Automatic optimization method and system for high-reliability brush type sealing structure

Abstract

The invention relates to the technical field of aero-engine sealing, in particular to an automatic optimization method, system and equipment for a high-reliability brush type sealing structure, a medium and a program product. Obtaining a performance index of the brush type sealing structure corresponding to the geometric parameters of each group of grooves; constructing an agent model, and performing training; iteratively optimizing the groove geometric parameters of the database to obtain optimal groove geometric parameters; and an optimized brush type sealing structure is designed. The brush type sealing structure is automatically designed, manual intervention is reduced, and the design efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of aero-engine sealing technology, specifically to a method, system, equipment, medium, and program product for automatic optimization of a high-reliability brush seal structure. Background Technology

[0002] Brush seals, as a highly efficient sealing technology, are widely used in aero engines, gas turbines, and other high-speed rotating machinery operating under high-temperature and high-pressure environments. Their main advantages are effectively reducing leakage, withstanding high-temperature and high-pressure conditions, and providing high sealing stability and a long service life.

[0003] However, brush seals still face some challenges in practical applications, especially under high temperature, high pressure, and high swirling conditions. The following application difficulties exist: Under high temperature conditions, the brush filaments and sealing ring undergo significant thermal expansion, leading to structural deformation and changes in frictional properties. Secondly, under high swirling conditions, the brush filaments are prone to circumferential slippage, resulting in decreased stability or even seal failure. Furthermore, the complex geometry of brush seals, including the arrangement, length, and angle of the brush filaments, directly affects sealing performance. The more complex geometry of brush seals, especially when considering fluid dynamics and thermodynamic effects, significantly increases the design workload.

[0004] In the design and optimization of brush seals, existing technologies often require computational fluid dynamics (CFD) methods to evaluate seal performance, especially when considering factors such as fluid-structure interaction, temperature gradients, and pressure changes. Due to the complexity of brush seal structures, traditional CFD simulations often require fine mesh generation and lengthy calculations, resulting in high computational costs and a large workload, thus affecting design efficiency.

[0005] Therefore, there is a need to provide a highly reliable automatic optimization method and system for brush seal structures to solve the above problems. Summary of the Invention

[0006] To address the problem that existing CFD simulation technologies often require detailed mesh generation and lengthy calculations in brush seal design and optimization, resulting in high computational costs and heavy workloads that affect design efficiency, this invention provides a highly reliable automatic optimization method and system for brush seal structures. The aim is to improve the performance of brush seals, reduce computational costs, shorten optimization time, and enhance the design accuracy and reliability of the seal structure by optimizing the design process.

[0007] The first aspect of this invention provides an automatic optimization method for a high-reliability brush seal structure, the method employing the following technical solution, including: Design a through groove on the original brush seal front baffle and determine the groove geometry parameters; Multiple sets of groove geometric parameters are obtained based on a preset range of groove geometric parameters, and the performance indicators of the brush seal structure corresponding to each set of groove geometric parameters are obtained. The performance indicators include: sealing leakage rate and swirling velocity upstream of the brush filament bundle. A database is constructed using the geometric parameters of each set of slots and their corresponding performance indicators; a proxy model is constructed, and the proxy model is trained based on the database to obtain a trained target proxy model; Based on the target proxy model, the swirling velocity and sealing leakage rate upstream of the brush filament bundle in the performance indicators are optimized. The multi-objective optimization algorithm is used to iteratively optimize the groove geometry parameters in the database. The database is updated according to the groove geometry parameters generated after each iteration and their corresponding swirling velocity and sealing leakage rate upstream of the brush filament bundle until the swirling velocity and sealing leakage rate upstream of the brush filament bundle are minimized. The optimal groove geometry parameters are the set of groove geometric parameters that minimize both the swirling velocity and the sealing leakage rate upstream of the brush filament bundle. Based on the optimal groove geometry parameters, the optimized brush seal structure is designed.

[0008] A further technical solution of the present invention is that the groove geometric parameters include: groove width, groove length, groove spacing, groove inclination angle, and groove depth.

[0009] A further technical solution of the present invention is to use the Latin cube sampling method to sample from a preset range of groove geometric parameters to generate multiple sets of groove geometric parameters.

[0010] A further technical solution of the present invention is that the step of obtaining the performance index of the brush seal structure corresponding to each set of groove geometric parameters is as follows: Automated simulation models of the brush seal structure corresponding to the geometric parameters of each set of grooves are generated. Mesh generation is performed on the simulation model of the brush seal structure; Numerical simulation calculations were performed on the simulation model of the brush seal structure after meshing to obtain the performance indicators of the brush seal structure corresponding to the geometric parameters of each set of grooves.

[0011] A further technical solution of the present invention is that, when performing mesh generation on the simulation model of the brush seal structure, a local densification strategy is applied to the brush filament region of the brush seal structure to generate the mesh.

[0012] A further technical solution of the present invention is that the multi-objective optimization algorithm is a Bayesian optimization algorithm.

[0013] A second aspect of the present invention provides a high-reliability automatic optimization system for brush seal structures, comprising: The parameter acquisition module is used to design through grooves on the original brush seal front baffle and determine the groove geometry parameters. The numerical simulation module is used to obtain multiple sets of groove geometric parameters based on a preset range of groove geometric parameters, and to obtain the performance indicators of the brush seal structure corresponding to each set of groove geometric parameters. The performance indicators include: seal leakage rate and swirl velocity upstream of the brush filament bundle. The surrogate model building module is used to build a database with each set of slot geometry parameters and its corresponding performance indicators; build surrogate models; and train the surrogate models based on the database to obtain the trained target surrogate model. The multi-objective optimization module is used to optimize the groove geometry parameters in the database based on the objective proxy model, with the swirling velocity and sealing leakage rate of the upstream of the brush filament bundle as the optimization objectives. The multi-objective optimization algorithm is used to iteratively optimize the groove geometry parameters in the database. The database is updated according to the groove geometry parameters generated after each iteration and their corresponding swirling velocity and sealing leakage rate upstream of the brush filament bundle, until the swirling velocity and sealing leakage rate upstream of the brush filament bundle are minimized. The set of groove geometry parameters corresponding to the minimum swirling velocity and sealing leakage rate upstream of the brush filament bundle is taken as the optimal groove geometry parameters. The optimal structure design module is used to design an optimized brush seal structure based on the optimal groove geometry parameters.

[0014] A third aspect of the present invention provides an electronic device, a processor, a memory, and a computer program stored in the memory, wherein the computer program, when executed by the processor, implements the steps of the automatic optimization method for a high-reliability brush seal structure provided in the first aspect of the present invention.

[0015] A fourth aspect of the present invention provides a program product comprising a computer program, which, when run, performs the steps of a highly reliable automatic optimization method for a brush seal structure provided in the first aspect of the present invention.

[0016] A fifth aspect of the invention provides a storage medium having a computer program stored thereon, which, when run, performs the steps of a highly reliable automatic optimization method for a brush seal structure provided in the first aspect of the invention.

[0017] The beneficial effects of this invention are: Compared to traditional manual design and testing processes, this invention first establishes a surrogate model, replacing the costly CFD simulation process, significantly reducing computation time and hardware resource consumption, and improving optimization efficiency. In this invention, the swirling velocity upstream of the brush filament bundle and the sealing leakage rate are used as optimization objectives. Based on the groove geometry parameters of the brush seal's front baffle, a multi-objective optimization algorithm is used for global optimization to obtain a brush seal structure that improves leakage and swirling flow. In other words, this invention automates the design of the brush seal structure, reducing manual intervention and improving design efficiency. The use of a Bayesian optimization strategy can find the optimal design within a limited number of simulations, ensuring high accuracy and reliability. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating an automatic optimization method for a high-reliability brush seal structure according to the present invention. Figure 2 This is a schematic diagram of the brush sealing structure in an embodiment of the present invention; Figure 3 This is a schematic diagram of the brush sealing structure in the XZ and YZ planes in an embodiment of the present invention; Figure 4 This is a schematic diagram of the database construction process in an embodiment of the present invention; Figure 5 This is a flowchart illustrating the Bayesian optimization algorithm in an embodiment of the present invention; Figure 6 This is a schematic diagram of the Pareto front results in an embodiment of the invention; Figure 7 This is a schematic diagram of an electronic device suitable for implementing embodiments of the present invention. Detailed Implementation

[0020] 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. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] This invention provides an embodiment of an automatic optimization method for a high-reliability brush seal structure. Taking a brush seal structure of a certain type of aero-engine as an example, the optimization objective is as follows: Under high swirling flow conditions, the brush filaments of the brush seal will experience circumferential slippage under the action of the swirling flow, causing the filament tips to radially fly away from the rotor, increasing the radial clearance, leading to an increased sealing leakage rate and reduced sealing performance. Therefore, it is necessary to design a grooved front baffle brush seal structure to reduce the inlet swirling velocity (the swirling velocity upstream of the filament bundle), thereby improving the stability of the brush seal filaments. The groove is parameterized, and the optimization method of this invention is used for optimization prediction to obtain the grooved brush seal structure with the best swirling reduction effect. Specifically, as shown... Figure 1 As shown, the method in this embodiment includes: S1. Determine the groove geometry parameters of the through groove; For example, in one specific embodiment, a through groove is designed on the original brush seal front baffle, and the groove geometry parameters are determined, including: groove width. W , groove length L Slot spacing P groove inclination angle α and trench depth H It should be noted that, as Figure 2 and Figure 3 As shown, the groove width W The length of the slot along the circumferential direction of the rotor; slot length L The length of the slot along the radial direction of the rotor.

[0022] S2. Obtain the performance indicators of the brush seal structure corresponding to the geometric parameters of each set of grooves; Specifically, multiple sets of groove geometric parameters are obtained based on a preset range of groove geometric parameters, and the performance indicators of the brush seal structure corresponding to each set of groove geometric parameters are obtained. The performance indicators include: sealing leakage rate and swirl velocity upstream of the brush filament bundle.

[0023] For example, in one specific embodiment, the range of groove geometry parameters for the brush seal front baffle is shown in Table 1.

[0024] Table 1

[0025] For example, in one specific embodiment, the step of obtaining multiple sets of groove geometric parameters based on a preset range of groove geometric parameters is as follows: using the Latin cube sampling method to sample from the range of groove geometric parameters shown in Table 1 to generate multiple sets of groove geometric parameters.

[0026] For example, such as Figure 4As shown, in a specific embodiment, the steps for obtaining the performance indicators of the brush seal structure corresponding to each set of groove geometric parameters are as follows: automatically establishing a simulation model of the brush seal structure corresponding to each set of groove geometric parameters; performing mesh generation on the simulation model of the brush seal structure; and performing numerical simulation calculation on the meshed simulation model of the brush seal structure to obtain the performance indicators of the brush seal structure corresponding to each set of groove geometric parameters. The performance indicators include: sealing leakage rate and swirling velocity upstream of the brush filament bundle.

[0027] The steps for automatically establishing a simulation model of the brush seal structure corresponding to each set of groove geometric parameters are as follows: In a specific embodiment, taking 100 sets of groove geometric parameters as an example, based on each set of groove geometric parameters sampled, and by calling a general modeling tool or a custom modeling module through a programming language (such as C language or Python), the automated geometric modeling of the brush seal structure is realized.

[0028] The mesh generation process involves automatically generating the computational mesh required for CFD calculations by calling open-source or commercial mesh generation tools. In this embodiment, when meshing the brush seal structure, a local refinement strategy is applied to the brush filament region of the brush seal structure to ensure simulation accuracy.

[0029] The numerical simulation calculation steps are as follows: use a general CFD solver to perform numerical simulation calculations on the brush seal structure corresponding to each set of groove geometric parameters to obtain the seal leakage rate and the swirl velocity upstream of the brush filament bundle.

[0030] S3. Construct the agent model and train it; Specifically, a database is constructed using the geometric parameters of each set of slots and their corresponding performance indicators; a proxy model is constructed, and the proxy model is trained based on the database to obtain a trained target proxy model; For example, in one specific embodiment, a database can be established based on the geometric parameters of each set of grooves and their corresponding performance indicators obtained in step S2.

[0031] For example, in one specific embodiment, the steps of constructing the proxy model are as follows: using machine learning algorithms, such as Gaussian process regression (GPR) and artificial neural networks (ANN), to construct the proxy model.

[0032] For example, in one specific embodiment, the step of training the proxy model to obtain the trained target proxy model based on the database is as follows: using the input parameters of each set of slot geometry parameters in the database and the performance indicators as output parameters, the proxy model is trained to establish a mapping relationship between the input parameters and the output parameters, thereby obtaining the trained target proxy model.

[0033] S4. Iteratively optimize the slot geometry parameters in the database to obtain the optimal slot geometry parameters; Specifically, based on the target surrogate model, the swirling velocity and sealing leakage rate upstream of the brush filament bundle are optimized as performance indicators. A multi-objective optimization algorithm is used to iteratively optimize the groove geometry parameters in the database. The database is updated based on the groove geometry parameters generated after each iteration and their corresponding swirling velocity and sealing leakage rate upstream of the brush filament bundle until the swirling velocity and sealing leakage rate upstream of the brush filament bundle are minimized. The set of groove geometry parameters corresponding to the minimum swirling velocity and sealing leakage rate upstream of the brush filament bundle is taken as the optimal groove geometry parameters.

[0034] For example, in one specific embodiment, after obtaining the target surrogate model in step 3, the key to the optimization process is how to find the optimal brush seal structure in the high-dimensional design space. In this embodiment, the multi-objective optimization algorithm is a Bayesian optimization algorithm. The Bayesian optimization algorithm is used to iteratively optimize the groove geometric parameters. The specific optimization steps are as follows: S41. Acquisition function selection: Based on the output of the surrogate model, select a suitable acquisition function (such as the expected improvement function EI or the upper confidence bound function UCB) to gradually approximate the optimal solution in the design space. In this embodiment, the upper confidence bound function UCB is used.

[0035] S42. Optimization process: By exploring the design space through the Bayesian optimization method, the groove geometry parameters most likely to improve the sealing performance are gradually selected, reducing the demand for CFD simulation resources. In this embodiment, the optimization objective is to minimize both the swirling velocity upstream of the brush bundle and the sealing leakage rate.

[0036] S43. Iterative Update: After each optimization iteration, the database is updated by the target proxy model based on the groove geometry parameters generated after each iteration and the corresponding swirling velocity and sealing leakage rate upstream of the brush bundle. This continues until the swirling velocity and sealing leakage rate upstream of the brush bundle are both minimized. Then, the set of groove geometry parameters corresponding to the minimum swirling velocity and sealing leakage rate upstream of the brush bundle is taken as the optimal groove geometry parameters.

[0037] In this embodiment, such as Figure 5 As shown, based on the database constructed in step S3, an optimization program based on the Bayesian optimization algorithm is written, and a Gaussian process regression surrogate model is used as the surrogate model for prediction in this embodiment. The specific optimization process is as follows: Figure 3As shown, the system comprises an outer loop and an inner loop. The inner loop primarily uses a Gaussian process regression surrogate model, employing a database to establish the relationship between the channel geometry parameters and the swirling velocity and seal leakage rate. A Bayesian optimization algorithm is then used as the optimization objective, based on the trained objective surrogate model, to provide a predicted optimal solution. The outer loop verifies the optimal solution through CFD calculations and adds the results to the database. The optimization process continues until the difference between the Pareto front solution and the previous loop is less than 1% or the maximum number of iterations is reached, at which point the optimization process is considered complete.

[0038] It should be noted that, based on the target surrogate model, a Bayesian multi-objective optimization algorithm is used for optimization, and the swirling velocity upstream of the brush bundle and the sealing leakage rate are taken as optimization objectives, both of which are solved by minimizing the characteristics. Figure 6 The results of the multi-objective optimization are shown in the figure. The horizontal axis represents the swirl velocity ratio (the ratio of the swirl velocity of the optimized brush seal to that of the original brush seal, where the original brush seal is a brush seal structure without through grooves), and the vertical axis represents the seal leakage rate ratio (the ratio of the seal leakage rate of the optimized brush seal to that of the original brush seal). Gray represents the sample, blue represents the optimized structure, green represents the Pareto front solution, and red represents the basic model. Figure 4 In the process, the optimization direction generally tends to move downwards and to the left (negative X and Y directions), ultimately yielding four Pareto front solutions. It should be noted that in multi-objective optimization problems, there are usually multiple objectives that need to be optimized simultaneously, and achieving optimality for all these objectives is difficult. Therefore, trade-offs are necessary, hence the existence of Pareto front solutions. The definition of a Pareto front solution is: no room for improvement: there are no other feasible solutions that can improve at least one objective without worsening any other objective. Trade-off optimality: this solution has reached its optimal state in the trade-off of multiple objectives; any optimization of one objective must come at the expense of at least one other objective. Two representative cases were selected: Case A (optimal despin effect) and Case B (optimal sealing performance), with parameters shown in Table 2.

[0039] Table 2

[0040] S5. Optimized brush seal structure; Specifically, the optimized brush seal structure is designed based on the optimal groove geometry parameters.

[0041] An embodiment of a high-reliability brush seal structure automatic optimization system includes: a parameter acquisition module, a numerical simulation module, a surrogate model construction module, a multi-objective optimization module, and an optimal structure design module. The parameter acquisition module designs a through groove on the original brush seal front baffle and determines the groove's geometric parameters. The numerical simulation module acquires multiple sets of groove geometric parameters based on a preset range and obtains the performance indicators of the brush seal structure corresponding to each set of groove geometric parameters. These performance indicators include: seal leakage rate and swirling velocity upstream of the brush filament bundle. The surrogate model construction module constructs a database using each set of groove geometric parameters and its corresponding performance indicators; constructs a surrogate model; and trains the surrogate model based on the database to obtain a trained target surrogate model. The multi-objective optimization module is used to optimize the target surrogate model. The model optimizes the swirling velocity and sealing leakage rate upstream of the brush filament bundle as performance indicators. It uses a multi-objective optimization algorithm to iteratively optimize the groove geometry parameters in the database. The database is updated based on the groove geometry parameters generated after each iteration and their corresponding swirling velocity and sealing leakage rate upstream of the brush filament bundle until the swirling velocity and sealing leakage rate upstream of the brush filament bundle are minimized. The set of groove geometry parameters corresponding to the minimum swirling velocity and sealing leakage rate upstream of the brush filament bundle is taken as the optimal groove geometry parameters. The optimal structure design module is used to design the optimized brush seal structure based on the optimal groove geometry parameters.

[0042] Figure 7 A schematic diagram of an electronic device suitable for implementing embodiments of the present invention is shown. It should be noted that... Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0043] like Figure 7 As shown, the electronic device includes a Central Processing Unit (CPU) 101, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 102 or programs loaded from Storage Section 108 into Random Access Memory (RAM) 103. The RAM 103 also stores various programs and data required for system operation. The CPU 101, ROM 102, and RAM 103 are interconnected via a bus 104. An Input / Output (I / O) interface 105 is also connected to the bus 104.

[0044] The following components are connected to I / O interface 105: an input section 106 including a keyboard, mouse, etc.; an output section 107 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 108 including a hard disk, etc.; and a communication section 109 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 109 performs communication processing via a network such as the Internet. A drive 110 is also connected to I / O interface 105 as needed. Removable media 111, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 110 as needed so that computer programs read from them can be installed into storage section 108 as needed.

[0045] In particular, according to embodiments of the present invention, the processes described below with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a storage medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 109, and / or installed from removable medium 111. When the computer program is executed by central processing unit (CPU) 101, it performs various functions defined in the system of this application.

[0046] Specifically, the aforementioned electronic devices can be computers, tablets, or server devices.

[0047] It should be noted that the storage medium shown in the embodiments of the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, wherein computer-readable program code is carried. Such transmitted data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any storage medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the storage medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0048] It should be noted that, as another aspect, this application also provides a storage medium, which may be included in an electronic device or may exist independently without being assembled into the electronic device. The aforementioned storage medium carries one or more programs, which, when executed by an electronic device, cause the electronic device to perform the methods described in the following embodiments. For example, the electronic device may perform... Figure 1 The steps of the method shown.

[0049] In one embodiment, this application also provides a computer program product, including a computer program that, when executed by a processor, implements... Figure 1 The steps of the method shown.

[0050] Furthermore, the accompanying drawings are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention and are not intended to be limiting. It is readily understood that the processes shown in the drawings do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

Claims

1. An automatic optimization method for a high-reliability brush seal structure, characterized in that, include: Design a through groove on the original brush seal front baffle and determine the groove geometry parameters; Multiple sets of groove geometric parameters are obtained based on a preset range of groove geometric parameters, and the performance indicators of the brush seal structure corresponding to each set of groove geometric parameters are obtained. The performance indicators include: sealing leakage rate and swirling velocity upstream of the brush filament bundle. A database is constructed using the geometric parameters of each set of slots and their corresponding performance indicators; a proxy model is constructed, and the proxy model is trained based on the database to obtain a trained target proxy model; Based on the target proxy model, the swirling velocity and sealing leakage rate upstream of the brush filament bundle are optimized as performance indicators. A multi-objective optimization algorithm is used to iteratively optimize the groove geometry parameters in the database. The database is updated based on the groove geometry parameters generated after each iteration and their corresponding swirling velocity and sealing leakage rate upstream of the brush filament bundle until the swirling velocity and sealing leakage rate upstream of the brush filament bundle are minimized. The set of groove geometry parameters corresponding to the minimum swirling velocity and sealing leakage rate upstream of the brush filament bundle is taken as the optimal groove geometry parameters. The optimized brush seal structure is designed based on the optimal groove geometry parameters.

2. The automatic optimization method for a high-reliability brush seal structure according to claim 1, characterized in that, The geometry parameters of the groove include: groove width, groove length, groove spacing, groove inclination angle, and groove depth.

3. The automatic optimization method for a high-reliability brush seal structure according to claim 1, characterized in that, Multiple sets of groove geometric parameters are generated by sampling from a preset range of groove geometric parameters using the Latin cube sampling method.

4. The automatic optimization method for a high-reliability brush seal structure according to claim 1, characterized in that, The steps to obtain the performance indicators of the brush seal structure corresponding to each set of groove geometric parameters are as follows: Automated simulation models of the brush seal structure corresponding to the geometric parameters of each set of grooves are generated. Mesh generation is performed on the simulation model of the brush seal structure; Numerical simulation calculations were performed on the simulation model of the brush seal structure after meshing to obtain the performance indicators of the brush seal structure corresponding to the geometric parameters of each set of grooves.

5. The automatic optimization method for a high-reliability brush seal structure according to claim 4, characterized in that, When meshing the simulation model of the brush seal structure, a local refinement strategy is used to generate the mesh for the brush filament region of the brush seal structure.

6. The automatic optimization method for a high-reliability brush seal structure according to claim 1, characterized in that, The multi-objective optimization algorithm is the Bayesian optimization algorithm.

7. A high-reliability automatic optimization system for brush seal structures, characterized in that, include: The parameter acquisition module is used to design through grooves on the original brush seal front baffle and determine the groove geometry parameters. The numerical simulation module is used to obtain multiple sets of groove geometric parameters based on a preset range of groove geometric parameters, and to obtain the performance indicators of the brush seal structure corresponding to each set of groove geometric parameters. The performance indicators include: seal leakage rate and swirl velocity upstream of the brush filament bundle. The surrogate model building module is used to build a database with each set of slot geometry parameters and its corresponding performance indicators; build surrogate models; and train the surrogate models based on the database to obtain the trained target surrogate model. The multi-objective optimization module is used to optimize the groove geometry parameters in the database based on the objective proxy model, with the swirling velocity and sealing leakage rate of the upstream of the brush filament bundle as the optimization objectives. The multi-objective optimization algorithm is used to iteratively optimize the groove geometry parameters in the database. The database is updated according to the groove geometry parameters generated after each iteration and their corresponding swirling velocity and sealing leakage rate upstream of the brush filament bundle, until the swirling velocity and sealing leakage rate upstream of the brush filament bundle are minimized. The set of groove geometry parameters corresponding to the minimum swirling velocity and sealing leakage rate upstream of the brush filament bundle is taken as the optimal groove geometry parameters. The optimal structure design module is used to design an optimized brush seal structure based on the optimal groove geometry parameters.

8. An electronic device, characterized in that, A processor, a memory, and a computer program stored in the memory, wherein the computer program, when executed by the processor, implements the steps of the method according to any one of claims 1-6.

9. A program product, characterized in that, Includes a computer program, which, when run, performs the steps of the method according to any one of claims 1-6.

10. A storage medium, characterized in that, It contains a computer program that, when run, performs the steps of the method described in any one of claims 1-6.

Images