Carbon fiber composite material performance auxiliary prediction method based on multiple scales

Abstract

The invention relates to the technical field of material performance auxiliary prediction, and discloses a carbon fiber composite material performance auxiliary prediction method based on multiple scales, and the method comprises the steps: obtaining the multi-scale features of a carbon fiber composite material; performing correlation analysis on the multi-scale features and performance indexes of the carbon fiber composite material to obtain related features in the multi-scale features, the performance indexes including a target performance index and a non-target performance index; generating constraint conditions of the performance indexes according to application scene requirements of the carbon fiber composite material; generating a target function of the performance of the carbon fiber composite material according to the target performance index, the non-target performance index and a preset self-adaptive penalty function; according to the method, the practicability and reliability of performance prediction of the carbon fiber composite material are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of material performance auxiliary prediction, and in particular to a multi-scale carbon fiber composite material performance auxiliary prediction method. Background Art

[0002] As a multiphase composite material, carbon fiber composite materials are composed of carbon fiber and matrix materials (such as resin matrix). Their internal structure is highly complex at different scales. Ordinary carbon fiber composite material performance auxiliary prediction methods often only focus on the macroscopic characteristics of the material and approximate the composite material as a uniform continuum. Multi-scale performance auxiliary prediction methods can help engineers accurately predict the performance of materials in the material design stage, thereby optimizing the composition and structure of materials according to specific engineering requirements. By adjusting the fiber layup, selecting appropriate fiber and matrix materials, and optimizing the manufacturing process, carbon fiber composite materials with better performance and lower cost can be designed to improve the comprehensive performance and cost performance of the material.

[0003] Before predicting the performance of carbon fiber composite materials, it is necessary to optimize the proportion of key components of carbon fiber composite materials. In the process of optimizing the proportion of key components of carbon fiber composite materials, a universal optimization target is often constructed; and in the optimization algorithm of carbon fiber composite material performance, the conventional practice is to establish an objective function. In this process, various performance indicators are comprehensively optimized with fixed weights, which leads to the following defects in the auxiliary prediction of the performance of carbon fiber composite materials:

[0004] 1. The existence of universal optimization goals makes the prediction results disconnected from the actual application scenarios. The universal optimization goals lack customized considerations for specific industry application scenarios and cannot accurately reflect the performance of carbon fiber composite materials in specific industries under actual working conditions. In addition, universal goals may cause the model to rely too much on general data sets, while ignoring industry-specific experimental data or working conditions, further weakening the practicality and reliability of the prediction method for the performance of carbon fiber composite materials.

[0005] 2. Fixed weights are used to coordinately optimize various performance indicators. This strategy lacks in-depth consideration of the characteristics of different application scenarios. The fixed weight optimization method cannot dynamically adjust the optimization direction according to the needs of specific scenarios. This static optimization strategy is difficult to adapt to multi-objective conflicts under complex working conditions. For example, the pursuit of high strength may sacrifice the toughness or processing performance of the material. This optimization method restricts the application value of the prediction method of carbon fiber composite material performance in actual industry. Summary of the invention

[0006] The present invention provides a multi-scale carbon fiber composite material performance auxiliary prediction method, whose main purpose is to solve the problem that in the prior art, in the process of optimizing the performance of carbon fiber composite materials, a universal optimization target is usually constructed, and the universal optimization target lacks customized considerations for specific industry application scenarios, thereby weakening the practicability and reliability of carbon fiber composite material performance prediction.

[0007] To achieve the above object, the present invention provides a multi-scale carbon fiber composite material performance auxiliary prediction method, comprising:

[0008] S1: Obtaining multi-scale characteristics of carbon fiber composites;

[0009] S2: performing a correlation analysis on the multi-scale features and the performance indicators of the carbon fiber composite material to obtain relevant features in the multi-scale features, wherein the performance indicators include: target performance indicators and non-target performance indicators;

[0010] S3: generating constraint conditions of the performance index according to the application scenario requirements of the carbon fiber composite material;

[0011] S4: generating a target function of the carbon fiber composite material performance according to the target performance index, the non-target performance index and a preset adaptive penalty function;

[0012] S5: Under the constraint conditions, optimizing the parameter set of the objective function based on a gradient descent algorithm to obtain an approximate minimum value of the objective function, and determining an optimal parameter set according to the approximate minimum value of the objective function;

[0013] S6: determining an optimal performance prediction value of the carbon fiber composite material according to the optimal parameter set, and synthesizing the carbon fiber composite material according to the optimal parameter set.

[0014] Optionally, the obtaining of multi-scale characteristics of the carbon fiber composite material includes:

[0015] SS1: The carbon fiber composite material samples are prepared using different carbon fibers, different matrices, different fiber volume fractions and different laying methods;

[0016] SS2: Performing microscopic, mesoscopic and macroscopic structural analysis on the carbon fiber composite material sample to obtain the multi-scale characteristics of the carbon fiber composite material.

[0017] Optionally, the performing correlation analysis on the multi-scale features and the performance indicators of the carbon fiber composite material to obtain relevant features in the multi-scale features includes:

[0018] S21. Substitute the multi-scale feature and the performance index into the Pearson correlation coefficient formula to obtain the correlation coefficient of the multi-scale feature, wherein the Pearson correlation coefficient formula is as follows:

[0019]

[0020] in, Indicates The carbon fiber composite material samples Multi-scale features, Indicates The carbon fiber composite material samples The performance value of each performance indicator, represents the total number of carbon fiber composite material samples, and represent the average values ​​of the multi-scale characteristics and the performance indexes in all carbon fiber composite material samples, respectively, Indicates The carbon fiber composite material samples The correlation coefficient of multi-scale features;

[0021] S22. Determine the The carbon fiber composite material samples Whether the correlation coefficient of the multi-scale features is significant with the performance index, wherein the significance test formula is as follows:

[0022]

[0023] in, represents the total number of carbon fiber composite material samples, Indicates The carbon fiber composite material samples The correlation coefficient of the multi-scale features is Indicates The carbon fiber composite material samples Statistics of the multi-scale features;

[0024] S23, in In the distribution table, according to the degrees of freedom and The carbon fiber composite material samples The statistics of the multi-scale features are retrieved to obtain the corresponding Value, when If the value is less than the preset significance level, it is considered The carbon fiber composite material samples The multi-scale features and The carbon fiber composite material samples There is a significant correlation between the performance indicators and The carbon fiber composite material samples The multi-scale features are marked as the relevant features, where The value represents the probability of obtaining the current data result if the null hypothesis is true.

[0025] Optionally, the constraint condition is as follows:

[0026]

[0027] in, represents the index of the target performance indicator, represents the index of the non-target performance indicator, Indicates performance value of the target performance indicator, Indicates The superior value of the target performance indicator, Indicates performance value of the non-target performance indicator, Indicates The lower threshold of the non-target performance indicator, represents the relevant feature set corresponding to the target performance indicator, represents the relevant feature set corresponding to the non-target performance indicator, represents the set of related features, Indicates the total number of the performance indicators.

[0028] Optionally, the objective function is as follows:

[0029]

[0030] in, represents the index of the target performance indicator, represents the index of the non-target performance indicator, Indicates performance value of the target performance indicator, Indicates The superior value of the target performance indicator, Indicates performance value of the non-target performance indicator, Indicates The lower threshold of the non-target performance indicator, represents the relevant feature set corresponding to the target performance indicator, represents the relevant feature set corresponding to the non-target performance indicator, represents the set of related features, represents the total number of the performance indicators, represents the objective function, represents the adaptive penalty function, Indicates taking and The maximum of two numbers.

[0031] Optionally, the preset adaptive penalty function is as follows:

[0032]

[0033] in, represents the adaptive penalty function, represents the basic penalty factor, Represents the maximum amount of violation among all non-target performance indicators.

[0034] Optionally, the steps of constructing the adaptive penalty function are as follows:

[0035] Step 1: Calculate the difference between the performance value of all the non-target performance indicators and the lower limit threshold of the corresponding non-target performance indicators. , then it means If there is a default amount in the performance value of each of the non-target performance indicators, the maximum default amount among all the non-target performance indicators is determined according to the minimum value of all the differences, wherein the calculation formula of the maximum default amount is as follows:

[0036]

[0037] in, represents the index of the non-target performance indicator, Indicates performance value of the non-target performance indicator, Indicates The lower threshold of the non-target performance indicator, represents the adjustment parameter, represents the maximum amount of default among all non-target performance indicators;

[0038] Step 2: Construct an adaptive penalty function based on the maximum default amount and the basic penalty factor.

[0039] Optionally, the optimizing the parameter set of the objective function based on the gradient descent algorithm to obtain an approximate minimum value of the objective function includes:

[0040] The parameter set of the objective function is optimized by the update formula of the gradient descent algorithm, wherein the update formula is as follows:

[0041]

[0042] in, represents the set of related features, Indicates The parameter set for the iteration, Indicates The parameter set for the iteration, represents the learning rate, It means that the objective function is The gradient at

[0043] When the change in the objective function value is less than a preset threshold, an approximate minimum value of the objective function is obtained.

[0044] Optionally, the optimal parameter set is:

[0045]

[0046] in, represents the optimal parameter set, Indicated in The updated parameter set at the iteration, Represents a set of related features.

[0047] Optionally, determining the optimal performance prediction value of the carbon fiber composite material according to the optimal parameter set, and synthesizing the carbon fiber composite material according to the optimal parameter set includes:

[0048] The optimal performance prediction value of the carbon fiber composite material is calculated based on the material performance prediction algorithm and the optimal parameter set, wherein the material performance prediction algorithm is as follows:

[0049]

[0050] in, represents the optimal parameter set, represents the optimal performance prediction value, represents a material property prediction model;

[0051] The optimal material ratio of the carbon fiber composite material is determined according to the optimal parameter set, and the carbon fiber composite material is synthesized according to the optimal material ratio and manufacturing process.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] 1. Generate constraints for performance indicators based on the application scenario requirements of carbon fiber composite materials, distinguish between target performance indicators and non-target performance indicators, set superior values ​​for target performance indicators to ensure that they reach or exceed the expected level, and set lower limit thresholds for non-target performance indicators to meet the requirements for basic material performance in specific scenarios, improve the pertinence of carbon fiber composite material performance prediction results, enhance the adaptability and practicality of the prediction model, and provide strong support for the research and development and application of carbon fiber composite materials;

[0054] 2. By constructing an adaptive penalty function, the flexibility and efficiency of the multi-objective optimization process in the carbon fiber composite material performance auxiliary prediction method can be improved, and the adaptability of the carbon fiber composite material performance auxiliary prediction method to complex working conditions can be enhanced, so that it can better meet the diversified needs of different application scenarios, thereby improving the performance and reliability of carbon fiber composite materials in practical applications. The adaptive penalty function can dynamically adjust the penalty intensity according to the default of non-target performance indicators. When the non-target performance indicator does not reach the lower limit threshold, the value of the adaptive penalty function will increase significantly, increasing the constraint on the optimization process, prompting the optimization algorithm to give priority to adjusting the parameters of the objective function to reduce the degree of default; this dynamic adjustment capability not only improves the optimization efficiency, but also can better balance the conflict problems in multi-objective optimization;

[0055] 3. Under the constraints, the parameter set of the objective function is optimized based on the gradient descent algorithm, which can improve the efficiency and accuracy of the multi-objective optimization process. The parameters are adjusted according to the change of the objective function value. When the objective function value change is less than the preset threshold, the approximate minimum value is obtained and the optimal parameter set is determined. In the optimization process, the adaptive penalty function makes the gradient of the objective function change dynamically with the degree of default of the non-objective performance index, so that the gradient descent algorithm is more inclined to adjust the parameters of the objective function to improve the degree of default, and realize the dynamic adaptation of the optimization direction. This optimization strategy provides more scientific and reliable guidance for the design and process improvement of carbon fiber composite materials, and improves the performance and applicability of materials in practical applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A schematic diagram of a flow chart of a multi-scale carbon fiber composite material performance auxiliary prediction method provided by an embodiment of the present invention;

[0057] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0058] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0059] The embodiment of the present application provides a multi-scale carbon fiber composite material performance auxiliary prediction method. The execution subject of the multi-scale carbon fiber composite material performance auxiliary prediction method includes but is not limited to at least one of the electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided in the embodiment of the present application. In other words, the multi-scale carbon fiber composite material performance auxiliary prediction method can be executed by software or hardware installed on a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

[0060] Reference Figure 1 FIG. 1 is a flow chart of a multi-scale carbon fiber composite material performance auxiliary prediction method provided by an embodiment of the present invention. In this embodiment, the multi-scale carbon fiber composite material performance auxiliary prediction method includes:

[0061] S1: Obtaining multi-scale characteristics of carbon fiber composites.

[0062] In an embodiment of the present invention, the step of obtaining multi-scale characteristics of the carbon fiber composite material includes:

[0063] SS1: The carbon fiber composite material samples are prepared using different carbon fibers, different matrices, different fiber volume fractions and different laying methods;

[0064] SS2: Performing microscopic, mesoscopic and macroscopic structural analysis on the carbon fiber composite material sample to obtain the multi-scale characteristics of the carbon fiber composite material.

[0065] In detail, the carbon fiber and its bonding interface with the matrix were observed by scanning electron microscopy to obtain the microscopic morphology of the carbon fiber composite material; the 3D structure inside the carbon fiber composite material was obtained by multiphoton microscopy, and the thermal stability and thermal behavior of the carbon fiber composite material were studied using differential scanning calorimetry (DSC) and thermogravimetric analyzer (TGA).

[0066] Among them, the multi-scale features represent information describing the internal structure of the carbon fiber composite material sample from different scales. The multi-scale features include micro-scale data (single fiber diameter, fiber surface roughness), meso-scale data (fiber volume fraction, fiber arrangement and directionality) and macro-scale data (overall laminate structure, overall geometric size and shape). Performance indicators such as rigidity, elasticity, toughness, fatigue life, etc. are obtained through tensile tests, impact tests, fatigue tests and other methods.

[0067] For example, the parameters of different carbon fiber composite samples are as follows:

[0068]

[0069] S2: performing a correlation analysis on the multi-scale features and performance indicators of the carbon fiber composite material to obtain relevant features in the multi-scale features, wherein the performance indicators include: target performance indicators and non-target performance indicators.

[0070] In an embodiment of the present invention, the performing correlation analysis on the multi-scale features and the performance indicators of the carbon fiber composite material to obtain the relevant features in the multi-scale features includes:

[0071] S21. Substitute the multi-scale feature and the performance index into the Pearson correlation coefficient formula to obtain the correlation coefficient of the multi-scale feature, wherein the Pearson correlation coefficient formula is as follows:

[0072]

[0073] in, Indicates The carbon fiber composite material samples Multi-scale features, Indicates The carbon fiber composite material samples The performance value of each performance indicator, represents the total number of carbon fiber composite material samples, and represent the average values ​​of the multi-scale characteristics and the performance indexes in all carbon fiber composite material samples, respectively, Indicates The carbon fiber composite material samples The correlation coefficient of multi-scale features;

[0074] Among them, the Pearson correlation coefficient formula is used to measure the linear correlation between two variables. The value range is [-1, 1]. The value 1 indicates a perfect positive correlation, -1 indicates a perfect negative correlation, and 0 indicates no correlation.

[0075] S22. Determine the The carbon fiber composite material samples Whether the correlation coefficient of the multi-scale features is significant with the performance index, wherein the significance test formula is as follows:

[0076]

[0077] in, represents the total number of carbon fiber composite material samples, Indicates The carbon fiber composite material samples The correlation coefficient of the multi-scale features is Indicates The carbon fiber composite material samples Statistics of the multi-scale features;

[0078] S23, in In the distribution table, according to the degrees of freedom and The carbon fiber composite material samples The statistics of the multi-scale features are retrieved to obtain the corresponding Value, when If the value is less than the preset significance level, it is considered The carbon fiber composite material samples The multi-scale features and The carbon fiber composite material samples There is a significant correlation between the performance indicators and The carbon fiber composite material samples The multi-scale features are marked as the relevant features, where The value represents the probability of obtaining the current data result when the null hypothesis is established, and the degrees of freedom represent the number of observation data points that can change independently when the multi-scale features are used to perform correlation analysis with the performance index.

[0079] S3: generating constraints of the performance index according to application scenario requirements of the carbon fiber composite material.

[0080] In the embodiment of the present invention, the constraint conditions are as follows:

[0081]

[0082] in, represents the index of the target performance indicator, represents the index of the non-target performance indicator, Indicates performance value of the target performance indicator, Indicates The superior value of the target performance indicator, Indicates performance value of the non-target performance indicator, Indicates The lower threshold of the non-target performance indicator, represents the relevant feature set corresponding to the target performance indicator, represents the relevant feature set corresponding to the non-target performance indicator, represents the set of related features, Indicates the total number of the performance indicators.

[0083] The superiority value represents the optimal performance value of the target performance indicator, which is used to ensure that the target performance indicator reaches or exceeds the desired target level.

[0084] S4: generating an objective function of the performance of the carbon fiber composite material according to the objective performance index, the non-objective performance index and a preset adaptive penalty function.

[0085] In this embodiment of the present invention, the objective function is as follows:

[0086]

[0087] in, represents the index of the target performance indicator, represents the index of the non-target performance indicator, Indicates performance value of the target performance indicator, Indicates The superior value of the target performance indicator, Indicates performance value of the non-target performance indicator, Indicates The lower threshold of the non-target performance indicator, represents the relevant feature set corresponding to the target performance indicator, represents the relevant feature set corresponding to the non-target performance indicator, represents the set of related features, represents the total number of the performance indicators, represents the objective function, represents the adaptive penalty function, Indicates taking and The maximum of two numbers.

[0088] exist middle, represents the optimization direction of the performance value of the target performance indicator, that is, As close to or as high as possible, while satisfying the constraints of non-target performance indicators, It is used to measure the degree to which non-target performance indicators are not met and impose constraints on the optimization process, that is, represents the penalty term, when Not reached , then punishment is imposed, when all When , the value of the penalty term is 0, and the objective function is only , when a Not reached , then the penalty term will increase The value of drives the optimization process to adjust parameters to reduce the degree of default.

[0089] In detail, the preset adaptive penalty function is as follows:

[0090]

[0091] in, represents the adaptive penalty function, represents the basic penalty factor, Represents the maximum amount of violation among all non-target performance indicators.

[0092] In detail, the steps of constructing the adaptive penalty function are as follows:

[0093] Step 1: Calculate the difference between the performance value of all the non-target performance indicators and the lower limit threshold of the corresponding non-target performance indicators. , then it means If there is a default amount in the performance value of each of the non-target performance indicators, the maximum default amount among all the non-target performance indicators is determined according to the minimum value of all the differences, wherein the calculation formula of the maximum default amount is as follows:

[0094]

[0095] in, represents the index of the non-target performance indicator, Indicates performance value of the non-target performance indicator, Indicates The lower threshold of the non-target performance indicator, represents the adjustment parameter, represents the maximum amount of default among all non-target performance indicators;

[0096] Step 2: Construct an adaptive penalty function based on the maximum default amount and the basic penalty factor.

[0097] When all All reached the corresponding ,Right now ,but ,therefore , which makes The value of is small; when at least one Not reached ,Right now ,but The value of increases significantly, which makes The value of increases.

[0098] S5: Under the constraint conditions, the parameter set of the objective function is optimized based on the gradient descent algorithm to obtain an approximate minimum value of the objective function, and the optimal parameter set is determined according to the approximate minimum value of the objective function.

[0099] In an embodiment of the present invention, the step of optimizing the parameter set of the objective function based on the gradient descent algorithm to obtain an approximate minimum value of the objective function includes:

[0100] The parameter set of the objective function is optimized by the update formula of the gradient descent algorithm, wherein the update formula is as follows:

[0101]

[0102] in, represents the set of related features, Indicates The parameter set for the iteration, Indicates The parameter set for the iteration, represents the learning rate, It means that the objective function is The gradient at .

[0103] in, The calculation formula is as follows:

[0104]

[0105] in, and Respectively and about , The gradient of express about The gradient of , Indicates when The value is 1 when it is, otherwise it is 0. Denotes the adaptive penalty function.

[0106] Among them, the penalty term is calculated about The formula for the gradient is as follows:

[0107]

[0108] in, Indicates about The gradient of express about The gradient of , represents the adaptive penalty function.

[0109] Among them, the adaptive penalty function is calculated with respect to The formula for the gradient is as follows:

[0110]

[0111] in, express about The gradient of Indicates performance value of the non-target performance indicator, Indicates The lower threshold of the non-target performance indicator, represents the basic penalty factor, Indicates the adjustment parameter.

[0112] When the change in the objective function value is less than a preset threshold, an approximate minimum value of the objective function is obtained.

[0113] In the objective function, when near hour, A smaller value indicates that the penalty term in the objective function is smaller and has a weaker effect on optimization. Much lower than hour, The value of increases significantly, resulting in a sharp increase in the value of the objective function. The gradient becomes larger during the optimization process, making the gradient descent algorithm more inclined to adjust the parameters of the objective function to improve the degree of default, and Not reached The penalty for the resulting difference increases dynamically with the degree of default.

[0114] Specifically, during the optimization process, if a non-target performance indicator The corresponding lower threshold is not reached , the difference between the two is large, the adaptive penalty function will increase significantly, thereby applying a greater correction force in the gradient descent process of the objective function, so that the optimization algorithm prioritizes adjusting the parameters of the objective function to reduce the above difference. This adaptive adjustment can avoid the problems of slow convergence or difficulty in meeting all constraints that may be encountered in traditional fixed penalty methods.

[0115] In detail, the optimal parameter set is:

[0116]

[0117] in, represents the optimal parameter set, Indicated in The updated parameter set at the iteration, Represents a set of related features.

[0118] S6: determining an optimal performance prediction value of the carbon fiber composite material according to the optimal parameter set, and synthesizing the carbon fiber composite material according to the optimal parameter set.

[0119] In an embodiment of the present invention, determining the optimal performance prediction value of the carbon fiber composite material according to the optimal parameter set, and synthesizing the carbon fiber composite material according to the optimal parameter set includes:

[0120] The optimal performance prediction value of the carbon fiber composite material is calculated based on the material performance prediction algorithm and the optimal parameter set, wherein the material performance prediction algorithm is as follows:

[0121]

[0122] in, represents the optimal parameter set, represents the optimal performance prediction value, represents a material property prediction model;

[0123] in, Describes the mapping relationship from the optimal parameter set to the optimal performance prediction value, The model can be built based on machine learning algorithms, which can learn the complex nonlinear relationship between parameters and performance from a large amount of experimental data by using machine learning algorithms such as neural networks and support vector machines. For example, a multi-layer perceptron (MLP) neural network is used, with the parameter set as the input layer and the performance prediction value as the output layer. The network is trained with training data to obtain a model that can accurately predict performance.

[0124] The optimal material ratio of the carbon fiber composite material is determined according to the optimal parameter set, and the carbon fiber composite material is synthesized according to the optimal material ratio and manufacturing process.

[0125] For example, setting the target performance indicator as rigid , the corresponding superiority value is set to 100, and the non-target performance is toughness , fatigue life Need to meet minimum requirements, toughness The lower threshold is 55, fatigue life The lower threshold is 65;

[0126] Initialization parameters: Rigidity ,toughness , fatigue life ;

[0127] Optimization objective function: basic penalty factor , adjustment parameters , learning rate = 0.1, maximum number of iterations = 50;

[0128] Calculate the maximum default amount: ;

[0129] Calculate the adaptive penalty function: ;

[0130] Optimized rigidity ,toughness , fatigue life , the specific steps are as follows:

[0131] Update target performance indicators:

[0132] Update non-target performance indicators:

[0133]

[0134]

[0135] Recalculate the maximum default amount: ;

[0136] Calculate the new adaptive penalty function: ;

[0137] Repeat to optimize rigidity ,toughness , fatigue life Steps, 50 iterations, after 50 iterations:

[0138] , , , , the target performance index (rigidity) is maximized, increasing from 80 to 100.2, and the non-target performance index (toughness, fatigue life) meets the minimum requirements. The adaptive penalty function is automatically adjusted during the optimization process to improve the optimization accuracy, and finally the optimal parameter set is determined, and the optimization goal is achieved.

[0139] In detail, according to the optimal parameter set, the key component ratios of the corresponding carbon fiber composite materials are first analyzed, including carbon fiber type (such as high modulus carbon fiber, high strength carbon fiber), matrix material (such as epoxy resin, polyamide, phenolic resin), fiber volume fraction (such as 30%, 50%, 70%) and layup method (unidirectional layup, cross layup, random layup), etc., and the physical, chemical and mechanical properties of the material are comprehensively considered to determine the optimal material ratio that meets the target performance index requirements; after obtaining the optimal material ratio, combined with manufacturing process parameters (such as prepreg preparation, hot pressing curing, vacuum assisted resin transfer molding (VARTM), automatic layup process, etc.), optimize process parameters such as temperature, pressure, curing time, and layup sequence to ensure that the final synthesized carbon fiber composite material achieves the expected effect in the target application scenario. At the same time, using material simulation and experimental verification, the manufactured carbon fiber composite material is subjected to performance tests, such as tensile test, impact test, fatigue test, etc., to further adjust and optimize the ratio and process to ensure the reliability, stability and manufacturability of the final synthesized material, so as to meet specific engineering needs.

[0140] It should be noted that steps S1-S5 are auxiliary processes for determining the optimal performance prediction value of the carbon fiber composite material.

[0141] In several embodiments provided by the present invention, it should be understood that the disclosed method can be implemented in other ways.

[0142] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0143] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method and technology of using digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0144] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A multi-scale carbon fiber composite material performance auxiliary prediction method, characterized in that: The method comprises: S1: Obtaining multi-scale characteristics of carbon fiber composites; S2: performing a correlation analysis on the multi-scale features and the performance indicators of the carbon fiber composite material to obtain relevant features in the multi-scale features, wherein the performance indicators include: target performance indicators and non-target performance indicators; S3: generating constraint conditions of the performance index according to the application scenario requirements of the carbon fiber composite material; S4: generating a target function of the carbon fiber composite material performance according to the target performance index, the non-target performance index and a preset adaptive penalty function; S5: Under the constraint conditions, optimizing the parameter set of the objective function based on a gradient descent algorithm to obtain an approximate minimum value of the objective function, and determining an optimal parameter set according to the approximate minimum value of the objective function; S6: determining an optimal performance prediction value of the carbon fiber composite material according to the optimal parameter set, and synthesizing the carbon fiber composite material according to the optimal parameter set.

2. The multi-scale carbon fiber composite material performance auxiliary prediction method according to claim 1, characterized in that: The method of obtaining multi-scale characteristics of the carbon fiber composite material comprises: SS1: The carbon fiber composite material samples are prepared using different carbon fibers, different matrices, different fiber volume fractions and different laying methods; SS2: Performing microscopic, mesoscopic and macroscopic structural analysis on the carbon fiber composite material sample to obtain the multi-scale characteristics of the carbon fiber composite material.

3. The multi-scale carbon fiber composite material performance auxiliary prediction method according to claim 1, characterized in that: The performing correlation analysis on the multi-scale features and the performance indicators of the carbon fiber composite material to obtain relevant features in the multi-scale features includes: S21. Substitute the multi-scale feature and the performance index into the Pearson correlation coefficient formula to obtain the correlation coefficient of the multi-scale feature, wherein the Pearson correlation coefficient formula is as follows: in, Indicates The carbon fiber composite material samples Multi-scale features, Indicates The carbon fiber composite material samples The performance value of each performance indicator, represents the total number of carbon fiber composite material samples, and represent the average values ​​of the multi-scale characteristics and the performance indexes in all carbon fiber composite material samples, respectively, Indicates The carbon fiber composite material samples The correlation coefficient of multi-scale features; S22. Determine the The carbon fiber composite material samples Whether the correlation coefficient of the multi-scale features is significant with the performance index, wherein the significance test formula is as follows: in, represents the total number of carbon fiber composite material samples, Indicates The carbon fiber composite material samples The correlation coefficient of the multi-scale features is Indicates The carbon fiber composite material samples A statistic of the multi-scale features; S23, in In the distribution table, according to the degrees of freedom and The carbon fiber composite material samples The statistics of the multi-scale features are retrieved to obtain the corresponding Value, when If the value is less than the preset significance level, it is considered The carbon fiber composite material samples The multi-scale features and The carbon fiber composite material samples There is a significant correlation between the performance indicators and The carbon fiber composite material samples The multi-scale features are marked as the relevant features, where The value represents the probability of obtaining the current data result if the null hypothesis is true.

4. The multi-scale carbon fiber composite material performance auxiliary prediction method according to claim 1, characterized in that: The constraints are as follows: in, represents the index of the target performance indicator, represents the index of the non-target performance indicator, Indicates performance value of the target performance indicator, Indicates The superior value of the target performance indicator, Indicates performance value of the non-target performance indicator, Indicates The lower threshold of the non-target performance indicator, represents the relevant feature set corresponding to the target performance indicator, represents the relevant feature set corresponding to the non-target performance indicator, represents the set of related features, Indicates the total number of the performance indicators.

5. The multi-scale carbon fiber composite material performance auxiliary prediction method according to claim 1, characterized in that: The objective function is as follows: in, represents the index of the target performance indicator, represents the index of the non-target performance indicator, Indicates performance value of the target performance indicator, Indicates The superior value of the target performance indicator, Indicates performance value of the non-target performance indicator, Indicates The lower threshold of the non-target performance indicator, represents the relevant feature set corresponding to the target performance indicator, represents the relevant feature set corresponding to the non-target performance indicator, represents the set of related features, represents the total number of the performance indicators, represents the objective function, represents the adaptive penalty function, Indicates taking and The maximum of two numbers.

6. The multi-scale carbon fiber composite material performance auxiliary prediction method according to claim 1, characterized in that: The preset adaptive penalty function is as follows: in, represents the adaptive penalty function, represents the basic penalty factor, Represents the maximum amount of violation among all non-target performance indicators.

7. The multi-scale carbon fiber composite material performance auxiliary prediction method according to claim 6, characterized in that: The steps for constructing the adaptive penalty function are as follows: Step 1: Calculate the difference between the performance value of all the non-target performance indicators and the lower limit threshold of the corresponding non-target performance indicators. , then it means If there is a default amount in the performance value of each of the non-target performance indicators, the maximum default amount among all the non-target performance indicators is determined according to the minimum value of all the differences, wherein the calculation formula of the maximum default amount is as follows: in, represents the index of the non-target performance indicator, Indicates performance value of the non-target performance indicator, Indicates The lower threshold of the non-target performance indicator, represents the adjustment parameter, represents the maximum amount of default among all non-target performance indicators; Step 2: Construct an adaptive penalty function based on the maximum default amount and the basic penalty factor.

8. The multi-scale carbon fiber composite material performance auxiliary prediction method according to claim 1, characterized in that: The step of optimizing the parameter set of the objective function based on the gradient descent algorithm to obtain an approximate minimum value of the objective function includes: The parameter set of the objective function is optimized by the update formula of the gradient descent algorithm, wherein the update formula is as follows: in, represents the set of related features, Indicates The parameter set for the iteration, Indicates The parameter set for the iteration, represents the learning rate, It means that the objective function is The gradient at When the change in the objective function value is less than a preset threshold, an approximate minimum value of the objective function is obtained.

9. The multi-scale carbon fiber composite material performance auxiliary prediction method according to claim 1, characterized in that: The optimal parameter set is: in, represents the optimal parameter set, Indicated in The updated parameter set at the iteration, Represents a set of related features.

10. The multi-scale carbon fiber composite material performance auxiliary prediction method according to claim 1, characterized in that: Determining the optimal performance prediction value of the carbon fiber composite material according to the optimal parameter set, and synthesizing the carbon fiber composite material according to the optimal parameter set includes: The optimal performance prediction value of the carbon fiber composite material is calculated based on the material performance prediction algorithm and the optimal parameter set, wherein the material performance prediction algorithm is as follows: in, represents the optimal parameter set, represents the optimal performance prediction value, represents a material property prediction model; The optimal material ratio of the carbon fiber composite material is determined according to the optimal parameter set, and the carbon fiber composite material is synthesized according to the optimal material ratio and manufacturing process.

Images