Performance requirement based composite formulation process optimization method

Abstract

The application provides a composite material formula process optimization method based on performance requirements, relates to the technical field of data processing, and comprises the following steps: acquiring matrix material information and performance requirements, determining missing performance requirements and their missing degrees; determining a reinforcing material configuration relationship list; configuring formula test variables; constructing a test space, obtaining a test data set, and analyzing and processing the test data set to construct a target data set; and optimizing the target data set to obtain a formula process optimization result. The application can solve the technical problem that, in the prior art, due to the lack of performance fusion analysis of reinforcing materials, the performance of composite materials is difficult to meet the demand performance, and the technical effect of improving the formula process accuracy of composite materials and then ensuring the adaptability of the performance of composite materials to the demand performance is achieved by optimizing and analyzing the formula processing technology of reinforcing materials after missing performance analysis of matrix materials.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method for optimizing composite material formulation processes based on performance requirements. Background Technology

[0002] With the development of industrial technology, composite materials are being used more and more widely in various fields. Performance optimization of composite materials is a key step in enhancing their application value, encompassing aspects such as strength optimization and thermal property optimization. The strength of composite materials can be effectively improved by increasing the volume content of reinforcing materials, optimizing the distribution and orientation of reinforcing materials, and performing surface treatments. However, to improve the performance of composite materials, one or more reinforcing materials are often added. The interaction between different materials can affect the properties of the composite material, leading to deviations in its performance.

[0003] Formulation of reinforcing materials is a crucial step in improving the performance of composite materials. However, traditional formulation optimization processes lack holistic analysis of the performance of reinforcing materials, resulting in composite materials failing to meet performance requirements. Summary of the Invention

[0004] The purpose of this application is to provide a method for optimizing the formulation and process of composite materials based on performance requirements, in order to solve the technical problem in the prior art where the performance of composite materials is difficult to meet the required performance due to the lack of performance integration analysis of reinforcing materials.

[0005] In view of the above problems, this application provides a method for optimizing composite material formulation processes based on performance requirements. The method includes: acquiring matrix material information and performance requirements; performing performance support decomposition based on the matrix material information and performance requirements to determine missing performance requirements and their degree of absence, wherein the missing performance requirement is the performance whose deviation value from the performance support is greater than a preset value, and the degree of absence is the ratio of the deviation value from the performance support to the performance requirement; performing reinforcing material matching analysis based on the missing performance requirements and their degree of absence to determine a list of reinforcing material configuration relationships; performing relationship matching analysis based on the missing performance requirements and their degree of absence and the list of reinforcing material configuration relationships to extract the fusion performance relationship between the matrix material information and the reinforcing materials, and configuring formulation test variables; acquiring processing parameters, configuring process test variables, constructing an experimental space based on the formulation test variables and the process test variables to obtain an experimental dataset, analyzing and processing the experimental dataset to construct a target dataset; setting constraints based on the performance requirements and processing technology, optimizing the target dataset, and obtaining the formulation process optimization result.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: The process involves acquiring matrix material information and performance requirements. Based on this information and these requirements, performance support is decomposed to identify missing performance requirements and their degree of absence. Missing performance requirements are defined as those where the deviation from the performance support exceeds a preset value, and the degree of absence is the ratio of this deviation to the performance requirement itself. Reinforcing material matching analysis is then performed based on these missing performance requirements and their degree of absence to determine a list of reinforcing material configuration relationships. Relationship matching analysis is then conducted using the missing performance requirements, their degree of absence, and the list of reinforcing material configuration relationships to extract the fusion performance relationship between the matrix material information and the reinforcing materials, and to configure formulation test variables. Processing parameters are acquired, and process test variables are configured. An experimental space is constructed based on these variables to obtain an experimental dataset. This dataset is then analyzed and processed to construct a target dataset. Finally, constraints are set based on the performance requirements and processing technology, and the target dataset is optimized to obtain the optimized formulation process. This process, by analyzing the missing performance of the matrix material and then optimizing the formulation and processing technology of the reinforcing materials, improves the accuracy of the composite material formulation process, thereby ensuring the compatibility of the composite material's performance with the required performance.

[0007] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0009] Figure 1 This is a flowchart illustrating the composite material formulation and process optimization method based on performance requirements proposed in this application. Detailed Implementation

[0010] This application addresses the technical problem in existing technologies where the performance of composite materials fails to meet required performance due to a lack of performance integration analysis of reinforcing materials. By providing a method for optimizing the formulation and processing of composite materials based on performance requirements, the method improves the accuracy of the composite material formulation and processing, thereby ensuring the compatibility of the composite material's performance with the required performance.

[0011] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0012] Please see the appendix Figure 1 This application provides a method for optimizing composite material formulation processes based on performance requirements, the method specifically including the following steps: Step 1: Obtain matrix material information and performance requirements. Based on the matrix material information and performance requirements, perform performance support decomposition to determine missing performance requirements and their missing degree. The missing performance requirement is the performance where the deviation between the performance requirement and the performance support is greater than a preset value. The missing degree is the ratio of the deviation between the performance requirement and the performance support to the performance requirement. Specifically, composite materials refer to materials composed of two or more different types of materials. The composition of composite materials typically includes a matrix material and reinforcing materials. The matrix material is the continuous phase in the composite material, used to maintain the overall structural shape and uniformly transfer loads to the reinforcing materials. It usually has good toughness and ductility, can absorb vibration and impact energy, and also protects the reinforcing materials from direct damage from the external environment; examples include polyethylene and polypropylene. The reinforcing material is the dispersed phase embedded in the matrix material. Its main function is to improve the mechanical, thermal, and electrical properties of the composite material; examples include carbon fiber, glass fiber, and aramid fiber.

[0013] Matrix material information refers to the composition, structure, and properties of the matrix materials used in the synthesis of composite materials. Performance requirements refer to the performance requirements of the composite material, such as hardness and toughness, which need to be determined based on actual conditions. Then, performance support is decomposed. Simply put, the performance of the matrix material in the matrix material information is compared with the performance requirements. If there is a significant deviation between any performance of the matrix material and the performance requirement, and these deviations exceed a preset threshold, then these performance requirements are considered missing. Performance support is the quantified value of any performance of the matrix material, and the missing value is the ratio of the deviation between the performance requirement and the performance support to the performance requirement itself. It reflects the degree of deficiency of the matrix material in a specific performance aspect. For example, if the composite material requires a tensile strength of 100 MPa, and the actual tensile strength of the matrix material is 90 MPa, the actual tensile strength is the performance support, the missing performance requirement is 10 MPa, and the missing value is 10%. This provides the missing performance requirements and their missing values, facilitating subsequent optimization of the reinforcing material formulation to ensure that the composite material's performance meets the performance requirements.

[0014] Step 2: Based on the missing performance requirements and their degree of absence, perform reinforcement material matching analysis to determine the list of reinforcement material configuration relationships; Specifically, based on the missing performance requirements and their degree of deficiency, reinforcing materials that can compensate for these deficiencies are selected. For example, if the tensile strength of the matrix material is insufficient, it is necessary to find fiber-reinforcing materials that can significantly improve the strength. First, a reinforcing material database is constructed by those skilled in the art based on existing technologies. This database contains different reinforcing materials and their corresponding reinforcing properties. For example, carbon fiber is typically used to improve strength and modulus, while glass fiber may be more suitable for improving heat resistance and corrosion resistance. Further, based on the missing performance requirements and their degree of deficiency, a comprehensive matching process is performed in the reinforcing material database to match reinforcing properties with the missing performance requirements and corresponding reinforcing materials. Then, based on the degree of deficiency and the degree of performance improvement achieved by a certain number of reinforcing materials, the addition ratio of reinforcing materials is obtained. A reinforcing material configuration relationship list is constructed using reinforcing materials, reinforcing properties, and addition ratios, providing a foundation for subsequent formulation optimization. It should be noted that one performance requirement in the missing performance can correspond to multiple reinforcing materials.

[0015] Step 3: Perform relationship matching analysis based on the missing performance requirements and their degree of absence, and the list of reinforcement material configuration relationships; fuse and extract the fusion performance relationship between the matrix material information and the reinforcement material; and configure the formula test variables. Specifically, the addition of reinforcing materials enhances the deficient properties of the matrix material, while potentially having positive or negative effects on other properties, such as increasing tensile strength while decreasing overall strength. Based on this, a relationship matching analysis is performed using the deficient performance requirements and their degree of deficiency, along with the list of reinforcing material configurations. This involves extracting the reinforcing material and its addition ratio corresponding to any deficient performance requirement and its degree of deficiency. Further analysis of the reinforcing material and its addition ratio is conducted to analyze the performance impact of the reinforcing material on the matrix material, yielding a fusion performance relationship. In other words, the fusion performance relationship includes the influence of the reinforcing material on the matrix material's performance. Based on this fusion performance relationship, the proportion of reinforcing materials is adjusted to ensure that the reinforcing material compensates for the deficient performance requirement without causing other properties to fail to meet the requirements. If a particular reinforcing material has a significant impact on other properties, multiple reinforcing materials used to improve the deficient performance requirement need to be used in combination. The types and proportions of these reinforcing materials then become the variables in the formulation experiment.

[0016] Step 4: Obtain processing parameters, configure process test variables, construct an experimental space based on the formula test variables and the process test variables, obtain an experimental dataset, analyze and process the experimental dataset, and construct a target dataset; Specifically, processing parameters refer to the processing parameters used in the synthesis of matrix and reinforcing materials, including but not limited to temperature, pressure, and time. Parameters that significantly affect the performance of the composite material, such as temperature and pressure, are selected as process test variables. Existing correlation analysis methods can be used to analyze the correlation between different parameters and the composite material's performance, identifying parameters with a correlation greater than a preset threshold as process test variables. A multi-dimensional experimental space is constructed using formulation test variables (type and proportion of reinforcing materials, etc.) and process test variables (temperature, pressure, time, etc.). Based on this constructed experimental space, historical data is extracted to construct an experimental dataset. Analyzing and processing this dataset involves performing mutation processing on data from different dimensions to obtain the target dataset, providing support for subsequent formulation and process optimization and ensuring optimization accuracy.

[0017] Step 5: Based on the performance requirements and processing technology, set constraints and optimize the target dataset to obtain the formulation and process optimization results.

[0018] Specifically, performance requirements include material strength, modulus, heat resistance, and corrosion resistance, while processing technology includes temperature, pressure, and time. Constraints refer to the range of parameters in the processing technology; that is, the processing technology may affect material properties, and it is necessary to ensure that the material properties meet performance requirements. The parameter range of the processing technology that meets the performance requirements is set as a constraint. Based on the constraints, the target dataset is screened to find the optimal formulation and process parameters that satisfy all constraints. That is, the formulation and process in the target dataset that satisfies all constraints and is closest to the required performance is selected as the formulation and process optimization result. The formulation and process optimization result includes the processing technology parameters and the parameters corresponding to the configured process experimental variables. This achieves formulation and process optimization of composite materials, ensuring that the composite material's performance meets performance requirements and improving the accuracy of composite material synthesis.

[0019] Furthermore, step three of this application also includes: Based on the missing performance requirements and their degree of absence, priorities are set according to the degree of absence, and the list of reinforcement material configuration relationships is traversed and matched according to priority to determine the matching relationship of the reinforcement materials; based on the fusion performance relationship between the matrix material information and the reinforcement materials, fusion adjustment coefficients are generated, including forward fusion adjustment and reverse fusion adjustment, and the matching relationship of the reinforcement materials is adjusted using the fusion adjustment coefficients; based on the performance indicators of the performance requirements, the matching relationship of the reinforcement materials is configured and extracted to obtain deviation performance indicators, which are used as variables for the formulation experiment.

[0020] Specifically, the process of configuring formulation test variables by performing relationship matching analysis based on the missing performance requirements and their degree of absence, the list of reinforcing material configuration relationships, and fusing and extracting the fusion performance relationship between the matrix material information and the reinforcing materials is as follows: Based on the missing performance requirements and their degree of absence, priorities are assigned according to the degree of absence, where the degree of absence is directly proportional to the priority. That is, the missing performance requirements are sorted from highest to lowest degree of absence, with the requirement with the highest degree of absence having the highest priority. Then, the reinforcement material configuration relationship list is traversed and matched according to priority. Specifically, the highest priority missing performance requirements are matched first, and then the reinforcement materials and their proportions are matched to the higher-priority missing performance requirements in the reinforcement material configuration relationship list. This is used as the matching relationship for the reinforcement materials.

[0021] Furthermore, based on the fusion performance relationship between the matrix material information and the reinforcing material, a fusion adjustment coefficient is generated. This fusion adjustment coefficient includes positive fusion adjustment and negative fusion adjustment. Positive fusion adjustment refers to the mutual influence between the matrix material information and the materials contained in the reinforcing material, affecting the performance of the composite material. Positive fusion adjustment means that different types of materials have the same direction of influence on performance; for example, both materials increase tensile strength. The superposition of the influence of different types of materials on performance can be used as the fusion adjustment coefficient. Negative fusion adjustment means that different types of materials have different directions of influence on the composite material; for example, one reinforcing material increases tensile strength while another decreases it. The influence of different types of materials on performance is offset according to their respective directions of influence, and this is used as the fusion adjustment coefficient.

[0022] Then, the matching relationship of the reinforcing materials is adjusted using the fusion adjustment coefficient. Specifically, the reinforcing performance in the matching relationship of the reinforcing materials is adjusted and optimized using the fusion adjustment coefficient. Further, the matching relationship of the reinforcing materials is configured and extracted according to the performance indicators of the performance requirements to obtain deviation performance indicators. Simply put, based on the matching relationship of the reinforcing materials, the performance indicators corresponding to the performance requirements after adding reinforcing materials are extracted according to the performance indicators of the performance requirements, such as tensile strength and toughness. Therefore, the performance indicators of the performance requirements are compared with the performance indicators corresponding to the performance requirements after adding reinforcing materials. If the performance indicators of the performance requirements are consistent with the performance indicators corresponding to the performance requirements after adding reinforcing materials, they are not used as variables in the formulation test. If they are inconsistent, that is, the performance requirements cannot be met after adding multiple reinforcing materials, then the corresponding reinforcing materials and proportions are used as variables in the formulation test. The formulation test variables can then be optimized to ensure that the performance of the composite material meets the requirements.

[0023] Furthermore, step four of this application also includes: Based on the formula test variables and the process test variables, a historical data set is obtained; the historical data set is traversed according to the performance indicators of the performance requirements to obtain the original data set; the range of missing variables and the prediction of variable inflection points are extracted based on the original data set; an experimental space is set according to the range of missing variables and the variable inflection points to conduct experiments and obtain an experimental data set.

[0024] Furthermore, this application also includes the following steps: Starting with the historical data dataset, and using the experimental data dataset as the direction of mutation, a mutation derivation is performed to obtain a mutated dataset; the fitness of the mutated dataset is evaluated, and mutated individuals that are superior to those in the original data dataset are selected to replace the original data dataset to obtain the target dataset.

[0025] Furthermore, this application also includes the following steps: Set a variable length, take the historical data dataset as the starting point and the experimental data dataset as the mutation direction to perform mutation to obtain a first mutated dataset, wherein the variable length is a positive number randomly selected from the difference between the minimum value of the variable in the historical data dataset and the minimum value of the variable in the experimental data dataset; obtain the cross-derivation rule, and perform same-position same-dimensional cross-mutation on the historical data dataset and the first mutated dataset according to the cross-derivation rule to obtain the mutated dataset.

[0026] Furthermore, this application also includes the following steps: The original dataset is selected from the historical data set according to the constraint strength of each performance indicator of the performance requirements. The performance derivation direction of the original dataset is determined, which is the direction of change that is positively related to the performance indicator. Based on the historical data set, the dimensions of the control variables are determined, and a dimension mapping matrix is ​​configured. The original dataset is projected onto the dimension mapping matrix, and the performance derivation direction is used as the constraint condition of the dimension variables. Based on the variable dimensions, a random number interval is determined, which is from 1 to the variable dimension. A random number function is used to generate a random update dimension index. According to the random update dimension index and the performance derivation direction, parameters with the same position and dimension are randomly selected from the mutated dataset for replacement.

[0027] Furthermore, this application also includes the following steps: The original record datasets are extracted according to the formula test variables and the process test variables to construct datasets for each test variable; the datasets for each test variable are orthogonally processed according to data size to obtain data distribution; missing intervals are filtered according to the data distribution to obtain the range of missing variables; a data distribution curve is fitted based on the data distribution, and inflection point prediction is performed based on the data distribution curve.

[0028] Specifically, the process of constructing the experimental space and obtaining the experimental dataset based on the formula experimental variables and the process experimental variables is as follows: Using the formulation test variables and process test variables as index elements, and based on existing internet big data, historical production data of composite materials corresponding to the formulation test variables and process test variables are retrieved to obtain a historical record dataset. The historical record dataset includes the historical variables corresponding to the formulation test variables and process test variables. The historical record dataset is then iterated through according to the performance indicators of the performance requirements, that is, the data corresponding to each performance indicator of the performance requirements is extracted as the original record dataset.

[0029] Furthermore, based on the original record dataset, the missing variable range and variable inflection point prediction are extracted as follows: The original record dataset is extracted according to the formulation experiment variable and the process experiment variable. This means extracting the data corresponding to each experiment variable from the original record dataset, which serves as the dataset for each experiment variable. The datasets for each experiment variable are then ordered by data size, that is, sorted in descending order. The sorting result is used as the data distribution for each experiment variable. Missing intervals are then filtered according to the data distribution, that is, intervals with no data distribution are extracted as the missing variable range. Simply put, after ordering the datasets for each experiment variable by data size, the data for each experiment variable is missing in some intervals. For example, if the dataset corresponding to a certain experiment variable contains data from 1 to 30, after sorting, it is found that there is no data distribution in the range of 10 to 15. This range is the missing variable range.

[0030] Further, curves are plotted based on the data distribution to obtain a fitted data distribution curve. The fitted data distribution curve can represent the changing trend of the dataset of each experimental variable. Inflection points are then predicted based on the data distribution curve. Inflection points usually refer to local maxima or minima of the data distribution curve, or points where the slope of the curve changes significantly. Inflection point identification is performed in this way to obtain local maxima or minima of the data distribution curve, or points where the slope of the curve changes significantly, as variable inflection points, providing a foundation for the subsequent construction of experimental datasets.

[0031] Then, based on the range of missing variables and the inflection points of the variables, an experimental space is set up for testing. This involves selecting the endpoints and intermediate values ​​of the range of missing variables, as well as the variable values ​​corresponding to the inflection points, as the experimental space to conduct composite material synthesis experiments. The variable parameters corresponding to the formulation test variables and the process test variables, as well as the properties of the composite materials, are recorded during the experiments. This data serves as the experimental dataset, facilitating subsequent data variation analysis, providing data support for formulation and process optimization, and helping to select better process parameters.

[0032] The process of analyzing and processing the experimental dataset to construct the target dataset is as follows: First, starting with the historical data dataset and using the experimental data dataset as the mutation direction, mutation derivation is performed to obtain the mutated dataset. The specific process is as follows: A variable asynchronous length is set, which refers to the step size for updating parameters in the historical data dataset. This variable asynchronous length is a positive number randomly selected from the difference between the minimum value of the variable in the historical data dataset and the minimum value of the variable in the experimental data dataset. Starting with the historical data dataset and using the experimental data dataset as the mutation direction, mutation is performed. That is, the historical data dataset is updated according to the variable asynchronous length based on the data change direction in the experimental data dataset. The update result of the historical data dataset is used as the first mutated dataset.

[0033] Furthermore, the cross-derivative rules are obtained as follows: First, based on performance requirements, data that meets the limits of each performance indicator is selected from the historical dataset. For example, if performance requirements include tensile strength and heat resistance, the performance indicator limits represent the range of constraints on these performance thresholds. Only data that meets these limits is selected as the original dataset. The selected original dataset is then analyzed to determine performance derivation directions. Performance derivation directions refer to changes that are positively correlated with the performance indicator; that is, performance improves as the direction changes. This can be achieved through existing statistical and regression analyses. Based on the historical dataset, variables affecting performance are identified. These variables are parameters that can be adjusted to influence performance, such as the composition of the reinforcing material, processing temperature, and pressure. Each parameter is treated as a control variable dimension. A dimension mapping matrix is ​​constructed according to these control variable dimensions. Each row in the dimension mapping matrix represents a parameter corresponding to a dimension, and each column represents a control variable dimension.

[0034] The filtered original dataset is projected onto a dimension mapping matrix. Each row of the dimension mapping matrix represents parameters belonging to the same control variable dimension in the original dataset, and each column represents the control variable dimension. Using the performance derivation direction as a constraint, a random number interval is defined, typically from 1 to the control variable dimension. This interval is used to generate random update dimension indices. A random number function, such as a pseudo-random number generator, is used to generate a random number within the random number interval as the random update dimension indices. Based on the randomly generated update dimension indices and the performance derivation direction, parameter values ​​belonging to the same location and the same control variable dimension are randomly selected from the mutated dataset for replacement. This process enables the discovery of location-based formulation processes, improving the comprehensiveness of optimization and ensuring the suitability of the formulation process for the required performance of the composite material.

[0035] The historical data dataset and the first mutated dataset are subjected to same-position, same-dimensional cross mutation according to the cross-derivation rules to obtain the mutated dataset.

[0036] Finally, according to the cross-derivation rules, the historical data set and the first variant dataset are subjected to same-position, same-dimensional cross-mutation. That is, parameter values ​​belonging to the same position and the same control variable dimension as those in the historical data set are randomly selected from the first variant dataset and used to replace data in the historical data set, resulting in the variant dataset. Further, the variant dataset is evaluated for fitness. This involves obtaining the performance metrics corresponding to the required performance from the variant dataset, and selecting variant individuals with performance metrics superior to those in the original data set to replace the original data set. Each variant individual contains parameters corresponding to multiple control variable dimensions. Using these variant individuals as the target dataset helps find a better parameter combination in the control variable dimensions to improve the performance of the composite material and ensure its suitability for performance requirements.

[0037] Furthermore, step five of this application also includes: An abnormal case set is collected, and the abnormal case set is clustered according to performance anomalies to obtain a multi-performance anomaly cluster; parameter probability and anomaly relationship fitting are performed on the multi-performance anomaly cluster to obtain abnormal parameter information; environmental parameters and equipment control parameters are extracted from the processing technology to obtain process constraint parameters and constraint range; correlation analysis is performed between the abnormal parameter information and the process constraint parameters and constraint range to obtain the constraint conditions.

[0038] Specifically, in the process of setting constraints based on the performance requirements and processing technology, and optimizing the target dataset to obtain the formulation and process optimization results, the method for obtaining the constraints is as follows: First, it is necessary to collect cases of performance anomalies during the processing, including scrap, rework, or non-conforming products reported by customers. The anomaly case set includes the abnormal performance and the corresponding process parameters. Existing statistical or machine learning methods, such as K-means clustering, hierarchical clustering, and DBSCAN, are used to perform cluster analysis on the anomaly case set, grouping similar anomaly cases into one category to form multi-performance anomaly clusters.

[0039] Each performance anomaly cluster is analyzed in depth, fitting parameter probabilities and anomaly relationships. Parameter probabilities refer to the distribution probability of process parameters in the anomaly case set, which can be obtained through existing statistical learning or machine learning methods. Anomaly relationships refer to the mutual influence between parameters, which can be obtained through existing correlation analysis methods. Parameters with higher probabilities and those that affect other parameters are selected as anomaly parameter information. Further, the processing technology is analyzed to identify environmental parameters (such as temperature, humidity, and air pressure) and equipment control parameters (such as speed, pressure, and power) that directly affect the composite material performance, serving as process constraint parameters. Simultaneously, experts in the field determine the constraint ranges for these parameters based on historical experience; that is, the minimum and maximum values ​​they should maintain under normal production conditions, which are then used as constraint ranges. Correlation analysis is performed between the anomaly parameter information and the process constraint parameters and constraint ranges, which can be accomplished using existing data mining techniques, such as association rule learning and mutual information calculation. This identifies which parameter anomalies are related to violations of process constraint parameters and constraint ranges, obtaining the violated process constraint parameters and constraint ranges as the constraint conditions. Subsequently, formulation and process optimization are performed within the constraint conditions to reduce the anomaly risk after composite material production and ensure the performance of the composite material matches the required performance.

[0040] In summary, the composite material formulation and process optimization method based on performance requirements provided in this application has the following technical effects: The process involves acquiring matrix material information and performance requirements. Based on this information and these requirements, performance support is decomposed to identify missing performance requirements and their degree of absence. Missing performance requirements are defined as those where the deviation between the performance requirement and the performance support exceeds a preset value. The degree of absence is the ratio of the deviation to the required performance. Reinforcing material matching analysis is performed based on these missing performance requirements and their degree of absence to determine a list of reinforcing material configuration relationships. Relationship matching analysis is then performed based on the missing performance requirements, their degree of absence, and the list of reinforcing material configuration relationships. The fusion performance relationship between the matrix material information and the reinforcing materials is extracted, and formulation test variables are configured. Processing parameters are acquired, and process test variables are configured. An experimental space is constructed based on these variables to obtain an experimental dataset. This dataset is then analyzed and processed to construct a target dataset. Constraints are set based on the performance requirements and processing technology. The target dataset is then optimized to obtain optimized formulation process results. Therefore, by analyzing the missing performance of the matrix material and optimizing the formulation and processing technology of the reinforcing materials, the accuracy of the composite material formulation process is improved, thereby ensuring the compatibility of the composite material's performance with the required performance.

[0041] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0042] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for optimizing composite material formulations and processes based on performance requirements, characterized in that, include: Obtain matrix material information and performance requirements, and perform performance support decomposition based on the matrix material information and performance requirements to determine missing performance requirements and their missing degree. The missing performance requirement is the performance whose deviation value between the performance requirement and the performance support is greater than a preset value, and the missing degree is the ratio of the deviation value between the performance requirement and the performance support to the performance requirement. Based on the missing performance requirements and their degree of absence, a reinforcement material matching analysis is performed to determine a list of reinforcement material configuration relationships. Based on the missing performance requirements and their degree of absence, and the list of reinforcement material configuration relationships, a relationship matching analysis is performed to fuse and extract the fusion performance relationship between the matrix material information and the reinforcement material, and to configure the formulation test variables. Obtain processing parameters, configure process test variables, construct an experimental space based on the formula test variables and the process test variables, obtain an experimental dataset, analyze and process the experimental dataset, and construct a target dataset; Based on the performance requirements and processing technology constraints, the target dataset is optimized to obtain the formulation and process optimization results. The step of analyzing and processing the experimental dataset to construct the target dataset includes: Starting with the historical data dataset and using the experimental data dataset as the direction of mutation, we derive mutations to obtain a mutated dataset. The fitness of the mutated dataset is evaluated, and mutated individuals that are superior to those in the original record dataset are selected to replace the original record dataset to obtain the target dataset. Starting with the historical data dataset and using the experimental record dataset as the direction of mutation, a mutation derivation is performed to obtain a mutated dataset, including: Set the variable length, take the historical data dataset as the starting point and the experimental data dataset as the mutation direction to perform mutation to obtain the first mutated dataset, wherein the variable length is a positive number randomly selected from the difference between the minimum value of the variable in the historical data dataset and the minimum value of the variable in the experimental data dataset; Obtain the cross-derivation rules, and perform co-position and same-dimensional cross-mutation between the historical data dataset and the first mutated dataset according to the cross-derivation rules to obtain the mutated dataset; The acquisition of cross-derivative rules includes: The original dataset is selected from the historical data set according to the constraint strength of each performance indicator of the performance requirements, and the performance derivation direction is determined for the original dataset. The performance derivation direction is the direction of change that is positively related to the performance indicator. Based on the historical data dataset, determine the dimensions of the control variables and configure the dimension mapping matrix; The original dataset is projected onto the dimension mapping matrix, and the performance-derived direction is used as a constraint condition for the dimension variable. Based on the variable dimension, a random number interval is determined, which is from 1 to the variable dimension. A random number function is used to generate a random update dimension index. According to the random update dimension index and the performance derivation direction, parameters with the same position and dimension are randomly selected from the mutation dataset for replacement.

2. The method as described in claim 1, characterized in that, Based on the missing performance requirements and their degree of absence, and the list of reinforcement material configuration relationships, a relationship matching analysis is performed to fuse and extract the fusion performance relationship between the matrix material information and the reinforcement material, and to configure formulation test variables, including: Based on the missing performance requirements and their degree of absence, priority is set according to the degree of absence, and the list of reinforcement material configuration relationships is traversed and matched according to the priority to determine the matching relationship of reinforcement materials. Based on the relationship between the matrix material information and the fusion performance of the reinforcing material, a fusion adjustment coefficient is generated. The fusion adjustment coefficient includes positive fusion adjustment and negative fusion adjustment. The matching relationship of the reinforcing material is adjusted using the fusion adjustment coefficient. The matching relationship of the reinforcing material is configured and extracted based on the performance indicators of the performance requirements to obtain the deviation performance index, which is used as the variable for the formulation test.

3. The method as described in claim 2, characterized in that, An experimental space is constructed based on the formula experimental variables and the process experimental variables to obtain an experimental dataset, including: Based on the formula test variables and the process test variables, obtain the historical data set; The historical data dataset is traversed according to the performance metrics of the performance requirements to obtain the original data dataset; Based on the original record dataset, extract the range of missing variables and predict variable inflection points; Based on the range of the missing variables and the inflection points of the variables, an experimental space is set up to conduct experiments and obtain an experimental dataset.

4. The method as described in claim 3, characterized in that, Based on the original record dataset, extract the range of missing variables and predict variable inflection points, including: The original record datasets were extracted according to the formula test variables and the process test variables to construct datasets for each test variable; The datasets of each experimental variable are orthogonally ordered according to data size to obtain the data distribution. Missing intervals are then filtered according to the data distribution to obtain the range of the missing variables. A data distribution curve is fitted based on the data distribution, and inflection point prediction is performed based on the data distribution curve.

5. The method as described in claim 1, characterized in that, Based on the performance requirements and processing technology constraints, the target dataset is optimized to obtain the formulation and process optimization results, including: Collect an abnormal case set, and cluster the abnormal case set according to performance anomalies to obtain multiple performance anomaly clusters; The abnormal parameter information is obtained by fitting the parameter probabilities and abnormal relationships to the multi-performance abnormal cluster. Environmental parameters and equipment control parameters are extracted from the processing technology to obtain process constraint parameters and constraint ranges. The constraint conditions are obtained by performing correlation analysis between the abnormal parameter information and the process constraint parameters and constraint range.

Images