A STEP-based feature recognition method and system for shaft parts

Abstract

The embodiment of the present invention provides a method and system for identifying shaft parts features based on STEP, which belongs to the field of manufacturing industry. The method includes: obtaining the STEP file part information corresponding to the shaft parts to be identified; inputting it into the STEP file parser, so that the STEP file parser outputs the geometric information and topological information of the identified features according to the preset data format; generating feature attributes and feature size information based on the geometric information and topological information, and using a predefined database model to store and manage the feature attributes and feature size information. By obtaining the STEP file according to the established part model, the features are identified and the geometric information is extracted based on the rules and adjacency graph ideas, which facilitates the subsequent process planning based on the features, thereby realizing automated production and intelligent manufacturing. And using the database idea, the feature recognition results are stored and managed to enhance the convenience of feature data management.

Description

Technical Field

[0001] The present invention relates to the technical field of manufacturing industry, and in particular to a method and system for identifying features of shaft parts based on STEP. Background Art

[0002] Modern manufacturing is facing the market demand for personalized and customized products, which makes the production process more complicated. With the improvement of computer technology, sensor technology and data processing capabilities, the amount of data in the manufacturing process has increased dramatically, and traditional process planning methods have been unable to handle these complex data parts. Through automated process planning, human intervention can be reduced, planning efficiency and accuracy can be improved, and the market requirements for diversified products can be met. Intelligent process planning is a complex task involving many subtasks such as machine selection, feature recognition, setting plan and tool selection. Among these subtasks, automatic recognition of processing features is one of the difficulties in realizing intelligent manufacturing. Extracting and identifying manufacturing information from 3D models is regarded as the key to intelligent manufacturing.

[0003] Feature recognition is the process of identifying and extracting application-related information from part geometry. In order to complete the machining of parts, machining features are named with traditional part shape descriptors, such as chamfers, fillets, grooves, keyways, etc. These descriptors can tell the generator what type of machining operation should be used. Due to the large number of computer-aided design and computer-aided manufacturing systems available, the use of neutral formats is inevitable. There are various neutral formats available, such as STL, DXF, IGES, STEP, etc. Among them, STEP is used for product data exchange. It is favored because it contains more product and manufacturing information and has fewer storage requirements. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a method and system for identifying features of shaft parts based on STEP, so as to fully or partially solve the technical problems existing in the above-mentioned prior art.

[0005] In order to achieve the above object, an embodiment of the present invention provides a method for identifying features of shaft parts based on STEP, comprising:

[0006] Obtaining STEP file part information corresponding to the shaft parts to be identified, wherein for different types of shaft parts, corresponding part model three-dimensional images are established and saved as STEP format files;

[0007] Inputting the STEP file part information into a STEP file parser so that the STEP file parser outputs the geometric information and topological information of the identified features according to a preset data format;

[0008] Feature attributes and feature size information are generated based on the geometric information and topological information, and the feature attributes and feature size information are stored and managed using a predefined database model.

[0009] Optionally, obtain the STEP file part information corresponding to the shaft part to be identified, including:

[0010] Use the OCC library to open the STEP file, read the STEP file for information retrieval, and extract the geometric information and topological information described in the STEP file to filter out key information;

[0011] The extracted structured information is temporarily stored in the form of key-value pairs, and the geometric information in the STEP file is assigned to the XYZ coordinate values ​​and vector values ​​of the Cartesian points, the positioning points and vector values ​​of the edge lines according to the data structure of body-surface-loop-edge-point.

[0012] Optionally, the STEP file part information is input into a STEP file parser, so that the STEP file parser outputs the geometric information and topological information of the identified features according to a preset data format, including:

[0013] Acquire feature surface and feature edge information, wherein the feature surface and feature edge information at least includes feature surface type, feature surface geometric topology information, feature edge type, feature edge geometric topology information and feature edge quantity;

[0014] According to the predefined feature recognition rules, the feature surface and feature edge information are matched. If the predefined feature recognition rules are met, the type of the feature surface is determined according to the feature surface and feature edge information;

[0015] If it does not meet the predefined feature recognition rules, the feature is inferred, and the undefined feature edge information is extracted, the transition features are deleted, and the feature attribute adjacency graph is reconstructed;

[0016] The generated feature attributes and dimension information are stored and managed using the defined database model.

[0017] Optionally, according to predefined feature recognition rules, feature surface and feature edge information are matched. If the predefined features are met, the type of the feature surface is determined according to the feature surface and feature edge information, including:

[0018] If it is a simple feature, the same feature type and geometric topology information are merged according to the feature surface and feature edge information, and the simple feature and geometric topology information are extracted;

[0019] If it is a complex feature, identify the feature base surface, retrieve the edge information of the feature base surface, and reversely search for the attribute and geometric topology information of the feature surface adjacent to the feature base surface until a simple feature surface is retrieved;

[0020] According to the attributes of the feature base surface and adjacent feature surfaces, an attribute adjacency graph is constructed to determine the type of complex feature. If the match is successful, the complex feature geometry and topology information is extracted. If the match fails, the adjacency graph and the corresponding feature surface are marked as unidentified features, and feature reasoning is performed.

[0021] Optionally, for unrecognized feature faces, the reasoning process includes:

[0022] Obtain the attributes of the unidentified feature surface and its edge information, and disassemble the unidentified feature surface to obtain the edge attributes, quantity, edge vertices and direction;

[0023] Retrieve the adjacent surface attributes to determine whether it is a simple feature. If so, write feature recognition rules based on the edge attributes. If it is a complex feature, reversely infer the corresponding adjacent surface information based on the edge information, delete the transition surface features, and determine the corresponding feature base surface based on the adjacent surface information to reconstruct the attribute adjacency graph.

[0024] Optionally, for complex features, identification is performed according to the following formula:

[0025]

[0026] In the formula, is the control point, k is the degree of the prescribed basis function, is the k-order B-spline basis function.

[0027] On the other hand, a STEP-based shaft parts feature recognition system includes:

[0028] The acquisition module is used to obtain the STEP file part information corresponding to the shaft part to be identified, wherein for different types of shaft parts, a corresponding three-dimensional diagram of the part model is established and saved as a STEP format file;

[0029] A parsing system for outputting geometric information and topological information of the identified features in a preset data format;

[0030] The model library storage module is used to generate feature attributes and feature size information based on the geometric information and topological information, and use a predefined database model to store and manage the feature attributes and feature size information.

[0031] Optionally, the parsing system is specifically used for:

[0032] Acquire feature surface and feature edge information, wherein the feature surface and feature edge information at least includes feature surface type, feature surface geometric topology information, feature edge type, feature edge geometric topology information and feature edge quantity;

[0033] According to the predefined feature recognition rules, the feature surface and feature edge information are matched. If the predefined feature recognition rules are met, the type of the feature surface is determined according to the feature surface and feature edge information;

[0034] If it does not meet the predefined feature recognition rules, the feature is inferred, and the undefined feature edge information is extracted, the transition features are deleted, and the feature attribute adjacency graph is reconstructed;

[0035] The generated feature attributes and dimension information are stored and managed using the defined database model.

[0036] On the other hand, the present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the steps of the above-mentioned STEP-based shaft part feature recognition method.

[0037] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned STEP-based shaft part feature recognition method are implemented.

[0038] Through the above technical solution, STEP files are obtained according to the established part model. Based on the rules and adjacency graph ideas, features are identified and geometric information is extracted, which facilitates subsequent process planning based on features, thereby realizing automated production and intelligent manufacturing. The database idea is used to store and manage feature recognition results, enhancing the convenience of feature data management.

[0039] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0041] Figure 1 It is an implementation flow chart of a method for identifying shaft parts features based on STEP provided by an embodiment of the present invention;

[0042] Figure 2 is a flow chart of an entity retrieval algorithm provided by an embodiment of the present invention;

[0043] Figure 3 is a flow chart of end face feature recognition provided by an embodiment of the present invention;

[0044] Figure 4 is a keyway feature recognition flow chart provided by an embodiment of the present invention;

[0045] Figure 5 is a feature reasoning flow chart provided by an embodiment of the present invention;

[0046] Figure 6 is a schematic diagram of a parsed data structure provided by an embodiment of the present invention;

[0047] Figure 7 It is a schematic diagram of a database structure provided by an embodiment of the present invention;

[0048] Figure 8 It is a structural schematic diagram of a shaft parts feature recognition system based on STEP provided by an embodiment of the present invention;

[0049] Fig. 9 It is a schematic diagram of the structure of a STEP parsing system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0051] See also Figure 1 As shown, it is a flowchart of an implementation method of a shaft part feature recognition method based on STEP provided by an embodiment of the present invention, including the following execution steps:

[0052] Step 100: Obtain the STEP file part information corresponding to the shaft part to be identified, wherein for different types of shaft parts, create a corresponding three-dimensional drawing of the part model and save it as a STEP format file.

[0053] Specifically, when executing step 100, the following steps may be performed:

[0054] S1000: Use the OCC library to open the STEP file, read the STEP file for information retrieval, and extract the geometric information and topological information described in the STEP file to filter out key information.

[0055] S1001: Temporarily store the extracted structured information in the form of key-value pairs, and assign the geometric information in the STEP file to the XYZ coordinate values ​​and vector values ​​of the Cartesian points, the positioning points and vector values ​​of the edge lines according to the data structure of body-surface-loop-edge-point.

[0056] In some embodiments, information retrieval first uses the OCC library to open the STEP file, calls a function to read each line of the STEP file, and uses the start and end identifier segment keywords of the data as the identifier of the start and end of the data. Information retrieval is performed using the character string defined by the entity as the keyword. Information extraction mainly extracts the geometric and topological information described in the STEP file to filter out key information. According to the entity structure of the file: #data number=entity keyword ('attribute', #data number, #data number, ·······), extract information according to the entity structure of body-face-loop-edge-point. First, search for the '=' position in combination with the entity keyword to obtain the entity row, then loop to search for the information in '(', ')' to obtain the data number, and then search according to the data number to obtain the entity name or attribute, and finally obtain the entity information containing the loop reading of each line, and connect the character string lines describing the entity in series. Information instantiation is to set the data_root variable and temporarily store the extracted structured information in the form of key-value pairs. According to the data structure of body-surface-loop-edge-point, the geometric information in STEP is assigned to the XYZ coordinate values ​​and vector values ​​of Cartesian points, the positioning points and vector values ​​of edge lines, etc., and the instantiated objects are mapped to the data table in.

[0057] Step 101: input the STEP file part information into a STEP file parser, so that the STEP file parser outputs the geometric information and topological information of the identified features according to a preset data format.

[0058] Specifically, when executing step 101, the following steps may be specifically performed:

[0059] S1010: Acquire feature surface and feature edge information, wherein the feature surface and feature edge information at least includes feature surface type, feature surface geometric topology information, feature edge type, feature edge geometric topology information, and feature edge quantity.

[0060] In some embodiments, see Figure 2 As shown, the matching of feature faces first requires traversing the parsed file model entity data. The specific steps are as follows:

[0061] (1) Obtaining the geometric topological information of the structure of body-surface-loop-edge-point after analysis;

[0062] (2) Classify entities by entity keywords, determine whether the entity name is the "CLOSED_SHELL" entity type, and extract the characteristic entity attributes;

[0063] (3) Traverse the feature surface and obtain the geometric topological attributes of the feature surface;

[0064] (4) Obtain the ring element attributes of the corresponding feature;

[0065] (5) Traverse the directed edge elements to obtain the geometric properties of the directed edges and the geometric position information of the edge vertices;

[0066] (6) Determine whether there are any edge attributes that have not been traversed. If so, return to process (5) until all edges on the ring have been retrieved;

[0067] (7) Otherwise, determine whether there are any ring attributes that have not been traversed. If so, return to process (4) until all rings on the corresponding feature surface are retrieved;

[0068] (8) Otherwise, determine whether there are any face attributes that have not been traversed. If so, return to process (3) until all feature faces on the entity have been retrieved.

[0069] Otherwise, the search ends and the feature surface and edge information are obtained. After the traversal is completed, the feature surface data of each type is stored in different sets. The general structure of the feature surface can be understood based on the feature surface edge type and endpoint position information.

[0070] S1011: Match feature surface and feature edge information according to predefined feature recognition rules. If the predefined feature recognition rules are met, determine the type of the feature surface according to the feature surface and feature edge information.

[0071] This predefined feature recognition rule algorithm includes recognition rules for simple and complex features. Simple feature algorithms have been implemented, such as end faces, chamfers, fillets, tapers, outer circles, step surfaces, spherical surfaces, etc.; complex feature algorithms such as keyways, grooves, threads, etc. According to the feature rule algorithm, the above feature faces and feature edge information are retrieved to match the predefined features. If the predefined features are met, the type of feature face is determined based on the feature face and feature edge information.

[0072] In some implementations, when executing step S1011, it is necessary to set predefined feature rules. The simple feature takes the end face feature as an example. For the analysis of the simple feature predefined rule method, refer to Figure 3As shown. The end face is composed of a plane. In the STEP file, the surface attribute is PLANE, and the parameters contained include vertices and directions on the plane. The boundary contains one or more boundaries, such as: the outer boundary (FACE_OUTER_BOUND) or the inner boundary (FACE_BOUND). In most cases, the end face must contain the outer boundary of the surface. But no matter how the boundary type changes, it must contain loop (EDGE_LOOP) information. Therefore, the main thing is to retrieve and filter the topological information of the loop to find the corresponding high-level surface. The end face feature is at both ends of the part, corresponding to the set of two end faces of the part. Therefore, the principles for determining the end face are: (1) The end face is a plane; (2) There are two arcs on the boundary of the face; (3) The position of the end face coordinate point is the maximum value, that is, the coordinate point of the center of the left end face is the minimum value, and the coordinate point of the center of the right end face is the maximum value. Only faces that meet the above given conditions are identified as end faces. Therefore, the specific identification steps of end faces and step faces in machining features are as follows:

[0073] 1. Traverse all feature planes of the part, retrieve the target element feature plane keyword, obtain the PLANE feature plane attribute, if the attribute on the feature plane is PLANE, it means that the feature plane is a plane attribute, mark the feature plane as true, and continue searching.

[0074] 2. When the feature surface is a plane, check the boundary element information of the feature surface. If the plane boundary contains the inner boundary FACE_BOUND of the feature surface, obtain the geometric properties of the curve and the Cartesian coordinates of the vertices. According to the edge information, form an adjacency graph with other feature surfaces to judge the features. If it contains the outer boundary of the feature surface, traverse the feature surface to obtain the Cartesian coordinates of the vertices of the curve and their geometric properties.

[0075] 3. Extract the position coordinates of the surface to which it belongs and determine whether it meets the end face edge rule. If so, retrieve the position information of the surface to which it belongs. Otherwise, exit the search and perform other feature judgments on the surface. If it is not recognized, mark the surface as an unrecognized feature surface.

[0076] 4. Determine whether the search plane is located on the axis. If so, determine whether the feature surface is located at both ends of the feature. Compare the coordinate position of the arc center with the axis. If the arc X=Y=0, then the plane is located at the axis. Otherwise, delete the plane.

[0077] 5. If so, the feature z coordinate is at its maximum value as the right end face, and the feature z coordinate is at its minimum value as the left end face. Finally, the left / right end face, the center coordinate position and the edge geometry information are output.

[0078] 6. Otherwise, exit the search and perform other feature judgment on this face. If it is not recognized, mark this face as an unrecognized feature face.

[0079] In some embodiments, when executing step S1011, it is necessary to set predefined feature rules. The complex feature takes the keyway feature as an example. For the analysis of the complex feature predefined rule method, refer to Figure 4 As shown. For general processing, the keyway feature can be machined by turning and milling. A rounded rectangle is placed on the outer cylindrical surface and slotted to a certain depth to form a keyway feature. In the STEP file, the keyway feature is decomposed into six feature faces, one keyway bottom face and five keyway side faces. In the recognition process, the keyway bottom face is first identified and used as the feature base face. The edge information is extracted from the feature base face, and then the adjacent faces are matched according to the edge information to identify the keyway feature.

[0080] The identification steps are as follows: Identify the feature base surface: traverse each feature surface (ADVANCED_FACE), and check whether the value object contains PLANE. If so, retrieve the edge line of the EDGE_LOOP value ORIENTED-EDGE in FACE_OUTER_BOUND. Determine whether there are only three arcs and two straight lines. If so, obtain the feature base surface, retrieve the position information (center coordinates) and radius, and determine whether the arc radii are equal. If so, compare the positions of the three arcs, merge the two identical arc centers, extract the two different arc coordinates and radii, and output the distance between the two different arcs, merge the feature base surface and the feature side surface, and find the auxiliary feature surface according to the keyway position to obtain the keyway depth dimension. The output feature is keyway + ID, and the two arc coordinates, radius, depth and length. Identify adjacent feature faces: obtain the feature base surface, retrieve the position information (center coordinates) and radius according to the intersecting edges, find the feature surface with the same edge attributes, obtain the feature surface number containing this edge, retrieve the attributes of the feature surface and the edge geometric topology information, store this feature surface information, count this surface, merge the feature base surface and feature side surface, find the auxiliary feature surface according to the keyway position, obtain the keyway depth dimension, and output the feature as keyway + ID, as well as two arc coordinates, radius, depth and length.

[0081] Design an algorithm to extract the depth dimension of the flat key. First, extract the characteristic center coordinates of the flat key (X1, Y1, Z1), (X2, Y2, Z2), extract X and Y and assign dx=x1, dy=y1, and calculate the distance from the flat key to the axis. The formula is:

[0082]

[0083] Then, according to the attribute adjacency graph, find the radius of the outer circle feature corresponding to the flat key position, traverse the coordinate position of the feature center of each outer circle, extract the radius of the outer circle surface that meets the requirements, and record it as R. Then the depth of the flat key H = R-r1, and add it and store it in the flat key dictionary. According to the steps, the keyway feature is identified, and its position information, radius, depth, length and other geometric information are stored

[0084] Specifically, when executing step S1011, the following steps may be specifically performed:

[0085] S1: If it is a simple feature, the same feature type and geometric topology information are merged according to the feature surface and feature edge information, and the simple feature and geometric topology information are extracted.

[0086] In some embodiments, if it is a simple feature, the same feature type and geometric topology information are merged according to the feature face and feature edge information, and then the simple feature and geometric topology information are extracted. According to the nature of the STEP file, symmetrical rotation parts with cylindrical surfaces, conical surfaces and annular surfaces should be considered in particular. Although each of these feature faces is displayed as a single face in any CAD model, they are interpreted and saved as two separate faces in the structure of the STEP file. Therefore, when extracting feature information, two feature faces of the same type and geometric topology information should be merged.

[0087] S2: If it is a complex feature, identify the feature base surface, retrieve the edge information of the feature base surface, and reversely search for the attribute and geometric topology information of the feature surface adjacent to the feature base surface until a simple feature surface is retrieved;

[0088] S3: According to the attributes of the feature base surface and the adjacent feature surfaces, an attribute adjacency graph is constructed to determine the type of complex feature. If the match is successful, the complex feature geometry and topology information is extracted. If the match fails, the adjacency graph and the corresponding feature surface are marked as unidentified features, and feature reasoning is performed.

[0089] Specifically, when executing S3, the unidentified feature surface attributes and their edge information can be obtained, and the unidentified feature surface can be disassembled to obtain the edge attributes, quantity, edge vertices and direction; the adjacent surface attributes can be retrieved to determine whether it is a simple feature. If so, the feature recognition rules are written according to the edge attributes. If it is a complex feature, the corresponding adjacent surface information is reversed according to the edge information, and the transition surface features are deleted. The corresponding feature base surface is determined according to the adjacent surface information, and the attribute adjacency graph is reconstructed.

[0090] In some embodiments, among the complex features, the thread feature is a complex feature composed of curved surfaces, and the thread feature information extraction is different from other features. The helix of the thread feature is a straight line spiraling outward in space to form a spiral-like curve structure, which is represented by a B-spline curve in the STEP file. The B-spline curve is composed of segments, and the interval of each segment parameter is [0, 1]. The mathematical formula is as follows:

[0091]

[0092] In the formula, (i=0,1…n) is the control point, k is the order of the specified basis function, (i=0,1…n) is the k-order B-spline basis function.

[0093] The generation principle of B-spline curves is based on a set of control vertices, node sets and B-spline basis functions, which together determine the shape and characteristics of the curve. Control vertices: are some specific points on the curve that define the shape and position of the curve. In mathematical expression, these vertices are usually represented as, where i is the index of the vertex. The node set is a set of parameter values ​​that is used to define the parameter domain of the curve. These nodes determine the segmentation of the curve in the parameter space. B-spline basis functions are a set of mathematical functions used to calculate points on the curve based on the control vertices and node sets. They have the property of local support, and when a control vertex is changed, only part of the curve is affected, not the entire curve.

[0094] In the STEP file of the axis class, the control vertex position information is stored in the Cartesian coordinate system of "ORIENTED_EDGE", "EDGE_CURVE" and "VERTEX_POINT", which represents the endpoints of the spline curve, generally located at the upper and lower vertices in the X-axis direction. When extracting thread features, the thread size information is determined by extracting the thread control vertex position.

[0095] S1012: If the predefined feature recognition rules are not met, the feature is inferred, and the undefined feature edge information is extracted, the transition features are deleted, and the feature attribute adjacency graph is reconstructed.

[0096] In some implementations, when executing step S1012, refer to Figure 5As shown in the figure, it is a detailed flow chart of the feature reasoning method in the feature automatic recognition system, which specifically includes the following execution steps: obtaining the attributes of the unrecognized feature surface and its edge information; disassembling the feature surface to decompose the attributes and quantity of the directed edges, the position and direction of the edge vertices; retrieving the adjacent surface attributes to determine whether it is a simple feature. If it is a simple feature, then write the feature recognition rules and feature size extraction algorithm according to the edge attributes; otherwise, delete the transition feature information, determine the feature base surface, and reconstruct the feature adjacency graph (if it is a complex feature, execute the following steps: according to the feature surface edge information, reverse the corresponding adjacent surface number from the upper layer container, and delete the transition surface feature; determine the feature base surface according to the adjacent surface information, reconstruct the attribute adjacency graph, and write the complex feature size extraction algorithm; input the above feature recognition rules and feature size extraction algorithm into the feature recognition system, complete the undefined feature reasoning, and write the undefined feature into the system.).

[0097] S1013: The generated feature attributes and dimension information are stored and managed using the defined database model.

[0098] Step 102: Generate feature attributes and feature size information based on the geometric information and topological information, and use a predefined database model to store and manage the feature attributes and feature size information.

[0099] In some embodiments, see Figure 6 As shown, it is a schematic diagram of a parsed data structure provided by an embodiment of the present invention. First, the part entity (SHELL) is parsed into multiple advanced faces (ADVANCED_FACE), and then parsed into outer boundaries (FACE_OUTER_BOUND) and inner boundaries (FACE_BOUND) - edge loops (EDGE_LOOP) - multiple oriented edges (ORIENTED_EDGE) - edge curves (EDGE_CURVE) - vertices (VERTEX_POINT) / line attributes (line (LINE), circle (CIRCLE)) - Cartesian coordinates (CARTESIAN_POINT), direction vector (DIRECTION), plane (PLANE), cylindrical surface (CYLINDRICAL_SURPACE), conical surface (CONICAL_SURFACE) and torus (TOROIDAL_SURFACE) - curves - Cartesian coordinates (CARTESIAN_POINT), direction vector (DIRECTION).

[0100] In some embodiments, it is necessary to design the logical structure of the feature library to facilitate the storage, management and retrieval of different part feature models. The logical structure design consists of two parts: table structure and index management. The logical relationship of different feature entities is represented by the feature library conceptual structure in the form of a two-dimensional data table and stored in the PostgreSQL database. Among them, the table structure is to create a database table to store different feature entity types and detailed dimension data. Each part feature entity corresponds to a table, and the feature attribute information identified in the conceptual structure design is included in the fields of the table. For example, the end face feature type, position coordinates, and feature dimension information. The index structure can improve the retrieval speed of the feature library table through appropriate indexes. Indexes are created through commonly used query fields (part type-part name-feature type), thereby realizing rapid retrieval of feature recognition results and improving the response speed of the feature library. The feature library uses the python computer programming language to enter the component table into the PostgreSQL system. The feature library storage structure is as follows Figure 7 As shown in the figure. The PostgreSQL database management system is divided into three modules: PostgreSQL process management, shared storage area, and file storage area. The modular hierarchical structure and the association between adjacent modules realize the connection between different modules and the transmission of task information, and form a complete query, storage and other functional tool chains. The PostgreSQL database manages concurrent transactions and data consistency through the multi-version concurrency control (MVCC) mechanism to complete operations such as query, add, update and delete feature data, ensuring that the model library system manages the database efficiently. The PostgreSQL process module includes check pointers, index management, WAL management, log writing, etc., connects to the system driver, and performs storage system operations. The shared storage area is used to cache table and index data and maintain database operations through the data buffer and XLOG buffer, and improves performance by using multiple memory areas and caching strategies. The file storage area contains data files (storing actual table and index data), WAL files, transaction log files, and control file information.

[0101] See also Figure 8 FIG. 1 is a schematic diagram of a structure of a shaft part feature recognition system based on STEP provided by an embodiment of the present invention, comprising:

[0102] The acquisition module 80 is used to acquire the STEP file part information corresponding to the shaft part to be identified, wherein for different types of shaft parts, a corresponding three-dimensional diagram of the part model is established and saved as a STEP format file;

[0103] The analysis system 81 is used to output the geometric information and topological information of the identified features according to a preset data format;

[0104] The model library storage module 82 is used to generate feature attributes and feature size information based on the geometric information and topological information, and use a predefined database model to store and manage the feature attributes and feature size information.

[0105] In some implementations, the analysis system 82 is specifically used to:

[0106] Acquire feature surface and feature edge information, wherein the feature surface and feature edge information at least includes feature surface type, feature surface geometric topology information, feature edge type, feature edge geometric topology information and feature edge quantity;

[0107] According to the predefined feature recognition rules, the feature surface and feature edge information are matched. If the predefined feature recognition rules are met, the type of the feature surface is determined according to the feature surface and feature edge information;

[0108] If it does not meet the predefined feature recognition rules, the feature is inferred, and the undefined feature edge information is extracted, the transition features are deleted, and the feature attribute adjacency graph is reconstructed;

[0109] The generated feature attributes and dimension information are stored and managed using the defined database model.

[0110] In some embodiments, see Fig. 9 As shown, a schematic diagram of the structure of a STEP parsing system provided by an embodiment of the present invention is provided. Based on a STEP file containing cloud data information, manufacturing information, physical properties, material information and other information, the STEP file is retrieved to filter out the manufacturing information of the product, the manufacturing information is extracted, the product geometry and topology information is obtained, the product geometry and topology information is instantiated, and the information is stored in a body-surface-loop-line-point structure.

[0111] On the other hand, the present invention also provides an electronic 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 STEP-based shaft parts feature recognition method described in any one of the above embodiments are implemented.

[0112] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the STEP-based shaft part feature recognition method described in any of the above embodiments are implemented.

[0113] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0114] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0115] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0116] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0117] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0118] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0119] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0120] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0121] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the present application.

Claims

1. A method for identifying shaft parts features based on STEP, characterized in that: include: Obtaining STEP file part information corresponding to the shaft parts to be identified, wherein for different types of shaft parts, corresponding part model three-dimensional images are established and saved as STEP format files; Inputting the STEP file part information into a STEP file parser so that the STEP file parser outputs the geometric information and topological information of the identified features according to a preset data format; Generate feature attributes and feature size information based on the geometric information and topological information, and use a predefined database model to store and manage the feature attributes and feature size information; The STEP file part information is input into a STEP file parser so that the STEP file parser outputs the geometric information and topological information of the identified features according to a preset data format, including: Acquire feature surface and feature edge information, wherein the feature surface and feature edge information at least includes feature surface type, feature surface geometric topology information, feature edge type, feature edge geometric topology information and feature edge quantity; According to the predefined feature recognition rules, the feature surface and feature edge information are matched. If the predefined feature recognition rules are met, the type of the feature surface is determined according to the feature surface and feature edge information; If it does not meet the predefined feature recognition rules, the feature is inferred, and the undefined feature edge information is extracted, the transition features are deleted, and the feature attribute adjacency graph is reconstructed; The generated feature attributes and dimension information are stored and managed using the defined database model; Among them, according to the predefined feature recognition rules, the feature surface and feature edge information are matched. If the predefined features are met, the type of the feature surface is determined according to the feature surface and feature edge information, including: If it is a simple feature, the same feature type and geometric topology information are merged according to the feature surface and feature edge information, and the simple feature and geometric topology information are extracted; If it is a complex feature, identify the feature base surface, retrieve the edge information of the feature base surface, and reversely search for the attribute and geometric topology information of the feature surface adjacent to the feature base surface until a simple feature surface is retrieved; According to the attributes of the feature base surface and the adjacent feature surface, an attribute adjacency graph is constructed to determine the type of complex feature. If the match is successful, the complex feature geometry and topology information is extracted. If the match fails, the adjacency graph and the feature surface to which it belongs are marked as unrecognized features, and feature reasoning is performed. Among them, the reasoning process for unrecognized feature faces includes: Obtain the attributes of the unidentified feature surface and its edge information, and disassemble the unidentified feature surface to obtain the edge attributes, quantity, edge vertices and direction; Retrieve the adjacent surface attributes to determine whether it is a simple feature. If so, write feature recognition rules based on the edge attributes. If it is a complex feature, reversely infer the corresponding adjacent surface information based on the edge information, delete the transition surface features, and determine the corresponding feature base surface based on the adjacent surface information to reconstruct the attribute adjacency graph. Among them, for complex features, identification is performed according to the following formula: In the formula, is the control point, k is the degree of the prescribed basis function, is the k-order B-spline basis function; Among them, simple features include: end face, chamfer, fillet, cone, outer circle, step surface, and spherical surface; complex features include: keyway, groove, and thread.

2. The method for identifying shaft parts features based on STEP according to claim 1 is characterized in that: Get the STEP file part information corresponding to the shaft parts to be identified, including: Use the OCC library to open the STEP file, read the STEP file for information retrieval, and extract the geometric information and topological information described in the STEP file to filter out key information; The extracted structured information is temporarily stored in the form of key-value pairs, and the geometric information in the STEP file is assigned to the XYZ coordinate values ​​and vector values ​​of the Cartesian points, the positioning points and vector values ​​of the edge lines according to the data structure of body-surface-loop-edge-point.

3. A STEP-based shaft parts feature recognition system applied to the STEP-based shaft parts feature recognition method according to claim 1 or 2, characterized in that: include: The acquisition module is used to obtain the STEP file part information corresponding to the shaft part to be identified, wherein for different types of shaft parts, a corresponding three-dimensional diagram of the part model is established and saved as a STEP format file; A parsing system for outputting geometric information and topological information of the identified features in a preset data format; A model library storage module, used to generate feature attributes and feature size information based on the geometric information and topological information, and to store and manage the feature attributes and feature size information using a predefined database model; Wherein, the analysis system is specifically used for: Acquire feature surface and feature edge information, wherein the feature surface and feature edge information at least includes feature surface type, feature surface geometric topology information, feature edge type, feature edge geometric topology information and feature edge quantity; According to the predefined feature recognition rules, the feature surface and feature edge information are matched. If the predefined feature recognition rules are met, the type of the feature surface is determined according to the feature surface and feature edge information; If it does not meet the predefined feature recognition rules, the feature is inferred, and the undefined feature edge information is extracted, the transition features are deleted, and the feature attribute adjacency graph is reconstructed; The generated feature attributes and dimension information are stored and managed using the defined database model.

4. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the STEP-based shaft parts feature recognition method as described in any one of claims 1-2 are implemented.

5. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the STEP-based shaft part feature recognition method as described in any one of claims 1-2 are implemented.

Images