Electrode punching method, device and equipment applied to turbine blade

Abstract

The embodiment of the invention discloses an electrode punching method, device and equipment applied to a turbine blade. A specific embodiment of the method comprises the following steps: generating data information of a to-be-processed special-shaped hole according to a pre-trained semantic segmentation model and three-dimensional data information of a blade; according to the data information of the to-be-machined special-shaped hole, initial motion path information is generated; generating changed motion path information according to the initial motion path information; generating electrode motion path information according to the changed motion path information, the blade three-dimensional data information and the electrode tool three-dimensional data information; according to the multi-axis linkage punching treatment mode, the real-time pulse voltage information and the electrode movement path information, a preset electrode punching tool is controlled to conduct punching treatment on the to-be-punched workpiece information, and initial special-shaped hole information is obtained; and obtaining the special-shaped hole information according to a preset quality standard constraint condition and the initial special-shaped hole information. According to the implementation mode, the time consumption of the punching process period is shortened, and the consumed material cost is reduced.

Description

Technical Field

[0001] This application relates to the field of computer and machining technology, specifically to electrode drilling methods, apparatus and equipment applied to turbine blades. Background Technology

[0002] Machining numerous complex irregular holes on turbine blades can create a cooling film to protect the blades operating in extreme high-temperature environments. Current methods for drilling holes in turbine blades involve generating fixed parameters based on a simplified geometric model, and then performing electrical discharge machining (EDM) on these parameters to create the irregular holes.

[0003] However, in practice, it has been found that the following technical problems often arise when drilling holes in turbine blades using the above method: The fixed parameters generated by the simplified geometric model are not adaptable enough to the processing of new or complex irregular holes. Before the actual drilling process, repeated parameter adjustments and offline testing are required for trial processing, which results in a long drilling cycle. In addition, the trial processing will directly consume the tool electrode and turbine blade material, resulting in high material costs.

[0004] The information disclosed in this background section is only intended to enhance the understanding of the background of the inventive concept, and therefore may contain information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0006] Some embodiments of this disclosure provide methods, apparatus, electronic devices, and computer-readable media for electrode drilling applied to turbine blades to solve one or more of the technical problems mentioned in the background section above.

[0007] In a first aspect, some embodiments of this disclosure provide an electrode drilling method applied to turbine blades. The method includes: generating data information of a non-standard hole to be processed based on three-dimensional data information of the blade corresponding to the workpiece to be drilled, using a pre-trained semantic segmentation model and acquired data; generating initial motion path information of a preset electrode drilling tool based on the non-standard hole data; generating modified motion path information based on the initial motion path information; and generating electrode motion path information based on the modified motion path information, the three-dimensional data information of the blade, and the three-dimensional data information of the electrode tool. The generation of electrode motion path information based on the modified motion path information, the three-dimensional data information of the blade, and the three-dimensional data information of the electrode tool includes: generating electrode motion path information based on the modified motion path information, the three-dimensional data information of the blade, and the three-dimensional data information of the electrode tool. The path information, the aforementioned blade 3D data information, and the electrode tool 3D data information are used to generate a multiphysics drilling simulation model and corresponding boundary conditions for the multiphysics drilling simulation model. Based on the multiphysics drilling simulation model, the aforementioned boundary conditions, and the preset result data structure template, predicted processing result information is generated. In response to the detection that the predicted processing result information meets the preset processing standard constraints, the aforementioned changed motion path information is determined as the electrode motion path information. Based on the multi-axis linkage drilling processing method, real-time pulse voltage information, and the aforementioned electrode motion path information, the aforementioned preset electrode drilling tool is controlled to perform drilling processing on the aforementioned workpiece information to be drilled, obtaining initial irregular hole information. Based on the preset quality standard constraints and the aforementioned initial irregular hole information, the irregular hole information is determined.

[0008] Secondly, some embodiments of this disclosure provide an electrode drilling device for turbine blades, including a first generation unit configured to generate data information of a non-standard hole to be processed based on a pre-trained semantic segmentation model and the acquired blade 3D data information corresponding to the workpiece to be drilled; a second generation unit configured to generate initial motion path information of a preset electrode drilling tool based on the aforementioned non-standard hole data information; a third generation unit configured to generate modified motion path information based on the aforementioned initial motion path information; and a fourth generation unit configured to generate electrode motion path information based on the aforementioned modified motion path information, the aforementioned blade 3D data information, and the electrode tool 3D data information, wherein the aforementioned modified motion path information, the aforementioned blade 3D data information, and the electrode tool 3D data information are used to generate electrode motion path information. The tool's three-dimensional data information is used to generate electrode motion path information, including: generating a multiphysics drilling simulation model and corresponding boundary conditions based on the modified motion path information, the blade's three-dimensional data information, and the electrode tool's three-dimensional data information; generating predicted processing result information based on the multiphysics drilling simulation model, the boundary conditions, and a preset result data structure template; and determining the modified motion path information as electrode motion path information in response to detecting that the predicted processing result information meets preset processing standard constraints. A drilling unit is configured to control the preset electrode drilling tool to drill the workpiece information to be drilled according to a multi-axis linkage drilling processing method, real-time pulse voltage information, and the electrode motion path information, to obtain initial irregular hole information. A determination unit is configured to determine the irregular hole information based on preset quality standard constraints and the initial irregular hole information.

[0009] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0010] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method described in any of the implementations of the first or second aspect.

[0011] The above-described embodiments of this disclosure have the following beneficial effects: The electrode drilling method for turbine blades according to some embodiments of this disclosure can shorten the drilling process cycle time and reduce material costs. The reason for the long drilling process cycle time and high material costs is that the fixed parameters generated based on simplified geometric models are insufficiently adaptable to processing new or complex irregular holes. Before actual drilling, repeated parameter adjustments and offline testing are required for trial processing, resulting in a long drilling process cycle. Furthermore, the trial processing directly consumes tool electrode and turbine blade materials, leading to high material costs. Therefore, the electrode drilling method for turbine blades according to some embodiments of this disclosure first generates irregular hole data information based on a pre-trained semantic segmentation model and the obtained blade 3D data information corresponding to the workpiece to be drilled. Thus, the irregular hole data to be processed can be obtained. Then, based on the aforementioned irregular hole data information, the initial motion path information of the corresponding preset electrode drilling tool is generated. Thus, the initial motion path of the corresponding preset electrode drilling tool can be obtained. Subsequently, based on the initial motion path information, modified motion path information is generated. This allows the initial motion path of the preset electrode drilling tool to be modified, resulting in a modified motion path. Next, based on the modified motion path information, the blade 3D data information, and the electrode tool 3D data information, electrode motion path information is generated. This generation of electrode motion path information includes: generating a multiphysics drilling simulation model and corresponding boundary conditions based on the modified motion path information, the blade 3D data information, and the electrode tool 3D data information; generating predicted processing result information based on the multiphysics drilling simulation model, the boundary conditions, and a preset result data structure template; and, in response to the detection that the predicted processing result information meets preset processing standard constraints, determining the modified motion path information as the electrode motion path information. Thus, the final motion path of the preset electrode drilling tool can be obtained. Subsequently, based on the multi-axis linkage drilling processing method, real-time pulse voltage information, and the aforementioned electrode motion path information, the preset electrode drilling tool is controlled to drill the workpiece information to be drilled, obtaining initial irregular hole information. Thus, the workpiece information to be drilled can be drilled to obtain initial irregular holes. Finally, based on preset quality standard constraints and the aforementioned initial irregular hole information, the irregular hole information is determined. Thus, the final irregular hole can be determined.Because it doesn't rely on fixed parameters generated from a simplified geometric model, but rather uses a pre-trained semantic segmentation model and the type of the irregular hole to be processed to segment the data, and determines the electrode movement path based on this data, it can better meet actual production needs, reducing rework due to defects and shortening the time spent on rework. Furthermore, because it uses a multi-axis linkage drilling process, controlling a preset electrode drilling tool to drill holes in the workpiece information, and introducing preset quality standard constraints to verify the initial irregular hole information, it can improve the quality of the processed irregular holes, thereby reducing material waste caused by rework. Therefore, it can shorten the drilling process cycle time and reduce material costs. Attached Figure Description

[0012] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0013] Figure 1 This is a flowchart of some embodiments of the electrode drilling method applied to turbine blades according to the present disclosure; Figure 2 This is a schematic diagram of the structure of some embodiments of the electrode drilling device applied to turbine blades according to the present disclosure; Figure 3 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure; Figure 4 This is a magnifying glass inspection diagram of a drilled turbine blade suitable for implementing some embodiments of the present disclosure; Figure 5 This is a schematic diagram of a drilled turbine blade suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0014] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0015] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0016] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0017] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0018] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0019] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] Figure 1 A flow chart 100 of some embodiments of the electrode drilling method for turbine blades according to the present disclosure is shown. The electrode drilling method for turbine blades includes the following steps: Step 101: Generate the data information of the irregular hole to be processed based on the pre-trained semantic segmentation model and the obtained three-dimensional data information of the blade corresponding to the workpiece information to be drilled.

[0021] In some embodiments, the execution entity (e.g., a computing device) of the electrode drilling method applied to turbine blades can generate data information of irregular holes to be processed based on a pre-trained semantic segmentation model and the acquired blade 3D data information corresponding to the workpiece information to be drilled. The aforementioned blade 3D data information can represent a 3D CAD model of the turbine blade. The pre-trained semantic segmentation model can represent a semantic segmentation model; for example, the pre-trained semantic segmentation model can be a variant of the U-Net model. The pre-trained semantic segmentation model can include an encoder path, a bottleneck layer, a decoder path, and an output layer. The encoder path can include four sequentially connected downsampling stages. The downsampling stages can sequentially include a first convolutional layer, a first activation function layer, a second convolutional layer, a second activation function layer, and a downsampling layer. The decoder path can include four sequentially connected upsampling stages. The upsampling stages can sequentially include an upsampling layer, a feature concatenation layer, a third convolutional layer, a third activation function layer, a fourth convolutional layer, and a fourth activation function layer. The pre-trained semantic segmentation model can take the aforementioned blade 3D data information as input and the data information of the irregular holes to be processed as output. The pre-trained semantic segmentation model can be trained in batches. The data information of the irregular hole to be processed can characterize the type, theoretical centerline, inlet profile, outlet profile, and three-dimensional spatial vector direction of the axis of the irregular hole corresponding to the three-dimensional data information of the blade. Here, the type of the irregular hole is not limited; for example, the irregular hole can be a film gas hole. The theoretical centerline can characterize the axis of the aforementioned irregular hole as pre-defined. The inlet profile can characterize the boundary shape formed on the machining start surface after the electrode cuts into the turbine blade. The outlet profile can characterize the boundary shape formed on the machining end surface after the electrode cuts out of the workpiece. The machining start surface can characterize the three-dimensional spatial plane or curved surface into which the electrode begins to discharge and cuts. The machining end surface can characterize the three-dimensional spatial plane or curved surface cut out when the electrode ends to discharge. The three-dimensional spatial vector direction of the axis can characterize the three-dimensional vector of the theoretical centerline. The workpiece information to be drilled can characterize the turbine blade to be processed. In practice, the aforementioned execution entity can input the aforementioned three-dimensional data information of the blade into the aforementioned pre-trained semantic segmentation model to obtain the data information of the irregular hole to be processed.

[0022] Optionally, prior to step 101, the aforementioned execution entity may also perform the following steps: The first step involves modifying the 3D data generation model based on the target workpiece's 3D information set, resulting in a modified 3D data generation architecture. The target workpiece's 3D information in the aforementioned set can represent a 3D CAD model file of a turbine blade. The 3D data generation model can represent a neural network architecture based on hierarchical vector quantization encoding and conditional discrete diffusion. This neural network architecture can include a denoising diffusion probability model, an autoregressive decoder, and multiple parallel vector quantization autoencoders. Each of these parallel vector quantization autoencoders can include an encoder and a decoder. The encoder can include an input embedding layer, multiple Transformer encoding layers, and a vector quantization layer. The decoder can include an input layer, multiple Transformer decoding layers, and an output layer. The denoising diffusion probability model can represent a conditional diffusion model based on a Transformer architecture. This model can include multiple network blocks. Each network block can include a cross-attention layer. The denoising diffusion probability model can take a conditional vector as input and a three-level neural code tree as output. This denoising diffusion probability model can be trained in batches. The aforementioned autoregressive decoder may include an input embedding layer, multiple Transformer decoding layers, and an output layer. In practice, the execution entity uses a cross-entropy-guided masked autoregressive pre-training method to pre-train the aforementioned 3D data generation model using the target workpiece's 3D information set as labels, resulting in the pre-trained 3D data generation model.

[0023] The second step is to generate a condition vector based on the target workpiece parameters. These target workpiece parameters can represent the pre-defined design parameters of the turbine blade requiring drilling. The specific content of these design parameters is not limited here; for example, the design parameter could be the blade height. The condition vector represents the instructions from the 3D data generation model to generate the corresponding 3D blade data information based on the design parameters. In practice, firstly, the executing entity can encode the target workpiece parameters using an embedded lookup table to obtain the encoded target workpiece parameters. Then, the encoded target workpiece parameters are used as the condition vector.

[0024] The third step is to generate the blade's three-dimensional data information based on the three-dimensional data generation model and the conditional vectors described above.

[0025] Optionally, the aforementioned execution entity can generate blade three-dimensional data information based on the aforementioned three-dimensional data generation model and condition vector through the following steps: Based on the above 3D data, generate the model and perform the following steps: The first step is to generate a three-level neural code tree based on the aforementioned conditional vectors. This three-level neural code tree can represent the implicit neural representation of the turbine blade. The three-level neural code tree can include a global layer, a contour layer, and a curve layer. The global layer represents the shape and topology of the turbine blade. The contour layer represents the cross-sectional contour of the turbine blade. The curve layer represents the size and shape of the turbine blade. In practice, the executing entity can input the aforementioned conditional vectors into the aforementioned denoising diffusion probability model to obtain the three-level neural code tree.

[0026] The second step involves generating the blade's three-dimensional data information corresponding to the workpiece information to be drilled, based on the aforementioned three-level neural code tree. In practice, the executing entity can input the aforementioned three-level neural code tree into the aforementioned autoregressive decoder to obtain the blade's three-dimensional data information corresponding to the workpiece information to be drilled.

[0027] Step 102: Generate the initial motion path information of the corresponding preset electrode drilling tool based on the data information of the irregular hole to be processed.

[0028] In some embodiments, the execution entity can generate initial motion path information for a corresponding preset electrode drilling tool based on the data information of the irregular hole to be processed. The preset electrode drilling tool can represent the electrode used to drill holes in the turbine blade. The initial motion path information can represent the trajectory of the preset electrode drilling tool from the inlet contour to the outlet contour. In practice, firstly, the execution entity can generate an electrode processing pose sequence based on the data information of the irregular hole to be processed using an adaptive slicing algorithm. The electrode processing pose sequence can represent the various positions and orientations of the electrode during turbine blade processing. Then, the initial motion path information is generated based on the electrode processing pose sequence using a spatial scanning volume algorithm.

[0029] Step 103: Generate modified motion path information based on the initial motion path information.

[0030] In some embodiments, the executing entity can generate modified motion path information based on the initial motion path information. The modified motion path information can represent the optimized initial motion path information.

[0031] In addressing the technical problems mentioned above, and considering the application scenario of machining densely distributed, nested air-film cooling irregular holes, the following technical problem often arises: When machining these nested irregular holes, drilling based on fixed parameters generated from a simplified geometric model cannot adjust the machining order of inner and outer holes according to the nesting relationship. The material in the inner hole area loses support due to the outer holes being machined first, making it prone to collisions when the electrode enters the machined area, damaging both the electrode and the workpiece, resulting in excessive material waste. Furthermore, the disordered path increases idle travel, leading to a longer overall drilling process time. Considering the following requirements for this application scenario: adaptability to machining nested irregular holes and adaptability to machining densely distributed irregular holes, we have decided to adopt the following solution: In some optional implementations of certain embodiments, the execution entity may generate modified motion path information based on the initial motion path information through the following steps: The first step involves extracting and processing the initial motion path information to obtain a set of hole position feature points. These hole position feature points can represent structured data containing the geometric, technological, or topological attributes of the irregularly shaped hole. Geometric attributes characterize the physical features of the irregularly shaped hole. The specific type of these geometric attributes is not limited; for example, it could be the depth of the irregularly shaped hole. Technological attributes characterize the parameters and requirements for processing the irregularly shaped hole. The specific content of these technological attributes is not limited; for example, it could be electrical parameters set to a peak current of 12A and a pulse width of 50µs. Topological attributes characterize the connection relationship between the irregularly shaped hole and other structures of the turbine blade. The specific type of these other structures is not limited; for example, it could be the cooling chamber of the turbine blade. In practice, the executing entity first uses a feature recognition algorithm to extract and process the data information of the irregularly shaped hole to be processed, obtaining the hole position feature point information for each hole. Then, the hole position feature point information is determined as a set of hole position feature points. For example, the feature recognition algorithm could be the PointNet++ algorithm.

[0032] The second step involves generating nesting relationship information for irregular holes based on the target geometric inclusion determination method and the aforementioned set of hole feature point information. The target geometric inclusion determination method can characterize a geometric relationship determination method based on a combination of axial projection bounding box detection and ray casting. The aforementioned nesting relationship information for irregular holes can characterize the true inclusion, false inclusion, intersection, or disjoint relationships between the various irregular holes represented by the aforementioned data information of the irregular holes to be processed. A true inclusion relationship indicates that the projection bounding box of any irregular hole is completely inside the projection bounding box of another irregular hole, and all feature points of any irregular hole are located within the outline of the other irregular hole. A false inclusion relationship indicates that the projection bounding box of any irregular hole is completely inside the projection bounding box of another irregular hole, but some feature points of any irregular hole are located outside the outline of the other irregular hole. An intersection relationship indicates that the projection bounding box of any irregular hole intersects with the projection bounding box of another irregular hole. A disjoint relationship indicates that the projection bounding box of any irregular hole is disjoint from the projection bounding box of another irregular hole. The aforementioned projection bounding box can characterize the bounding box. In practice, the aforementioned execution entity can analyze and process the hole position feature point information in the aforementioned hole position feature point information set through the aforementioned target geometric inclusion determination method to obtain the nesting relationship information of irregular holes.

[0033] The third step is to generate priority constraint hole position information based on the aforementioned nested hole relationship information. This priority constraint hole position information represents the rules governing the processing order of irregular holes. It can include first constraint information and second constraint information. The first constraint information indicates that nested inner holes must be processed before outer holes. The second constraint information indicates that non-nested, same-level irregular holes are processed in ascending order of their adjacent distance. In practice, firstly, the executing entity can use a four-way linked list construction method to transform the aforementioned irregular hole nested relationship information into a tree-like hierarchical structure. Then, using a depth-first traversal algorithm, the priority constraint hole position information is determined based on the tree-like hierarchical structure.

[0034] The fourth step involves constructing a mathematical optimization model based on the aforementioned priority constraint hole location information. This mathematical optimization model can be represented as a mathematical programming model. It can include decision variables, an objective function, and constraints. The decision variables can be binary variables. The objective function can be a function that minimizes the electrode's idle travel. The constraints can be priority constraints, indicating that the highest priority irregular holes are processed first. In practice, the executing entity can first use a generalized traveling salesman problem modeling method to model the priority constraint hole location information to obtain the mathematical optimization model.

[0035] Fifth, based on the above mathematical optimization model, perform the following steps: The first sub-step involves initializing the aforementioned set of hole position feature points using a target mean clustering method to generate an initial path solution set. This target mean clustering method can be a fuzzy C-means (FCM) clustering algorithm. The initial path solutions in the initial path solution set represent the processing sequence of the various irregular holes to be processed on the turbine blade. In practice, the execution entity can use the target mean clustering method to cluster and group the aforementioned set of hole position feature points, obtaining a clustered set of hole position feature points. Then, a path generation process is performed on the clustered set of hole position feature points using a combination of the nearest neighbor algorithm and centroid-based hierarchical clustering connections to obtain the initial path solution set.

[0036] The second sub-step generates a candidate path solution set based on the initial path solution set and the combined optimization method. The combined optimization method can be a combination of an improved genetic algorithm (GA) and a greedy algorithm. The candidate path solutions in the candidate path solution set represent the optimized initial path solution set. In practice, the execution entity can optimize the initial path solution set using the combined optimization method to obtain the candidate path solution set.

[0037] The third sub-step involves determining the changed motion path information based on the aforementioned candidate path solution set. In practice, the executing entity can use a multi-objective decision analysis method to determine the changed motion path information based on the aforementioned candidate path solution set. For example, the multi-objective decision analysis method could be the weighted sum method.

[0038] The above technical solution, as an inventive point of this disclosure, solves technical problem two: "leading to excessive material consumption and long overall drilling time." The reasons for excessive material consumption and long overall drilling time are as follows: When processing irregularly shaped holes with spatial nesting, drilling based on fixed parameters generated by a simplified geometric model cannot adjust the processing order of inner and outer holes according to the spatial nesting relationship. The material in the inner hole area loses support because the outer holes are processed first, making it prone to collisions when the electrode enters the processed area, damaging the electrode and workpiece, thus resulting in excessive material consumption. Furthermore, disordered paths increase idle travel, leading to a longer overall drilling time. Solving these factors can reduce material consumption and shorten the overall drilling time. To achieve this effect, the electrode drilling method for turbine blades disclosed in this disclosure analyzes the extracted hole position feature point information set through a target geometry inclusion determination method to determine the nesting relationship between irregularly shaped holes. Furthermore, based on the nesting relationship between irregularly shaped holes, priority constraints on hole position information are determined. Furthermore, by constructing a mathematical optimization model, the initial motion path information is optimized to obtain modified motion path information. Therefore, material consumption can be reduced, and the overall drilling process time can be shortened.

[0039] Step 104: Generate electrode motion path information based on the changed motion path information, blade 3D data information, and electrode tool 3D data information.

[0040] In some embodiments, the executing entity can generate electrode motion path information based on the modified motion path information, the blade 3D data information, and the electrode tool 3D data information. The electrode tool 3D data information can represent a 3D CAD model of the electrode used to drill holes in the turbine blade. The electrode motion path information can represent the final optimized initial motion path information corresponding to the preset electrode drilling tool.

[0041] In some optional implementations of certain embodiments, the execution entity can generate electrode motion path information based on the modified motion path information, the blade three-dimensional data information, and the electrode tool three-dimensional data information through the following steps: The first step is to generate a multiphysics drilling simulation model and corresponding boundary conditions based on the above-mentioned changed motion path information, the above-mentioned blade three-dimensional data information, and the electrode tool three-dimensional data information.

[0042] The second step involves generating predicted processing results information based on the aforementioned multiphysics drilling simulation model, boundary conditions, and preset result data structure template. This predicted processing results information characterizes the quality inspection results of the processed irregular holes, predicted based on the multiphysics drilling simulation model. This information may include the predicted material removal rate, predicted electrode axial loss length, predicted electrode end face center depression depth, predicted surface roughness, and predicted recast layer thickness. The electrode axial loss length characterizes the axial loss of the electrode. The electrode end face center depression depth characterizes the depression depth at the center of the electrode end face.

[0043] Third, in response to the detection that the predicted processing result information meets the preset processing standard constraints, the modified motion path information is determined as the electrode motion path information. The preset processing standard constraints can include the following: a material removal rate greater than a preset material removal rate; an electrode axial loss length less than a preset electrode axial loss length; an electrode end face center depression depth less than a preset electrode end face center depression depth; a surface roughness less than a preset surface roughness; and a recast layer thickness less than a preset recast layer thickness. Specifically, the preset material removal rate can be 2.0 mm³ / min, the preset electrode axial loss length can be 0.05 mm, the preset electrode end face center depression depth can be 0.01 mm, the preset surface roughness can be 1.6 μm, and the preset recast layer thickness can be 10 μm.

[0044] In addressing the aforementioned technical problems in the process of adopting technical solutions, and considering the application scenario of batch processing of film cooling holes for gas turbine single-crystal high-temperature alloy blades, the following technical problem often arises: Single-crystal high-temperature alloy blades are expensive, and the processing precision requirements for film cooling holes are high. Processing methods based on fixed parameters are difficult to adapt to the spatial variations of complex blade surfaces, resulting in low processing precision. Repeated trial processing and debugging of precision machining equipment are necessary to determine the optimal processing technology, leading to significant energy consumption. Furthermore, simplified geometric models cannot predict sudden changes in process states caused by unstable discharge or poor chip removal during drilling, nor can they pinpoint the specific process steps where such changes occur, leading to blind equipment adjustments and a prolonged overall drilling process. Considering the following requirements for this application scenario: adaptability to drilling high-cost workpieces, adaptability to high-precision film cooling hole processing, and adaptability to low energy consumption, we have decided to adopt the following solution: Optionally, the aforementioned executing entity may also generate a multiphysics drilling simulation model and corresponding boundary conditions for the multiphysics drilling simulation model based on the aforementioned changed motion path information, the aforementioned blade three-dimensional data information, and the electrode tool three-dimensional data information through the following steps: The first step is to generate an initial simulation environment based on the aforementioned three-dimensional data of the blade and the acquired three-dimensional data of the electrode tool corresponding to the aforementioned preset electrode drilling tool. This initial simulation environment can characterize a multiphysics simulation base model including a discretized geometric mesh, material properties, and initial and boundary conditions. The discretized geometric mesh can characterize the division of a continuous geometric space (such as a plane, curved surface, or three-dimensional volume) into a series of finite, non-overlapping, and fully covered small geometric units. The material properties can characterize the materials of the turbine blade and electrode set in the initial simulation environment. In practice, the executing entity can call the preprocessing interface of the multiphysics simulation software to perform mesh generation, material property allocation, and initial condition setting on the aforementioned three-dimensional data of the blade and electrode tool to obtain the initial simulation environment. The specific type of multiphysics simulation software is not limited here; for example, it can be ANSYS Multiphysics. The initial conditions can characterize the initial states set in the aforementioned initial simulation environment. The specific states represented by the initial conditions are not limited; for example, the initial conditions can characterize temperature, pressure, rotational speed, flow rate, or initial shape. The boundary conditions described above can characterize the constraints of the pre-defined initial simulation environment. The specific state represented by these boundary conditions is not limited; for example, the boundary conditions could be for machining turbine blades based on the aforementioned changed motion path information.

[0045] The second step is to determine the set of simulated physical processes corresponding to the initial simulation environment. These simulated physical processes can be gap discharge, heat transfer, or working fluid flow. The working fluid flow characterizes the flow of a preset working fluid within the machining area. The machining area characterizes the location where electrical discharge machining (EDM) is performed in the initial simulation environment. In practice, the executing entity can determine the set of simulated physical processes corresponding to the initial simulation environment using a decision tree algorithm. The preset working fluid characterizes the dielectric fluid immersing the workpiece information to be drilled and the preset electrode drilling tool. The specific type of the preset working fluid is not limited here; for example, the preset working fluid can be kerosene.

[0046] The third step involves constructing a multiphysics drilling simulation model based on the initial simulation environment and the coupled multiphysics control equations. This multiphysics drilling simulation model characterizes the simulation model of coupled multiphysics. Each physical field in the multiphysics can characterize an electric field, a thermal field, or a flow field. The coupled multiphysics control equations characterize the set of mathematical equations governing the internal workings and interactions of the multiphysics. Here, the specific type of mathematical equations in the set of equations is not limited; for example, the mathematical equations could be the Poisson equation describing charge distribution. In practice, the executing entity can use multiphysics simulation software to configure the coupled multiphysics control equations into the initial simulation environment based on the set of simulated physical processes, thus obtaining the constructed multiphysics drilling simulation model.

[0047] The fourth step is to determine the boundary conditions corresponding to the multiphysics drilling simulation model based on the changed motion path information.

[0048] Optionally, the aforementioned execution entity can also generate predicted processing result information based on the aforementioned multiphysics drilling simulation model, the aforementioned boundary conditions, and the preset result data structure template through the following steps: The first step is to generate the calculation results for each time step based on the aforementioned dynamic boundary conditions. These calculation results characterize the calculation results for each physical field at each time step. In practice, the execution entity can invoke the solver of the multiphysics simulation software to perform transient simulation calculations and generate the calculation results for each time step.

[0049] The second step involves defining the calculation results obtained at each time step as a simulation process data stream. This simulation process data stream characterizes the sequence of field variables output by the solver of the multiphysics simulation software during the calculation process. This sequence of field variables characterizes the various field variables generated sequentially in chronological order.

[0050] The third step involves dimensionality reduction of the simulation process data stream to obtain sampled simulation data. This sampled simulation data characterizes the selected irregular hole forming region and the physical field data at pre-defined time points. The irregular hole forming region characterizes the area on the turbine blade where irregular holes need to be machined. The physical field data characterizes the quantified values ​​of the distribution of any physical field included in the multiphysics drilling simulation model in both spatial (mesh node / cell) and temporal (transient simulation) dimensions. Here, the specific type and content of the physical field data are not limited; for example, the type of physical field data can be temperature field data, and the content can be "the temperature of node A at t=3 seconds = 85°C". In practice, the executing entity can perform post-processing operations using the multiphysics simulation software to extract the sampled simulation data from the simulation process data stream.

[0051] The fourth step involves generating key feature information based on the aforementioned sampled simulation data. This key feature information characterizes parameters extracted from the sampled simulation data that measure the processing effect and state of irregularly shaped holes. The specific type of this key feature information is not limited here; for example, it could be the material removal rate. In practice, the executing entity can use feature extraction algorithms to extract and process the sampled simulation data to obtain the key feature information. The specific type of this feature extraction algorithm is not limited here; for example, it could be a geometric feature extraction algorithm.

[0052] Fifth, based on the aforementioned key feature information and the preset result data structure template, generate the prediction processing result information. The preset result data structure template represents the data format used to organize and store the aforementioned key feature information. In practice, the executing entity can use serialization operations to fill and bind the aforementioned key feature information and the preset result data structure template to obtain the prediction processing result information.

[0053] The above-described technical solution, as an inventive point of this disclosure, solves technical problem three: "resulting in low processing accuracy, high energy consumption, and long overall drilling time." The reasons for this are as follows: Single-crystal high-temperature alloy blades are expensive, requiring high processing accuracy for the film cooling holes. Processing methods based on fixed parameters are difficult to adapt to the spatial variations of the blade's complex curved surface, leading to low processing accuracy. Repeated trial processing and debugging of precision machining equipment are necessary to determine the optimal processing technology, resulting in high energy consumption. Furthermore, simplified geometric models cannot predict sudden changes in process state caused by unstable discharge or poor chip removal during drilling, nor can they pinpoint the specific process steps where such changes occur, leading to blind equipment adjustments and a long overall drilling time. Solving these factors can improve processing accuracy, reduce energy consumption, and shorten the overall drilling time. To achieve this effect, the electrode drilling method for turbine blades disclosed herein constructs a multiphysics drilling simulation model based on the three-dimensional data of the blade, the three-dimensional data of the electrode tool, and the coupled multiphysics control equations. Then, the multiphysics drilling simulation model simulates each process step under the multiphysics field and collects key feature information. Finally, combined with a preset result data structure template, predicted processing result information is generated. Therefore, it can improve processing accuracy, reduce energy consumption, and shorten the overall drilling process time.

[0054] Optionally, after step 104, in response to the detection that the predicted processing result information does not meet the preset processing standard constraints, the executing entity can also update the changed motion path information according to the target optimization method to obtain the updated changed motion path information as the changed motion path information. The target optimization method can characterize an optimization algorithm. Here, the specific type of the target optimization method is not limited; for example, the target optimization method can be gradient descent. In practice, the executing entity can adjust the path description parameters of the changed motion path information using the target optimization method to obtain the adjusted changed motion path information as the changed motion path information. The path description parameters can characterize parameters describing electrode motion. The path description parameters can include, but are not limited to, any of the following: feed rate, oscillation amplitude, oscillation frequency, tilt angle, and rotation speed.

[0055] Step 105: Based on the multi-axis linkage drilling processing method, real-time pulse voltage information and electrode motion path information, control the preset electrode drilling tool to drill the workpiece information to be drilled, and obtain the initial irregular hole information.

[0056] In some embodiments, the aforementioned execution entity can control the aforementioned preset electrode drilling tool to drill the workpiece information to be drilled, based on a multi-axis linkage drilling processing method, real-time pulse voltage information, and the aforementioned electrode movement path information, to obtain initial irregular hole information. The aforementioned multi-axis linkage drilling processing method can be a drilling method using a multi-axis linkage mechanism. The aforementioned real-time pulse voltage information can characterize the voltage applied by the pulse power supply between the aforementioned preset electrode drilling tool and the workpiece information to be drilled. The aforementioned initial irregular hole information can characterize irregular holes used for cooling on turbine blades. It should be noted that both the workpiece information to be drilled and the aforementioned preset electrode drilling tool are immersed in a preset working fluid.

[0057] In some optional implementations of certain embodiments, the execution entity can control the preset electrode drilling tool to drill the workpiece information to be drilled by following the steps of multi-axis linkage drilling processing method, real-time pulse voltage information, and the electrode motion path information to obtain initial irregular hole information: The first step is to generate electrode rotation state information based on the aforementioned preset electrode drilling tool. This electrode rotation state information characterizes the rotational speed of the preset electrode drilling tool. In practice, the executing entity can monitor the preset electrode drilling tool in real time using a speed sensor to obtain the electrode rotation state information. The specific type of speed sensor is not limited here; for example, it can be a photoelectric sensor.

[0058] The second step involves performing the following processing steps based on the electrode rotation status information described above: The first sub-step involves generating multi-axis motion quantities in response to the detection that the electrode rotation state information meets a preset rotation condition, based on the multi-axis linkage drilling processing method and the electrode motion path information. The preset rotation condition can be that the electrode rotation state information exceeds a preset rotation threshold. The specific value of the preset rotation threshold is not limited here; for example, it can be 300 revolutions per minute. The multi-axis motion quantities can represent the motion quantity of a target axis. The specific type of the target axis and the motion quantity is not limited here; for example, the target axis can represent the Z-axis of the preset electrode drilling tool, and the motion quantity can be the change in angle. In practice, the execution entity can control a motion controller to obtain the multi-axis motion quantities using an interpolation algorithm based on the multi-axis linkage drilling processing method and the electrode motion path information.

[0059] The second sub-step involves generating multi-axis linkage motion commands corresponding to the preset electrode drilling tool based on the aforementioned multi-axis motion quantities. These multi-axis linkage motion commands can represent pulse signals or analog signals that control the preset electrode drilling tool to perform multi-axis motion. In practice, the executing entity can convert the aforementioned multi-axis motion quantities into multi-axis linkage motion commands using electronic gear ratios.

[0060] The third sub-step involves generating optimized servo feed commands based on the aforementioned real-time pulse voltage information. In practice, the executing entity can use a parameter adaptive control algorithm to generate optimized servo feed commands based on the real-time pulse voltage information. These optimized servo feed commands can characterize standardized electrical signals that adjust the axial (e.g., Z-axis) feed speed and position of the electrode.

[0061] The fourth sub-step involves performing a drilling process on the workpiece information to be drilled, based on the optimized servo feed command, the multi-axis linkage motion command, and the preset electrode drilling tool, to obtain the modified workpiece information as the initial irregular hole information. In practice, the execution entity can use a feed servo system to control the preset electrode drilling tool to perform the drilling process based on the multi-axis linkage motion command and the optimized servo feed command, obtaining the drilled workpiece information as the initial irregular hole information.

[0062] Step 106: Determine the irregular hole information based on the preset quality standard constraints and the initial irregular hole information.

[0063] In some embodiments, the execution entity can determine the irregular hole information based on preset quality standard constraints and the initial irregular hole information. The preset quality standard constraints can be that the irregular hole quality parameters meet a quantification standard. Here, the quantification standard is not specifically limited and can be adjusted according to actual needs. For example, the quantification standard can be a surface roughness of less than 2 μm.

[0064] In addressing the technical problems mentioned above, and considering the application scenario of processing the first piece of a batch of directional film cooling composite holes for gas turbines, the following technical problem often arises: When drilling a large batch of turbine blades, the first blade serves as the process certification part, and its drilling process parameters are used as the benchmark for subsequent mass production. The EDM drilling process is a complex process involving the coupling of multiple physical fields (e.g., thermal, electric, and flow fields). Even small deviations in the drilling process parameters can affect the final drilling quality through nonlinear amplification. Using this as the process certification part for subsequent mass production results in low heat dissipation efficiency for the entire batch of blades, leading to a shorter service life and significant material waste. To meet the following requirements of this application scenario—high reliability of process certification—we have decided to adopt the following solution: In some optional implementations of certain embodiments, the aforementioned execution entity can obtain the irregular hole information by following the following steps based on preset quality standard constraints and the aforementioned initial irregular hole information: First, based on the initial irregular hole information above, perform the following verification steps: The first sub-step involves generating irregular hole image information based on the aforementioned initial irregular hole information. This irregular hole image information can represent the image corresponding to the initial irregular hole information. In practice, the executing entity can obtain the image of the initial irregular hole information from an associated database as the irregular hole image information.

[0065] The second sub-step involves generating irregular hole quality parameter information based on the aforementioned irregular hole image information. This irregular hole quality parameter information characterizes the geometric accuracy and surface roughness of the initial irregular hole information. The geometric accuracy may include dimensional accuracy, hole shape error, and positional accuracy. In practice, the executing entity can use machine vision image processing algorithms to extract geometric features and analyze surface defects in the irregular hole image information to obtain the irregular hole quality parameter information. Here, the methods for geometric feature extraction and surface defect analysis are not limited; for example, the geometric feature extraction method can be an image edge extraction algorithm, and the surface defect analysis method can be a texture analysis algorithm.

[0066] The third sub-step involves generating Boolean value results based on the aforementioned irregular hole quality parameter information and preset quality standard constraints. These Boolean value results characterize whether the irregular hole quality parameter information satisfies the preset quality standard constraints. The Boolean value results can represent either a first Boolean value result or a second Boolean value result. The first Boolean value result indicates that the irregular hole quality parameter information satisfies the preset quality standard constraints. The second Boolean value result indicates that the irregular hole quality parameter information does not satisfy the preset quality standard constraints. In practice, the executing entity can use a logical comparison method based on a preset threshold to compare the irregular hole quality parameter information according to the preset quality standard constraints. In response to the detection that the irregular hole quality parameter information satisfies the preset quality standard constraints, the first Boolean value result is determined as a Boolean value result. In response to the detection that the irregular hole quality parameter information does not satisfy the preset quality standard constraints, the second Boolean value result is determined as a Boolean value result.

[0067] The fourth sub-step is to determine the initial irregular hole information as irregular hole information in response to the detection that the above Boolean value result information is the first Boolean value result information.

[0068] The fifth sub-step, in response to detecting that the above Boolean value result information is the second Boolean value result information, executes the following steps: The first execution step involves updating the aforementioned electrode motion path information and real-time pulse voltage information to obtain the electrode motion path information and real-time pulse voltage information. In practice, the execution entity can first use an adaptive algorithm to update the aforementioned electrode motion path information and real-time pulse voltage information to obtain updated electrode motion path information and updated real-time pulse voltage information. Then, the updated electrode motion path information and the updated real-time pulse voltage information are determined as the electrode motion path information and real-time pulse voltage information. Here, the specific type of the aforementioned adaptive algorithm is not limited; for example, the adaptive algorithm can be a servo feed fuzzy adaptive control algorithm based on discharge gap state recognition.

[0069] The second execution step involves re-executing the above processing steps based on the electrode movement path information and the real-time pulse voltage information to obtain the initial irregular hole information.

[0070] The third execution step is to use the obtained initial irregular hole information as the initial irregular hole information and execute the above verification steps again.

[0071] The above-described technical solution, as an inventive point of this disclosure, solves technical problem four: "resulting in low heat dissipation efficiency for the entire batch of blades, leading to a short service life and excessive material waste." The reasons for this low heat dissipation efficiency, short service life, and excessive material waste are as follows: When drilling a large batch of turbine blades, the first blade serves as a process certification part, and its drilling process parameters are used as the benchmark for subsequent mass production. The electrical discharge machining (EDM) process is a complex process involving the coupling of multiple physical fields (e.g., thermal, electric, and flow fields). Even small deviations in the drilling process parameters can affect the final drilling quality through nonlinear amplification. Using this as a process certification part for subsequent mass production results in low heat dissipation efficiency for the entire batch of blades, leading to a short service life and excessive material waste. Solving these factors can improve the heat dissipation efficiency of the entire batch of blades, extend the service life of the workpiece, and reduce material waste. To achieve this effect, the electrode drilling method for turbine blades disclosed in this disclosure first extracts the quality parameter information of the irregular hole from the irregular hole image information. Then, the quality parameters of the irregular holes are compared with the preset quality standard constraints, and the irregular hole information that meets the preset quality standard constraints is selected. Furthermore, for irregular hole information that does not meet the preset quality standard constraints, its corresponding electrode motion path information and real-time pulse voltage information are modified, and the drilling verification is performed again until the preset quality standard constraints are met. Therefore, the heat dissipation efficiency of the entire batch of blades can be improved, the service life of the workpiece can be extended, and the waste of workpiece material can be reduced.

[0072] Figure 4 This is a magnifying glass inspection diagram of a turbine blade after drilling, suitable for implementing some embodiments of the present disclosure. It can be seen that the integrity of the irregular hole drilled by the above-described electrode drilling method applied to turbine blades can be inspected by a magnifying glass, verifying the feasibility of the above-described electrode drilling method applied to turbine blades.

[0073] Figure 5 This is a schematic diagram of microscopic inspection of a turbine blade after drilling, which is suitable for implementing some embodiments of the present disclosure. It can be seen that the integrity of the irregular hole drilled by the electrode drilling method applied to turbine blades described above can be detected by microscope, thus verifying the feasibility of the electrode drilling method applied to turbine blades described above.

[0074] The above-described embodiments of this disclosure have the following beneficial effects: The electrode drilling method for turbine blades according to some embodiments of this disclosure can shorten the drilling process cycle time and reduce material costs. The reason for the long drilling process cycle time and high material costs is that the fixed parameters generated based on simplified geometric models are insufficiently adaptable to processing new or complex irregular holes. Before actual drilling, repeated parameter adjustments and offline testing are required for trial processing, resulting in a long drilling process cycle. Furthermore, the trial processing directly consumes tool electrode and turbine blade materials, leading to high material costs. Therefore, the electrode drilling method for turbine blades according to some embodiments of this disclosure first generates irregular hole data information based on a pre-trained semantic segmentation model and the obtained blade 3D data information corresponding to the workpiece to be drilled. Thus, the irregular hole data to be processed can be obtained. Then, based on the aforementioned irregular hole data information, the initial motion path information of the corresponding preset electrode drilling tool is generated. Thus, the initial motion path of the corresponding preset electrode drilling tool can be obtained. Subsequently, based on the initial motion path information, modified motion path information is generated. This allows the initial motion path of the preset electrode drilling tool to be modified, resulting in a modified motion path. Next, based on the modified motion path information, the blade 3D data information, and the electrode tool 3D data information, electrode motion path information is generated. This generation of electrode motion path information includes: generating a multiphysics drilling simulation model and corresponding boundary conditions based on the modified motion path information, the blade 3D data information, and the electrode tool 3D data information; generating predicted processing result information based on the multiphysics drilling simulation model, the boundary conditions, and a preset result data structure template; and, in response to the detection that the predicted processing result information meets preset processing standard constraints, determining the modified motion path information as the electrode motion path information. Thus, the final motion path of the preset electrode drilling tool can be obtained. Subsequently, based on the multi-axis linkage drilling processing method, real-time pulse voltage information, and the aforementioned electrode motion path information, the preset electrode drilling tool is controlled to drill the workpiece information to be drilled, obtaining initial irregular hole information. Thus, the workpiece information to be drilled can be drilled to obtain initial irregular holes. Finally, based on preset quality standard constraints and the aforementioned initial irregular hole information, the irregular hole information is determined. Thus, the final irregular hole can be determined.Because it doesn't rely on fixed parameters generated from a simplified geometric model, but rather uses a pre-trained semantic segmentation model and the type of the irregular hole to be processed to segment the data, and determines the electrode movement path based on this data, it can better meet actual production needs, reducing rework due to defects and shortening the time spent on rework. Furthermore, because it uses a multi-axis linkage drilling process, controlling a preset electrode drilling tool to drill holes in the workpiece information, and introducing preset quality standard constraints to verify the initial irregular hole information, it can improve the quality of the processed irregular holes, thereby reducing material waste caused by rework. Therefore, it can shorten the drilling process cycle time and reduce material costs.

[0075] Further reference Figure 2 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of an electrode drilling method applied to turbine blades. These device embodiments are similar to... Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0076] like Figure 2As shown, an electrode drilling device 200 for turbine blades in some embodiments includes: a first generation unit 201, a second generation unit 202, a third generation unit 203, a fourth generation unit 204, a drilling unit 205, and a determining unit 206. The first generation unit 201 is configured to generate data information of a non-standard hole to be processed based on a pre-trained semantic segmentation model and the acquired blade 3D data information corresponding to the workpiece to be drilled; the second generation unit 202 is configured to generate initial motion path information of a preset electrode drilling tool based on the aforementioned non-standard hole data information; the third generation unit 203 is configured to generate modified motion path information based on the aforementioned initial motion path information; and the fourth generation unit 204 is configured to generate electrode motion path information based on the modified motion path information, the aforementioned blade 3D data information, and the electrode tool 3D data information. In this process, the generation of electrode motion path information based on the modified motion path information, the blade 3D data information, and the electrode tool 3D data information includes: generating a multiphysics drilling simulation model and corresponding boundary conditions based on the modified motion path information, the blade 3D data information, and the electrode tool 3D data information; generating predicted processing result information based on the multiphysics drilling simulation model, the boundary conditions, and a preset result data structure template; and determining the modified motion path information as electrode motion path information in response to detecting that the predicted processing result information meets preset processing standard constraints. The drilling unit 205 is configured to control the preset electrode drilling tool to perform drilling processing on the workpiece information to be drilled, based on the multi-axis linkage drilling processing method, real-time pulse voltage information, and the electrode motion path information, to obtain initial irregular hole information. The determining unit 206 is configured to determine the irregular hole information based on preset quality standard constraints and the initial irregular hole information.

[0077] It is understandable that the units described in the electrode drilling device 200 applied to turbine blades are similar to those in the reference. Figure 1 The steps in the described method correspond accordingly. Therefore, the operations, features, and beneficial effects described above for the method are also applicable to the electrode drilling device 200 applied to turbine blades and the units contained therein, and will not be repeated here.

[0078] The following is for reference. Figure 3 It shows a schematic diagram of the structure of an electronic device 300 (e.g., a computing device) suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0079] like Figure 3As shown, the electronic device 300 may include a processing unit 301 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. The RAM 303 also stores various programs and data required for the operation of the electronic device 300. The processing unit 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0080] Typically, the following devices can be connected to I / O interface 305: input devices 306 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 307 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 308 including, for example, magnetic tapes, hard disks, etc.; and communication devices 309. Communication device 309 allows electronic device 300 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 3 An electronic device 300 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively. Figure 3 Each box shown can represent a device or multiple devices as needed.

[0081] In particular, according to some embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication device 309, or installed from storage device 308, or installed from ROM 302. When the computer program is executed by processing device 301, it performs the functions defined in the methods of some embodiments of this disclosure.

[0082] It should be noted that, in some embodiments of this disclosure, the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In some embodiments of this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In some embodiments of this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0083] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP (Hypertext Transfer Protocol) and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet of Things), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future-developed networks.

[0084] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device. The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: generate data information of the irregular hole to be processed based on a pre-trained semantic segmentation model and the acquired blade 3D data information corresponding to the workpiece to be drilled; generate initial motion path information of a corresponding preset electrode drilling tool based on the aforementioned irregular hole data information; generate modified motion path information based on the aforementioned initial motion path information; and generate electrode motion path information based on the aforementioned modified motion path information, the aforementioned blade 3D data information, and the electrode tool 3D data information, wherein generating electrode motion path information based on the aforementioned modified motion path information, the aforementioned blade 3D data information, and the electrode tool 3D data information includes: based on the aforementioned... The modified motion path information, the aforementioned blade 3D data information, and the electrode tool 3D data information are used to generate a multiphysics drilling simulation model and corresponding boundary conditions for the multiphysics drilling simulation model. Based on the multiphysics drilling simulation model, the aforementioned boundary conditions, and the preset result data structure template, predicted processing result information is generated. In response to the detection that the predicted processing result information meets the preset processing standard constraints, the modified motion path information is determined as the electrode motion path information. Based on the multi-axis linkage drilling processing method, real-time pulse voltage information, and the aforementioned electrode motion path information, the preset electrode drilling tool is controlled to perform drilling processing on the workpiece information to be drilled to obtain initial irregular hole information. Based on the preset quality standard constraints and the aforementioned initial irregular hole information, the irregular hole information is determined.

[0085] Computer program code for performing operations of some embodiments of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0086] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0087] The units described in some embodiments of this disclosure can be implemented in software or hardware. The described units can also be housed in a processor, and for example, can be described as: a first generation unit, a second generation unit, a third generation unit, a fourth generation unit, a drilling unit, and a determining unit. The names of these units do not necessarily limit the unit itself; for example, the first generation unit can also be described as "a unit that generates data information of irregular holes to be processed based on a pre-trained semantic segmentation model and the acquired three-dimensional data information of the blade corresponding to the workpiece information to be drilled."

[0088] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), and so on.

[0089] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A method for drilling electrodes for turbine blades, characterized in that, include: Based on the pre-trained semantic segmentation model and the obtained three-dimensional data information of the blade corresponding to the workpiece to be drilled, the data information of the irregular hole to be processed is generated. Based on the data information of the irregular hole to be processed, the initial motion path information of the corresponding preset electrode drilling tool is generated; Based on the initial motion path information, change motion path information is generated; Electrode motion path information is generated based on the modified motion path information, the blade 3D data information, and the electrode tool 3D data information. This generation of electrode motion path information includes: Based on the changed motion path information, the blade three-dimensional data information, and the electrode tool three-dimensional data information, a multiphysics drilling simulation model and corresponding boundary conditions for the multiphysics drilling simulation model are generated. Based on the multiphysics drilling simulation model, the boundary conditions, and the preset result data structure template, predictive processing result information is generated. In response to the detection that the predicted processing result information meets the preset processing standard constraints, the changed motion path information is determined as the electrode motion path information; Based on the multi-axis linkage drilling processing method, real-time pulse voltage information and the electrode motion path information, the preset electrode drilling tool is controlled to drill the workpiece information to be drilled to obtain the initial irregular hole information. Based on the preset quality standard constraints and the initial irregular hole information, the irregular hole information is determined.

2. The method according to claim 1, characterized in that, Before generating the data information of the irregular hole to be processed based on the three-dimensional data information of the blade corresponding to the workpiece to be drilled, the method further includes: Based on the set of three-dimensional information of the target workpiece, the three-dimensional data generation architecture is modified to obtain the modified three-dimensional data generation architecture as the three-dimensional data generation model. Generate a condition vector based on the target workpiece parameters; Based on the three-dimensional data generation model and the condition vector, three-dimensional data information of the blade is generated.

3. The method according to claim 2, characterized in that, The step of generating blade three-dimensional data information based on the three-dimensional data generation model and the conditional vector includes: Based on the three-dimensional data, generate a model and perform the following steps: Generate a three-level neural code tree based on the condition vector; Based on the three-level neural code tree, the blade three-dimensional data information corresponding to the workpiece information to be drilled is generated.

4. The method according to claim 1, characterized in that, The method further includes: In response to the detection that the predicted processing result information does not meet the preset processing standard constraints, the electrode motion path information is updated according to the target optimization method to obtain the updated electrode motion path information as the changed motion path information.

5. The method according to claim 1, characterized in that, The process involves controlling a preset electrode drilling tool to drill holes in the workpiece based on a multi-axis linkage drilling method, real-time pulse voltage information, and the electrode motion path information, to obtain initial irregular hole information, including: Based on the preset electrode drilling tool, generate electrode rotation state information; Based on the electrode rotation state information, the following processing steps are performed: In response to the detection that the electrode rotation state information meets the preset rotation conditions, multi-axis motion is generated according to the multi-axis linkage drilling processing method and the electrode motion path information; Based on the multi-axis motion parameters, generate multi-axis linkage motion commands corresponding to the preset electrode drilling tool; Based on the real-time pulse voltage information, an optimized servo feed command is generated; According to the optimized servo feed command, the multi-axis linkage motion command, and the preset electrode drilling tool, the workpiece information to be drilled is processed to obtain the modified workpiece information to be drilled as the initial irregular hole information.

6. An electrode drilling device for turbine blades, characterized in that, include: The first generation unit is configured to generate the data information of the irregular hole to be processed based on the three-dimensional data information of the blade corresponding to the workpiece to be drilled, which is a pre-trained semantic segmentation model and the obtained data information of the corresponding workpiece to be drilled. The second generation unit is configured to generate initial motion path information of the corresponding preset electrode drilling tool based on the data information of the irregular hole to be processed. The third generation unit is configured to generate modified motion path information based on the initial motion path information; The fourth generation unit is configured to generate electrode motion path information based on the changed motion path information, the blade three-dimensional data information, and the electrode tool three-dimensional data information. The generation of electrode motion path information based on the changed motion path information, the blade three-dimensional data information, and the electrode tool three-dimensional data information includes: Based on the changed motion path information, the blade three-dimensional data information, and the electrode tool three-dimensional data information, a multiphysics drilling simulation model and corresponding boundary conditions for the multiphysics drilling simulation model are generated. Based on the multiphysics drilling simulation model, the boundary conditions, and the preset result data structure template, predictive processing result information is generated. In response to the detection that the predicted processing result information meets the preset processing standard constraints, the changed motion path information is determined as the electrode motion path information; The drilling unit is configured to control the preset electrode drilling tool to drill the workpiece information to be drilled according to the multi-axis linkage drilling processing mode, real-time pulse voltage information and the electrode motion path information, so as to obtain the initial irregular hole information. The determining unit is configured to determine the irregular hole information based on preset quality standard constraints and the initial irregular hole information.

7. An electronic device, characterized in that, include: One or more processors; A storage device on which one or more programs are stored; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 5.

8. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 5.

Images