the pores to obtain a raw data set of element distribution. For example, suppose the distribution of a certain key element within the pores exhibits localized clustering, with the element density in the central region being 0.5 units per cubic millimeter and only 0.2 units at the edges. Statistical tools are used to quantify the distribution density and determine the locations of high-cluster areas. If the degree of clustering exceeds a preset threshold, for example, the density in the central region exceeds 0.4 units per cubic millimeter, the key element positions in that region are marked, and the element position data to be adjusted is extracted. The uniform distribution optimization algorithm is then used to redistribute the element position data in the marked regions, gradually migrating elements from high-density areas to low-density areas. For example, after adjustment, the density in the central region drops to 0.3 units and increases to 0.25 units at the edges, resulting in a more balanced overall distribution. Generate improved element distribution data based on the adjusted position distribution information and determine whether it meets the uniform distribution requirements. If not, return to the previous adjustment steps until the uniform distribution goal is achieved.

[0021] like Figure 1 、 5As shown, in step S104, according to the improved solution data generated in step S103, a virtual parameter configuration model of the porous material preparation process is constructed, and the optimal process parameter combination is determined through simulation testing. Specifically, the initial process conditions and parameter sets are first extracted from the improved solution data, such as the temperature is set to 800 degrees Celsius, the pressure is 2.5 atmospheres, and the raw material ratio is 3:1. A multi-round simulation method is used to generate operating data under different parameter combinations, such as the temperature is adjusted between 750 degrees Celsius and 850 degrees Celsius, and the pressure varies within the range of 2.0 to 3.0 atmospheres. 10 sets of data are generated in each round and the change in pore surface area is recorded. Assume that the first round of simulation results show that the surface area is 300 square meters per gram when the temperature is 800 degrees Celsius and the pressure is 2.5 atmospheres, and the surface area increases to 320 square meters per gram when the temperature rises to 820 degrees Celsius. For the simulation result data set, the trend of changes between process parameters and pore surface area was analyzed, and it was found that the surface area increased by an average of 5 square meters per gram for every 10 degrees Celsius increase in temperature, while the pressure change had little effect on the surface area. If there is a significant correlation pattern in the correlation data, the mapping relationship between process parameters and pore surface area is further quantified through regression analysis to determine the key influencing factors. For example, assuming that the regression model shows that the weight coefficient of temperature is higher, the temperature conditions are optimized first, and the temperature is fine-tuned from 800 degrees Celsius to 810 degrees Celsius to observe whether the surface area is closer to the target value of 400 square meters per gram. A new parameter combination data set is generated and the simulation test process is repeated until the deviation between the predicted surface area and the target value is less than the preset threshold, and the optimal process parameter combination is finally locked.

[0022] In step S105, real-time pore formation data from the preparation process is acquired using the optimal process parameter combination determined in step S104. Pore uniformity is then measured and the process parameters are adjusted through a feedback mechanism to obtain corrected parameter values. Specifically, a sensor system acquires real-time pore data from the preparation process, such as pore size and distribution density. Assuming the sensor collects data once per minute, the pore size is recorded and divided into multiple intervals ranging from 0.1 micron to 1.0 micron, and the pore fraction in each interval is calculated. The collected pore data is then preliminarily processed to obtain structured pore distribution information. Pore uniformity is analyzed using image processing techniques, such as using a high-resolution microscope to capture an image of the material surface, using an image segmentation algorithm to identify pore regions, and calculating a uniformity index. Assuming the uniformity index is set to 0.8, an actual value of 0.6 indicates uneven pore distribution. A pre-established feedback mechanism is used to evaluate the process parameters and determine the deviation range of the current parameters. For example, analysis reveals that high temperature leads to uneven pore distribution, with a deviation range of approximately 20 degrees Celsius. A support vector machine model is used to optimize process parameters and generate recommended values ​​for these adjustments. For example, the temperature can be adjusted to 480°C and the stirring speed can be increased from 300 to 350 rpm. These recommended values ​​are transmitted to the control system through a feedback mechanism, resulting in an updated process parameter configuration. Pore data from the preparation process is then collected again to determine whether the uniformity index has reached a preset threshold. If it remains below the threshold, the process parameters are adjusted again through a feedback loop until the uniformity index reaches or exceeds the preset value.

[0023] In step S106, dynamic control instructions for porous material preparation are generated based on the corrected parameter values ​​obtained in step S105. The element utilization rates during instruction execution are monitored in real time, utilization fluctuation data is collected, and a dynamic adjustment plan for element distribution is determined. Specifically, an initial dynamic control model is constructed by collecting parameter adjustment data during the preparation process, providing a preliminary basis for generating preparation instructions. For example, assuming a temperature fluctuation range of 200°C to 220°C, a pressure maintained between 1.5 and 2.0 atmospheres, and a flow rate of 10 liters per minute, these data are input into the model to generate preliminary preparation instructions. Based on the preparation instructions output by the dynamic control model, changes in element utilization rates are monitored in real time, and utilization fluctuation data is recorded. For example, assume that the utilization rate drops from 85% to 75% during a certain preparation period. Data recording reveals that the fluctuations are primarily concentrated in the raw material mixing stage. Based on the distribution of the utilization fluctuation data, data analysis methods are used to extract key indicators of the changing trend. For example, a 2% decrease in utilization rate per hour for more than 30 minutes is considered an abnormal trend. Further analysis may reveal that the primary influencing factor is uneven raw material distribution, providing guidance for strategic adjustments. If the key trend indicator exceeds a preset threshold, new control instructions are generated by adjusting the dynamic strategy for element distribution, such as changing the raw material feed ratio from 1:1 to 1:1.2. Based on the adjusted operating parameters, the dynamic control model is updated, and a support vector machine algorithm is used to predict element utilization and assess the stability of the predicted results. Ultimately, an element distribution adjustment plan is generated, resulting in optimized control instructions for porous material preparation.

[0024] In step S107, the surface area and element utilization test data of the porous material after preparation are obtained through the dynamic adjustment scheme generated in step S106, and a comprehensive analysis is performed on the test data. A data comparison method is used to determine whether the preset performance indicators are met, and the final performance verification result is obtained. Specifically, the preparation scheme of the porous material is dynamically adjusted by the automated system to obtain the initial surface area value and test data related to the element utilization rate. For example, assume that the initial surface area value is detected to be 800 square meters per gram and the element utilization rate data is 75%. The surface area value and element utilization rate data are pre-processed using a standardized processing method and mapped to a range of 0 to 1 to form a standardized first data set. For the first data set, a support vector machine algorithm is used to extract features from the surface area value and element utilization rate to determine a set of key performance features. For example, it is found that there is a positive correlation between the surface area value and the element utilization rate, and the utilization rate fluctuation is the smallest when the surface area value is in the range of 700 to 900 square meters per gram. By performing a comprehensive analysis on the set of key performance features, the correlation distribution between the features is obtained, and it is determined whether the feature distribution conforms to the preset distribution model. If the model matches the pre-set criteria, the feature set is compared against the pre-set criteria to generate a preliminary performance match. For example, if the preliminary match indicates a performance index that meets the 85% standard, a logistic regression algorithm is used to perform a secondary validation of the match. If the actual index is 80%, further adjustments are required. Ultimately, the porous material's performance verification results are generated, confirming whether the preparation solution meets the target requirements.

[0025] In summary, this invention optimizes the entire porous material preparation process, from acquiring microscopic pore distribution data to generating final performance verification results, by combining intelligent methods and data analysis techniques. This method significantly improves the material's surface area, pore uniformity, and key element utilization, resolving the issues of insufficient material performance and resource waste in traditional preparation processes. It provides reliable technical support for the application of porous materials in catalysis, environmental protection, and other fields.

Claims

1. A method for optimizing the preparation process of porous materials, characterized in that: The following steps are involved: Obtain microscopic pore distribution characteristic data and generate preliminary design parameters; Construct microstructure models and optimize pore size parameters; Analyze the distribution of key elements and adjust the element positions; Build virtual parameter configurations and determine the optimal process parameter combination through simulation testing; Real-time detection of pore uniformity and adjustment of process parameters through feedback mechanism; Generate dynamic control instructions and monitor element utilization; Comprehensively analyze test data and generate final performance verification results.

2. The method for optimizing the preparation process of porous materials according to claim 1, characterized in that: In the step of obtaining microscopic pore distribution characteristic data and generating preliminary design parameters, the support vector machine algorithm is used to analyze the corresponding relationship data between pore size and surface area values ​​to determine the key size and surface area matching pattern.

3. The method for optimizing the preparation process of porous materials according to claim 2, characterized in that: Abnormal data were removed through data cleaning tools to obtain the adjusted pore structure data set, and the pore characteristic parameters within the optimized range were extracted.

4. The method for optimizing the preparation process of porous materials according to claim 1, characterized in that: In the steps of constructing the microstructure model and optimizing the pore size parameters, a genetic algorithm is used to iteratively optimize the pore size parameters to generate an adjusted parameter data set.

5. The method for optimizing the preparation process of porous materials according to claim 4, characterized in that: The microstructure model is further updated according to the adjusted parameter data set, and the optimized structure model is reconstructed to obtain new pore distribution characteristic data.

6. The method for optimizing the preparation process of porous materials according to claim 1, characterized in that: In the step of analyzing the distribution of key elements and adjusting the element positions, a uniform distribution optimization algorithm is used to redistribute the element position data to be adjusted to generate improved element distribution scheme data.

7. The method for optimizing the preparation process of porous materials according to claim 6, characterized in that: Further determine whether the improved element distribution scheme data meets the uniform distribution requirements. If not, return to the adjustment step until the target is achieved.

8. The method for optimizing the preparation process of porous materials according to claim 1, characterized in that: In the steps of constructing virtual parameter configurations and determining the optimal process parameter combination through simulation testing, multiple rounds of simulation methods are used to generate operating data under different parameter combinations and analyze the changing trends between process parameters and pore surface area.

9. The method for optimizing the preparation process of porous materials according to claim 8, characterized in that: The mapping relationship between process parameters and pore surface area was further quantified by regression analysis method, key influencing factors were determined and a new parameter combination data set was generated.

Images