Machining feature recognition method for irregular-shaped air film holes

Abstract

The present invention relates to a method for identifying features in processing irregular air film holes, comprising the following steps: S10: model preprocessing; S20: potential feature search and separation; S30: feature identification and matching; and S40: merging features to obtain feature recognition results. The present invention utilizes feature search to obtain potential features, with a low probability of non-recognition, misidentification, or missed recognition. A secondary identification is then performed to further avoid non-recognition, misidentification, or missed recognition, effectively identifying cylindrical-based mixed face group hole features and improving recognition accuracy and efficiency. After obtaining the feature recognition results, they are directly output to the feature programming link. Feature-based programming simplifies the programming process, enabling feature-based automated programming and efficient reuse of tool paths, thereby improving processing efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of computer-aided process design, and in particular to a method for identifying machining features of special-shaped air film holes. Background Art

[0002] Turbine blades have always been a key component of aircraft engines. The rapid development of my country's aviation industry in recent years has placed higher demands on the performance of domestically produced aircraft engines. To increase turbine inlet temperatures, the most effective and widely used technology is to create cooling film holes on the blades.

[0003] The first holes used for film cooling on turbine blades were cylindrical holes. Eckert et al. conducted early experimental studies on the cooling effect of cylindrical film holes and found that cylindrical holes with compound angles exhibited excellent film cooling. As research progressed, domestic and international scholars discovered that cylindrical holes, due to their structural limitations, provide poor spanwise coverage of the cooling airflow. Furthermore, the large normal momentum of the cold flow exiting cylindrical holes results in poor cooling near the wall. Consequently, domestic and international research on hole shapes has focused on special-shaped holes.

[0004] Since the air film holes are widely distributed on the turbine and there are a large number of them, but they are highly consistent in structure and processing methods, a lot of repetitive work is required when using traditional manual programming methods for processing, and production efficiency is low. Therefore, processing feature recognition technology has emerged. Processing feature recognition technology uses certain methods to extract feature objects with processing significance from the part model, simplifies the programming process through feature-based programming, realizes feature-based automated programming and efficient reuse of tool paths, and improves processing efficiency. The current common feature recognition methods are mainly aimed at common 2.5D processing features, which are mostly simple structures such as grooves, platforms, and holes, which are easy to identify. When using general feature recognition methods to identify special-shaped air film holes, the recognition efficiency is low and the effect is poor, and there are cases of non-recognition, misrecognition, and missed recognition. Summary of the Invention

[0005] To this end, the technical problem to be solved by the present invention is to overcome the defects of low feature recognition efficiency, poor effect, non-recognition, misrecognition and missed recognition in the existing technology, and provide a feature recognition method that improves the programming and processing efficiency of special-shaped air film holes, improves recognition accuracy and recognition efficiency, and reduces recognition omissions.

[0006] To solve the above technical problems, the present invention provides a method for identifying the processing features of irregular-shaped air film holes, comprising the following steps:

[0007] S10: Model preprocessing: define the surface type of the topological surface as a feature base surface, a transition surface, or a structural surface, identify the surface type of each topological surface of the model, select the closed cylindrical geometric surface as the search starting surface, and set the feature base surface as the search ending surface;

[0008] S20: Potential feature search and separation: For each search starting point face, a topological ring set W and a potential feature face set F are obtained; for each element w in the topological ring set W, the topological ring set W and the feature face set F are supplemented according to the characteristics of the topological faces adjacent to the element; the feature face set F obtained after traversing the topological ring set W is output as a potential feature;

[0009] S30: Feature identification and matching: The potential features are screened to obtain the first identification features; the faces other than the first identification features on the extracted model are defined as the residual model, and the first identification features and the residual model are used to obtain the supplementary potential features through a graph matching algorithm; the supplementary potential features are screened to obtain the second identification features;

[0010] S40: Merge: Merge the first identification feature and the second identification feature to obtain a feature recognition result.

[0011] In one embodiment of the present invention, in step S20, supplementing the topological ring set W and the characteristic face set F according to the characteristics of the topological faces adjacent to the element includes the following steps:

[0012] S21: for the first unsearched ring in the topological ring set W, check the topological faces adjacent to the ring and extract the faces that do not belong to the potential feature face set F as the search face group;

[0013] S22: Determine whether all faces in the search face group are connected. If not, go to step S26; otherwise, go to step S23.

[0014] S23: Determine whether there is a transition surface in the search surface group. If so, determine whether the transition surface is directly topologically adjacent to the current search starting point surface. If not, identify the transition surface as the feature search end surface.

[0015] S24: Determine whether there is a search termination surface in the search surface group. If so, go to step S26; otherwise, go to step 25.

[0016] S25: Add all closed rings composed of topological edges in the search face group that are not adjacent to elements in the feature face set F and are not common edges of the search face group to the front end of the topological ring set W, and add all faces of the search face group to the feature face set F;

[0017] S26: Determine whether the topological ring set W is traversed. If it is traversed, output the feature face set F as a potential feature. If it is not traversed, repeat S21-S26.

[0018] In one embodiment of the present invention, the topological ring set W is an ordered queue, and the outer ring of the search starting point surface is located at the front end of the topological ring set W.

[0019] In one embodiment of the present invention, the potential feature face set F is an unordered set, which includes a search starting point face.

[0020] In one embodiment of the present invention, in step S30, the following rules are used to screen the latent features and the supplementary latent features:

[0021] S31: The faces of the same feature are connected, and adjacent faces are topologically adjacent through at least one edge;

[0022] S32: The number of features is less than the scale constant of the irregular air film hole;

[0023] S33: The number of search start faces in the feature is 1, and the number of transition faces is less than 3;

[0024] S34: The diameter of the hole of the feature in the axial direction of the search starting point surface changes with the search starting point surface as the center toward the edge of the feature according to the set situation.

[0025] In one embodiment of the present invention, in step S34, the identification method is as follows:

[0026] S341: Selecting the central axis of the search starting point surface of the current feature as the central axis of the feature;

[0027] S342: Based on the shape of the irregular air film hole, a layer of annularly connected face groups is selected from one side or both sides of the search starting point face, and the maximum envelopable area of the face groups projected along the axis direction is calculated.

[0028] S343: Repeat S342 from the inside out until the feature boundary is reached, and record the change of the maximum envelopable area;

[0029] S344: If the obtained maximum envelopable areas all change according to the set conditions, it is determined that the conditions are met.

[0030] In one embodiment of the present invention, in step S30, the method for obtaining the second identification feature includes the following steps:

[0031] S35: generating an attribute adjacency graph corresponding to the first identification feature and the residual model;

[0032] S36: The graph corresponding to each first-identified feature is used as the subgraph to be found, and the model corresponding to the residual model is used as the target graph. The graph matching algorithm is called to sequentially match and search each subgraph on the target graph. The model face group corresponding to each subgraph on the target graph obtained by the search is saved and defined as a supplementary potential feature.

[0033] S37: Screening the supplementary potential features to obtain the second identification features.

[0034] In one embodiment of the present invention, the graph matching algorithm is the VF2 algorithm.

[0035] In one embodiment of the present invention, in step S10, the missing edges and topological relationships in the model are repaired before the face type is identified.

[0036] In one embodiment of the present invention, the feature recognition result is obtained in step S40, and after feedback confirmation, the correct feature model face group is output.

[0037] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the steps of the above method are implemented when the processor executes the program.

[0038] A computer-readable storage medium stores a computer program, which implements the steps of the above method when executed by a processor.

[0039] A processor is used to run a program, wherein the program executes the above method when running.

[0040] The above technical solution of the present invention has the following advantages over the prior art:

[0041] The processing feature recognition method described in the present invention searches for potential feature objects from the model and screens them through the identification rules of special-shaped air film holes to obtain the first identification result; generates a matching graph of the first identification feature, and matches the residual model after the first separation through graph matching, and performs feature identification on the successfully matched result through the rules to obtain the second identification result. By using the search method to obtain potential features, the probability of non-identification, misidentification, and missed identification is low. At the same time, a secondary identification is performed to further avoid the situations of non-identification, misidentification, and missed identification, and effectively identify the mixed surface group hole features based on the cylinder, thereby improving the accuracy and efficiency of identification. After obtaining the feature recognition results, they are directly output to the feature programming link. The programming process is simplified through feature-based programming, and feature-based automated programming and efficient reuse of tool paths are realized, thereby improving the efficiency of processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to make the content of the present invention more clearly understood, the present invention is further described in detail below based on specific embodiments of the present invention in conjunction with the accompanying drawings, wherein

[0043] Figure 1 It is a schematic diagram of the surface type definition in the model of the present invention;

[0044] Figure 2 This is a schematic diagram of a special-shaped hole that satisfies the neutrality and increases gradually on both sides of the present invention;

[0045] Figure 3 It is a structural schematic diagram of the special-shaped air film hole of the present invention and its attribute adjacency diagram.

[0046] Figure numerals: 1. characteristic base surface; 2. transition surface; 3. structural surface; 4. outer ring; 5. inner ring. DETAILED DESCRIPTION

[0047] The present invention will be further described below with reference to the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it. However, the embodiments are not intended to limit the present invention.

[0048] The method for identifying the processing features of irregular-shaped air film holes of the present invention comprises the following steps:

[0049] S10: Model preprocessing: Define the surface type of the topological surface as feature base surface 1, transition surface 2 or structural surface 3. For details, refer to Figure 1 As shown, the surface with two or more inner rings 5 is defined as a characteristic base surface 1, the surface containing one inner ring 5 is identified as a transition surface 2, and the surface without an inner ring 5 is identified as a structural surface 3.

[0050] The worm turbine blade model was parsed to obtain all topological surfaces. To prevent issues such as feature loss in the model, missing edges and topological relationships were first repaired. Then, according to the above definition, the face type of each topological face was identified. The closed cylindrical geometric face was selected as the search starting face, and all feature base faces 1 were set as the search ending faces.

[0051] S20: Potential feature search and separation: For each search starting point face, a topological ring set W and a potential feature face set F are obtained. The elements in the topological ring set W are w, representing each ring to be checked, and the elements in the potential feature area F are f, representing each face considered to constitute the current potential feature.

[0052] Furthermore, to improve the efficiency of the search, the topological ring set W is set as an ordered queue and sorted according to the order of entry and exit, so that the outer ring 4 of the search starting point face is located at the front end of the topological ring set W. At this time, when traversing the topological ring set W, we first start from the feature starting point face, where there are many adjacent topological faces, so that the potential feature face set F can be completed as quickly as possible.

[0053] For the potential feature face set F, the search starting face must be the face of the potential feature, so the search starting face is added as the initial content of the potential feature face set F. There is no order requirement for the faces of the potential features during the search process, so F is an unordered set.

[0054] In order to ensure that there are as few features missed as possible during the feature recognition process, the topological face groups in the model that may become features are separated. For the element w in the topological ring set W, the elements of the topological ring set W and the feature face set F are supplemented according to the characteristics of the topological faces adjacent to the element, i.e. the ring; the feature face set F obtained after traversing the topological ring set W is output as a potential feature.

[0055] Specifically, the following steps are included:

[0056] S21: for the first unsearched ring in the topological ring set W, i.e., element w-first, check all topological faces adjacent to the ring and extract all faces that do not belong to the potential feature face set F as the search face group;

[0057] S22: Determine whether all faces in the search face group are connected. If not, no path can be formed between the faces, so go to step S26; otherwise, go to step S23;

[0058] S23: Determine whether there is a transition surface 2 in the search surface group. If so, determine whether the transition surface 2 is directly topologically adjacent to the current search starting surface. If not, identify the transition surface 2 as the feature search termination surface. That is, the transition surface 2 will become the search termination surface under certain circumstances.

[0059] S24: Determine whether there is a search termination surface in the search surface group. In this case, the search termination surface includes the feature base surface 1 and the transition surface 2 identified in step S23. If it exists, go to step S26; otherwise, go to step 25.

[0060] S25: Add all closed rings composed of topological edges in the search face group that are not adjacent to elements in the feature face set F and are not common edges of the search face group to the front end of the unsearched elements in the topological ring set W in sequence, and add all faces of the search face group to the feature face set F; thus, the features are supplemented.

[0061] S26: Determine whether the topological ring set W is traversed. If it is traversed, output the feature face set F as a potential feature. If it is not traversed, repeat S21-S26.

[0062] In this embodiment, to facilitate determining whether a topological ring set W has been traversed, in step S21, the first element in W is removed, and steps S21-S25 are searched. After the search is complete, in step S26, the searched w-first is removed from W. This means that the first unsearched element in W remains in the first position in W, and the ring added to W in S25 can be directly added to the front of W. At this point, determining whether W is empty determines whether W has been traversed. A potential feature can be obtained for each search starting point face.

[0063] S30: Feature identification and matching: Screen potential features to obtain the first identified features. In this embodiment, taking the processed feature as a special-shaped air film hole, the screening rules are as follows:

[0064] S31: All faces of the same feature are completely connected, and adjacent faces are topologically adjacent through at least one edge;

[0065] S32: Define the scale constant of the special-shaped air film hole as M. In this embodiment, M is taken as 1.5 times the number of topological faces of the common special-shaped air film hole model. Define the number of features as nf, and the feature satisfies nf < M; thus, some abnormal features are restricted.

[0066] S33: The number of starting faces for searching in the feature is 1, and the number of transitional feature faces is less than 3; this restricts the feature type and avoids incorrect feature recognition.

[0067] S34: The hole diameter of the feature in the axial direction of the starting face for searching changes from the center of the starting face to the edge of the feature in a set pattern. In this embodiment, the hole diameter at the center of the special-shaped air film hole is smaller than the hole diameter at the edge of the feature. Therefore, the hole diameter increases monotonically along the search direction, and based on this condition, the special-shaped hole is determined to be a non-cylindrical hole.

[0068] Determine the potential features that meet the above screening rules as the first identified features.

[0069] Furthermore, as shown in Figure 2 For a special-shaped air film hole shape of the present invention, to determine whether the hole diameter in S34 increases monotonically, the following identification method is adopted:

[0070] S341: Select the central axis of the closed cylinder contained in the current feature as the central axis of the feature;

[0071] S342: Since the hole diameters at both ends of the special-shaped air film hole designed in this embodiment increase, starting from both sides of the closed cylinder, take a layer of annularly connected face groups respectively, and calculate the maximum enclosing area of their projections in the axial direction;

[0072] S343: Repeat S342 from the inside to the outside until the feature boundary, and record the change of the maximum enclosing area;

[0073] S344: If the obtained maximum enclosing areas are all monotonically increasing from the inside to the outside, it is determined that the condition of S34 is met.

[0074] After obtaining the faces of the first identified features, extract the faces on the original model that do not belong to the first identified features from the original model and define them as the residual model. Search for the missing features from it through the graph matching algorithm and classify them as the second identified features.

[0075] Specifically, as shown in Figure 3 It includes the following steps:

[0076] S35: Generate an attribute adjacency graph corresponding to the first identified features and the residual model. The faces and their shape attributes of the model correspond to the vertices and vertex attributes in the attribute graph. Each bidirectional edge of the model corresponds to a set of bidirectional edges in the attribute graph. The attributes of undirected edges are set to be the same by default. This transforms the problem of identifying machining features into a process of searching for the "small image" of machining features within the "large image" of the part, enabling rapid identification of machining features.

[0077] S36: The graph corresponding to each first-identified feature is used as the subgraph to be searched, and the model corresponding to the residual model is used as the target graph, and a graph matching algorithm is invoked. In this embodiment, the VF2 algorithm is specifically used, and other graph matching algorithms can also be used in other embodiments of the present invention. Each subgraph is sequentially matched and searched on the target graph, and the model face group corresponding to each subgraph on the searched target graph is saved and defined as a supplementary potential feature;

[0078] S37: Screening the supplementary potential features to obtain a second identification feature. Specific screening rules are the same as those for the first identification feature screening.

[0079] S40: Merge: The first and second identification features are merged to obtain a feature recognition result. The recognition result is fed back for confirmation, and the correct feature model face group is ultimately output. In this embodiment, the feature recognition result is fed back to the user, and after the user modifies and confirms it, the correct feature model module is output. Based on the existence of a subsequent feature programming step, it is directly output to the feature programming step.

[0080] An embodiment of the present application provides a computer device for identifying processing features, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the above method are implemented.

[0081] An embodiment of the present application provides a computer-readable storage medium, in which a processing feature recognition instruction is stored. When the processing feature recognition instruction is executed by a processor, the steps of the above method are implemented.

[0082] An embodiment of the present application provides a processor, which is used to run a program, wherein the program executes the above method when it is run.

[0083] Obviously, the above embodiments are merely examples for clarity of explanation and are not intended to limit the implementation methods. Those skilled in the art will appreciate that other variations or modifications can be made based on the above description. It is not necessary and impossible to enumerate all implementation methods here. Obvious variations or modifications arising therefrom remain within the scope of protection of the present invention.

Claims

1. A method for identifying the processing features of irregular air film holes, characterized in that: The steps include: S10: Model preprocessing: Define the surface type of the topological surface as a feature base surface, a transition surface, or a structural surface, identify the surface type of each topological surface of the model, select the closed cylindrical geometric surface as the search starting surface, set the feature base surface as the search ending surface, define the surface with two or more inner rings as the feature base surface, identify the surface containing one inner ring as a transition surface, and identify the surface without an inner ring as a structural surface; S20: Potential feature search and separation: obtaining a topological ring set W and a potential feature face set F for each search starting point face; For each element w in the topological ring set W, the topological ring set W and the characteristic face set F are supplemented according to the characteristics of the topological faces adjacent to the element; The feature face set F obtained after traversing the topological ring set W is output as the potential feature; S30: Feature identification and matching: The potential features are screened to obtain the first identification features; the faces other than the first identification features on the extracted model are defined as the residual model, and the first identification features and the residual model are used to obtain the supplementary potential features through a graph matching algorithm; the supplementary potential features are screened to obtain the second identification features; S40: Merge: Merge the first identification feature and the second identification feature to obtain a feature recognition result.

2. The method for identifying the processing features of irregular-shaped air film holes according to claim 1, characterized in that: In step S20, supplementing the topological ring set W and the characteristic face set F according to the characteristics of the topological faces adjacent to the element includes the following steps: S21: for the first unsearched ring in the topological ring set W, check the topological faces adjacent to the ring and extract the faces that do not belong to the potential feature face set F as the search face group; S22: Determine whether all faces in the search face group are connected. If not, go to step S26; otherwise, go to step S23. S23: Determine whether there is a transition surface in the search surface group. If so, determine whether the transition surface is directly topologically adjacent to the current search starting point surface. If not, identify the transition surface as the feature search end surface. S24: Determine whether there is a search termination surface in the search surface group. If so, go to step S26; otherwise, go to step 25. S25: Add all closed rings composed of topological edges in the search face group that are not adjacent to elements in the feature face set F and are not common edges of the search face group to the front end of the topological ring set W, and add all faces of the search face group to the feature face set F; S26: Determine whether the topological ring set W is traversed. If it is traversed, output the feature face set F as a potential feature. If it is not traversed, repeat S21-S26.

3. The method for identifying the processing features of irregular-shaped air film holes according to claim 1, characterized in that: The topological ring set W is an ordered queue, and the outer ring of the search starting point surface is located at the front end of the topological ring set W.

4. The method for identifying the processing features of irregular-shaped air film holes according to claim 1, characterized in that: The potential feature face set F is an unordered set, which includes the search starting point face.

5. The method for identifying the processing features of irregular-shaped air film holes according to claim 1, characterized in that: In step S30, the potential features and supplementary potential features are screened using the following rules: S31: The faces of the same feature are connected, and adjacent faces are topologically adjacent through at least one edge; S32: The number of features is less than the scale constant of the irregular air film hole; S33: The number of search start faces in the feature is 1, and the number of transition faces is less than 3; S34: The diameter of the hole of the feature in the axial direction of the search starting point surface changes with the search starting point surface as the center toward the edge of the feature according to the set situation.

6. The method for identifying the processing features of irregular-shaped air film holes according to claim 5, characterized in that: In step S34, the identification method is as follows: S341: Selecting the central axis of the search starting point surface of the current feature as the central axis of the feature; S342: Based on the shape of the irregular air film hole, a layer of annularly connected face groups is selected from one side or both sides of the search starting point face, and the maximum envelopable area of the face groups projected along the axis direction is calculated. S343: Repeat S342 from the inside out until the feature boundary is reached, and record the change of the maximum envelopable area; S344: If the obtained maximum envelopable areas all change according to the set conditions, it is determined that the conditions are met.

7. The method for identifying the processing features of irregular-shaped air film holes according to claim 1, characterized in that: In step S30, the method for obtaining the second identification feature includes the following steps: S35: generating an attribute adjacency graph corresponding to the first identification feature and the residual model; S36: The graph corresponding to each first-identified feature is used as the subgraph to be found, and the model corresponding to the residual model is used as the target graph. The graph matching algorithm is called to sequentially match and search each subgraph on the target graph. The model face group corresponding to each subgraph on the target graph obtained by the search is saved and defined as a supplementary potential feature. S37: Screening the supplementary potential features to obtain the second identification features.

8. The method for identifying the processing features of irregular-shaped air film holes according to claim 7, characterized in that: The graph matching algorithm is the VF2 algorithm.

9. The method for identifying the processing features of irregular-shaped air film holes according to claim 1, wherein: In step S10, before identifying the face type, the missing edges and topological relationships in the model are repaired.

10. The method for identifying the processing features of irregular-shaped air film holes according to claim 1, characterized in that: In step S40, the feature recognition result is obtained, and after feedback confirmation, the correct feature model face group is output.

11. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the method according to any one of claims 1 to 10 are implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 10 are implemented.

13. A processor, characterized in that: The processor is configured to run a program, wherein the program executes the method according to any one of claims 1 to 10 when running.

Images