Reliability Analysis Method and System for Composite Material Structures Based on Adaptive Hybrid Surrogate Model

Abstract

The present invention discloses a reliability analysis method and system for composite material structures based on an adaptive hybrid surrogate model, comprising the following steps: defining a reliability problem, determining the distribution type and statistical characteristics of basic random variables, and generating an initial design experiment; using a current DOE to train a Kriging model and an artificial neural network model to construct a surrogate model; calculating the weights of different surrogate models on candidate sample points based on an entropy weight method to achieve adaptive integration of the surrogate models; using an MMHDR mechanism to generate a candidate sample set, and searching for update points through a learning function to optimize the surrogate model; judging whether the accuracy of the integrated model meets the requirements, and if so, stopping the update; otherwise, continuing to optimize the surrogate model; and outputting a failure probability based on the integrated surrogate model. The present invention effectively improves the accuracy, efficiency, and robustness of composite material structure reliability analysis by combining the advantages of different surrogate models and utilizing EWM and MMHDR strategies.

Description

Technical Field

[0001] The present invention relates to the technical field of composite material structure reliability analysis, and more particularly to a composite material structure reliability analysis method and system based on an adaptive hybrid agent model. Background Art

[0002] At present, composite materials play an important role in different engineering problems due to their advantages such as high strength, high specific modulus, high temperature resistance, good thermal stability, strong design, simple manufacturing process and low cost.

[0003] However, the mechanical properties of composite structures are affected by multiple parameters, including ply angle, ply thickness, elastic modulus, shear modulus, Poisson's ratio and density. In addition, due to manufacturing defects, lack of experience and structural complexity, the mechanical properties of composite structures produced on a large scale in industry often show significant variability. At the same time, the random changes in external loading conditions and environmental factors also make the uncertainty in evaluating the mechanical properties of composite structures particularly important.

[0004] However, traditional reliability analysis methods, such as finite element simulation to evaluate limit states, are computationally expensive. In order to improve the computational efficiency of reliability analysis of composite structures, developing more efficient proxy models has become a research focus.

[0005] In recent years, some studies have used a single surrogate model or combined different surrogate models to build an integrated model for time-consuming limit state assessment; however, these methods often construct the integrated model by calculating the weights of local prediction errors, ignoring the generalization ability of the surrogate model on data of different dimensional types.

[0006] Therefore, how to improve the computational efficiency and accuracy of composite material structure reliability analysis methods is an urgent problem that needs to be solved by those skilled in the art. Summary of the Invention

[0007] In view of this, the present invention provides a composite material structure reliability analysis method and system based on an adaptive hybrid agent model to solve the technical problems mentioned in the background technology.

[0008] In order to achieve the above object, the present invention adopts the following technical solutions:

[0009] A composite structure reliability analysis method based on an adaptive hybrid surrogate model comprises the following steps:

[0010] S1. Determine the distribution type and statistical characteristics of the basic random variables of the composite structure, set the number of sample points for the initial design experiment (DOE), and calculate the actual limit state function value of the initial DOE;

[0011] S2. Use the current DOE to train surrogate models including Kriging model and artificial neural network (ANN) model, generate Monte Carlo candidate sample set MC according to the statistical characteristics of random variables, and use different surrogate models to predict sample points in the MC set;

[0012] S3. Based on the EWM entropy weight method, the prediction error and entropy value of the proxy model are combined to calculate the weights of different proxy models on the candidate sample points, realize the adaptive integration of the proxy models, and thus obtain the combined model;

[0013] S4, using the MMHDR mechanism to generate a conditional sample point set based on the Monte Carlo candidate sample set MC, and searching for update points through the learning function, and adding the update points to the initial DOE;

[0014] S5. Retrain the proxy model using the updated DOE, and determine whether the accuracy of the current integrated model meets the requirements based on a preset threshold. Repeat steps S3 to S5 until the convergence criterion is met or the maximum number of iterations is reached.

[0015] S6. After the iteration is completed, the failure probability of the composite structure based on the integrated agent model is output.

[0016] Preferably, step S1 further comprises analyzing the composition, function and working conditions of the structure based on the data information of the composite material structure to be evaluated, and determining the failure mode of the structure and the corresponding limit state equation.

[0017] Preferably, in step S2, when constructing the proxy model, cross-validation and jackknife techniques are used to calculate the predicted values and predicted variances of different proxy models.

[0018] Preferably, the specific content of step S3 is:

[0019] The entropy weight is calculated based on the EWM entropy weight method, specifically:

[0020]

[0021] Among them, E j is the entropy of the j-th surrogate model, p ij is the ratio of the i-th sample point in the j-th proxy model, k is the number of candidate sample points, N M is the total number of proxy models;

[0022] Calculate the coefficient of variation G for each model j =1-E j , and calculate the entropy weight factor based on the difference coefficient

[0023] Calculate the weights of different proxy models on candidate sample points as follows:

[0024]

[0025] Among them, e j (x) is the prediction error of the j-th proxy model on the candidate sample point.

[0026] Preferably, in step S4, the MMHDR mechanism is used to generate a conditional sample point set based on the Monte Carlo candidate sample set MC, and the specific content of searching for the update point through the learning function is:

[0027] S41. Randomly select half of the sample points N1 in the current MC population and their predicted values as the initial subset, and sort the predicted values in ascending order;

[0028] S42. Select the first P0N1 samples as the seeds for generating the next subset, where P0 is the seed selection ratio, and use the MMHDR strategy to generate N1 conditional sample point sets with a probability density function f(x) based on the selected seeds;

[0029] S43. Repeat this process until the stopping condition is met, and combine the first reciprocal subset and the second reciprocal subset to search the local range L of the proxy model update point e ;

[0030] S44. Use U function to filter the local range L e The sample points within the range are obtained, and the updated points are added to the DOE.

[0031] Preferably, in step S5, the judgment condition for whether the accuracy of the current integrated model meets the requirements is:

[0032]

[0033] Among them, P f,j is the failure probability estimated by the jth surrogate model, P f is the failure probability calculated by the integrated model, ε t is the preset threshold;

[0034] If the conditions are met, the update is stopped; otherwise, the process returns to step S2 to continue updating the proxy model.

[0035] A composite material structure reliability analysis system based on an adaptive hybrid surrogate model, based on the composite material structure reliability analysis method based on an adaptive hybrid surrogate model, comprising: a reliability problem definition module, an initial surrogate model construction module, a weight calculation and model integration module, a model optimization module, and a reliability result output module;

[0036] Reliability problem definition module, which is used to determine the distribution type and statistical characteristics of the basic random variables of the composite structure, set the number of sample points of the initial design experiment (DOE), and calculate the actual limit state function value of the initial DOE;

[0037] The initial surrogate model construction module is used to use the current DOE to train surrogate models including Kriging model and artificial neural network ANN model, generate Monte Carlo candidate sample set MC according to the statistical characteristics of random variables, and use different surrogate models to predict sample points in the MC set;

[0038] The weight calculation and model integration module is used to calculate the weights of different proxy models on candidate sample points based on the EWM entropy weight method, combined with the prediction error and entropy value of the proxy model, to achieve adaptive integration of the proxy model and thus obtain a combined model;

[0039] The model optimization module is used to generate a set of conditional sample points based on the Monte Carlo candidate sample set MC using the MMHDR mechanism, search for update points through the learning function, and add the update points to the initial DOE; the proxy model is retrained using the updated DOE, and the accuracy of the current integrated model is judged to meet the requirements based on the preset threshold until the convergence criterion is met or the maximum number of iterations is reached;

[0040] The reliability result output module is used to output the failure probability of the composite structure based on the integrated agent model after the iteration is completed.

[0041] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements a composite material structure reliability analysis method based on an adaptive hybrid agent model.

[0042] A processing terminal includes a memory and a processor. The memory stores a computer program that can be run on the processor. When the processor executes the computer program, a composite material structure reliability analysis method based on an adaptive hybrid agent model is implemented.

[0043] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses a method and system for reliability analysis of composite materials structures based on an adaptive hybrid proxy model. By combining the advantages of different proxy models, the integrated proxy model can more accurately predict the limit state function and improve the accuracy of reliability analysis; the local learning strategy and MMHDR mechanism are adopted to effectively reduce the size of the candidate sample set, reduce the computational cost, and improve the computational efficiency; the EWM strategy is adopted to consider the overall stability of the proxy model, so that the integrated proxy model exhibits stronger generalization ability on data of different dimensional types, thereby enhancing the robustness of reliability analysis; the present invention is particularly suitable for reliability analysis of complex composite materials structures with low failure probability, which not only ensures the accuracy of the analysis but also improves the computational efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0045] Figure 1 Flowchart of the composite material structure reliability analysis method based on the adaptive hybrid surrogate model provided by the present invention;

[0046] Figure 2 A schematic diagram of a scenario of a composite material structure reliability analysis method based on an adaptive hybrid agent model provided by the present invention;

[0047] Figure 3 A schematic diagram of the entropy weight calculation process provided by the present invention;

[0048] Figure 4 The distribution of sample points under different sampling strategies provided by the present invention;

[0049] Figure 5 A comparison chart of the accuracy and efficiency of different reliability analysis methods provided by embodiments of the present invention in steel column reliability analysis;

[0050] Figure 6 The accuracy and efficiency of different reliability analysis methods provided by the embodiments of the present invention are compared in the reliability analysis of inflatable offshore crash barriers. DETAILED DESCRIPTION

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0052] Example 1

[0053] The embodiment of the present invention discloses a composite material structure reliability analysis method based on an adaptive hybrid agent model, such as Figure 1 and Figure 2 , including the following steps:

[0054] S1. Define the reliability problem: Determine the distribution type and statistical characteristics of the basic random variables of the composite structure, set the number of sample points N0 for the initial design of experiment (DOE), and calculate the actual limit state function (LSF) value of the initial DOE;

[0055] S2. Constructing the surrogate model: Using the current DOE training including the surrogate model of Kriging model and artificial neural network ANN model, the Monte Carlo candidate sample set MC is generated according to the statistical characteristics of the random variable, including N c Sample points, use different proxy models to predict the sample points in the MC set;

[0056] S3. Calculate the weights of the proxy models: Based on the EWM entropy weight method, combined with the prediction error and entropy value of the proxy model, calculate the weights of different proxy models on the candidate sample points, realize the adaptive integration of the proxy models, and thus obtain the combined model;

[0057] S4. Establish a candidate sample set and search for update points: Use the MMHDR mechanism (Modified Metropolis-Hastings with Delayed Rejection, i.e., the modified Metropolis-Hastings algorithm with delayed rejection) to generate a conditional sample point set based on the Monte Carlo candidate sample set MC, and search for update points through the learning function, and add the update points to the initial DOE;

[0058] S5. Determine the stopping condition of model update: Use the updated DOE to retrain the proxy model and determine whether the accuracy of the current integrated model meets the requirements based on the preset threshold. Repeat steps S3 to S5 until the convergence criterion is met or the maximum number of iterations is reached.

[0059] S6. Output reliability analysis results: After the iteration is completed, the failure probability of the composite structure based on the integrated agent model is output.

[0060] In this embodiment, when step S6 outputs the failure probability based on the integrated agent model, a reliability index, such as the reliability index β, may also be output simultaneously to provide a more comprehensive reliability analysis result.

[0061] In order to further implement the above technical solution, step S1 also includes analyzing the composition, function and working conditions of the structure based on the data information of the composite material structure to be evaluated, including but not limited to the instructions, design standards, expert opinions and historical data, and determining the failure mode of the structure and the corresponding limit state equation.

[0062] In order to further implement the above technical solution, in step S2, when constructing the proxy model, the cross-validation and jackknife techniques are used to calculate the predicted values and prediction variances of different proxy models.

[0063] In order to further implement the above technical solutions, Figure 3 , the specific content of step S3 is:

[0064] The entropy weight is calculated based on the EWM entropy weight method, specifically:

[0065]

[0066] Among them, E j is the entropy of the j-th surrogate model, p ij is the ratio of the i-th sample point in the j-th proxy model, k is the number of candidate sample points, N M is the total number of proxy models;

[0067] Calculate the coefficient of variation G for each model j =1-E j , and calculate the entropy weight factor based on the difference coefficient

[0068] Calculate the weights of different proxy models on candidate sample points as follows:

[0069]

[0070] Among them, e j (x) is the prediction error of the j-th proxy model on the candidate sample point;

[0071]

[0072] in, is the local prediction result of the combined model, is the mean of the global prediction results of the combined model.

[0073] In this embodiment, the combination model obtained in step S3 is specifically:

[0074]

[0075] Among them, N M represents the total number of combined models, represents the predicted value of the ith surrogate model, w i (x) represents the weight of the proxy model in the i-th combined model. In order to further implement the above technical solution, in step S4, Figure 4 , the MMHDR mechanism is used to generate a conditional sample point set based on the Monte Carlo candidate sample set MC, and the specific content of searching for update points through the learning function is:

[0076] S41. Randomly select half of the sample points in the current MC population (N1 = 0.5N c ) and its predicted values as the initial subset, and sort the predicted values in ascending order;

[0077] S42. Select the first P0N1 samples as the seeds for generating the next subset, where P0 is the seed selection ratio, and use the MMHDR strategy to generate N1 conditional sample point sets with probability density function f(x) based on the selected seeds (the initial state points of the P0N1 Markov chains);

[0078] S43. Repeat S42 until the stopping condition is met (until the P0N1th performance function value is not greater than 0), combine the first reciprocal subset and the second reciprocal subset to search the local range L of the proxy model update point e ;

[0079] S44. Use U function to filter the local range L e The sample points within the range are obtained, and the updated points are added to the DOE.

[0080] In order to further implement the above technical solution, in step S5, the judgment condition of whether the accuracy of the current integrated model meets the requirements is:

[0081]

[0082] Among them, P f,j is the failure probability estimated by the jth surrogate model, P f is the failure probability calculated by the integrated model, ε t It is a preset threshold value, which can be adjusted according to the requirements of specific engineering problems to ensure the accuracy and efficiency of reliability analysis;

[0083] If the conditions are met, the update is stopped; otherwise, the process returns to step S2 to continue updating the proxy model.

[0084] The method for calculating the failure probability is:

[0085]

[0086] Among them, N MC Indicates the number of samples in the sample set MC established by the Monte Carlo method, It indicates marking the number of sample points in the safe and medium range. Its value is determined according to the output of the combined model and can be expressed by the following formula:

[0087]

[0088] Example 2

[0089] This embodiment takes the reliability analysis of steel columns as an example;

[0090] (1) Analyze the composition, function, and working conditions of the steel column structure to be evaluated based on the specifications, design standards, expert opinions, historical data, and other information, determine the failure mode of the steel column structure and the corresponding limit state equation, and obtain the random variables that affect the structural function and their distribution information;

[0091] The limit state equation in this embodiment is expressed as:

[0092]

[0093] Where P is the axial force of the steel column and Pcr is the yield stress;

[0094] PCR is calculated by the following formula:

[0095]

[0096] Where λ represents the control slenderness ratio, F y represents the yield stress, A s represents the cross section of the column;

[0097] In this embodiment, the statistical characteristics of each random variable are shown in Table 1;

[0098] Table 1 Statistical properties of random variables:

[0099] variable name distributed Mean Cov P(kips) Gumbel 200 0.12 λ Lognormal 1.35 0.12 <![CDATA[F y ]]> Normal 36 0.05 <![CDATA[A s ]]> Normal 21.8 0.05

[0100] (2) Use LHS to generate an initial DOE containing N0 = 100 sample points, and train the Kriging model and artificial neural network model. A three-layer structure is used, including 10 hidden layer nodes, using the ReLU activation function, and the sample points in the initial DOE and their corresponding limit state function values are used as training data;

[0101] (3) Calculate the prediction errors of different proxy models on the candidate sample points, calculate the entropy values of different proxy models, set the initial weight factor to 0.5, and then determine the weight of each proxy model;

[0102] (4) Using the MMHDR strategy to search for update points in the candidate sample set, in this embodiment, the seed selection ratio P0 is 0.1;

[0103] (5) Add the updated points to the DOE, retrain the proxy model using the updated DOE, and repeat steps (3) to (5) until the convergence criterion ε is met. t = 0.01 or the maximum number of iterations is 100;

[0104] (6) The reliability index β of the steel column is calculated using the final proxy model, and the entire calculation process is completed.

[0105] The method proposed in this invention is compared with other reliability analysis methods, and the results are shown in Table 2.

[0106] Table 2 Calculation results of steel column example:

[0107]

[0108]

[0109] As can be seen from Table 2, the method proposed in the present invention has obvious advantages in both computational efficiency and accuracy. Figure 5 The iterative process of various reliability methods and the weight changes of individual surrogate models of the two proposed reliability methods are shown. It can be seen from the figure that the proposed method converges faster. When comparing the weights of different surrogate models, it can be observed that in the combined surrogate model, the contribution of ANN is relatively small, while the Kriging model plays a more important role in accurately estimating the failure probability. As the DOE continues to expand, the Kriging model maintains its dominant position.

[0110] Example 3

[0111] This embodiment takes the reliability analysis of an inflatable marine crash barrier structure as an example.

[0112] (1) Analyze the composition, function, and operating conditions of the inflatable offshore crash barrier structure to be evaluated based on the specifications, design standards, expert opinions, historical data, and other information, determine the failure mode of the structure and the corresponding limit state equation, and obtain the random variables that affect the structural function and their distribution information;

[0113] The limit state equation in this embodiment is expressed as:

[0114]

[0115] Wherein, x1 is the thickness of the inflatable marine crash barrier structure, x2 is the primary modulus of the impact load response, x3 is the secondary modulus of the impact load response, x4 is the HSMST full impact stress, and x5 is the HSMST full impact strain. In this embodiment, each variable obeys a normal distribution, and the statistical characteristics are shown in Table 3.

[0116] Table 3 Statistical properties of random variables:

[0117]

[0118]

[0119] (2) Generate an initial DOE with N0 = 200 sample points using LHS; train the Kriging model and artificial neural network model with 20 hidden layer nodes, using the Sigmoid activation function, and using the sample points in the initial DOE and their corresponding limit state function values as training data;

[0120] (3) Calculate the prediction errors of different proxy models on the candidate sample points, calculate the entropy values of different proxy models, set the initial weight factor to 0.5, and then determine the weight of each proxy model;

[0121] (4) Using the MMHDR strategy to search for update points in the candidate sample set, in this embodiment, the seed selection ratio P0 is 0.1;

[0122] (5) Add the updated points to the DOE, retrain the proxy model using the updated DOE, and repeat steps (3) to (5) until the convergence criterion ε is met. t = 0.01 or the maximum number of iterations is 100;

[0123] (6) The final proxy model is used to calculate the reliability index β of the inflatable offshore crash barrier structure, and the entire calculation process is completed.

[0124] The method proposed in this invention is compared with other reliability analysis methods, and the results are shown in Table 4.

[0125] Table 4 Calculation results of offshore inflatable fender sea retaining structure example:

[0126]

[0127]

[0128] It can be seen from the table that the method proposed in the present invention has obvious advantages in both computational efficiency and accuracy. Figure 6The iterative process of various reliability methods and the weight changes of individual agent models of the two proposed reliability methods are shown. It can be seen from the figure that the EWM-MMHDR method converges faster, and the LSF area is quickly identified by the MMHDR method, which significantly improves the efficiency of the reliability method based on the intelligent model. When comparing the weight changes of different agent models in the proposed method, it is noted that the Kriging model initially receives a larger weight at the beginning of the iteration. However, as the DOE becomes more comprehensive, the artificial neural network model plays a more substantial role in the combined model.

[0129] Example 4

[0130] This embodiment proposes a composite material structure reliability analysis system based on an adaptive hybrid surrogate model, based on a composite material structure reliability analysis method based on an adaptive hybrid surrogate model, comprising: a reliability problem definition module, an initial surrogate model construction module, a weight calculation and model integration module, a model optimization module, and a reliability result output module;

[0131] Reliability problem definition module, which is used to determine the distribution type and statistical characteristics of the basic random variables of the composite structure, set the number of sample points of the initial design experiment (DOE), and calculate the actual limit state function value of the initial DOE;

[0132] The initial surrogate model construction module is used to use the current DOE to train surrogate models including Kriging model and artificial neural network ANN model, generate Monte Carlo candidate sample set MC according to the statistical characteristics of random variables, and use different surrogate models to predict sample points in the MC set;

[0133] The weight calculation and model integration module is used to calculate the weights of different proxy models on candidate sample points based on the EWM entropy weight method, combined with the prediction error and entropy value of the proxy model, to achieve adaptive integration of the proxy model and thus obtain a combined model;

[0134] The model optimization module is used to generate a set of conditional sample points based on the Monte Carlo candidate sample set MC using the MMHDR mechanism, search for update points through the learning function, and add the update points to the initial DOE; the proxy model is retrained using the updated DOE, and the accuracy of the current integrated model is judged to meet the requirements based on the preset threshold until the convergence criterion is met or the maximum number of iterations is reached;

[0135] The reliability result output module is used to output the failure probability of the composite structure based on the integrated agent model after the iteration is completed.

[0136] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements a composite material structure reliability analysis method based on an adaptive hybrid agent model.

[0137] A processing terminal includes a memory and a processor. The memory stores a computer program that can be run on the processor. When the processor executes the computer program, a composite material structure reliability analysis method based on an adaptive hybrid agent model is implemented.

[0138] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0139] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one 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 invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A composite material structure reliability analysis method based on an adaptive hybrid surrogate model, characterized in that: The following steps are involved: S1. Determine the distribution type and statistical characteristics of the basic random variables of the composite structure, set the number of sample points for the initial design experiment (DOE), and calculate the actual limit state function value of the initial DOE; S2. Use the current DOE to train surrogate models including Kriging model and artificial neural network (ANN) model, generate Monte Carlo candidate sample set MC according to the statistical characteristics of random variables, and use different surrogate models to predict sample points in the MC set; S3. Based on the EWM entropy weight method, the prediction error and entropy value of the proxy model are combined to calculate the weights of different proxy models on the candidate sample points, realize the adaptive integration of the proxy models, and thus obtain the combined model; S4, using the MMHDR mechanism, i.e., the improved Metropolis–Hastings algorithm with delayed rejection, generates a set of conditional sample points based on the Monte Carlo candidate sample set MC, searches for update points through the learning function, and adds the update points to the initial DOE; S5. Retrain the proxy model using the updated DOE, and determine whether the accuracy of the current integrated model meets the requirements based on a preset threshold. Repeat steps S3 to S5 until the convergence criterion is met or the maximum number of iterations is reached. S6. After the iteration is completed, the failure probability of the composite structure based on the integrated agent model is output.

2. A composite material structure reliability analysis method based on an adaptive hybrid agent model according to claim 1, characterized in that: Step S1 also includes analyzing the composition, function and working conditions of the composite material structure to be evaluated based on the data information of the composite material structure, and determining the failure mode of the structure and the corresponding limit state equation.

3. The composite material structure reliability analysis method based on the adaptive hybrid agent model according to claim 1 is characterized in that: In step S2, when constructing the surrogate model, the predicted values and prediction variances of different surrogate models are calculated using cross-validation and jackknife techniques.

4. The composite material structure reliability analysis method based on the adaptive hybrid agent model according to claim 1, characterized in that: The specific content of step S3 is: The entropy weight is calculated based on the EWM entropy weight method, specifically: Among them, E j is the entropy of the j-th surrogate model, p ij is the ratio of the i-th sample point in the j-th proxy model, k is the number of candidate sample points, N M is the total number of proxy models; Calculate the coefficient of variation G for each model j =1-E j , and calculate the entropy weight factor based on the difference coefficient Calculate the weights of different proxy models on candidate sample points as follows: Among them, e j (x) is the prediction error of the j-th proxy model on the candidate sample point.

5. The composite material structure reliability analysis method based on the adaptive hybrid agent model according to claim 1, characterized in that: In step S4, the MMHDR mechanism is used to generate a conditional sample point set based on the Monte Carlo candidate sample set MC, and the specific content of searching for the update point through the learning function is: S41. Randomly select half of the sample points N1 in the current MC population and their predicted values as the initial subset, and sort the predicted values in ascending order; S42. Select the first P0N1 samples as the seeds for generating the next subset, where P0 is the seed selection ratio, and use the MMHDR strategy to generate N1 conditional sample point sets with a probability density function f(x) based on the selected seeds; S43. Repeat this process until the stopping condition is met, and combine the first reciprocal subset and the second reciprocal subset to search the local range L of the proxy model update point e ; S44. Use U function to filter the local range L e The sample points within the range are obtained, and the updated points are added to the DOE.

6. The composite material structure reliability analysis method based on the adaptive hybrid agent model according to claim 1, characterized in that: In step S5, the judgment condition for whether the accuracy of the current integrated model meets the requirements is: Among them, P f,j is the failure probability estimated by the jth surrogate model, P f is the failure probability calculated by the integrated model, ε t is the preset threshold; If the conditions are met, the update is stopped; otherwise, the process returns to step S2 to continue updating the proxy model.

7. A composite material structure reliability analysis system based on an adaptive hybrid agent model, characterized in that: A composite material structure reliability analysis method based on an adaptive hybrid surrogate model according to any one of claims 1 to 6, comprising: a reliability problem definition module, an initial surrogate model construction module, a weight calculation and model integration module, a model optimization module, and a reliability result output module; Reliability problem definition module, which is used to determine the distribution type and statistical characteristics of the basic random variables of the composite structure, set the number of sample points of the initial design experiment (DOE), and calculate the actual limit state function value of the initial DOE; The initial surrogate model construction module is used to use the current DOE to train surrogate models including Kriging model and artificial neural network ANN model, generate Monte Carlo candidate sample set MC according to the statistical characteristics of random variables, and use different surrogate models to predict sample points in the MC set; The weight calculation and model integration module is used to calculate the weights of different proxy models on candidate sample points based on the EWM entropy weight method, combined with the prediction error and entropy value of the proxy model, to achieve adaptive integration of the proxy model and thus obtain a combined model; The model optimization module is used to generate a set of conditional sample points based on the Monte Carlo candidate sample set MC using the MMHDR mechanism, search for update points through the learning function, and add the update points to the initial DOE; the proxy model is retrained using the updated DOE, and the accuracy of the current integrated model is judged to meet the requirements based on the preset threshold until the convergence criterion is met or the maximum number of iterations is reached; The reliability result output module is used to output the failure probability of the composite material structure based on the integrated agent model after the iteration is completed.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the computer program implements the composite material structure reliability analysis method based on the adaptive hybrid agent model according to any one of claims 1 to 6.

9. A processing terminal comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the computer program, the method for analyzing the reliability of composite material structures based on an adaptive hybrid agent model as described in any one of claims 1 to 6 is implemented.

Images