Ribbed conical shell structure design method, system and equipment based on Bayesian optimization algorithm and medium

Abstract

The invention aims at providing a reinforced conical shell structure design method, system, equipment and medium based on a Bayesian optimization algorithm aiming at challenges of an existing reinforced conical shell structure optimization design method in the aspects of calculation efficiency, resource use and development time, so that the number of finite element simulation evaluation is reduced, and the design efficiency is improved. Therefore, the design period is shortened and resource consumption is reduced. According to the technical scheme, the reinforced conical shell structure design method based on the Bayesian optimization algorithm comprises the specific implementation steps of defining design variables, determining an optimization target, constructing a training sample set, creating N groups of weight vectors, randomly selecting # imgabs0 # group weight vectors, conducting parallel optimization, updating the sample set and judging termination conditions. According to the method, the simulation evaluation frequency is remarkably reduced, and the calculation cost is reduced; the problem of high-dimensional multi-objective optimization in engineering is efficiently solved, and the design precision is improved; through a Pareto optimization strategy, falling into a local optimal solution is effectively avoided; and the design period is shortened.

Description

Technical Field

[0001] The invention relates to the field of ship structure engineering optimization design, and in particular to a method, system, equipment and medium for designing a reinforced conical shell structure based on a Bayesian optimization algorithm. Background Art

[0002] With the continuous progress of marine engineering and ship technology, the demand for lightweight and high-performance ship structures is growing. While ensuring the structural strength and stiffness, how to reduce the weight of the ship structure and improve its load-bearing capacity and fatigue resistance has become a key issue in the field of ship design. As the supporting structure of the shafting system, the vibration characteristics of the reinforced conical shell play a decisive role in the stability and acoustic performance of the entire underwater structure. Due to the particularity of the underwater environment, the vibration generated by the structure when the shafting rotates not only affects its own structural safety, but may also interfere with the acoustic performance such as sonar detection and communication. Therefore, reducing the structural response of the reinforced conical shell structure under the excitation of the shafting rotation is of great significance to improving the overall performance and concealment of the underwater structure. The reinforced conical shell structure, with its unique geometric shape and structural characteristics, has been widely used in key parts such as the hull and deck of the ship.

[0003] The design of a reinforced conical shell requires comprehensive consideration of multiple factors, including material properties, geometric parameters, load conditions, etc., in order to achieve structural optimization. At present, in the design stage of a reinforced conical shell, it is usually necessary to use the finite element analysis method to numerically simulate the mechanical properties of the structure. Although this method can provide relatively accurate simulation results, the calculation process is complicated and consumes a lot of time and computing resources. In addition, multi-objective optimization problems usually require a trade-off between multiple performance indicators, which further increases the complexity of the design process. Traditional multi-objective optimization algorithms, such as multi-objective particle swarm optimization (MOPSO) and multi-objective genetic algorithm (MOGA), can find a set of feasible solutions in some cases, but when faced with high-dimensional, nonlinear, and multi-peak optimization problems, they often require a large number of simulation evaluations and are prone to fall into local optimal solutions. Summary of the invention

[0004] In order to solve the challenges of the prior art in the optimization design method of reinforced conical shell structure in terms of computational efficiency, resource utilization and development time, the present invention proposes a reinforced conical shell structure design method, system, equipment and medium based on a Bayesian optimization algorithm to reduce the number of finite element simulation evaluations, thereby shortening the design cycle and reducing resource consumption.

[0005] The technical solution adopted by the present invention is:

[0006] A design method for a reinforced conical shell structure based on a Bayesian optimization algorithm comprises the following steps:

[0007] Step S1: define the design variables d, which include the size parameters of the stiffener and the plate thickness; the set of design variables is expressed as , the i-th design variable d i The value range is ,in ;

[0008] Step S2: Determine the optimization goal; the optimization goal includes maximizing the overall buckling stress of the structure , minimize the circumferential stress on the mid-surface of the conical shell , minimize the longitudinal stress on the inner surface of the conical shell , minimize the internal stress of the stiffener , and minimize the total weight of the structure ;

[0009] Step S3: according to the value range of the design variable d in step S1, the design variable d is sampled in the design space using a sampling scheme, each sampling point is simulated and calculated using finite element software, the sampling points and the optimization target results are sorted, and a training sample set is constructed;

[0010] Step S4: Create N sets of weight vectors , which is used to subsequently integrate the optimization objectives of multiple reinforced conical shell structures into a single optimization objective; the weight vector is defined in a normalized space; where each component Indicates The weight of the optimization objective;

[0011] Step S5: Randomly select a weight vector from the N groups of weight vectors created in step S4. group the weight vector;

[0012] Step S6: Use the Bayesian optimization algorithm to optimize the randomly selected The weight vectors are optimized in parallel and generated simultaneously candidate sample points;

[0013] Step S7: The generated The candidate sample points are added to the training sample set constructed in step S3, the training sample set is updated, and the simulation design is continued;

[0014] Step S8: Determine whether the stiffened conical shell structure design has reached a preset maximum number of iterations. If yes, output the current Pareto optimal solution; otherwise, re-execute the steps S5 to S8.

[0015] Furthermore, in the parallel optimization in step S6, When there are candidate sample points, the process of generating each candidate sample point is the same, and specifically includes the following steps:

[0016] Step S61: using a weighted sum method to convert the multiple optimization objectives in step S2 into a single scalar value;

[0017] Step S62: constructing a Gaussian process model according to the training sample set created in step S3 and the scalar value obtained in step S61;

[0018] Step S63: Randomly select from the n design variables d in step S1 sub-design variables and based on The sub-design variables generate new subspace design variable sample points;

[0019] Step S64: using the crossover mutation operator of the Bayesian optimization algorithm to calculate the new subspace design variable sample points generated in step S63 to generate new design variable sample points; using the Gaussian process model constructed in step S62 for each of the design variable sample points to calculate the EI value corresponding to each of the design variable sample points;

[0020] Step S65: Determine whether the Bayesian optimization algorithm has reached the maximum number of iterations. If so, take the design variable sample point with the largest EI value as the first The candidate sample points of the optimization process are selected, otherwise, the step S64 to the step S65 are executed again.

[0021] Furthermore, in step S61, the calculation formula for converting the multiple optimization objectives into a single scalar value using the weighted sum method is:

[0022]

[0023] in, Indicates The value of the optimization objective;

[0024] Each portion Indicates The weight of the optimization objective

[0025] is the number of optimization targets.

[0026] Furthermore, in step S63, p≥n / 2.

[0027] Furthermore, the sampling scheme used in step S2 is a Latin hypercube sampling scheme.

[0028] Furthermore, the number of sampling points in step S3 is twice or more than the number of design variables d.

[0029] Furthermore, the preset maximum number of iterations in step S8 is 40 to 200 times.

[0030] Based on the same inventive concept, the present invention also provides a reinforced conical shell structure design system based on the Bayesian optimization algorithm, and implements the aforementioned reinforced conical shell structure design method based on the Bayesian optimization algorithm, including:

[0031] Definition module, the definition module is used to define the design variable d, the design variable d includes the size parameters of the stiffener and the plate thickness; the design variable set is expressed as , the i-th design variable d i The value range is ,in ;

[0032] A determination module is used to determine an optimization target; the optimization target includes maximizing the overall buckling stress of the structure , minimize the circumferential stress on the mid-surface of the conical shell , minimize the longitudinal stress on the inner surface of the conical shell , minimize the internal stress of the stiffener , and minimize the total weight of the structure .

[0033] The sampling and simulation module is used to sample the design variable d in the design space using a sampling scheme according to the value range of the design variable d in step S1, and to perform simulation calculations on each sampling point using finite element software; at the same time, the sampling points and the optimization target results are sorted to construct a training sample set.

[0034] A creation module is used to create N groups of weight vectors , which is used to subsequently integrate the optimization objectives of multiple reinforced conical shell structures into a single optimization objective; the weight vector is defined in a normalized space; where each component Indicates The weight of the optimization objective.

[0035] A selection module is used to randomly select one of the N groups of weight vectors created in step S4. The weight vector is set.

[0036] The optimization module is used to use the Bayesian optimization algorithm to optimize the randomly selected The weight vectors are optimized in parallel and generated simultaneously candidate sample points;

[0037] An update module is used to update the generated The candidate sample points are added to the training sample set constructed in step S3, the training sample set is updated, and the simulation design is continued.

[0038] A judgment module is used to judge whether the design of the reinforced conical shell structure has reached a preset maximum number of iterations. If so, the current Pareto optimal solution is output; otherwise, the selection module, the optimization module and the update module are reused to perform corresponding operations, and the judgment module re-judges.

[0039] Based on the same inventive concept, the present invention also provides a computer device, including: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the aforementioned method for designing a reinforced conical shell structure based on a Bayesian optimization algorithm by executing the computer instructions.

[0040] Based on the same inventive concept, the present invention also provides a computer-readable storage medium, on which computer instructions are stored, and the computer instructions are used to enable a computer to execute the aforementioned method for designing a reinforced conical shell structure based on a Bayesian optimization algorithm.

[0041] The beneficial effects of the present invention are:

[0042] 1. Compared with the prior art, the invention significantly reduces the number of simulation evaluations and reduces the calculation cost.

[0043] 2. The present invention can generate candidate sample points, thereby shortening the design cycle, efficiently handling high-dimensional multi-objective optimization problems in engineering, and improving design accuracy.

[0044] 3. The present invention effectively avoids falling into a local optimal solution through the Pareto optimization strategy, and accelerates the transformation speed of products from concept to market. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in 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 described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 A flowchart of a method for designing a reinforced conical shell structure based on a Bayesian optimization algorithm of the present invention;

[0047] Figure 2 It is a schematic diagram of the finite element constructed for the reinforced conical shell structure according to the present invention;

[0048] Figure 3 This is a hypervolume iteration curve diagram for optimizing the size of the stiffened conical shell according to the present invention. DETAILED DESCRIPTION

[0049] In order to solve the challenges of the prior art in the optimization design method of reinforced conical shell structure in terms of computational efficiency, resource utilization and development time, the present invention proposes a reinforced conical shell structure design method, system, equipment and medium based on a Bayesian optimization algorithm to reduce the number of finite element simulation evaluations, thereby shortening the design cycle and reducing resource consumption.

[0050] The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present invention but not to limit the present invention.

[0051] The present invention will be further described below in conjunction with the accompanying drawings.

[0052] Reference Figure 1 As shown, this embodiment is based on a design method of a reinforced conical shell structure based on a Bayesian optimization algorithm, comprising the following steps:

[0053] Step S1: define the design variables d, which include the size parameters of the stiffener and the plate thickness; the set of design variables is expressed as , the i-th design variable d i The value range is ,in .

[0054] In this embodiment, the design variables of the reinforced conical shell structure include the size parameters of the reinforcement ribs and the plate thickness. The radius of the large end and the radius of the small end of the reinforced conical shell are 5000mm and 3000mm respectively. The conical shell is divided by 11 reinforcement ribs with a spacing of 1000mm. The sizes of these 11 reinforcement ribs are different, and the thickness of the 12 divided plates is different. The elastic modulus of the reinforced conical shell material is , Poisson's ratio is 0.3, and the density is The design variables can be determined as 11 rib size parameters (one rib size parameter has 4 variables) and 12 plate thickness sections. The lower bound of the 4 variables of each rib is [200, 10, 100, 10] mm, the upper bound is [340, 24, 240, 24] mm, and the value range of each plate thickness section is [50, 64] mm.

[0055] Step S2: Determine the optimization target; in this embodiment, there are five performance parameters of the optimization target, including maximizing the overall buckling stress of the structure , minimize the circumferential stress on the mid-surface of the conical shell , minimize the longitudinal stress on the inner surface of the conical shell , minimize the internal stress of the stiffener , and minimize the total weight of the structure The performance parameter values ​​of the optimization target are obtained by simulation analysis of the reinforced conical shell structure using the commercial software ANSYS. Figure 2 A schematic diagram of the finite element simulation is shown.

[0056] Step S3: According to the value range of the design variable d in step S1, the design variable d is sampled in the design space using a Latin hypercube sampling scheme, each sampling point is simulated and calculated using finite element software, the sampling points and the optimization target results are sorted, and a training sample set is constructed.

[0057] Since the number of design variables d of the optimization problem is 56 (the size parameters of the 11 stiffeners described in step S1 * the size parameters of each stiffener have 4 variables + 12 sections of plate thickness), it is a high-dimensional optimization problem. In order to better obtain the optimization result, the number of sampling points in this embodiment is set to 112.

[0058] Step S4: Create N sets of weight vectors , which is used to subsequently integrate the optimization objectives of multiple reinforced conical shell structures into a single optimization objective; the weight vector is defined in a normalized space; where each component Indicates The weight of the optimization objective.

[0059] In this example, the number of weight vectors is set to 20. The number of weight vectors should be set according to the optimization objectives and the structural characteristics of the problem.

[0060] Step S5: Randomly select a weight vector from the N groups of weight vectors created in step S4. The weight vectors are grouped to prepare for the subsequent parallel optimization process.

[0061] In this embodiment, 5 groups of weight vectors are randomly selected from the N groups of weight vectors created in step S4, namely =5, which means that 5 simulation calculations can be run simultaneously. This parameter only represents the setting of this embodiment, and the specific setting value can be appropriately adjusted according to the simulation conditions.

[0062] Step S6: In this embodiment, the Bayesian optimization algorithm is used to optimize the randomly selected The weight vectors are optimized in parallel and generated simultaneously candidate sample points.

[0063] In this embodiment, the parallel optimization process can generate 5 candidate sample points at the same time, thereby shortening the design cycle. To further improve the optimization efficiency, the number of sub-design variables is set to 35 (the number of sub-design variables is greater than half of the number of design variables). The process of generating each candidate sample point is the same, and specifically includes the following steps:

[0064] Step S61: Use a weighted sum method to convert the multiple optimization objectives in step S2 into a single scalar value; the calculation is as follows:

[0065]

[0066] in, Indicates The value of the optimization objective;

[0067] Each portion Indicates The weight of the optimization objective

[0068] is the number of optimization targets.

[0069] In this embodiment, the design variable with the smallest scale value is stored in The minimum scale value is stored in middle.

[0070] Step S62: constructing a Gaussian process model according to the training sample set created in step S3 and the scalar value obtained in step S61.

[0071] Step S63: Randomly select from the n design variables d in step S1 sub-design variables, and generate new subspace design variable sample points based on the p sub-design variables.

[0072] Step S64: Use the crossover mutation operator of the Bayesian optimization algorithm to calculate the new subspace design variable sample points generated in step S63 to generate new design variable sample points; for each of the design variable sample points, use the Gaussian process model constructed in step S62 to calculate the EI value corresponding to each of the design variable sample points.

[0073] In this embodiment, the crossover mutation operator of the genetic algorithm is used to generate new design variable sample points and calculate the EI value of each sample. The calculation of EI is as follows:

[0074]

[0075] and are the predicted value and standard deviation of the Gaussian process model, and They represent the probability density function and cumulative distribution function of the standard normal distribution, is the best scale value for the current optimization process. When calculating the EI value, other sub-variables other than the selected sub-dimension need to be used Corresponding position variable replacement.

[0076] Step S65: Determine whether the Bayesian optimization algorithm has reached a preset maximum number of iterations, such as 30 times; if it has reached 30 times, take the design variable sample point with the largest EI value as the first The candidate sample points of the optimization process are selected, otherwise, the step S64 to the step S65 are executed again.

[0077] Step S7: The parallel optimization generated in step S6 The candidate sample points are added to the training sample set in step S3, the training sample set is updated, and the simulation design is continued to prepare for the next step.

[0078] Step S8: Determine whether the stiffened conical shell structure design has reached a preset maximum number of iterations, such as 40 times; if so, output the current Pareto optimal solution, otherwise re-execute the steps S5 to S8.

[0079] The hypervolume is the volume of the target space area enclosed by the non-dominated solution set obtained by the Bayesian optimization algorithm and the reference point; the larger the hypervolume value, the better the overall performance of the algorithm. In this embodiment, the hypervolume value is used to analyze the optimization results. Figure 3 The hypervolume iteration curve is shown. It can be seen that the parallel multi-objective Bayesian optimization design method can find a set of better solutions in about 17 iterations, which greatly shortens the design cycle compared to the evolutionary algorithm that needs to be calculated thousands of times, and can achieve better optimization results with fewer simulation optimization times.

[0080] This embodiment is based on a reinforced conical shell structure design method based on a Bayesian optimization algorithm, and designs a reinforced conical shell structure design system based on a Bayesian optimization algorithm, including:

[0081] Definition module, the definition module is used to define the design variable d, the design variable d includes the size parameters of the stiffener and the plate thickness; the design variable set is expressed as , the i-th design variable d i The value range is ,in .

[0082] A determination module is used to determine an optimization target; the optimization target includes maximizing the overall buckling stress of the structure , minimize the circumferential stress on the mid-surface of the conical shell , minimize the longitudinal stress on the inner surface of the conical shell , minimize the internal stress of the stiffener , and minimize the total weight of the structure .

[0083] The sampling and simulation module is used to sample the design variable d in the design space using a sampling scheme according to the value range of the design variable d in step S1, and to perform simulation calculations on each sampling point using finite element software; at the same time, the sampling points and the optimization target results are sorted to construct a training sample set.

[0084] A creation module is used to create N groups of weight vectors , which is used to subsequently integrate the optimization objectives of multiple reinforced conical shell structures into a single optimization objective; the weight vector is defined in a normalized space; where each component Indicates The weight of the optimization objective.

[0085] A selection module is used to randomly select one of the N groups of weight vectors created in step S4. The weight vector is set.

[0086] The optimization module is used to use the Bayesian optimization algorithm to optimize the randomly selected The weight vectors are optimized in parallel and generated simultaneously candidate sample points.

[0087] An update module is used to update the generated The candidate sample points are added to the training sample set constructed in step S3, the training sample set is updated, and the simulation design is continued.

[0088] A judgment module is used to judge whether the design of the reinforced conical shell structure has reached a preset maximum number of iterations. If so, the current Pareto optimal solution is output; otherwise, the selection module, the optimization module and the update module are reused to perform corresponding operations, and the judgment module re-judges.

[0089] This embodiment is based on a method for designing a reinforced conical shell structure based on a Bayesian optimization algorithm, and designs a computer device, including: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for designing a reinforced conical shell structure based on a Bayesian optimization algorithm in this embodiment by executing the computer instructions.

[0090] This embodiment is based on a method for designing a reinforced conical shell structure based on a Bayesian optimization algorithm, and designs a computer-readable storage medium. The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute a method for designing a reinforced conical shell structure based on a Bayesian optimization algorithm in this embodiment.

[0091] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention without departing from the principles and purpose of the present invention.

Claims

1. A design method for a reinforced conical shell structure based on a Bayesian optimization algorithm, characterized in that: The following steps are involved: Step S1: defining a design variable d, wherein the design variable d includes the size parameters of the stiffener and the plate thickness; The set of design variables is expressed as , the i-th design variable The value range is ,in ; Step S2: Determine the optimization goal; the optimization goal includes maximizing the overall buckling stress of the structure , minimize the circumferential stress on the mid-surface of the conical shell , minimize the longitudinal stress on the inner surface of the conical shell , minimize the internal stress of the stiffener , and minimize the total weight of the structure ; Step S3: according to the value range of the design variable d in step S1, the design variable d is sampled in the design space using a sampling scheme, each sampling point is simulated and calculated using finite element software, the sampling points and the optimization target results are sorted, and a training sample set is constructed; Step S4: Create N sets of weight vectors , which is used to subsequently integrate the optimization objectives of multiple reinforced conical shell structures into a single optimization objective; the weight vector is defined in a normalized space; where each component Indicates The weight of the optimization objective; Step S5: Randomly select a weight vector from the N groups of weight vectors created in step S4. group the weight vector; Step S6: Use the Bayesian optimization algorithm to optimize the randomly selected The weight vectors are optimized in parallel and generated simultaneously Candidate sample points; Step S7: The generated The candidate sample points are added to the training sample set constructed in step S3, the training sample set is updated, and the simulation design is continued; Step S8: Determine whether the stiffened conical shell structure design has reached a preset maximum number of iterations. If yes, output the current Pareto optimal solution; otherwise, re-execute the steps S5 to S8.

2. A method for designing a reinforced conical shell structure based on a Bayesian optimization algorithm according to claim 1, characterized in that: In the parallel optimization in step S6, at the same time When there are candidate sample points, the process of generating each candidate sample point is the same, and specifically includes the following steps: Step S61: using a weighted sum method to convert the multiple optimization objectives in step S2 into a single scalar value; Step S62: constructing a Gaussian process model according to the training sample set created in step S3 and the scalar value obtained in step S61; Step S63: Randomly select from the n design variables d in step S1 sub-design variables and based on The sub-design variables generate new subspace design variable sample points; Step S64: using the crossover mutation operator of the Bayesian optimization algorithm to calculate the new subspace design variable sample points generated in step S63 to generate new design variable sample points; using the Gaussian process model constructed in step S62 for each of the design variable sample points to calculate the EI value corresponding to each of the design variable sample points; Step S65: Determine whether the Bayesian optimization algorithm has reached the maximum number of iterations. If so, take the design variable sample point with the largest EI value as the first The candidate sample points of the optimization process are selected, otherwise, the step S64 to the step S65 are executed again.

3. A method for designing a reinforced conical shell structure based on a Bayesian optimization algorithm according to claim 2, characterized in that: The calculation formula for converting the multiple optimization objectives into a single scalar value using the weighted sum method in step S61 is: in, Indicates The value of the optimization objective; Each portion Indicates The weight of the optimization objective is the number of optimization targets.

4. The method for designing a reinforced conical shell structure based on a Bayesian optimization algorithm according to claim 2, characterized in that: In step S63, p≥n / 2.

5. The method for designing a reinforced conical shell structure based on a Bayesian optimization algorithm according to claim 1, characterized in that: The sampling scheme used in step S2 is the Latin hypercube sampling scheme.

6. The method for designing a reinforced conical shell structure based on a Bayesian optimization algorithm according to claim 1, characterized in that: The number of sampling points in step S3 is twice or more than the number of design variables d.

7. The method for designing a reinforced conical shell structure based on a Bayesian optimization algorithm according to claim 1, characterized in that: The preset maximum number of iterations in step S8 is 40 to 200 times.

8. A reinforced conical shell structure design system based on Bayesian optimization algorithm, implementing a reinforced conical shell structure design method based on Bayesian optimization algorithm as claimed in any one of claims 1 to 7, characterized in that: include: A definition module, wherein the definition module is used to define a design variable d, wherein the design variable d includes a size parameter of a stiffener and a plate thickness; The set of design variables is expressed as , the i-th design variable d i The value range is ,in ; A determination module is used to determine an optimization target; the optimization target includes maximizing the overall buckling stress of the structure , minimize the circumferential stress on the mid-surface of the conical shell , minimize the longitudinal stress on the inner surface of the conical shell , minimize the internal stress of the stiffener , and minimize the total weight of the structure ; A sampling and simulation module, wherein the sampling and simulation module is used to sample the design variable d in the design space using a sampling scheme according to the value range of the design variable d in step S1, and to perform simulation calculations on each sampling point using finite element software; At the same time, the sampling points and the optimization target results are sorted to construct a training sample set; A creation module is used to create N groups of weight vectors , which is used to subsequently integrate the optimization objectives of multiple reinforced conical shell structures into a single optimization objective; the weight vector is defined in a normalized space; where each component Indicates The weight of the optimization objective; A selection module is used to randomly select one of the N groups of weight vectors created in step S4. group the weight vector; The optimization module is used to use the Bayesian optimization algorithm to optimize the randomly selected The weight vectors are optimized in parallel and generated simultaneously Candidate sample points; An update module is used to update the generated The candidate sample points are added to the training sample set constructed in step S3, the training sample set is updated, and the simulation design is continued; A judgment module is used to judge whether the design of the reinforced conical shell structure has reached a preset maximum number of iterations. If so, the current Pareto optimal solution is output; otherwise, the selection module, the optimization module and the update module are reused to perform corresponding operations, and the judgment module re-judges.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method for designing a reinforced conical shell structure based on a Bayesian optimization algorithm as described in any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute a reinforced conical shell structure design method based on a Bayesian optimization algorithm as described in any one of claims 1 to 7.

Images