Blade top design and optimization method based on radial basis function

Abstract

The invention provides a blade top design and optimization method based on a radial basis function, and relates to the technical field of aero-engine turbine blades. The method comprises the steps that according to flow field characteristics of each area of a blade top groove curved surface, modeling is conducted on each area based on the radial basis function, and the blade top groove curved surface is obtained; a blade top groove curved surface shape enabling aerodynamic performance and quality requirements to reach the optimal is searched through machine learning; a Bezier curve is used for controlling the shape of the groove in the shoulder wall of the blade top, and the shoulder wall groove shape enabling aerodynamic performance and quality requirements to reach the optimal is found through machine learning. By the adoption of the scheme, the turbine blade has the characteristic of light weight while maintaining high aerodynamic performance.

Description

Technical Field

[0001] This application relates to the technical field of aero-engine turbine blades, and particularly to a tip design and optimization method and device based on radial basis functions. Background Art

[0002] In the turbine component of an aero-engine, in order to prevent collisions between rotating components and stationary components, a certain radial clearance is generally designed between the two. However, due to the pressure difference between the suction surface and the pressure surface of the blade, a leakage flow will be formed in the clearance. Scholars generally believe that the leakage flow is an important part of aerodynamic losses. Experimental results show that an increase in the clearance at the turbine tip will lead to a decrease in the overall efficiency of the turbine. The most effective and intuitive method to control the leakage flow is to reduce the radial clearance. However, if the radial clearance is too small, it may cause mutual rubbing between the blade and the stationary component, accelerating the wear of the turbine blade and directly affecting the efficiency and service life of the turbine. Currently, the methods to control the tip leakage loss are mainly divided into active control and passive control. Active control is to input energy from the outside to control the leakage loss, including cold air injection and plasma control, etc. Passive control is to change the geometric structure of the tip to control the leakage flow loss without energy input. Among them, tip shaping is the simplest and most common control method in passive control. Currently, tip shaping generally forms different clearance channels by constructing special structures, changes the pressure distribution on the suction surface and the pressure surface of the tip, reduces the driving pressure difference at the tip, and thus achieves the effect of controlling the tip leakage flow. By obtaining blades with high aerodynamic performance through tip shaping, the overall performance of the aero-engine can be improved.

[0003] The thrust-to-weight ratio, as one of the main performance indicators of an aero-engine, reflects the relationship between thrust and engine weight. For military aero-engines, for engines with the same thermodynamic cycle, the higher the thrust-to-weight ratio, the better. Therefore, lightweight has become an important development trend of air defense engines. Compared with compressors, the working environment of turbines is more severe, and it is very difficult to reduce the weight on turbine blades. Since turbine blades need to be cooled, the inside is already a hollow structure and air film holes also need to be arranged on the blade surface. On this basis, it is even more difficult to reduce the mass of turbine blades. Currently, the most common and effective method is to arrange grooves at the tip, which can not only control the tip leakage flow but also meet the mass requirements of turbine blades. Previous studies were all designed and optimized based on a fixed groove shape, and local shape design optimization of the groove could not be achieved. Summary of the Invention

[0004] This application aims to solve at least one of the technical problems in the related technologies to some extent.

[0005] To this end, the first object of the present application is to propose a tip design and optimization method based on radial basis functions, which designs and optimizes the tip of a turbine blade according to engineering requirements to meet the requirements of high aerodynamic performance and lightweight, so that the turbine blade not only maintains high aerodynamic performance but also has the characteristics of lightweight.

[0006] The second object of the present application is to propose a tip design and optimization device based on radial basis functions.

[0007] To achieve the above object, an embodiment of the first aspect of the present application proposes a tip design and optimization method based on radial basis functions, including:

[0008] Model each region based on radial basis functions according to the flow field characteristics of each region of the tip groove surface to obtain the tip groove surface.

[0009] Find the shape of the tip groove surface that optimizes the aerodynamic performance and quality requirements through machine learning.

[0010] Use B-spline curves to control the shape of the groove on the tip shoulder wall, and find the optimal shape of the shoulder wall groove that optimizes the aerodynamic performance and quality requirements through machine learning.

[0011] Optionally, in an embodiment of the present application, modeling each region based on radial basis functions according to the flow field characteristics of each region of the tip groove surface to obtain the tip groove surface includes:

[0012] Generate an initial tip groove surface based on the existing airfoil.

[0013] Divide the initial tip groove surface into different regions from the leading edge to the trailing edge of the blade to generate a scatter plot of the tip groove surface.

[0014] For the flow structures in different regions, take the partial nodes in the corresponding regions of the scatter plot of the tip groove surface as control points for adjustment. When adjusting, select the Gaussian function as the kernel function for radial basis surface fitting, control the shape of the tip groove surface based on the selected control points, and complete the modeling of the tip groove surface by changing the coordinates of the control points.

[0015] Optionally, in an embodiment of the present application, finding the shape of the tip groove surface that optimizes the aerodynamic performance and quality requirements through machine learning includes:

[0016] Construct an RBF-IN surrogate model, select the leakage flow rate and the overall mass of the turbine blade as evaluation indicators, construct an objective function, and find the optimal solution through a genetic function to obtain the optimal tip surface.

[0017] Optionally, in an embodiment of the present application, controlling the shape of the groove on the blade tip shoulder wall using a Bessel curve includes:

[0018] Describing the two-dimensional shape of the shoulder wall groove using a third-order Bessel curve and a second-order Bessel curve, where the first Bessel curve is a third-order Bessel curve, the end point of the first Bessel curve is the starting point of the second Bessel curve, the second Bessel curve is a second-order Bessel curve, the end point of the second Bessel curve is the starting point of the third Bessel curve, and the third Bessel curve is a third-order Bessel curve.

[0019] Optionally, in an embodiment of the present application, finding the shoulder wall groove shape that optimizes the aerodynamic performance and quality requirements through machine learning includes:

[0020] For the constructed two-dimensional shoulder wall groove, constructing an RBF-IN surrogate model, selecting the leakage flow rate and the overall quality of the turbine blade as evaluation indicators, constructing an objective function, and finding the optimal solution through a genetic algorithm to obtain the optimal shoulder wall groove.

[0021] To achieve the above object, an embodiment of the second aspect of the present invention proposes a blade tip design and optimization device based on a radial basis function, including:

[0022] A blade tip groove surface design module for modeling each region based on the radial basis function according to the flow field characteristics of each region of the blade tip groove surface to obtain the blade tip groove surface;

[0023] A blade tip groove surface optimization module for finding the shape of the blade tip groove surface that optimizes the aerodynamic performance and quality requirements through machine learning;

[0024] A shoulder wall groove design and optimization module for controlling the shape of the groove on the blade tip shoulder wall using a Bessel curve and finding the shape of the shoulder wall groove that optimizes the aerodynamic performance and quality requirements through machine learning.

[0025] Optionally, in an embodiment of the present application, modeling each region based on the radial basis function according to the flow field characteristics of each region of the blade tip groove surface to obtain the blade tip groove surface includes:

[0026] Generating an initial blade tip groove surface based on the existing blade profile;

[0027] Dividing the initial blade tip groove surface from the leading edge to the trailing edge of the blade into different regions to generate a blade tip groove surface scatter plot;

[0028] For the flow structures in different regions, some nodes in the corresponding regions of the scatter plot of the tip groove surface are used as control points for adjustment. When adjusting, the Gaussian function is selected as the kernel function for radial basis surface fitting, and the shape of the tip groove surface is controlled based on the selected control points. By changing the coordinates of the control points, the modeling of the tip groove surface is completed.

[0029] Optionally, in an embodiment of the present application, the optimal shape of the tip groove surface that meets the aerodynamic performance and quality requirements is found through machine learning, including:

[0030] Construct an RBF-IN surrogate model, select the leakage flow rate and the overall mass of the turbine blade as evaluation indicators, construct an objective function, and find the optimal solution through a genetic function to obtain the optimal tip surface.

[0031] Optionally, in an embodiment of the present application, the shape of the groove on the tip shoulder wall is controlled using a Bezier curve, including:

[0032] The two-dimensional shape of the shoulder wall groove is described using a third-order Bezier curve and a second-order Bezier curve. Among them, the first Bezier curve is a third-order Bezier curve, the end point of the first Bezier curve is the starting point of the second Bezier curve, the second Bezier curve is a second-order Bezier curve, the end point of the second Bezier curve is the starting point of the third Bezier curve, and the third Bezier curve is a third-order Bezier curve.

[0033] Optionally, in an embodiment of the present application, the optimal shape of the shoulder wall groove that meets the aerodynamic performance and quality requirements is found through machine learning, including:

[0034] For the constructed two-dimensional shoulder wall groove, construct an RBF-IN surrogate model, select the leakage flow rate and the overall mass of the turbine blade as evaluation indicators, construct an objective function, and find the optimal solution through a genetic algorithm to obtain the optimal shoulder wall groove.

[0035] The tip design and optimization method based on radial basis functions in the embodiments of the present application uses radial basis functions to configure the tip groove surface of the turbine blade, designs different regions according to the flow field characteristics of different regions of the tip, and finds the optimal tip surface shape that meets the aerodynamic performance and quality requirements based on machine learning; then uses Bezier curves to control the shape of the groove on the tip shoulder wall and uses machine learning to find the optimal groove shape. This embodiment makes the turbine blade have the characteristics of lightweight while maintaining high aerodynamic performance by changing the shape of the local region of the tip.

[0036] Additional aspects and advantages of the present application will be given in part in the following description, become apparent in part from the following description, or be understood through the practice of the present application. Description of the Drawings

[0037] The above and / or additional aspects and advantages of the present application will become apparent and be readily understood from the following description of embodiments in conjunction with the accompanying drawings, where:

[0038] Figure 1 FIG.

[0039] Figure 2 is a schematic flow chart of a tip design and optimization method based on radial basis function provided in Embodiment 1 of the present application;

[0040] Figure 3 is a schematic diagram of scatter points of the tip groove surface in an embodiment of the present application;

[0041] Figure 4 is a schematic diagram of the movement of local control points of the tip groove surface in an embodiment of the present application;

[0042] Figure 5 is a schematic diagram of local plane fitting of the tip groove surface in an embodiment of the present application;

[0043] Figure 6 is a distribution diagram of the z coordinate of the tip groove surface in an embodiment of the present application;

[0044] Figure 7 is a schematic diagram of overall fitting of the tip groove surface in an embodiment of the present application;

[0045] Figure 8 is a schematic diagram of the shape of the shoulder wall groove defined based on Bessel curve in an embodiment of the present application;

[0046] Figure 9 is a schematic structural diagram of a tip design and optimization device based on radial basis function provided in an embodiment of the present application. Detailed Description of the Embodiment

[0047] The embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application and should not be construed as limiting the present application.

[0048] The tip design and optimization method and device based on radial basis function according to the embodiments of the present application will be described below with reference to the accompanying drawings.

[0049] Figure 1 is a schematic flow chart of a tip design and optimization method based on radial basis function provided in Embodiment 1 of the present application.

[0050] As Figure 1As shown in the figure, the blade tip design and optimization method based on radial basis function includes the following steps:

[0051] Step 101: Based on the flow field characteristics of each region of the blade tip groove surface, model each region using radial basis function to obtain the blade tip groove surface.

[0052] In this embodiment, a blade tip surface is generated according to the given blade profile. The blade tip surface is divided into several parts. The node coordinates of a part are used as control points. The z-direction coordinate (radial coordinate) of the control points is selected as the control variable. By changing the numerical value of the z-coordinate of the control points, the construction of the blade tip surface is completed using radial basis function.

[0053] Specifically, Figure 2 is the process of blade tip optimization for the radial basis function surface. As Figure 2 shown, first, the existing turbine blade tip is optimized. Based on the principle of mesh division, the blade tip groove surface scatter plot as shown in the figure is generated from the blade tip surface. Each scatter point is a node of the mesh. A part of the nodes is selected as control points, and the shape of the surface is realized by changing the z-direction coordinates of the control points. Taking Figure 3 a part of the control points in the circle in Figure 4 as an example, by changing the position of one of the control points, that is, by changing the z-direction coordinate of the control points in the circle in Figure 5 and making the z-direction coordinate translate 1 mm along the z direction, the local surface shape is completed. During the design process, the blade tip groove surface can be divided into different regions from the leading edge to the trailing edge of the blade, and each region is refined according to the flow structure of different regions. As Figure 6 shown, the schematic diagram of the local surface shape is generated through the above operations. Considering that the Gaussian function has good local response characteristics and can handle nonlinear problems well, the Gaussian function is selected as the kernel function for radial basis surface fitting. Other kernel functions can be selected according to the requirements of different blade tip surfaces. In this embodiment, a certain number of control points are selected to control the shape of the blade tip groove surface. As Figure 7 shown, the schematic diagram of the z-coordinate distribution of the blade tip groove surface is given, and different colors represent the z-coordinate values at different positions. As

[0054] shown, the overall schematic diagram of the blade tip groove surface is given. By changing the z-coordinates of four control points, the schematic diagram of the blade tip groove surface is completed. Cutting along the dotted line in the figure, the blade tip groove surface is obtained.

[0055] In this embodiment, 100 groups of samples are obtained by Latin hypercube sampling, parametric modeling is carried out, mesh division is performed using Ansys Workbench, and finally the CFD software is used for solving. A prediction model is established based on the results of CFD calculation, and the genetic algorithm is used to find the optimal solution. After obtaining the optimal tip shape, the above model construction and mesh division processes are repeated, and the CFD software is used for calculation verification.

[0056] Specifically, after the preliminary design of the tip groove surface is completed, the genetic algorithm is used to find the optimal solution. In this embodiment, an RBF-NN surrogate model is constructed. The leakage flow rate is selected as the evaluation index to evaluate the leakage flow control effect of different tip shapes, and the overall mass of the turbine blade is selected to evaluate the weight reduction effect. 100 groups of samples are obtained by Latin hypercube sampling (LHS), 80 groups of which are used as training samples and the remaining 20 groups of samples are used as test samples. The RBF-NN neural network is used to construct a surrogate model for training and verification. The population size is selected as 30 and the number of generations is selected as 100. First, the objective function is solved based on the RBF-NN surrogate model, then the crowding distance of each individual is calculated, and the parent population is formed by sorting based on the crowding distance. The crossover operation is performed on the parent population to generate the offspring population and the mutation operation is performed on the offspring population. The objective function values of each individual in the new population are evaluated, and the optimal population is selected to form the next generation of the parent population. The above operations are repeated until the maximum number of generations is reached, and the optimal solution set is output.

[0057] Step 103: Use Bezier curves to control the shape of the groove on the tip shoulder wall, and find the optimal shape of the shoulder wall groove that meets the optimal aerodynamic performance and quality requirements through machine learning.

[0058] In this embodiment, the shape of the shoulder wall groove is designed, and 3 Bezier curves are used to describe the two-dimensional shape of the groove. Finally, 100 groups of samples are obtained by Latin hypercube sampling. The above model construction and mesh division processes are repeated, and the CFD software is used to calculate the samples, construct a model and train and verify the model, completing the design and optimization process of the turbine tip.

[0059] Specifically, after the construction of the tip groove surface shape is completed, the shape of the shoulder wall groove is optimized. As Figure 8As shown, a schematic diagram of the two-dimensional shape of the shoulder wall groove constructed based on three Bezier curves is given. Two third-order Bezier curves and one second-order Bezier curve are used to construct the groove shape. The end point (control point D) of the first Bezier curve is the starting point of the second Bezier curve, and the end point of the second Bezier curve is the starting point (control point F) of the third Bezier curve. By continuously changing the x and y coordinates of each control point, different groove shapes can be obtained. Based on the above optimization process of the turbine groove tip, similar steps can be used to optimize the shape of the shoulder wall groove. Similarly, the method of machine learning is adopted to construct an RBF-NN surrogate model. The leakage flow rate and the weight of the turbine blade are also used as evaluation indicators. 100 groups of samples are obtained by Latin hypercube sampling and divided into training samples and test samples. Through the genetic algorithm, the optimal solution set is output. That is, the design and optimization process of the turbine tip structure is completed.

[0060] In the method for turbine tip design and optimization based on radial basis function according to the embodiment of the present application, the radial basis function is used to fit the curved surface, which can perform refined design on different regions of the turbine tip groove curved surface, has better adaptability to the non-linear curved surface shape, generates a smoother curved surface, and has a high approximation accuracy; uses multiple Bezier curves to control the shape of the groove on the shoulder wall, performs refined control on the shape of the groove, and generates more complex groove shapes; uses the method of machine learning to train the model, optimizes the shape of the turbine blade on the basis of the existing tip, and the optimized blade exhibits the characteristics of high aerodynamic performance and light weight.

[0061] To implement the above embodiment, the present application also proposes a turbine tip design and optimization device based on radial basis function.

[0062] Figure 9 It is a schematic structural diagram of a turbine tip design and optimization device based on radial basis function provided by the embodiment of the present application.

[0063] As Figure 9 shown, the turbine tip design and optimization device based on radial basis function includes:

[0064] A turbine tip groove curved surface design module, configured to model each region based on the radial basis function according to the flow field characteristics of each region of the turbine tip groove curved surface to obtain the turbine tip groove curved surface;

[0065] A turbine tip groove curved surface optimization module, configured to find the optimal shape of the turbine tip groove curved surface that meets the optimal aerodynamic performance and quality requirements through machine learning;

[0066] A shoulder wall groove design and optimization module, configured to control the shape of the groove on the turbine tip shoulder wall using Bezier curves, and find the optimal shape of the shoulder wall groove that meets the optimal aerodynamic performance and quality requirements through machine learning.

[0067] Optionally, in an embodiment of the present application, according to the flow field characteristics of each region of the tip groove surface, each region is modeled based on the radial basis function to obtain the tip groove surface, including:

[0068] Generate an initial tip groove surface according to the existing blade profile;

[0069] Divide the initial tip groove surface from the leading edge to the trailing edge of the blade into different regions to generate a scatter plot of the tip groove surface;

[0070] For the flow structures in different regions, part of the nodes in the corresponding regions of the scatter plot of the tip groove surface are used as control points for adjustment. When adjusting, the Gaussian function is selected as the kernel function for radial basis surface fitting, and the shape of the tip groove surface is controlled based on the selected control points. By changing the coordinates of the control points, the modeling of the tip groove surface is completed.

[0071] Optionally, in an embodiment of the present application, machine learning is used to find the tip groove surface shape that optimizes the aerodynamic performance and quality requirements, including:

[0072] Construct an RBF-IN surrogate model, select the leakage flow rate and the overall quality of the turbine blade as evaluation indicators, construct an objective function, and find the optimal solution through a genetic function to obtain the optimal tip surface.

[0073] Optionally, in an embodiment of the present application, the shape of the groove on the tip shoulder wall is controlled by using B-spline curves, including:

[0074] The two-dimensional shape of the shoulder wall groove is described by using a third-order B-spline curve and a second-order B-spline curve. Among them, the first B-spline curve is a third-order B-spline curve, the end point of the first B-spline curve is the start point of the second B-spline curve, the second B-spline curve is a second-order B-spline curve, the end point of the second B-spline curve is the start point of the third B-spline curve, and the third B-spline curve is a third-order B-spline curve.

[0075] Optionally, in an embodiment of the present application, machine learning is used to find the shoulder wall groove shape that optimizes the aerodynamic performance and quality requirements, including:

[0076] For the constructed two-dimensional shoulder wall groove, construct an RBF-IN surrogate model, select the leakage flow rate and the overall quality of the turbine blade as evaluation indicators, construct an objective function, and find the optimal solution through a genetic algorithm to obtain the optimal shoulder wall groove.

[0077] It should be noted that the foregoing explanation of the embodiments of the tip design and optimization method based on the radial basis function also applies to the tip design and optimization device based on the radial basis function of this embodiment, and will not be repeated here.

[0078] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" etc. mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0079] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present application, "a plurality of" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0080] Any process or method description in a flowchart or described in other ways herein may be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a customized logic function or process, and the scope of the preferred embodiments of the present application includes additional implementations, where the functions may be executed in a substantially simultaneous manner or in the reverse order according to the functions involved, rather than in the order shown or discussed, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0081] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definable sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium include the following: an electrical connection portion having one or more wirings (electronic device), a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then storing it in a computer memory.

[0082] It should be understood that various parts of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0083] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0084] In addition, each functional unit in various embodiments of the present application may be integrated into one processing module, may exist separately as individual physical units, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0085] The above-mentioned storage medium may be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A blade tip design and optimization method based on radial basis functions, characterized in that, Including: Model each region based on the flow field characteristics of each region of the tip groove surface using radial basis functions to obtain the tip groove surface; Find the shape of the tip groove surface that optimizes the aerodynamic performance and quality requirements through machine learning; Use Bezier curves to control the shape of the groove on the tip shoulder wall, and find the optimal shoulder wall groove shape that optimizes the aerodynamic performance and quality requirements through machine learning.

2. The method according to claim 1, wherein The step of modeling each region based on the flow field characteristics of each region of the tip groove surface using radial basis functions to obtain the tip groove surface includes: Generate an initial tip groove surface based on the existing blade profile; Divide the initial tip groove surface from the leading edge to the trailing edge of the blade into different regions to generate a scatter plot of the tip groove surface; For the flow structures in different regions, take the corresponding part of the nodes in the scatter plot of the tip groove surface in the corresponding region as control points for adjustment. When adjusting, select the Gaussian function as the kernel function for radial basis surface fitting, control the shape of the tip groove surface based on the selected control points, and complete the modeling of the tip groove surface by changing the coordinates of the control points.

3. The method according to claim 1, characterized in that The step of finding the shape of the tip groove surface that optimizes the aerodynamic performance and quality requirements through machine learning includes: Construct an RBF-IN surrogate model, select the leakage flow rate and the overall quality of the turbine blade as evaluation indicators, construct an objective function, and find the optimal solution through a genetic algorithm to obtain the optimal tip surface.

4. The method according to claim 1, wherein The step of using Bezier curves to control the shape of the groove on the tip shoulder wall includes: Use cubic Bezier curves and quadratic Bezier curves to describe the two-dimensional shape of the shoulder wall groove. Among them, the first Bezier curve is a cubic Bezier curve, the end point of the first Bezier curve is the starting point of the second Bezier curve, the second Bezier curve is a quadratic Bezier curve, the end point of the second Bezier curve is the starting point of the third Bezier curve, and the third Bezier curve is a cubic Bezier curve.

5. The method according to claim 4, wherein The step of finding the shape of the shoulder wall groove that optimizes the aerodynamic performance and quality requirements through machine learning includes: For the constructed two-dimensional shoulder wall groove, construct an RBF-IN surrogate model, select the leakage flow rate and the overall quality of the turbine blade as evaluation indicators, construct an objective function, and find the optimal solution through a genetic algorithm to obtain the optimal shoulder wall groove.

6. A tip design and optimization device based on radial basis functions, characterized in that, Including: A tip groove surface design module for modeling each region based on the flow field characteristics of each region of the tip groove surface using radial basis functions to obtain the tip groove surface; A tip groove surface optimization module for finding the shape of the tip groove surface that optimizes the aerodynamic performance and quality requirements through machine learning; A shoulder wall groove design and optimization module for using Bezier curves to control the shape of the groove on the tip shoulder wall and finding the shape of the shoulder wall groove that optimizes the aerodynamic performance and quality requirements through machine learning.

7. The device according to claim 6, characterized in that, The step of modeling each region based on the flow field characteristics of each region of the tip groove surface using radial basis functions to obtain the tip groove surface includes: Generate an initial tip groove surface based on the existing blade profile; Divide the initial blade tip groove surface into different regions from the leading edge to the trailing edge of the blade, and generate a scatter plot of the blade tip groove surface; For the flow structures in different regions, take the part of the nodes in the corresponding regions of the scatter plot of the blade tip groove surface as control points for adjustment. When adjusting, select the Gaussian function as the kernel function for radial basis surface fitting, control the shape of the blade tip groove surface based on the selected control points, and complete the modeling of the blade tip groove surface by changing the coordinates of the control points.

8. The device according to claim 6, characterized in that The method of finding the blade tip groove surface shape that optimizes the aerodynamic performance and quality requirements through machine learning includes: Construct an RBF-IN surrogate model, select the leakage flow rate and the overall mass of the turbine blade as evaluation indicators, construct an objective function, and find the optimal solution through a genetic function to obtain the optimal blade tip surface.

9. The device according to claim 6, characterized in that, The method of controlling the shape of the groove on the blade tip shoulder wall using B-spline curves includes: Use cubic B-spline curves and quadratic B-spline curves to describe the two-dimensional shape of the shoulder wall groove. Among them, the first B-spline curve is a cubic B-spline curve, the end point of the first B-spline curve is the starting point of the second B-spline curve, the second B-spline curve is a quadratic B-spline curve, the end point of the second B-spline curve is the starting point of the third B-spline curve, and the third B-spline curve is a cubic B-spline curve.

10. The device according to claim 9, characterized in that, The method of finding the shoulder wall groove shape that optimizes the aerodynamic performance and quality requirements through machine learning includes: For the constructed two-dimensional shoulder wall groove, construct an RBF-IN surrogate model, select the leakage flow rate and the overall mass of the turbine blade as evaluation indicators, construct an objective function, and find the optimal solution through a genetic algorithm to obtain the optimal shoulder wall groove.

Images