A multi-level variable hybrid optimization method for a radial force thermal wing structure of an aircraft

Abstract

The application belongs to the field of high-speed aircraft structure design, and discloses a multistage variable hybrid optimization method for a radial force-heat wing structure of an aircraft, comprising the following steps: obtaining a structure original configuration to obtain an original base structure; establishing a multistage variable hybrid optimization model, using a genetic algorithm to perform multistage variable hybrid optimization on the original base structure, and obtaining an optimal structure when an objective function of the multistage variable hybrid optimization model tends to be stable; judging whether the obtained optimal structure meets a design target, outputting a final structure if the design target is met, otherwise, changing a constraint condition to restructure the multistage variable hybrid optimization model for continuous optimization, and outputting a final structure meeting the design target. The application simultaneously considers a bearing / heat transport integrated path, increases optimization variables of a beam section shape and a heat transport structure size, completes multistage variable hybrid optimization, improves bearing and heat transport capacity of the aircraft structure, and realizes performance improvement of the radial beam type wing structure under typical force-heat load.

Description

Technical Field

[0001] This invention belongs to the field of high-speed aircraft structural design and relates to a multi-level variable hybrid optimization method for radial force-thermal wing structures of aircraft. Background Technology

[0002] In the design of high-speed aircraft, low-aspect-ratio wing structures are widely used due to their advantages in aerodynamic performance and attitude control. These structures not only play a crucial role in lift and aerodynamic attitude control but must also withstand intense aerodynamic and thermal loads under extreme flight conditions. Achieving structural lightweighting is a key objective in aircraft structural design to improve payload and mission performance, as it directly affects fuel efficiency and range. However, this lightweighting strategy inevitably leads to a reduction in structural stiffness, which in turn exacerbates aeroelastic effects—the deformation and vibration of the structure under aerodynamic loads. Therefore, aeroelasticity must be comprehensively considered in wing structure design to ensure the stability and safety of the structure during high-speed flight.

[0003] Traditional thermal protection systems face significant challenges in dealing with the extreme thermal environments of high-speed flight. While these systems can protect aircraft from high-temperature damage to some extent, their performance is often limited when faced with complex and variable thermal environments.

[0004] Traditional aircraft structural optimization design typically employs a hierarchical optimization strategy, separating layout and dimensional optimization, performing layout optimization first and then dimensional optimization. However, this approach ignores the correlation between optimization variables, limits the optimization design space, and reduces optimization effectiveness. Especially for aircraft with complex radial structures, the traditional base structure method requires a large number of pre-defined base structures, which not only increases the number of variables in the optimization process but also prolongs the optimization time and reduces design efficiency. Summary of the Invention

[0005] The purpose of this invention is to provide a multi-level variable hybrid optimization method for the radial force-thermal wing structure of an aircraft, which solves the problem of low optimization effect and efficiency of existing aircraft structures.

[0006] To achieve the above objectives, the present invention employs the following technical solution: A multi-level variable hybrid optimization method for a radial force-thermal wing structure of an aircraft, comprising: Obtain the original configuration of the structure to obtain the original base structure; A multi-level variable hybrid optimization model is established, and a genetic algorithm is used to perform multi-level variable hybrid optimization on the original base structure. When the objective function of the multi-level variable hybrid optimization model tends to stabilize, the optimal structure is obtained. Determine whether the obtained optimal structure meets the design objective. If it does, output the final structure. Otherwise, change the constraints, reconstruct the multi-level variable hybrid optimization model, and continue optimization to output the final structure that meets the design objective.

[0007] Furthermore, the objective function of the multi-level variable mixed optimization model is:

[0008] Among them, X T X is the topological variable of the structural component. A X is the angle variable of the structural component. IS X represents the dimensional variable of the structural component. IH Let the shape variable be the height factor, X IW X is the width factor. t LB is the width of the web of the I-beam; IS X is the dimension variable of the I-beam flange. IS Lower bound of value, UB IS LB represents the upper limit of the possible values. IW X is the dimensional variable of the web of the I-beam. IW Lower bound of value, UB IW LB represents the upper limit of the possible values. IH X is the height variable of the web of the I-beam. IH Lower bound of value, UB IH The upper limit of the value is denoted by Ms; Ms represents the total mass constraint of the wing surface load-bearing structure, heat transport structure, skin structure, thermal insulation structure, and wing root joint.

[0009] Furthermore, the design variables of the multi-level variable hybrid optimization model include the number, size, angle, beam cross-sectional shape, and heat transport structure dimensions of the wing spars.

[0010] Furthermore, the constraints of the multi-level variable hybrid optimization model include stress extrema, maximum tip displacement, structural mass, maximum and average temperatures under thermal conditions, beam angle range, beam flange and heat transport structure size range, beam web height range, and beam web size range.

[0011] Furthermore, the genetic algorithm includes: Based on the base structure, the optimization variables are chromosome-encoded, and binary strings are randomly generated as the initial population. Structural analysis is performed on the initial population to generate the offspring population; Decode the individuals in the offspring population, and reduce the population size by evaluating the fitness of the RBF neural network surrogate model to obtain the reduced offspring population. The reduced offspring population is decoded, a corresponding structural geometric model is constructed, a numerical model is generated according to the design goal, and the structural analysis results of each individual in the population are obtained through numerical analysis. Evaluate the fitness of the structure corresponding to each individual in the population, and output the optimal structure based on the multi-level variable mixture optimization objective.

[0012] Furthermore, the structural analysis method for the initial population is as follows: Fitness assessments were performed on different individuals in the initial population. Individuals with good fitness were selected, and their individual values ​​were decomposed into strings corresponding to different levels of design variables through variable decomposition. Crossover and mutation operations were then performed on each string to generate a new offspring population.

[0013] Furthermore, the method for reducing the population size is as follows: Decode the individuals in the offspring population, convert the individual's encoding string into the corresponding structural design variable, input the design variable into the RBF neural network surrogate model, obtain the predicted fitness function of the individuals in the population, evaluate and rank the individuals in the population according to the predicted target fitness function, and remove individuals with poor fitness performance in the population according to the target population size reduction value.

[0014] A multi-level variable hybrid optimization system for a radial force-thermal wing structure of an aircraft includes: The acquisition module is used to acquire the original configuration of the structure and obtain the original base structure; The optimization module is used to establish a multi-level variable hybrid optimization model, and to use a genetic algorithm to perform multi-level variable hybrid optimization on the original base structure. When the objective function of the multi-level variable hybrid optimization model tends to stabilize, the optimal structure is obtained. The judgment module is used to determine whether the obtained optimal structure meets the design goal. If it meets the design goal, the final structure is output; otherwise, the constraints are changed and a multi-level variable hybrid optimization model is reconstructed to continue optimization and output the final structure that meets the design goal.

[0015] A terminal device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method.

[0016] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method.

[0017] Compared with the prior art, the present invention has the following beneficial effects: This invention provides a multi-level variable hybrid optimization method for radial force-thermal wing structures of aircraft. By establishing a multi-level variable hybrid optimization model, a genetic algorithm is used to perform multi-level variable hybrid optimization on the original base structure. A surrogate model is used to predict the offspring population, quickly obtaining its predicted fitness function value, eliminating individuals with low fitness, reducing the computational load of the precise model, decreasing optimization costs, and improving optimization efficiency. Unlike existing hybrid optimization methods that consider aeroelasticity, this invention simultaneously considers the integrated load-bearing / heat transport path, adding optimization variables for beam cross-sectional shape and heat transport structure dimensions, completing multi-level variable hybrid optimization, reducing the aeroelastic influence of high-speed aircraft, improving the load-bearing and heat transport capabilities of the aircraft structure, and achieving performance improvement of radial beam wing structures under typical force and thermal loads. This provides important reference for quality assessment in the overall design stage of aircraft and preliminary design of aircraft structures, possessing significant academic value and application prospects.

[0018] Furthermore, the heat transport structure of this invention transfers heat from high-temperature regions to low-temperature regions using highly thermally conductive materials, effectively reducing the structure's maximum temperature and achieving a uniform temperature distribution. Combining the heat transport structure with a thermal insulation and protection system can more effectively cope with complex thermal environments and meet the thermal protection requirements of high-speed aircraft. Attached Figure Description

[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart of the multi-level variable hybrid optimization method for the radial force-thermal wing structure of an aircraft according to the present invention.

[0021] Figure 2 This is a flowchart of the multi-level variable hybrid optimization program of the present invention.

[0022] Figure 3 This is a schematic diagram showing the detailed shape of the I-beam cross-section of the present invention.

[0023] Figure 4 This is a diagram of the optimal radial individual structure of the present invention.

[0024] Figure 5 This is a schematic diagram of a multi-level variable hybrid optimization system for a radial force-thermal wing structure of an aircraft, according to a preferred embodiment of the present invention.

[0025] Figure 6This is a schematic diagram of the electronic device structure according to a preferred embodiment of the present invention. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0027] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0028] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of this application, including various details to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this application. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0029] Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of this application.

[0030] It should be noted that the terminals involved in the embodiments of this application may include, but are not limited to, mobile phones, personal digital assistants (PDAs), wireless handheld devices, tablet computers, personal computers (PCs), MP3 players, MP4 players, wearable devices (e.g., smart glasses, smartwatches, smart bracelets), smart home devices, and other smart devices.

[0031] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0032] The present invention will now be described in further detail with reference to the accompanying drawings: See Figure 1 This invention provides a multi-level variable hybrid optimization method for a radial force-thermal wing structure of an aircraft, specifically including the following steps: Step 1: Structural Configuration. Determine the original structural configuration, including structural dimensions, shape, and initial layout of the base structure.

[0033] Step 2: Structural optimization. Establish a multi-level variable hybrid optimization model.

[0034] For the hybrid optimization of structural topology, dimensions, angles, beam cross-sectional shape, and heat transport structure dimensions based on static aeroelasticity, the following optimization model is established:

[0035] In the formula, X T These are the topology variables for structural components, including 19 topology variables X. T A topology of (0 or 1), taking values ​​of 0 or 1; X A For the angular variables of structural components, the dimension is related to X. T Same, with values ​​ranging from 0° to 180°; X IS For the dimensional variables of structural components, the dimension is related to X. T The values ​​are the same, ranging from 0.5 to 20 mm; the shape variable is the height factor X. IH and width factor X IW , where X IH and X IW The values ​​are all between 0 and 1; for example Figure 3 As shown, the height h of the web of the I-beam is determined by the beam section height H and the height factor X. IH The web width IW is obtained by multiplication, while the web width X is obtained by multiplying. IS and width factor X IW The result is obtained by multiplication. The heat transport structure is described by three variables: length, height, and width. The length is equal to the beam length, determined by the wing's aerodynamic shape; the height is equal to the web height h of the I-beam; and the width is X. t The main design variable is X. The heat transport structure is evenly distributed on both sides of the web, with a single-side width of X. t / 2 LB IS X is the dimension variable of the I-beam flange. IS Lower bound of value, UB IS LB represents the upper limit of the possible values. IW X is the dimensional variable of the web of the I-beam. IW Lower bound of value, UB IW LB represents the upper limit of the possible values. IH X is the height variable of the web of the I-beam. IH Lower bound of value, UB IH M represents the upper limit of the possible values. sThe total mass constraint is defined for the wing surface load-bearing structure, heat transport structure, skin structure, thermal insulation structure, and wing root joint.

[0036] Objective function: Minimize the aeroelastic effects of the wing; Design variables: number, size, angle, beam cross-sectional shape, and dimensions of the heat transport structure; Constraints include: stress extremes, maximum tip displacement, structural mass, maximum and average temperatures under thermal conditions, beam angle range, beam flange and heat transport structure dimension range, beam web height range, and beam web dimension range.

[0037] Based on the above objective function, a structural optimization process is established, such as... Figure 2 As shown. A new model is generated by modifying the number, size, angle, beam cross-sectional shape, and heat transport structure dimensions of the base structure configuration. Its aeroelastic properties are analyzed, and the optimization objective is to minimize the aeroelastic influence under given constraints. The variable parameters are modified multiple times until the optimal structure is obtained.

[0038] Initialization: Based on the base structure, the optimization variables are chromosomally encoded. The chromosome for the hybrid optimization of structural topology, size, angle, beam cross-section shape, and heat transport structure size includes topology variables, size variables, angle variables, beam cross-section shape variables, and heat transport structure size variables. Topology variables are variables with values ​​of 0 and 1: a value of 1 indicates the existence of the structure; a value of 0 indicates the absence of the structure. Size variables, angle variables, beam cross-section shape variables, and heat transport structure size variables are continuous variables within a given range. A set of binary strings is randomly generated as the initial population according to the predetermined base structure form and encoding method.

[0039] Population Operations: Since the initial population in the first generation has not yet obtained fitness function values ​​for its individuals, this module is skipped, and the process proceeds directly to "Structural Analysis." For populations that have obtained fitness values ​​after "Convergence Judgment," fitness is evaluated based on the different individuals in the population, and individuals with better fitness performance are selected. The string is decomposed into strings corresponding to different levels of design variables through variable decomposition. Crossover and mutation operations are performed separately for each design variable, with independent operations between different design variables that do not affect each other. A completely new offspring population is generated, in which individuals inherit the "high fitness" gene from the initial population and are generated through crossover and mutation.

[0040] Population Reduction: Based on the established database, an RBF neural network surrogate model is trained. Individuals in the generated population are decoded, converting their encoded strings into corresponding structural design variables. These design variables are input into the established RBF neural network surrogate model to obtain the predicted fitness function for each individual. Individuals in the population are evaluated and ranked according to the predicted objective function. A certain number of individuals with poor fitness are removed according to a set population reduction value, and the individuals with better fitness are entered into the "Structure Analysis" module for precise model analysis. Furthermore, the structural performance data obtained from "Structure Analysis" is also added to the sample database after fitness evaluation to update the surrogate model and further improve its accuracy.

[0041] Structural analysis: Decode the offspring population, convert the individual strings into corresponding design variables with physical meaning, and construct the corresponding structural geometric model; apply external loads and boundary conditions according to the given flight environment to generate a numerical model; conduct numerical analysis; and obtain the structural analysis results for each individual in the population.

[0042] Convergence criterion: This invention selects the number of generations of population evolution as the convergence criterion for the optimization framework, or the optimization program can be manually terminated when the objective function is observed to be stable.

[0043] Step 3: Output the structure.

[0044] like Figure 4 As shown, check whether the optimization result meets the design requirements, and output the optimal structure from step two. If the design objective is met, output the final structure. Otherwise, change the constraints, reconstruct the optimization model, and repeat step two until a result that meets the design objective is obtained, and then output the final result.

[0045] Another object of the present invention is to provide a multi-level variable hybrid optimization system for the radial force-thermal wing structure of an aircraft, such as... Figure 5 As shown, an embodiment of the system includes: an acquisition module, an optimization module, and a judgment module.

[0046] The acquisition module is used to acquire the original configuration of the structure and obtain the original base structure; The optimization module is used to establish a multi-level variable hybrid optimization model, and to use a genetic algorithm to perform multi-level variable hybrid optimization on the original base structure. When the objective function of the multi-level variable hybrid optimization model tends to stabilize, the optimal structure is obtained. The judgment module is used to determine whether the obtained optimal structure meets the design goal. If it meets the design goal, the final structure is output; otherwise, the constraints are changed and a multi-level variable hybrid optimization model is reconstructed to continue optimization and output the final structure that meets the design goal.

[0047] It is understood that the multi-level variable hybrid optimization system for the radial force-thermal wing structure of an aircraft provided by the present invention corresponds to the multi-level variable hybrid optimization method for the radial force-thermal wing structure of an aircraft provided in the foregoing embodiments. The relevant technical features of the multi-level variable hybrid optimization system for the radial force-thermal wing structure of an aircraft can be referred to the relevant technical features of the multi-level variable hybrid optimization method for the radial force-thermal wing structure of an aircraft, and will not be repeated here.

[0048] A third objective of this invention is to provide an electronic device, such as... Figure 6 As shown, it includes a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the steps of the multi-level variable hybrid optimization method for the radial force-thermal wing structure of the aircraft.

[0049] The multi-level variable hybrid optimization method for the radial force-thermal wing structure of the aircraft includes the following steps: Obtain the original configuration of the structure to obtain the original base structure; A multi-level variable hybrid optimization model is established, and a genetic algorithm is used to perform multi-level variable hybrid optimization on the original base structure. When the objective function of the multi-level variable hybrid optimization model tends to stabilize, the optimal structure is obtained. Determine whether the obtained optimal structure meets the design objective. If it does, output the final structure. Otherwise, change the constraints, reconstruct the multi-level variable hybrid optimization model, and continue optimization to output the final structure that meets the design objective.

[0050] A fourth objective of this invention is to provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the multi-level variable hybrid optimization method for the radial force-thermal wing structure of the aircraft.

[0051] The multi-level variable hybrid optimization method for the radial force-thermal wing structure of the aircraft includes the following steps: Obtain the original configuration of the structure to obtain the original base structure; A multi-level variable hybrid optimization model is established, and a genetic algorithm is used to perform multi-level variable hybrid optimization on the original base structure. When the objective function of the multi-level variable hybrid optimization model tends to stabilize, the optimal structure is obtained. Determine whether the obtained optimal structure meets the design objective. If it does, output the final structure. Otherwise, change the constraints, reconstruct the multi-level variable hybrid optimization model, and continue optimization to output the final structure that meets the design objective.

[0052] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0053] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0054] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0055] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable apparatus for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0056] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

[0057] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A multi-level variable hybrid optimization method for a radial force-thermal wing structure of an aircraft, characterized in that, include: Obtain the original configuration of the structure to obtain the original base structure; A multi-level variable hybrid optimization model is established, and a genetic algorithm is used to perform multi-level variable hybrid optimization on the original base structure. When the objective function of the multi-level variable hybrid optimization model tends to stabilize, the optimal structure is obtained. Determine whether the obtained optimal structure meets the design goal. If it does, output the final structure. Otherwise, change the constraints, reconstruct the multi-level variable hybrid optimization model, and continue to optimize. Output the final structure that meets the design goal. The objective function of the multi-level variable mixed optimization model is: Among them, X T X is the topological variable of the structural component. A X is the angle variable of the structural component. IS X represents the dimensional variable of the structural component. IH Let the shape variable be the height factor, X IW X is the width factor. t LB is the width of the web of the I-beam; IS X is the dimension variable of the I-beam flange. IS Lower bound of value, UB IS LB represents the upper limit of the possible values. IW X is the dimensional variable of the web of the I-beam. IW Lower bound of value, UB IW LB represents the upper limit of the possible values. IH X is the height variable of the web of the I-beam. IH Lower bound of value, UB IH The upper limit of the value is denoted by Ms; Ms represents the total mass constraint of the airfoil load-bearing structure, heat transport structure, skin structure, thermal insulation structure, and airfoil root joint. The design variables of the multi-level variable hybrid optimization model include the number, size, angle, beam cross-sectional shape, and heat transport structure dimensions of the wing spars; The constraints of the multi-level variable hybrid optimization model include stress extrema, maximum tip displacement, structural mass, maximum and average temperatures under thermal conditions, beam angle range, beam flange and heat transport structure size range, beam web height range, and beam web size range.

2. The multi-level variable hybrid optimization method for a radial force-thermal wing structure of an aircraft according to claim 1, characterized in that, The genetic algorithm includes: Based on the base structure, the optimization variables are chromosome-encoded, and binary strings are randomly generated as the initial population. Structural analysis is performed on the initial population to generate the offspring population; Decode the individuals in the offspring population, and reduce the population size by evaluating the fitness of the RBF neural network surrogate model to obtain the reduced offspring population. The reduced offspring population is decoded, a corresponding structural geometric model is constructed, a numerical model is generated according to the design goal, and the structural analysis results of each individual in the population are obtained through numerical analysis. Evaluate the fitness of the structure corresponding to each individual in the population, and output the optimal structure based on the multi-level variable mixture optimization objective.

3. The multi-level variable hybrid optimization method for a radial force-thermal wing structure of an aircraft according to claim 2, characterized in that, The structural analysis method for the initial population is as follows: Fitness assessments were performed on different individuals in the initial population. Individuals with good fitness were selected, and their individual values ​​were decomposed into strings corresponding to different levels of design variables through variable decomposition. Crossover and mutation operations were then performed on each string to generate a new offspring population.

4. The multi-level variable hybrid optimization method for a radial force-thermal wing structure of an aircraft according to claim 2, characterized in that, The method for reducing the population size is as follows: Decode the individuals in the offspring population, convert the individual's encoding string into the corresponding structural design variable, input the design variable into the RBF neural network surrogate model, obtain the predicted fitness function of the individuals in the population, evaluate and rank the individuals in the population according to the predicted target fitness function, and remove individuals with poor fitness performance in the population according to the target population size reduction value.

5. A multi-level variable hybrid optimization system for a radial force-thermal wing structure of an aircraft, used to implement the steps of the method described in claim 1, characterized in that, include: The acquisition module is used to acquire the original configuration of the structure and obtain the original base structure; The optimization module is used to establish a multi-level variable hybrid optimization model, and to use a genetic algorithm to perform multi-level variable hybrid optimization on the original base structure. When the objective function of the multi-level variable hybrid optimization model tends to stabilize, the optimal structure is obtained. The judgment module is used to determine whether the obtained optimal structure meets the design goal. If it meets the design goal, the final structure is output; otherwise, the constraints are changed and a multi-level variable hybrid optimization model is reconstructed to continue optimization and output the final structure that meets the design goal.

6. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 4.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 4.

Images