A method and device for heating and curing carbon fiber composite material

Abstract

The present application provides a method and device for heating and curing carbon fiber composite materials, which relates to the technical field of carbon fiber composite material processing, including: randomly generating a first curing parameter, performing bubble simulation generation and resin loss simulation generation for multiple heating and curing, generating a first bubble map and a first resin loss map; performing bubble and resin loss scale analysis to obtain bubble and resin loss scale information, and performing bubble and resin loss credibility analysis to obtain bubble and resin loss credibility, and calculating and obtaining a first curing fitness; and continuing to optimize the curing parameters according to the first curing fitness to obtain the optimal curing parameters. The present application can solve the technical problem that the material bubble generation and resin loss cannot be effectively controlled due to the lack of accuracy and adaptability of the curing parameter setting in the existing heating and curing process, and can effectively reduce the material bubble generation and resin loss during the curing process, and significantly improve the material curing quality.

Description

Technical Field

[0001] The present application relates to the technical field of carbon fiber composite material processing, and in particular to a heating and curing method and device for carbon fiber composite material. Background Art

[0002] Carbon fiber composite materials are widely used in high-end manufacturing fields such as aerospace, automobile manufacturing, etc. due to their excellent strength, rigidity and lightweight properties.

[0003] In the manufacturing process of carbon fiber composite materials, heating and curing is a crucial link, which directly affects the mechanical properties and service life of the material. However, in the existing heating and curing process, the curing parameters (heating rate, pressure, etc.) mainly rely on empirical settings or fixed process standards, resulting in the lack of accuracy and adaptability of the curing parameters, resulting in large quality fluctuations inside the material, especially bubble generation and resin loss problems, which seriously affect the overall performance and stability of the material. Summary of the invention

[0004] The purpose of the present application is to provide a heating and curing method and device for carbon fiber composite materials, so as to solve the technical problem that the material bubble generation and resin loss cannot be effectively controlled due to the lack of accuracy and adaptability of the curing parameter settings in the existing heating and curing process for carbon fiber composite materials.

[0005] In view of the above problems, the present application provides a method and device for heating and curing a carbon fiber composite material.

[0006] In a first aspect, the present application provides a method for heating and curing a carbon fiber composite material, which is implemented by a heating and curing device for a carbon fiber composite material, including: laying up a carbon fiber composite material to be heated and cured, and obtaining a curing parameter space for heating and curing, wherein the curing parameters include a pressure parameter and a heating rate parameter; randomly generating a first curing parameter in the curing parameter space, performing bubble simulation generation and resin loss simulation generation for multiple heating and curing processes, obtaining multiple first bubble parameters and first resin loss parameters, and generating a first bubble map and a first resin loss map; performing a bubble scale analysis and a resin loss scale analysis based on the first bubble map and the first resin loss map to obtain bubble scale information and resin loss scale information, as well as performing a bubble credibility analysis and a resin loss credibility analysis to obtain bubble credibility and resin loss credibility, and calculating a first curing fitness of the first curing parameter; based on the first curing fitness, continuing to optimize the curing parameters to obtain an optimal curing parameter with the largest curing fitness, and performing heating and curing of the carbon fiber composite material.

[0007] In a second aspect, the present application also provides a heating and curing device for a carbon fiber composite material, which is used to execute a heating and curing method for a carbon fiber composite material as described in the first aspect, including: a curing parameter space acquisition module, which is used to lay up the carbon fiber composite material to be heated and cured, and obtain the curing parameter space for heating and curing, wherein the curing parameters include pressure parameters and heating rate parameters; a simulated heating and curing module, which is used to randomly generate a first curing parameter in the curing parameter space, perform bubble simulation generation and resin loss simulation generation for multiple heating and curing, obtain multiple first bubble parameters and first resin loss parameters, and generate a first bubble map and a first resin loss map; a curing fitness calculation module, which is used to perform bubble scale analysis and resin loss scale analysis according to the first bubble map and the first resin loss map, obtain bubble scale information and resin loss scale information, as well as perform bubble credibility analysis and resin loss credibility analysis, obtain bubble credibility and resin loss credibility, and calculate and obtain the first curing fitness of the first curing parameter; a curing parameter optimization module, which is used to continue to optimize the curing parameters according to the first curing fitness, obtain the optimal curing parameters with the largest curing fitness, and perform heating and curing of the carbon fiber composite material.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] The first curing parameter is randomly generated in the curing parameter space, and bubble simulation generation and resin loss simulation generation of multiple heating curing are performed according to the first curing parameter to obtain multiple first bubble parameters and first resin loss parameters, and the first bubble parameters and the first resin loss parameters are used as pixel values ​​of pixel points to construct a first bubble map and a first resin loss map; then, bubble scale analysis and resin loss scale analysis are performed according to the first bubble map and the first resin loss map to obtain bubble scale information and resin loss scale information, and on the other hand, bubble credibility analysis and resin loss credibility analysis are performed to obtain bubble credibility and resin loss credibility, and the first curing fitness of the first curing parameter is calculated according to the bubble scale information, the resin loss scale information, the bubble credibility and the resin loss credibility; finally, the curing parameters are continuously optimized according to the first curing fitness to obtain the optimal curing parameters with the largest curing fitness, and the carbon fiber composite material is heated and cured based on the optimal curing parameters; the scientificity, rationality and accuracy of the curing parameter setting can be improved, the material bubble generation and resin loss in the curing process can be effectively reduced, and the technical effect of significantly improving the curing quality of the carbon fiber composite material can be achieved.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0012] Figure 1 A schematic diagram of a process for heating and curing a carbon fiber composite material according to the present application;

[0013] Figure 2 A schematic diagram of a process for generating a first bubble diagram and a first resin loss diagram in a heating and curing method of a carbon fiber composite material according to the present application;

[0014] Figure 3 This is a schematic structural diagram of a heating and curing device for a carbon fiber composite material according to the present application.

[0015] Description of reference numerals:

[0016] A curing parameter space acquisition module 11 , a simulated heating curing module 12 , a curing fitness calculation module 13 , and a curing parameter optimization module 14 . DETAILED DESCRIPTION

[0017] The present application provides a method and device for heating and curing carbon fiber composite materials, which solves the technical problem that the material bubble generation and resin loss cannot be effectively controlled due to the lack of accuracy and adaptability of the curing parameter setting in the existing heating and curing process for carbon fiber composite materials. The scientificity, rationality and accuracy of the curing parameter setting can be improved, the material bubble generation and resin loss during the curing process can be effectively reduced, and the technical effect of significantly improving the curing quality of carbon fiber composite materials can be achieved.

[0018] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0019] For example, please refer to the attached Figure 1 The present application provides a method for heating and curing a carbon fiber composite material, which is applied to a device for heating and curing a carbon fiber composite material, and specifically comprises the following steps:

[0020] S100: Laying up carbon fiber composite materials to be heated and cured, and obtaining a curing parameter space for the heating and curing, wherein the curing parameters include a pressure parameter and a heating rate parameter.

[0021] Specifically, carbon fiber composite material layup refers to the process of laying carbon fiber materials pre-impregnated with resin on a mold or other substrate layer by layer according to specific design requirements when manufacturing carbon fiber composite materials. The purpose of this process is to form a composite material structure of the desired shape and strength by stacking multiple layers of carbon fiber materials. First, the carbon fiber composite material to be heated and cured is laid, that is, according to the design structural parameters of the carbon fiber composite material (such as the number of layers, thickness, fiber orientation, etc.), the carbon fiber composite material to be heated and cured is laid. During the laying process, ensure that each layer of carbon fiber prepreg (fiber material pre-impregnated with resin) is evenly arranged to avoid wrinkles, gaps or fiber dislocations to ensure the mechanical properties of the final material.

[0022] Then, according to the design structural parameters of the carbon fiber composite material, the curing parameters of the same carbon fiber composite material for heating and curing are indexed, wherein the curing parameters include pressure parameters and heating rate parameters. The pressure parameter refers to the pressure applied to the composite material during the heating and curing process, which is used to expel bubbles and pores in the material and enhance the density. If the curing pressure is too large, the resin may be lost, and if the pressure is too small, the gas may not be completely expelled, resulting in bubbles. The heating rate parameter refers to the speed from the initial temperature to the curing temperature. The heating rate has a direct impact on the curing quality of the material. Too fast or too slow will affect the performance of the final material. For example, too fast a heating rate will cause the resin to soften and flow rapidly, which may aggravate the loss of resin, especially in parts with complex geometric shapes. At the same time, rapid heating may cause the resin to have insufficient time to expel bubbles, resulting in internal defects of the material. A plurality of pressure parameters and a plurality of heating rate parameters are obtained, and a pressure parameter space is constructed based on the plurality of pressure parameters, and a heating rate parameter space is constructed based on the plurality of heating rate parameters. Then, a curing parameter space is obtained according to the combination of the pressure parameter space and the heating rate parameter space. By indexing the curing parameters of similar materials to construct the curing parameter space, the scientificity and rationality of the curing parameter space setting can be improved, providing support for subsequent curing parameter optimization analysis, while reducing blind parameter optimization and improving the efficiency and accuracy of curing parameter optimization analysis.

[0023] S200: randomly generating a first curing parameter in the curing parameter space, performing bubble simulation generation and resin loss simulation generation of multiple heating curing processes, obtaining multiple first bubble parameters and first resin loss parameters, and generating a first bubble map and a first resin loss map.

[0024] Specifically, any pressure parameter and any heating rate parameter are randomly selected and combined in the curing parameter space to generate the first curing parameter. On the other hand, a bubble simulator and a resin loss simulator for heating and curing simulation are constructed based on the BP neural network. The bubble simulator is used to predict bubbles according to the curing parameters, and the input data is the curing parameters, and the output data is the bubble parameters, that is, the predicted number of bubbles; the resin loss simulator is used to predict resin loss according to the curing parameters, and the input data is the curing parameters, and the output data is the resin loss parameters, that is, the resin loss weight ratio; a sample data set is obtained to supervise the training of the bubble simulator and the resin loss simulator to obtain a bubble simulator and a resin loss simulator that meet the expected convergence conditions. Then the first curing parameter is input into the trained bubble simulator and resin loss simulator, and multiple heating and curing bubble simulation generation and resin loss simulation generation are performed, and multiple first bubble parameters (first bubble number) and multiple first resin loss parameters (first resin loss weight ratio) are output.

[0025] On the other hand, a first bubble map is constructed using multiple first bubble parameters as pixel values ​​of pixel points, wherein each pixel point in the bubble map corresponds to a bubble generation result, and the pixel value represents the number of generated bubbles; a first resin loss map is constructed using multiple first resin loss parameters as pixel values ​​of pixel points, wherein each pixel point in the resin loss map represents a resin loss result, and the pixel value represents the weight ratio of resin loss. By constructing the first bubble map and the first resin loss map, the effects of different curing parameters on bubble generation and resin loss can be intuitively observed, thereby improving the efficiency of subsequent bubble scale analysis and resin loss scale analysis.

[0026] S300: According to the first bubble map and the first resin loss map, bubble scale analysis and resin loss scale analysis are performed to obtain bubble scale information and resin loss scale information, and bubble credibility analysis and resin loss credibility analysis are performed to obtain bubble credibility and resin loss credibility, and a first curing adaptability of the first curing parameter is calculated and obtained.

[0027] Specifically, a bubble scale analysis is performed based on the first bubble graph, that is, a plurality of first bubble parameters (first bubble quantity) in the first bubble graph are averaged to obtain a first average bubble parameter, and the first average bubble parameter is used as the bubble scale information. On the other hand, a resin loss scale analysis is performed based on the first resin loss graph, that is, a plurality of first resin loss parameters (first resin loss weight ratio) in the first resin loss graph are averaged to obtain a first average resin loss parameter, and the first average resin loss parameter is used as the resin loss scale information.

[0028] On the other hand, according to the first bubble diagram and the first resin loss diagram, bubble credibility analysis and resin loss credibility analysis are performed, wherein bubble generation and resin loss may be accidental due to improper material processing, such as poor prepreg operation of carbon fiber composite materials, uneven arrangement between fiber layers, uneven resin distribution, etc., so credibility analysis can effectively distinguish accidental problems from curing parameter setting problems. First, bubble credibility analysis is performed according to the first bubble diagram, that is, the parameter deviation of each bubble parameter and other bubble parameters is calculated, multiple bubble parameter deviations are determined, and the mean of multiple bubble parameter deviations is calculated, and the inverse of the mean calculation result is set as the bubble credibility, wherein the larger the bubble parameter deviation, the greater the accidental nature of the bubbles generated under the first curing parameter, and the smaller the bubble credibility; the smaller the bubble parameter deviation, the greater the probability of bubbles generated under the first curing parameter, and the greater the bubble credibility. Then, based on the same method for obtaining the bubble credibility, the resin loss credibility analysis is performed according to the first resin loss diagram, that is, the parameter deviation of each resin loss parameter and other resin loss parameters is calculated, the mean of multiple resin loss parameter deviations is calculated, and the inverse of the mean calculation result is set as the resin loss credibility.

[0029] Construct a solidified fitness calculation function: In the curing fitness calculation function, HCA is the curing fitness, is the bubble credibility, P is the bubble scale information, To preset bubble size information, is the reliability of resin loss, S is the scale information of resin loss, The preset resin loss scale information. The curing fitness calculation function is used to calculate the curing fitness of the first curing parameter for the bubble scale information, the resin loss scale information, the bubble credibility and the resin loss credibility, and the first curing fitness is output, wherein the larger the curing fitness is, the better the curing effect of the composite material is. By constructing a curing fitness calculation function to calculate the curing fitness, the curing effect of the curing parameters can be accurately evaluated, providing a basis for subsequent curing parameter optimization analysis.

[0030] S400: According to the first curing adaptability, the curing parameters are continuously optimized to obtain the optimal curing parameters with the maximum curing adaptability, and the carbon fiber composite material is heated and cured.

[0031] Specifically, a second curing parameter is randomly selected in the curing parameter space, wherein the second curing parameter is different from the first curing parameter, and a second curing fitness of the second curing parameter is calculated using the same method as the first curing fitness. The same method is used to continue iterative selection and curing fitness calculation in the curing parameter space until a predetermined number of selections is met, then the selection is stopped to obtain multiple curing fitnesses of multiple curing parameters. Finally, the curing parameter with the largest curing fitness is output as the optimal curing parameter, and the carbon fiber composite material is heated and cured according to the optimal curing parameter.

[0032] The heating and curing method of a carbon fiber composite material is applied to a heating and curing device for a carbon fiber composite material, which can solve the technical problem that the material bubble generation and resin loss cannot be effectively controlled due to the lack of accuracy and adaptability in the setting of curing parameters in the existing heating and curing process for carbon fiber composite materials. The first curing parameter is randomly generated in the curing parameter space, and bubble simulation generation and resin loss simulation generation of multiple heating curing are performed according to the first curing parameter to obtain multiple first bubble parameters and first resin loss parameters, and the first bubble parameters and the first resin loss parameters are used as pixel values ​​of pixel points to construct a first bubble map and a first resin loss map; then, bubble scale analysis and resin loss scale analysis are performed according to the first bubble map and the first resin loss map to obtain bubble scale information and resin loss scale information, and on the other hand, bubble credibility analysis and resin loss credibility analysis are performed to obtain bubble credibility and resin loss credibility, and the first curing fitness of the first curing parameter is calculated according to the bubble scale information, the resin loss scale information, the bubble credibility and the resin loss credibility; finally, the curing parameters are continuously optimized according to the first curing fitness to obtain the optimal curing parameters with the largest curing fitness, and the carbon fiber composite material is heated and cured based on the optimal curing parameters; the scientificity, rationality and accuracy of the curing parameter setting can be improved, the material bubble generation and resin loss in the curing process can be effectively reduced, and the technical effect of significantly improving the curing quality of the carbon fiber composite material can be achieved.

[0033] Further, the carbon fiber composite material to be heated and cured is layered and a curing parameter space of the heating and curing is obtained. The present application includes:

[0034] According to the structural parameters of the carbon fiber composite material, the carbon fiber composite material to be heated and cured is laid; according to the structural parameters, the pressure parameter space and the heating rate parameter space of the same carbon fiber composite material for heating and curing are indexed, and the curing parameter space is obtained by combining.

[0035] Specifically, first, the structural parameters of the carbon fiber composite material are obtained, and the structural parameters include the number of layers, thickness, fiber orientation, etc., which can be determined through design drawings or material design requirements; then, the carbon fiber composite material to be heated and cured is layered based on the structural parameters, and during the layering process, it is ensured that each layer of carbon fiber prepreg (fiber material pre-impregnated with resin) is evenly arranged to avoid wrinkles, gaps or fiber dislocation, so as to ensure the mechanical properties of the final material.

[0036] On the other hand, according to the structural parameters, a parameter matching database is called to index the curing parameters of similar carbon fiber composite materials for heating and curing, wherein the parameter matching database is a database containing various carbon fiber composite materials, and the database stores the structural parameters of different materials and the corresponding curing process parameters; wherein the curing parameters include pressure parameters and heating rate parameters, and the pressure parameter refers to the pressure applied to the composite material during the heating and curing process, which is used to expel bubbles and pores in the material and enhance the density; the heating rate parameter refers to the speed from the initial temperature to the curing temperature, and the heating rate has a direct impact on the curing quality of the material, and too fast or too slow will affect the performance of the final material; multiple pressure parameters and multiple heating rate parameters of similar carbon fiber composite materials are retrieved, and a pressure parameter space is constructed based on the multiple pressure parameters, and a heating rate parameter space is constructed based on the multiple heating rate parameters; then the curing parameter space is obtained according to the combination of the pressure parameter space and the heating rate parameter space.

[0037] By calling the parameter matching database and indexing the curing parameters of similar materials to construct the curing parameter space, the scientificity and rationality of the setting of the curing parameter space can be improved, providing support for subsequent curing parameter optimization analysis. At the same time, it can avoid blind parameter optimization and improve the efficiency and accuracy of the curing parameter optimization analysis.

[0038] Further, as attached Figure 2 As shown, a first curing parameter is randomly generated in the curing parameter space, and bubble simulation generation and resin loss simulation generation of multiple heating curing are performed. The present application includes:

[0039] Pre-training a bubble simulator and a resin loss simulator for heat curing simulation, wherein the bubble simulator and the resin loss simulator include a plurality of bubble simulation branches and a plurality of resin loss simulation branches, respectively; randomly generating a first curing parameter in the curing parameter space; inputting the first curing parameter into the plurality of bubble simulation branches and the plurality of resin loss simulation branches, respectively, performing bubble simulation generation and resin loss simulation generation of multiple heat curing, respectively, to obtain a plurality of first bubble parameters and a first resin loss parameter; using the plurality of first bubble parameters and the first resin loss parameters as pixel points, constructing and generating a first bubble map and a first resin loss map.

[0040] Specifically, BP neural network is a feedforward neural network that can learn complex nonlinear relationships through training data and is widely used in classification, regression and other fields. Based on BP neural network, a bubble simulator and resin loss simulator for heating and curing simulation are constructed. The bubble simulator and resin loss simulator are neural network models that can be iteratively optimized in machine learning, and are obtained through supervised training with sample data; the bubble simulator includes multiple bubble simulation branches, wherein the bubble simulation branch is used to predict bubbles according to curing parameters, the input data is the curing parameters, and the output data is the bubble parameters, that is, the predicted number of bubbles; the resin loss simulator includes multiple resin loss simulation branches, wherein the resin loss simulation branch is used to predict resin loss according to curing parameters, the input data is the curing parameters, and the output data is the resin loss parameters, that is, the resin loss weight ratio.

[0041] Then, any pressure parameter and any heating rate parameter are randomly selected in the curing parameter space for combination to obtain the first curing parameter; then, the first curing parameter is respectively input into the multiple bubble simulation branches and the multiple resin loss simulation branches, and the bubble simulation generation and the resin loss simulation generation of multiple heating curing are respectively performed to obtain multiple first bubble parameters and multiple first resin loss parameters, wherein the first bubble parameter is the number of first bubbles, and the first resin loss parameter is the weight ratio of the first resin loss. The multiple first bubble parameters may be the same or different, and then the multiple first bubble parameters are used as the pixel values ​​of the pixel points to construct a first bubble map, wherein each pixel point in the bubble map corresponds to a bubble generation result, and the pixel value represents the number of generated bubbles; the multiple first resin loss parameters are used as the pixel values ​​of the pixel points to construct a first resin loss map, wherein each pixel point in the resin loss map represents a resin loss result, and the pixel value represents the weight ratio of the resin loss. By constructing the first bubble map and the first resin loss map, the influence of different curing parameters on bubble generation and resin loss can be intuitively observed, thereby improving the efficiency of subsequent bubble scale analysis and resin loss scale analysis.

[0042] Further, a bubble simulator and a resin loss simulator for pre-training heating and curing simulation are provided, and the present application includes:

[0043] According to the historical heating and curing data of similar carbon fiber composite materials, a sample curing parameter set is collected, and the number of bubbles and the weight ratio of resin loss in the carbon fiber composite materials after curing under different sample curing parameters are collected to obtain a sample bubble parameter set and a sample resin loss parameter set; the sample curing parameter set and the sample bubble parameter set are combined and divided to obtain multiple groups of bubble simulation training data; using the multiple groups of bubble simulation training data, supervised training is performed to obtain multiple bubble simulation branches to obtain a bubble simulator; the sample curing parameter set and the sample resin loss parameter set are combined and divided, and supervised training is performed to obtain multiple resin loss simulation branches to obtain a resin loss simulator.

[0044] Specifically, first, the curing parameters are extracted based on the historical heating and curing data of similar carbon fiber composites to obtain a sample curing parameter set; then the number of bubbles and the weight ratio of resin loss in the carbon fiber composite materials after curing under different sample curing parameters are collected. Under the same sample curing parameters, the number of bubbles and the weight ratio of resin loss may be different after multiple heating and curing due to accidental reasons. Therefore, one sample curing parameter may correspond to multiple different sample bubble parameters. The number of bubbles is taken as the bubble parameter, and the weight ratio of resin loss is taken as the resin loss parameter to obtain a sample bubble parameter set and a sample resin loss parameter set.

[0045] Then, the sample solidification parameter set and the sample bubble parameter set are combined, where one sample solidification parameter corresponds to multiple sample bubble parameters, and the combination result is equally divided to obtain multiple groups of bubble simulation training data, each group of bubble simulation training data has the same amount of data but different specific data; then, the sample solidification parameters are used as input and the sample bubble parameters are used as supervision, and the multiple groups of bubble simulation training data are used to perform supervised training on multiple bubble simulation branches respectively, and the deviation between the prediction result of the model and the sample data is calculated through the loss function, and the weight of the model is adjusted by the back propagation algorithm to reduce the error for training, so as to obtain multiple convergent bubble simulation branches that meet the preset convergence conditions, and a bubble simulator is constructed based on the multiple bubble simulation branches.

[0046] On the other hand, the sample curing parameter set and the sample resin loss parameter set are combined, where one sample curing parameter corresponds to multiple sample resin loss parameters, and then the combination result is equally divided to obtain multiple groups of resin loss simulation training data; the multiple groups of resin loss simulation training data are further used to perform supervised training on multiple resin loss simulation branches, and multiple convergent resin loss simulation branches are obtained to construct a resin loss simulator.

[0047] By constructing a bubble simulator based on multiple convergent bubble simulation branches and a resin loss simulator based on multiple convergent resin loss simulation branches, each convergent bubble simulation branch has different training data, and the output of possibly different bubble parameters can be analyzed according to the input curing parameters. The output of multiple convergent bubble simulation branches is integrated to obtain the final bubble parameters, improve the accuracy of simulation analysis, and each bubble simulation branch has less training data, which improves the training convergence efficiency. In this way, the number of bubbles and the weight ratio of resin loss in various scenarios can be predicted, so that the comprehensiveness and rationality of the first bubble parameter and the first resin loss parameter can be improved, thereby improving the accuracy of the construction of the first bubble diagram and the first resin loss diagram.

[0048] Further, according to the first bubble map and the first resin loss map, bubble scale analysis and resin loss scale analysis are performed to obtain bubble scale information and resin loss scale information. The present application includes:

[0049] According to the first bubble map, the mean of multiple first bubble parameters in the first bubble map is calculated to obtain a first average bubble parameter as bubble scale information; according to the first resin loss map, the mean of multiple first resin loss parameters in the first resin loss map is calculated to obtain a first average resin loss parameter as resin loss scale information.

[0050] Specifically, a bubble scale analysis is performed based on the first bubble graph, that is, a plurality of first bubble parameters (first bubble quantity) in the first bubble graph are averaged to obtain a first average bubble parameter, that is, the average bubble quantity obtained by analysis, and the first average bubble parameter is used as the bubble scale information. On the other hand, a resin loss scale analysis is performed based on the first resin loss graph, that is, a plurality of first resin loss parameters (first resin loss weight ratio) in the first resin loss graph are averaged to obtain a first average resin loss parameter as the resin loss scale information.

[0051] Further, bubble credibility analysis and resin loss credibility analysis are performed to obtain bubble credibility and resin loss credibility, and the first curing adaptability of the first curing parameter is calculated and obtained. The present application includes:

[0052] In the first bubble graph, multiple groups of first bubble parameters are randomly selected multiple times, and multiple random bubble parameter means are calculated, the deviation amplitude between each first bubble parameter and each random bubble parameter mean is calculated, and the bubble parameter deviation mean is calculated, wherein the number of the multiple random bubble parameter means is the same as the number of the multiple first bubble parameters; based on the bubble parameter deviation mean, the bubble credibility is calculated, wherein the size of the bubble parameter deviation mean is negatively correlated with the size of the bubble credibility; based on the first resin loss graph, the resin loss credibility is calculated; based on the bubble scale information, the bubble credibility, the resin loss scale information and the resin loss credibility, the first curing adaptability of the first curing parameter is calculated, as shown in the following formula: ; Among them, HCA is the curing adaptability, is the bubble credibility, P is the bubble scale information, To preset bubble size information, is the reliability of resin loss, S is the scale information of resin loss, To preset the resin loss scale information.

[0053] Specifically, first, multiple groups of first bubble parameters are randomly selected multiple times in the first bubble graph, each group of first bubble parameters includes, for example, 3 first bubble parameters, and then the multiple groups of first bubble parameters are averaged to obtain multiple random bubble parameter means, wherein the number of the multiple random bubble parameter means is the same as the number of the multiple first bubble parameters. Then, the deviation amplitude of each first bubble parameter and each random bubble parameter mean is calculated, such as the ratio of the difference between each first bubble parameter and each random bubble parameter mean to each first bubble parameter, to obtain multiple bubble parameter deviation values, and then the multiple bubble parameter deviation values ​​are averaged to obtain the bubble parameter deviation mean. Further, the bubble credibility is obtained according to the bubble parameter deviation mean calculation, for example, the inverse of the bubble parameter deviation mean is used as the bubble credibility, wherein the size of the bubble parameter deviation mean is negatively correlated with the size of the bubble credibility, that is, the larger the bubble parameter deviation mean is, the more random the number of bubbles generated under the first curing parameter may be due to accidental reasons, such as occasionally more bubbles and occasionally fewer bubbles, and the corresponding bubble credibility is smaller.

[0054] The same method for calculating the bubble credibility is used to calculate the mean value of the resin loss parameter deviation according to the first resin loss graph, and the resin loss credibility is calculated according to the mean value of the resin loss parameter deviation, wherein the size of the mean value of the resin loss parameter deviation is negatively correlated with the size of the resin loss credibility. For example, the inverse of the mean value of the resin loss parameter deviation is calculated to obtain the resin loss credibility.

[0055] Then construct a solidified fitness calculation function: ; In the curing fitness calculation function, HCA is the curing fitness, and the greater the curing fitness, the better the curing effect; is the bubble credibility, P is the bubble scale information, is preset bubble scale information, which is a predetermined bubble quantity threshold value, and can be set according to material quality requirements, for example, 2; is the reliability of resin loss, S is the scale information of resin loss, The preset resin loss scale information is the preset resin loss scale information for the predetermined resin loss weight ratio, for example, 5%. The curing fitness is calculated by constructing a curing fitness calculation function, and the curing effect of the curing parameters can be accurately evaluated, providing a basis for subsequent curing parameter comparison and evaluation. The greater the bubble credibility and the greater the resin loss credibility, the more accurate and reliable the bubble scale information and resin loss scale information currently analyzed and calculated are, the greater the curing fitness, the smaller the bubble scale information and the resin loss scale information are, the better the quality of the carbon fiber composite material after the current curing, and the greater the curing fitness.

[0056] Finally, based on the curing fitness calculation function, the first curing fitness of the first curing parameter is calculated according to the bubble scale information, the bubble credibility, the resin loss scale information and the resin loss credibility.

[0057] Further, according to the first curing adaptability, the curing parameters are further optimized to obtain the optimal curing parameters with the maximum curing adaptability. The present application includes:

[0058] The curing parameters are continuously optimized in the curing parameter space until convergence; the curing parameters with the largest curing fitness in the optimization process are output to obtain the optimal curing parameters.

[0059] Specifically, the same method is then used to continue iteratively selecting curing parameters and calculating curing fitness in the curing parameter space until a predetermined number of selections is met, then the selection is stopped, and multiple curing fitnesses of multiple curing parameters are obtained. The multiple curing fitnesses are compared, and the curing parameter with the largest curing fitness is selected as the optimal curing parameter, and the carbon fiber composite material is heated and cured according to the optimal curing parameter.

[0060] In summary, the heating and curing method of a carbon fiber composite material provided in the present application has the following technical effects:

[0061] The first curing parameter is randomly generated in the curing parameter space, and bubble simulation generation and resin loss simulation generation of multiple heating curing are performed according to the first curing parameter to obtain multiple first bubble parameters and first resin loss parameters, and the first bubble parameters and the first resin loss parameters are used as pixel values ​​of pixel points to construct a first bubble map and a first resin loss map; then, bubble scale analysis and resin loss scale analysis are performed according to the first bubble map and the first resin loss map to obtain bubble scale information and resin loss scale information, and on the other hand, bubble credibility analysis and resin loss credibility analysis are performed to obtain bubble credibility and resin loss credibility, and the first curing fitness of the first curing parameter is calculated according to the bubble scale information, the resin loss scale information, the bubble credibility and the resin loss credibility; finally, the curing parameters are continuously optimized according to the first curing fitness to obtain the optimal curing parameters with the largest curing fitness, and the carbon fiber composite material is heated and cured based on the optimal curing parameters; the scientificity, rationality and accuracy of the curing parameter setting can be improved, the material bubble generation and resin loss in the curing process can be effectively reduced, and the technical effect of significantly improving the curing quality of the carbon fiber composite material can be achieved.

[0062] Embodiment 2: Based on the heating and curing method of a carbon fiber composite material in the above embodiment, the present application also provides a heating and curing device for a carbon fiber composite material, as shown in the attached Figure 3 ,include:

[0063] A curing parameter space acquisition module 11 is used to lay up the carbon fiber composite material to be heated and cured, and to obtain the curing parameter space for heating and curing, wherein the curing parameters include pressure parameters and heating rate parameters; a simulated heating and curing module 12 is used to randomly generate a first curing parameter in the curing parameter space, perform bubble simulation generation and resin loss simulation generation for multiple heating and curing, obtain multiple first bubble parameters and first resin loss parameters, and generate a first bubble map and a first resin loss map; a curing fitness calculation module 13 is used to perform bubble scale analysis and resin loss scale analysis according to the first bubble map and the first resin loss map, obtain bubble scale information and resin loss scale information, as well as perform bubble credibility analysis and resin loss credibility analysis, obtain bubble credibility and resin loss credibility, and calculate and obtain the first curing fitness of the first curing parameter; a curing parameter optimization module 14 is used to continue to optimize the curing parameters according to the first curing fitness, obtain the optimal curing parameters with the largest curing fitness, and perform heating and curing of the carbon fiber composite material.

[0064] Furthermore, the heating and curing device for a carbon fiber composite material is also used for:

[0065] According to the structural parameters of the carbon fiber composite material, the carbon fiber composite material to be heated and cured is laid; according to the structural parameters, the pressure parameter space and the heating rate parameter space of the same carbon fiber composite material for heating and curing are indexed, and the curing parameter space is obtained by combining.

[0066] Furthermore, the heating and curing device for a carbon fiber composite material is also used for:

[0067] Pre-training a bubble simulator and a resin loss simulator for heat curing simulation, wherein the bubble simulator and the resin loss simulator include a plurality of bubble simulation branches and a plurality of resin loss simulation branches, respectively; randomly generating a first curing parameter in the curing parameter space; inputting the first curing parameter into the plurality of bubble simulation branches and the plurality of resin loss simulation branches, respectively, performing bubble simulation generation and resin loss simulation generation of multiple heat curing, respectively, to obtain a plurality of first bubble parameters and a first resin loss parameter; using the plurality of first bubble parameters and the first resin loss parameters as pixel points, constructing and generating a first bubble map and a first resin loss map.

[0068] Furthermore, the heating and curing device for a carbon fiber composite material is also used for:

[0069] According to the historical heating and curing data of similar carbon fiber composite materials, a sample curing parameter set is collected, and the number of bubbles and the weight ratio of resin loss in the carbon fiber composite materials after curing under different sample curing parameters are collected to obtain a sample bubble parameter set and a sample resin loss parameter set; the sample curing parameter set and the sample bubble parameter set are combined and divided to obtain multiple groups of bubble simulation training data; using the multiple groups of bubble simulation training data, supervised training is performed to obtain multiple bubble simulation branches to obtain a bubble simulator; the sample curing parameter set and the sample resin loss parameter set are combined and divided, and supervised training is performed to obtain multiple resin loss simulation branches to obtain a resin loss simulator.

[0070] Furthermore, the heating and curing device for a carbon fiber composite material is also used for:

[0071] According to the first bubble map, the mean of multiple first bubble parameters in the first bubble map is calculated to obtain a first average bubble parameter as bubble scale information; according to the first resin loss map, the mean of multiple first resin loss parameters in the first resin loss map is calculated to obtain a first average resin loss parameter as resin loss scale information.

[0072] Furthermore, the heating and curing device for carbon fiber composite material is also used for: randomly selecting multiple groups of first bubble parameters in the first bubble diagram for multiple times, and calculating multiple random bubble parameter means, calculating the deviation amplitude between each first bubble parameter and each random bubble parameter mean, and calculating the bubble parameter deviation mean, wherein the number of the multiple random bubble parameter means is the same as the number of the multiple first bubble parameters; calculating the bubble credibility according to the bubble parameter deviation mean, wherein the size of the bubble parameter deviation mean is negatively correlated with the size of the bubble credibility; calculating the resin loss credibility according to the first resin loss diagram; calculating the first curing adaptability of the first curing parameter according to the bubble scale information, the bubble credibility, the resin loss scale information and the resin loss credibility, as shown in the following formula: ; Among them, HCA is the curing adaptability, is the bubble credibility, P is the bubble scale information, To preset bubble size information, is the reliability of resin loss, S is the scale information of resin loss, To preset the resin loss scale information.

[0073] Furthermore, the heating and curing device for a carbon fiber composite material is also used for:

[0074] The curing parameters are continuously optimized in the curing parameter space until convergence; the curing parameters with the largest curing fitness in the optimization process are output to obtain the optimal curing parameters.

[0075] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The heating and curing method of a carbon fiber composite material and the specific examples in the aforementioned embodiment 1 are also applicable to a heating and curing device for a carbon fiber composite material in this embodiment. Through the aforementioned detailed description of the heating and curing method of a carbon fiber composite material, those skilled in the art can clearly understand the heating and curing device for a carbon fiber composite material in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0076] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be 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 the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0077] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A method for heating and curing a carbon fiber composite material, characterized in that: Methods include: Laying up the carbon fiber composite material to be heated and cured, and obtaining a curing parameter space for the heating and curing, wherein the curing parameters include a pressure parameter and a heating rate parameter; Randomly generate a first curing parameter in the curing parameter space, perform bubble simulation generation and resin loss simulation generation for multiple heating and curing, obtain multiple first bubble parameters and first resin loss parameters, and generate a first bubble map and a first resin loss map; According to the first bubble map and the first resin loss map, bubble scale analysis and resin loss scale analysis are performed to obtain bubble scale information and resin loss scale information, and bubble credibility analysis and resin loss credibility analysis are performed to obtain bubble credibility and resin loss credibility, and a first curing adaptability of the first curing parameter is calculated and obtained; According to the first curing adaptability, the curing parameters are continuously optimized to obtain the optimal curing parameters with the maximum curing adaptability, and the carbon fiber composite material is heated and cured; Among them, the carbon fiber composite material to be heated and cured is laid up, and the curing parameter space of the heating and curing is obtained, including: Laying up the carbon fiber composite material to be heated and cured according to the structural parameters of the carbon fiber composite material; According to the structural parameters, the pressure parameter space and the heating rate parameter space for heating and curing of the same type of carbon fiber composite materials are indexed, and the curing parameter space is obtained by combining them; According to the first bubble map and the first resin loss map, bubble scale analysis and resin loss scale analysis are performed to obtain bubble scale information and resin loss scale information, including: According to the first bubble graph, calculating the average of a plurality of first bubble parameters in the first bubble graph to obtain a first average bubble parameter as bubble scale information; According to the first resin loss graph, the average of a plurality of first resin loss parameters in the first resin loss graph is calculated to obtain a first average resin loss parameter as resin loss scale information.

2. The method for heating and curing a carbon fiber composite material according to claim 1, characterized in that: Randomly generate a first curing parameter in the curing parameter space, perform bubble simulation generation and resin loss simulation generation for multiple heating curing, including: Pre-training a bubble simulator and a resin loss simulator for heat curing simulation, wherein the bubble simulator and the resin loss simulator include a plurality of bubble simulation branches and a plurality of resin loss simulation branches respectively; randomly generating a first curing parameter in the curing parameter space; Inputting the first curing parameters into the multiple bubble simulation branches and the multiple resin loss simulation branches respectively, performing multiple heating and curing bubble simulation generation and resin loss simulation generation respectively, and obtaining multiple first bubble parameters and first resin loss parameters; The plurality of first bubble parameters and the first resin loss parameters are used as pixel points to construct and generate a first bubble map and a first resin loss map.

3. The method for heating and curing a carbon fiber composite material according to claim 2, characterized in that: Pre-trained bubble simulator and resin loss simulator for heat cure simulation, including: According to the historical heating and curing data of similar carbon fiber composite materials, a sample curing parameter set is collected, and the number of bubbles and the weight ratio of resin loss in the carbon fiber composite materials after curing under different sample curing parameters are collected to obtain a sample bubble parameter set and a sample resin loss parameter set; The sample solidification parameter set and the sample bubble parameter set are combined and divided to obtain multiple groups of bubble simulation training data; Using the multiple groups of bubble simulation training data, supervised training is performed to obtain multiple bubble simulation branches, thereby obtaining a bubble simulator; The sample curing parameter set and the sample resin loss parameter set are combined and divided, and supervised training is performed to obtain multiple resin loss simulation branches to obtain a resin loss simulator.

4. The method for heating and curing a carbon fiber composite material according to claim 1, characterized in that: Performing bubble credibility analysis and resin loss credibility analysis to obtain bubble credibility and resin loss credibility, and calculating and obtaining the first curing adaptability of the first curing parameter, including: In the first bubble graph, multiple groups of first bubble parameters are randomly selected multiple times, and multiple random bubble parameter means are calculated to obtain the mean values, the deviation amplitude between each first bubble parameter and each random bubble parameter mean is calculated, and the bubble parameter deviation mean is calculated to obtain the mean value, wherein the number of the multiple random bubble parameter means is the same as the number of the multiple first bubble parameters; The bubble credibility is calculated according to the mean value of the bubble parameter deviation, wherein the size of the mean value of the bubble parameter deviation is negatively correlated with the size of the bubble credibility; Calculating the resin loss credibility according to the first resin loss graph; According to the bubble scale information, bubble credibility, resin loss scale information and resin loss credibility, a first curing adaptability of a first curing parameter is calculated and obtained as follows: ； Among them, HCA is the curing adaptability, is the bubble credibility, P is the bubble scale information, To preset bubble size information, is the reliability of resin loss, S is the scale information of resin loss, To preset the resin loss scale information.

5. The method for heating and curing a carbon fiber composite material according to claim 1, characterized in that: According to the first curing adaptability, the curing parameters are continuously optimized to obtain the optimal curing parameters with the maximum curing adaptability, including: Continuing to optimize the curing parameters in the curing parameter space until convergence; The curing parameters with the largest curing adaptability during the optimization process are output to obtain the optimal curing parameters.

6. A heating and curing device for carbon fiber composite materials, characterized in that: The steps for implementing the heating and curing method of a carbon fiber composite material according to any one of claims 1 to 5 include: A curing parameter space acquisition module is used to lay up the carbon fiber composite material to be heated and cured, and to obtain the curing parameter space of the heating and curing, wherein the curing parameters include pressure parameters and heating rate parameters; A simulation heating and curing module is used to randomly generate a first curing parameter in the curing parameter space, perform bubble simulation generation and resin loss simulation generation for multiple heating and curing, obtain multiple first bubble parameters and first resin loss parameters, and generate a first bubble map and a first resin loss map; a curing fitness calculation module, configured to perform bubble scale analysis and resin loss scale analysis according to the first bubble graph and the first resin loss graph to obtain bubble scale information and resin loss scale information, and to perform bubble credibility analysis and resin loss credibility analysis to obtain bubble credibility and resin loss credibility, and to calculate and obtain a first curing fitness of a first curing parameter; The curing parameter optimization module is used to continue to optimize the curing parameters according to the first curing adaptability, obtain the optimal curing parameters with the maximum curing adaptability, and perform heating and curing of the carbon fiber composite material.

Images