Method for arranging film holes of turbine blade

Abstract

The invention relates to the field of aero-engines, in particular to an air film hole arrangement method of a turbine blade. The gas film hole arrangement method of the turbine blade comprises the steps that a design sample space is constructed based on the value range of gas film hole arrangement parameters of the turbine blade; wherein the design sample space comprises a plurality of turbine blade sample models with different gas film hole arrangements; establishing a target function by taking the minimum stress predicted value of the turbine blade sample model as a target; wherein the stress prediction value is calculated according to a pre-trained stress prediction model; establishing constraint conditions based on the upper limit value and the lower limit value of the design sample space; and establishing a film hole arrangement optimization model according to the target function and the constraint conditions, and solving the film hole arrangement optimization model to determine target film hole arrangement parameters. According to the method, the gas film hole arrangement optimization efficiency of the turbine blade can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of aeroengines, and in particular to a method for arranging air film holes of a turbine blade. Background Art

[0002] Turbine blade film holes are a common blade cooling structure in modern aero-engines, and their arrangement on turbine blades is characterized by being small and dense. When parameterizing the film holes in traditional turbine blade film hole arrangement design, film holes in the same row are usually selected as components with continuous positions and the same spacing and drilling directions for parametric design or sketch-based manual interactive film hole modeling. The flow and heat transfer characteristics of film hole cooling methods under different hole array arrangements are compared through numerical simulation methods, and the influence of hole array arrangement on adiabatic cooling efficiency and film comprehensive cooling efficiency is obtained.

[0003] The disadvantages of this method are that, firstly, in the parametric design of the traditional film holes of turbine blades, each local row of film holes on the blade surface is regarded as arranged with continuous equal spacing and the same punching direction, but this cannot achieve the best cooling effect; secondly, the traditional film hole arrangement optimization usually requires the use of a proxy model to fit the simulation results. The design of the proxy model requires the knowledge of domain experts and a lot of manual labor. At the same time, the proxy model has weak generalization ability when dealing with complex and diverse data sets, which reduces the optimization efficiency of the turbine blade film hole arrangement; finally, the traditional film hole arrangement optimization design objective function mainly focuses on the influence of the film hole arrangement method on the blade cooling characteristics, and rarely considers the influence of the film hole arrangement on the blade surface stress into the optimization design considerations.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of the present disclosure is to provide a method for arranging air film holes of a turbine blade, aiming to solve the problem of low optimization efficiency of the arrangement of air film holes of a turbine blade.

[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0007] According to one aspect of an embodiment of the present disclosure, a method for arranging film holes of a turbine blade is provided, characterized by comprising:

[0008] Constructing a design sample space based on the value range of the air film hole arrangement parameter of the turbine blade; wherein the design sample space includes a plurality of turbine blade sample models with different air film hole arrangements;

[0009] Establishing an objective function with the goal of minimizing the stress prediction value of the turbine blade sample model; wherein the stress prediction value is calculated based on a pre-trained stress prediction model; and establishing constraint conditions based on the upper and lower limits of the design sample space;

[0010] An air film hole arrangement optimization model is established according to the objective function and the constraint conditions, and the air film hole arrangement optimization model is solved to determine target air film hole arrangement parameters.

[0011] According to some embodiments of the present disclosure, based on the aforementioned scheme, the air film hole arrangement parameters include position parameters and rotation angle parameters; wherein, the turbine blade includes multiple groups of air film holes, and the position parameters include one or more of the distance from the center position of the air film holes of a single group of air film holes to the central axis, the distance from the starting air film hole position to the central axis, the distance from the starting air film hole position to the blade top, the angle between the connecting line of the single group of air film holes and the horizontal axis, the number of air film holes in a single group, and the distance between air film holes in a single group; the rotation angle parameters include one or more of the rotation angle normal angle, the rotation angle circumferential angle, and the rotation angle circular angle of a single air film hole.

[0012] According to some embodiments of the present disclosure, based on the aforementioned scheme, the film holes located in the same row of the turbine blade, with continuous positions, the same film hole spacing and the same film hole rotation angle constitute a group of film holes.

[0013] According to some embodiments of the present disclosure, based on the above solution, the method further includes: pre-training the stress prediction model, wherein the pre-training the stress prediction model includes:

[0014] Extracting turbine blade sample models in the design sample space as training samples;

[0015] Performing blade strength simulation on the training samples to obtain stress simulation values ​​corresponding to each of the training samples;

[0016] The stress prediction model is trained according to the stress simulation values ​​corresponding to the training samples.

[0017] According to some embodiments of the present disclosure, based on the above scheme, the stress prediction model is a CGAN model, the CGAN model includes a definition generator and a discriminator, and the stress prediction model is trained according to the stress simulation values ​​corresponding to each of the training samples, including:

[0018] Expanding the surface of the training sample in two dimensions to obtain an air film pore distribution matrix;

[0019] Utilizing the definition generator to calculate the stress prediction value corresponding to the training sample according to the air film hole distribution matrix;

[0020] Using the discriminator to discriminate whether the stress prediction value is generated by the generator or is a stress simulation value;

[0021] The definition generator and the discriminator are alternately trained to modify model parameters until a training stop condition is met.

[0022] According to some embodiments of the present disclosure, based on the aforementioned solution, the step of calculating the stress value corresponding to the training sample according to the air film hole distribution matrix by using the definition generator includes:

[0023] For a training sample, encoding the air film hole distribution matrix of the training sample to obtain a first feature map;

[0024] The boundary conditions are converted by the first fully connected layer and added to the first feature map in an element-wise manner to obtain a stress distribution result;

[0025] Decoding the stress distribution result to obtain a stress value;

[0026] The training samples are traversed to obtain stress values ​​corresponding to the training samples.

[0027] According to some embodiments of the present disclosure, based on the aforementioned scheme, the discriminator is used to discriminate whether the stress prediction value belongs to a value generated by a generator or a stress simulation value:

[0028] For a training sample, the air film hole distribution matrix, the stress prediction value and the stress simulation value of the training sample are connected and encoded to obtain a second feature map;

[0029] Adding the boundary condition to the second feature map in an element-wise manner after being transformed by the second fully connected layer to obtain a feature result;

[0030] The characteristic results are converted and evaluated to determine whether the characteristic results belong to generator generation or stress simulation values.

[0031] According to a second aspect of an embodiment of the present disclosure, there is provided a film hole arrangement device for a turbine blade, comprising:

[0032] A sample module, used to construct a design sample space based on the value range of the air film hole arrangement parameter of the turbine blade; wherein the design sample space includes a plurality of turbine blade sample models with different air film hole arrangements;

[0033] A model module, for establishing an objective function with the goal of minimizing the stress prediction value of the turbine blade sample model; wherein the stress prediction value is calculated based on a pre-trained stress prediction model; and establishing constraint conditions based on the upper limit and lower limit of the design sample space;

[0034] A solution module is used to establish an air film hole arrangement optimization model according to the objective function and the constraint conditions, and solve the air film hole arrangement optimization model to determine target air film hole arrangement parameters.

[0035] According to a third aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method for arranging film holes of a turbine blade as in the above-mentioned embodiment is implemented.

[0036] According to the fourth aspect of an embodiment of the present disclosure, an electronic device is provided, characterized in that it includes: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the air film hole arrangement method of the turbine blade as in the above-mentioned embodiment.

[0037] The exemplary embodiments of the present disclosure may have some or all of the following beneficial effects:

[0038] In the technical solutions provided in some embodiments of the present disclosure, on the one hand, an objective function is established with the goal of minimizing the stress prediction value of the turbine blade sample model, and the stress distribution on the surface of the turbine blade is taken into consideration for optimization, so that the stress around the optimized air film hole is alleviated, and the phenomenon of air film hole stress interference can be avoided; on the other hand, a pre-trained stress prediction model is used to calculate the stress value. Compared with the simulation numerical calculation of the turbine blade sample model to obtain the stress value, the time of numerical calculation in the optimization process is greatly reduced, and the optimization efficiency and accuracy are improved. Compared with the traditional air film hole optimization using an agent model, it has the advantages of strong nonlinear modeling ability, better adaptability to complex data patterns and laws, stronger adaptability and parallel computing capabilities, and obvious advantages in processing large-scale data.

[0039] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present disclosure, and together with the specification, are used to explain the principles of the present disclosure. Obviously, the drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0041] Figure 1 A schematic diagram schematically illustrates a flow chart of a method for arranging air film holes of a turbine blade in an exemplary embodiment of the present disclosure;

[0042] Figure 2A schematic diagram schematically shows the arrangement of air film holes on a turbine blade in an exemplary embodiment of the present disclosure;

[0043] Figure 3 A schematic diagram schematically showing a film hole position parameter in an exemplary embodiment of the present disclosure;

[0044] Figure 4 A schematic diagram schematically illustrates a single set of air film hole position parameters in an exemplary embodiment of the present disclosure;

[0045] Figure 5 A schematic diagram schematically illustrates a rotation parameter of an air film hole in an exemplary embodiment of the present disclosure;

[0046] Figure 6 A schematic diagram schematically showing a rotation parameter of a single air film hole in an exemplary embodiment of the present disclosure;

[0047] Figure 7 A model structure diagram of a CGAN model in an exemplary embodiment of the present disclosure is schematically shown;

[0048] Figure 8 A schematic diagram schematically illustrates a flow chart of a stress prediction model training method in an exemplary embodiment of the present disclosure;

[0049] Fig. 9 A schematic diagram of a process for obtaining an air film pore distribution matrix in an exemplary embodiment of the present disclosure is schematically shown;

[0050] Fig.10 A schematic diagram schematically shows the composition of an air film hole arrangement device for a turbine blade in an exemplary embodiment of the present disclosure;

[0051] Fig.11 A schematic diagram schematically illustrates a computer-readable storage medium in an exemplary embodiment of the present disclosure;

[0052] Fig.12 The structure diagram of a computer system of an electronic device in an exemplary embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0053] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more comprehensive and complete and will fully convey the concept of the example embodiments to those skilled in the art.

[0054] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the present disclosure.

[0055] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0056] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0057] Turbine blade film holes are a commonly used blade cooling structure in modern aircraft engines. They are arranged small and densely on turbine blades. The basic principle is to set small holes between the two walls of the turbine blades, and form an air film by ejecting high-temperature gas to reduce the surface temperature and thermal stress of the blades, thereby improving the life and performance of the blades. The double-walled turbine blade film holes can not only effectively reduce the surface temperature of the blades, but also improve the internal flow field structure of the blades, improve work efficiency and thrust. The arrangement of film holes is designed to achieve passive cooling and active thermal management of the blades by arranging film holes on the blade surface, thereby improving the performance and life of the engine. It has the advantages of improving cooling effect, improving thrust effect, reducing thermal stress and thermal expansion, and reducing blade vibration.

[0058] When parameterizing the film holes in traditional turbine blade film hole arrangement design, the film holes in the same row are usually selected as components with continuous positions and the same spacing and drilling directions for parametric design, or manual interactive film hole modeling is performed based on sketches. The flow and heat transfer characteristics of film hole cooling methods under different hole array arrangements are compared through numerical simulation methods, and the influence of hole array arrangement on the adiabatic cooling efficiency and the comprehensive film cooling efficiency is obtained.

[0059] The disadvantages of the traditional optimization design of film hole arrangement of turbine blades are that, firstly, in the parametric design of film holes of traditional turbine blades, each local row of film holes on the blade surface is regarded as being arranged with continuous equal spacing and the same punching direction. However, in order to achieve the best cooling effect, the punching direction and hole spacing of each row of film holes may be different. The traditional film hole arrangement design method is difficult to parameterize the overall film hole arrangement of the turbine blade and cannot give the optimal film hole distribution strategy. Secondly, the traditional film hole arrangement optimization usually uses DOE experimental design to construct the design space, selects design sample points, performs numerical simulation calculations on each sample point, and then uses a proxy model to fit the simulation results. The proxy model usually requires manual design of feature extractors, rules or model structures, which may require the knowledge of domain experts and a lot of manual labor. At the same time, the proxy model has weak generalization ability when processing complex and diverse data sets, thereby reducing the optimization efficiency of the film hole arrangement of turbine blades. Finally, the objective function of the traditional film hole arrangement optimization design mainly focuses on the influence of the film hole arrangement method on the cooling characteristics of the blade, and rarely considers the influence of the film hole arrangement on the blade surface stress into the optimization design considerations.

[0060] Compared with traditional turbine cooling blades, the aperture of the film holes and the double-wall spacing of the double-wall turbine blades are only about 0.5 mm, which is much smaller than the span-wise height and flow-wise length of the turbine blades, and has a significant "cross-size" feature; at the same time, each cooling unit is arranged periodically, and each unit contains staggered and densely packed film holes, impact holes and spoiler columns. The structure is very complex, with the characteristics of small structural size, large number of holes / columns, and periodic and dense arrangement.

[0061] Therefore, in view of the characteristics of the traditional double-wall turbine blade film hole arrangement optimization method that cannot fully consider the internal forces of the blade, is difficult to parametrically describe the overall blade film holes, and cannot provide the optimal film hole distribution strategy, this application has developed a double-wall turbine blade film hole arrangement optimization design method. This method combines parametric modeling with the CGAN neural network model to predict the surface stress of the turbine blade under different film hole arrangements when numerically analyzing and calculating the performance of the turbine blade. The optimization algorithm is used to quickly complete the optimization process of the turbine blade film hole arrangement. This method can greatly improve the efficiency of using numerical methods to evaluate the strength of the film hole structure and reduce the calculation cost.

[0062] The implementation details of the technical solution of the embodiment of the present disclosure are elaborated in detail below.

[0063] Figure 1 The following is a schematic diagram of a flow chart of a method for arranging air film holes of a turbine blade in an exemplary embodiment of the present disclosure. Figure 1 As shown, the method for arranging air film holes of a turbine blade includes steps S101 to S103:

[0064] Step S101, constructing a design sample space based on the value range of the air film hole arrangement parameter of the turbine blade; wherein the design sample space includes a plurality of turbine blade sample models with different air film hole arrangements;

[0065] Step S102, establishing an objective function with the goal of minimizing the stress prediction value of the turbine blade sample model; wherein the stress prediction value is calculated based on a pre-trained stress prediction model; and establishing constraint conditions based on the upper limit and lower limit of the design sample space;

[0066] Step S103 , establishing an air film hole arrangement optimization model according to the objective function and the constraint conditions, and solving the air film hole arrangement optimization model to determine target air film hole arrangement parameters.

[0067] In the technical solutions provided in some embodiments of the present disclosure, on the one hand, an objective function is established with the goal of minimizing the stress prediction value of the turbine blade sample model, and the stress distribution on the surface of the turbine blade is taken into consideration for optimization, so that the stress around the optimized air film hole is alleviated, and the phenomenon of air film hole stress interference can be avoided; on the other hand, a pre-trained stress prediction model is used to calculate the stress value. Compared with the simulation numerical calculation of the turbine blade sample model to obtain the stress value, the time of numerical calculation in the optimization process is greatly reduced, and the optimization efficiency and accuracy are improved. Compared with the traditional air film hole optimization using an agent model, it has the advantages of strong nonlinear modeling ability, better adaptability to complex data patterns and laws, stronger adaptability and parallel computing capabilities, and obvious advantages in processing large-scale data.

[0068] Below, each step of a method for arranging air film holes for a turbine blade in this example implementation will be described in more detail with reference to the accompanying drawings and embodiments.

[0069] In step S101, a design sample space is constructed based on the value range of the film hole arrangement parameters of the turbine blade; wherein the design sample space includes a plurality of turbine blade sample models with different film hole arrangements.

[0070] The film hole is an important structure in the double-wall turbine cooling blade. The relative position of the film hole and the blade profile will significantly affect the film hole outflow and the flow characteristics of the blade channel. At the same time, there is a complex composite angle between the film hole and the blade surface. Therefore, the position and angle of the film hole should be refined, and these two aspects should also be considered in the parametric modeling design to determine the appropriate parametric design variables to facilitate the optimization of the model. The present disclosure proposes a parametric design method of associated characteristic dimensions, which can realize the flexible adjustment of the shape and position of the film hole, and fully explore the design space on the basis of ensuring the correctness of the model.

[0071] In one embodiment of the present disclosure, the air film hole arrangement parameters include position parameters and rotation angle parameters, wherein the position parameters characterize the arrangement of the air film holes, and the rotation angle parameters characterize the rotation angle of a single air film hole.

[0072] (1) Position parameters

[0073] Figure 2 A schematic diagram schematically shows the arrangement of air film holes on a turbine blade surface in an exemplary embodiment of the present disclosure, with reference to Figure 2 As shown in the figure, the arrangement of the air film holes on the turbine blade has the property of being densely arranged in columns. When the distance between the holes is too wide, the surrounding area of ​​each hole will bear a greater load, which will lead to a decrease in the overall strength of the material, thereby affecting the stability and life of the structure. On the contrary, when the hole spacing becomes narrower, stress interference around the holes will cause stress concentration in the material, which is easy to cause the formation of microcracks, which may cause fatigue damage and fracture of the material. Therefore, the spacing of the air film holes should be within a reasonable range.

[0074] Since the positions of the air film holes in a single row are still irregular, the present disclosure proposes to divide the air film holes on the turbine blade into multiple groups, and divide the air film holes located in the same row of the turbine blade, with continuous positions, the same air film hole spacing and the same air film hole rotation angle into the same group of air film holes. In this way, each row of air film holes is composed of several groups of air film holes, and the center position of the air film holes in this group is calculated by group, and then the single air film hole arrangement trajectory curve can be obtained by connecting the center positions of different groups of air film holes in a single row of air film holes.

[0075] In one embodiment of the present disclosure, the position parameters include one or more of the distance from the center position of the air film holes of a single group of air film holes to the central axis, the distance from the starting air film hole position to the central axis, the distance from the starting air film hole position to the blade top, the angle between the connecting line of the single group of air film holes and the horizontal axis, the number of air film holes in a single group, and the spacing between each air film hole in a single group.

[0076] Specifically, Figure 3 A schematic diagram schematically shows a film hole position parameter in an exemplary embodiment of the present disclosure. Figure 3 As shown, a single row of air film holes is divided into three groups, namely group 1, group 2, and group 3. S is the distance from the center position of the air film hole to the central axis, and the three groups correspond to S1, S2, and S3 respectively.

[0077] Figure 4 A schematic diagram of a single group of air film hole position parameters in an exemplary embodiment of the present disclosure is schematically shown. Taking a group of air film holes after grouping as a parameterized object as an example, the first air film hole in each group is taken as the starting air film hole position, and the single group of air film hole position parameters specifically include:

[0078] x: the distance between the starting air film hole position and the central axis;

[0079] y: the distance between the starting air film hole position and the leaf top;

[0080] θ: the angle between the line connecting a single group of air film holes and the horizontal axis;

[0081] N: the number of single group of air film holes;

[0082] d: The distance between each pair of air film holes in a single group of air film holes.

[0083] (2) Rotation angle parameters

[0084] In double-walled turbine blades, the film hole angle has an important influence on the blade strength and stability. The hole angle affects the rigidity and bending vibration characteristics of the blade. Due to the influence of gas flow, the film hole will produce tiny vibrations when the blade is running, further affecting the vibration characteristics of the blade. By optimizing the film hole angle, the stress level around the edge of the film hole and the blade surface can be reduced, and the durability and life of the blade can be improved.

[0085] In one embodiment of the present disclosure, the rotation angle parameter includes one or more of a rotation angle normal angle, a rotation angle circumferential angle, and a rotation angle circular angle of a single air film hole.

[0086] Figure 5 A schematic diagram of the rotation parameters of a film hole in an exemplary embodiment of the present disclosure is schematically shown. Since the aerodynamic shape of a turbine blade usually presents complex three-dimensional bending, twisting and sweeping characteristics, it is difficult to determine the deflection angle of the film hole. Therefore, it is necessary to establish a local coordinate system to realize the parametric design of the film hole. Figure 5 As shown, a local coordinate system is established by passing through the center point of the air film hole, taking the normal line along the normal direction of the blade surface as the x-axis, the tangential line as the y-axis, and the blade height direction as the z-axis.

[0087] Figure 6 The schematic diagram of the rotation parameters of a single air film hole in the exemplary embodiment of the present disclosure is schematically shown. The air film hole angle positioning parameters are designed with the air film hole rotation angle normal angle α around the local coordinate system y-axis; rotation angle circumferential angle β around the local coordinate system x-axis; and rotation angle circumferential angle γ around the local coordinate system z-axis as parameters.

[0088] In this way, the film hole arrangement parameters specifically include: the distance S from the center position of each group of film holes to the central axis, the distance x from the starting film hole position to the central axis, the distance y from the starting film hole position to the blade top, the angle θ between the connecting line of a single group of film holes and the horizontal axis, the number of film holes in a single group N, the distance d between each pair of film holes in a single group, and the rotation angle normal angle α, rotation angle circumferential angle β and rotation angle circular angle γ of a single film hole.

[0089] Then, in step S101, a design sample space is constructed based on the value range of the film hole arrangement parameters of the turbine blade. Specifically, after the film hole arrangement parameters are preset, a reasonable value range can be set for each film hole arrangement parameter, and the experimental design method (DOE) is used according to this value range. According to the variation range of the design variables, a plurality of turbine blade sample models with different film hole arrangements can be constructed as the design sample space.

[0090] Among them, DOE (Design of Experiments) is an experimental design method used to explore and verify the impact of factors on results. In DOE, experiments are usually divided into multiple combinations, each of which controls a factor and measures its impact on the results. In this way, we can have a more comprehensive understanding of the impact of factors on the results and determine the best factor combination.

[0091] In step S102, an objective function is established with the goal of minimizing the stress prediction value of the turbine blade sample model; wherein the stress prediction value is calculated based on a pre-trained stress prediction model; and constraint conditions are established based on the upper and lower limits of the design sample space.

[0092] Specifically, in order to balance the optimization efficiency and accuracy during the optimization process, the stress prediction value of the turbine blade sample model calculated by the stress prediction model is used as the stress analysis result of the model surface to replace the actual stress simulation value. In this way, there is no need to perform simulation calculations for each turbine blade sample model, which can greatly reduce the calculation process and improve the optimization efficiency of the air film hole arrangement design.

[0093] In one embodiment of the present disclosure, the method also includes: pre-training the stress prediction model, and the pre-training of the stress prediction model includes: extracting turbine blade sample models in the design sample space as training samples; performing blade strength simulation on the training samples to obtain stress simulation values ​​corresponding to each of the training samples; and training the stress prediction model according to the stress simulation values ​​corresponding to each of the training samples.

[0094] Specifically, the stress prediction model can be a CGAN (conditional generative adversarial neural network) model. In simple terms, CGAN puts the idea of ​​supervised learning on a generative model, and can expect to generate corresponding outputs based on the labels of the network input.

[0095] Figure 7 The model structure diagram of a CGAN model in an exemplary embodiment of the present disclosure is schematically shown. Figure 7 As shown, the CGAN model consists of a definition generator and a discriminator.

[0096] Figure 8A schematic diagram of a stress prediction model training method in an exemplary embodiment of the present disclosure is schematically shown, with reference to Figure 8 As shown, the stress prediction model is trained according to the stress simulation values ​​corresponding to the training samples, including:

[0097] Step S801, performing two-dimensional expansion on the surface of the training sample to obtain an air film hole distribution matrix;

[0098] Step S802, using the definition generator to calculate the stress prediction value corresponding to the training sample according to the air film hole distribution matrix;

[0099] Step S803, using the discriminator to discriminate whether the stress prediction value is generated by the generator or is a stress simulation value;

[0100] Step S804, alternately training the definition generator and the discriminator to modify model parameters until a training stop condition is met.

[0101] Specifically, in step S801, the surface of the training sample is two-dimensionally unfolded to obtain an air film hole distribution matrix.

[0102] Fig. 9 The following schematically shows a flow chart of obtaining a film hole distribution matrix in an exemplary embodiment of the present disclosure. Each training sample is a turbine blade sample model. The surface of the turbine blade is two-dimensionally unfolded and then divided into grids to extract the coordinate data of each grid part, thereby obtaining the film hole distribution matrix. Fig. 9 As shown in the figure, the square in the matrix indicates that there is an air film hole in this part, and α, β, and γ are the rotation angle parameters of the air film hole. The final output stress distribution result is also presented in the form of a matrix.

[0103] In step S802, the definition generator is used to calculate the stress prediction value corresponding to the training sample according to the air film hole distribution matrix.

[0104] In one embodiment of the present disclosure, the specific process of step S802 is as follows: for a training sample, the air film hole distribution matrix of the training sample is encoded to obtain a first feature map; the boundary condition is converted by a first fully connected layer and added to the first feature map in an element-by-element manner to obtain a stress distribution result; the stress distribution result is decoded to obtain a stress value; and the training samples are traversed to obtain the stress values ​​corresponding to each of the training samples.

[0105] like Figure 7As shown in the figure, the definition generator first encodes Input1 into a feature map. Input1 is the air film hole distribution matrix, which is the geometric information of the air film hole arrangement; then Input2 is converted by the first fully connected layer (FC1) and added to the feature map in an element-by-element manner. Input2 is the boundary condition of the training model; finally, the result is decoded into the output result to obtain the stress value, which is the stress prediction value generated by the definition generator.

[0106] In step S803, the discriminator is used to discriminate whether the stress prediction value is generated by the generator or is a stress simulation value;

[0107] In one embodiment of the present disclosure, the specific process of step S803 is as follows: for a training sample, the air film hole distribution matrix, stress prediction value and stress simulation value of the training sample are connected and encoded to obtain a second feature map; the boundary conditions are converted by the second fully connected layer and added to the second feature map in an element-by-element manner to obtain a feature result; the feature result is converted and evaluated to determine whether the feature result belongs to the generator or the stress simulation value.

[0108] like Figure 7 As shown in the figure, after defining the generator to convert geometric information and boundary conditions into stress distribution, the discriminator is used to evaluate the predicted data. The discriminator first uses the encoding block (Encode) to concatenate the geometric information and pressure distribution into the feature map. The pressure distribution includes the stress prediction value generated by the generator and the stress simulation value obtained by simulation; then, Input2 (boundary conditions) is added to this feature map in element form through the second fully connected layer (FC2); the result is finally converted through the "Conv" block to identify whether the stress distribution belongs to the generator or the stress simulation value.

[0109] In step S804, the definition generator and the discriminator are alternately trained to modify model parameters until a training stop condition is met.

[0110] Through model training, the stress prediction value generated by the definition generator can finally pass the verification of the discriminator. Therefore, through the definition generator in the trained stress prediction model, the stress prediction value of the turbine blade sample model can be calculated. This stress prediction value can be close to the stress simulation value obtained by blade strength simulation without the need for complex simulation experiments, which can greatly improve the optimization efficiency of the air film hole arrangement.

[0111] After the stress prediction model is trained, the optimization model for the arrangement of film holes can be constructed. The objective function is formed by minimizing the surface stress value σ=F(x) of the turbine blade; the distance S from the center position of each group of film holes to the central axis, the distance x from the starting film hole position to the central axis, the distance y from the starting film hole position to the blade top, the angle θ between the connecting line of a single group of film holes and the horizontal axis, the number N of a single group of film holes, the distance d between the two film holes in a single group of film holes, and the normal angle α, the circumferential angle β and the circumferential angle γ of the rotation angle of a single film hole are used as decision variables; and the upper and lower limits of the design sample space are set as constraints to construct the optimization model for the arrangement of film holes, as follows:

[0112] findX=[S, x, y, θ, N, d, α, β, γ] (5)

[0113] min[F(x)](6)

[0114] st. U≤X≤V (7)

[0115] Among them, X is a turbine blade sample model, U and V are the upper and lower limits of the design sample space respectively.

[0116] In step S103, an air film hole arrangement optimization model is established according to the objective function and the constraint conditions, and the air film hole arrangement optimization model is solved to determine target air film hole arrangement parameters.

[0117] Specifically, after the air film hole arrangement optimization model is established according to the objective function and constraint conditions in step S102, the optimization algorithm can be used to solve the model. The present disclosure does not specifically limit the optimization algorithm, for example, genetic algorithm, ant colony algorithm, simulated annealing algorithm, etc. can solve the problem.

[0118] In one embodiment of the present disclosure, the overall air film hole arrangement design optimization system is fully described, and the specific steps are as follows:

[0119] (1) Select the distance S from the center of the film hole to the central axis, the distance x from the starting film hole position to the central axis, the distance y from the starting film hole position to the blade tip, the angle θ between the line connecting a single group of film holes and the horizontal axis, the number N of film holes in a single group, the distance d between two film holes in a single group, the normal angle α, the circumferential angle β and the circumferential angle γ of the film hole as design variables, give their value ranges, and establish the design space;

[0120] (2) Using the DOE experimental design method, a series of design sample spaces X = (x1, x2, x3....xn) can be constructed in the design space;

[0121] (3) Based on the parametric design method of the air film hole, the blade strength simulation method is used to calculate the response σ = F (x) = (y1, y2, y3...yn) at each sample point (i.e., a turbine blade sample model), that is, the stress distribution on the turbine blade surface at each design sample point;

[0122] (4) Based on the existing DOE test design sample data, the CGAN neural network model is trained and outputs the stress distribution prediction value;

[0123] (5) Use the multi-island genetic algorithm to perform optimization calculations and determine the air film hole arrangement parameters under the optimal stress distribution.

[0124] Based on the above method, the present invention uses the distance S from the center position of the densely arranged film holes to the central axis, the distance x from the starting film hole position to the central axis, the distance y from the starting film hole position to the blade top, the angle θ between the line connecting a single group of film holes and the horizontal axis, the number N of film holes in a single group, the distance d between each pair of film holes in a single group, the normal angle α, the circumferential angle β and the circumferential angle γ of the film holes as design variables; the film hole arrangement design sample space and its response are obtained by using the DOE experimental design method and numerical simulation technology; the objective function is established through the numerical distribution of stress, the CGAN neural network model is trained based on the real results of simulation calculation, and the stress distribution on the surface of the turbine blade is predicted; finally, the film hole arrangement design optimization method is established in combination with the optimization algorithm, and the film hole arrangement method with better mechanical properties can be obtained through optimal calculation. The main technical effects are:

[0125] (1) The present invention develops a parameterized technology for film hole arrangement based on the effect of film hole arrangement on the strength of turbine blades in the complex service environment of turbine blades. The film hole arrangement mode and rotation angle are taken into account in the optimized design of film hole arrangement of turbine blades, and the design variables associated with them will be automatically coordinated and changed to ensure the integrity of the overall geometric model and the local cooling feature structure. The circumferential stress of the optimized film holes is alleviated, and the phenomenon of film hole stress interference is avoided. It is more comprehensive than the traditional film hole arrangement that only considers the local film hole spacing or treats each row of film holes as a continuous, equally spaced arrangement with the same punching direction.

[0126] (2) Combined with DOE experimental design, the conditional generative adversarial neural network (CGAN) model and optimization algorithm were used to construct an optimization system with the arrangement of film holes and the rotation angle as parameters and the stress distribution on the turbine blade surface as the objective function. Compared with the traditional film hole arrangement optimization design, the stress distribution on the turbine blade surface was taken into consideration during the optimization. At the same time, the use of the neural network model greatly reduced the time of numerical calculations in the optimization process, improved the optimization efficiency and accuracy, and compared with the traditional film hole optimization method using a proxy model, it has strong nonlinear modeling capabilities and can better adapt to complex data patterns and laws; automatic feature extraction, simplified model building process; stronger adaptability and parallel computing capabilities, and has obvious advantages in processing large-scale data.

[0127] Fig.10 A schematic diagram schematically shows the composition of a film hole arrangement device for a turbine blade in an exemplary embodiment of the present disclosure, as shown in FIG. Fig.10 As shown, the air film hole arrangement device 1000 for a turbine blade may include a sample module 1001, a model module 1002 and a solution module 1003. Among them:

[0128] The sample module 1001 is used to construct a design sample space based on the value range of the air film hole arrangement parameter of the turbine blade; wherein the design sample space includes a plurality of turbine blade sample models with different air film hole arrangements;

[0129] Model module 1002, used to establish an objective function with the minimum stress prediction value of the turbine blade sample model as the goal; wherein the stress prediction value is calculated based on a pre-trained stress prediction model; and to establish constraint conditions based on the upper limit value and the lower limit value of the design sample space;

[0130] The solution module 1003 is used to establish an air film hole arrangement optimization model according to the objective function and the constraint conditions, and solve the air film hole arrangement optimization model to determine target air film hole arrangement parameters.

[0131] According to an exemplary embodiment of the present disclosure, the air film hole arrangement parameters include position parameters and rotation angle parameters; wherein, the turbine blade includes multiple groups of air film holes, and the position parameters include one or more of the distance from the center position of the air film holes of a single group of air film holes to the central axis, the distance from the starting air film hole position to the central axis, the distance from the starting air film hole position to the blade top, the angle between the connecting line of the single group of air film holes and the horizontal axis, the number of air film holes in a single group, and the distance between each pair of air film holes in a single group; the rotation angle parameters include one or more of the rotation angle normal angle, rotation angle circumferential angle and rotation angle circular angle of a single air film hole.

[0132] According to an exemplary embodiment of the present disclosure, the film holes located in the same row of the turbine blade, with continuous positions, the same film hole spacing and the same film hole rotation angle constitute a group of film holes.

[0133] According to an exemplary embodiment of the present disclosure, the film hole arrangement device 1000 for a turbine blade also includes a training model module for pre-training the stress prediction model, including: extracting turbine blade sample models in the design sample space as training samples; performing blade strength simulation on the training samples to obtain stress simulation values ​​corresponding to each of the training samples; and training the stress prediction model according to the stress simulation values ​​corresponding to each of the training samples.

[0134] According to an exemplary embodiment of the present disclosure, the stress prediction model is a CGAN model, which includes a definition generator and a discriminator. The training model module is also used to two-dimensionally unfold the surface of the training sample to obtain an air film hole distribution matrix; use the definition generator to calculate the stress prediction value corresponding to the training sample according to the air film hole distribution matrix; use the discriminator to discriminate whether the stress prediction value belongs to the generator or the stress simulation value; alternately train the definition generator and the discriminator to modify the model parameters until the training stop condition is met.

[0135] According to an exemplary embodiment of the present disclosure, the training model module is also used to encode the air film hole distribution matrix of a training sample to obtain a first feature map; add the boundary conditions to the first feature map in an element-by-element manner after conversion through a first fully connected layer to obtain a stress distribution result; decode the stress distribution result to obtain a stress value; and traverse the training samples to obtain the stress values ​​corresponding to each of the training samples.

[0136] According to an exemplary embodiment of the present disclosure, the training model module is also used to connect and encode the air film hole distribution matrix, stress prediction value and stress simulation value of a training sample to obtain a second feature map; add the boundary conditions to the second feature map in an element-by-element manner after conversion through a second fully connected layer to obtain a feature result; convert and evaluate the feature result to determine whether the feature result belongs to the generator or the stress simulation value.

[0137] The specific details of each module in the above-mentioned film hole arrangement device 1000 for turbine blades have been described in detail in the corresponding film hole arrangement method for turbine blades, so they will not be repeated here.

[0138] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0139] In an exemplary embodiment of the present disclosure, a storage medium capable of implementing the above method is also provided. Fig.11 A schematic diagram schematically illustrates a computer-readable storage medium in an exemplary embodiment of the present disclosure, such as Fig.11 As shown, a program product 1100 for implementing the above method according to an embodiment of the present disclosure is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a mobile phone. However, the program product of the present disclosure is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0140] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided. Fig.12 The structure diagram of a computer system of an electronic device in an exemplary embodiment of the present disclosure is schematically shown.

[0141] It should be noted that Fig.12 The computer system 1200 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0142] like Fig.12 As shown, the computer system 1200 includes a central processing unit (CPU) 1201, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 1202 or the program loaded from the storage part 1208 to the random access memory (RAM) 1203. Various programs and data required for system operation are also stored in the RAM 1203. The CPU 1201, the ROM 1202 and the RAM 1203 are connected to each other through a bus 1204. An input / output (I / O) interface 1205 is also connected to the bus 1204.

[0143] The following components are connected to the I / O interface 1205: an input section 1206 including a keyboard, a mouse, etc.; an output section 1207 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1208 including a hard disk, etc.; and a communication section 1209 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 1209 performs communication processing via a network such as the Internet. A drive 1210 is also connected to the I / O interface 1205 as needed. A removable medium 1211, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 1210 as needed so that a computer program read therefrom is installed into the storage section 1208 as needed.

[0144] In particular, according to an embodiment of the present disclosure, the process described below with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part 1209, and / or installed from a removable medium 1211. When the computer program is executed by a central processing unit (CPU) 1201, various functions defined in the system of the present disclosure are executed.

[0145] It should be noted that the computer-readable medium shown in the embodiment of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by an instruction execution system, device or device or used in combination with it. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0146] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0147] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, and the units described may also be arranged in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0148] As another aspect, the present disclosure further provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the method described in the above embodiment.

[0149] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0150] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0151] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure.

[0152] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for arranging air film holes of a turbine blade, characterized in that: include: Constructing a design sample space based on the value range of the air film hole arrangement parameter of the turbine blade; wherein the design sample space includes a plurality of turbine blade sample models with different air film hole arrangements; Establishing an objective function with the goal of minimizing the stress prediction value of the turbine blade sample model; wherein the stress prediction value is calculated based on a pre-trained stress prediction model; and establishing constraint conditions based on the upper and lower limits of the design sample space; An air film hole arrangement optimization model is established according to the objective function and the constraint conditions, and the air film hole arrangement optimization model is solved to determine target air film hole arrangement parameters.

2. The method for arranging air film holes of a turbine blade according to claim 1, characterized in that: The film hole arrangement parameters include position parameters and rotation angle parameters; wherein, the turbine blade includes multiple groups of film holes, and the position parameters include one or more of the distance from the center position of the film holes of a single group of film holes to the central axis, the distance from the starting film hole position to the central axis, the distance from the starting film hole position to the blade top, the angle between the connecting line of the single group of film holes and the horizontal axis, the number of film holes in a single group, and the spacing between each pair of film holes in a single group; the rotation angle parameters include one or more of the rotation angle normal angle, rotation angle circumferential angle, and rotation angle circular angle of a single film hole.

3. The method for arranging air film holes of a turbine blade according to claim 2, characterized in that: The air film holes that are located in the same row of the turbine blade, have continuous positions, have the same air film hole spacing and the same air film hole rotation angle are a group of air film holes.

4. The method for arranging film holes of a turbine blade according to claim 1, characterized in that: The method further includes: pre-training the stress prediction model, wherein the pre-training the stress prediction model includes: Extracting turbine blade sample models in the design sample space as training samples; Performing blade strength simulation on the training samples to obtain stress simulation values ​​corresponding to each of the training samples; The stress prediction model is trained according to the stress simulation values ​​corresponding to the training samples.

5. The method for arranging film holes of a turbine blade according to claim 4, characterized in that: The stress prediction model is a CGAN model, and the CGAN model includes a definition generator and a discriminator. The stress prediction model is trained according to the stress simulation values ​​corresponding to each of the training samples, including: Expanding the surface of the training sample in two dimensions to obtain an air film pore distribution matrix; Utilizing the definition generator to calculate the stress prediction value corresponding to the training sample according to the air film hole distribution matrix; Using the discriminator to discriminate whether the stress prediction value is generated by the generator or is a stress simulation value; The definition generator and the discriminator are alternately trained to modify model parameters until a training stop condition is met.

6. The method for arranging air film holes of a turbine blade according to claim 5, characterized in that: The using the definition generator to calculate the stress value corresponding to the training sample according to the air film hole distribution matrix includes: For a training sample, encoding the air film hole distribution matrix of the training sample to obtain a first feature map; The boundary conditions are converted by the first fully connected layer and added to the first feature map in an element-wise manner to obtain a stress distribution result; Decoding the stress distribution result to obtain a stress value; The training samples are traversed to obtain stress values ​​corresponding to the training samples.

7. The method for arranging film holes of a turbine blade according to claim 5, characterized in that: The discriminator is used to discriminate whether the stress prediction value is generated by the generator or is a stress simulation value: For a training sample, the air film hole distribution matrix, the stress prediction value and the stress simulation value of the training sample are connected and encoded to obtain a second feature map; Adding the boundary condition to the second feature map in an element-wise manner after being transformed by the second fully connected layer to obtain a feature result; The characteristic results are converted and evaluated to determine whether the characteristic results belong to generator generation or stress simulation values.

8. A film hole arrangement device for a turbine blade, characterized in that: include: A sample module, used to construct a design sample space based on the value range of the air film hole arrangement parameter of the turbine blade; wherein the design sample space includes a plurality of turbine blade sample models with different air film hole arrangements; A model module, for establishing an objective function with the goal of minimizing the stress prediction value of the turbine blade sample model; wherein the stress prediction value is calculated based on a pre-trained stress prediction model; and establishing constraint conditions based on the upper limit and lower limit of the design sample space; A solution module is used to establish an air film hole arrangement optimization model according to the objective function and the constraint conditions, and solve the air film hole arrangement optimization model to determine target air film hole arrangement parameters.

9. A computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the method for arranging film holes for a turbine blade according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the method for arranging air film holes for a turbine blade as described in any one of claims 1 to 7.

Images