CN118279905B - A method for identifying machining features of broken surfaces based on attributed adjacency graph - Google Patents
A method for identifying machining features of broken surfaces based on attributed adjacency graphInfo
- Publication number
- CN118279905B CN118279905B CN202410627398.5A CN202410627398A CN118279905B CN 118279905 B CN118279905 B CN 118279905B CN 202410627398 A CN202410627398 A CN 202410627398A CN 118279905 B CN118279905 B CN 118279905B
- Authority
- CN
- China
- Prior art keywords
- nodes
- adjacency graph
- broken surface
- target processing
- attribute adjacency
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
- G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/771—Feature selection, e.g. selecting representative features from a multi-dimensional feature space
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
本申请关于基于属性邻接图的含碎面加工特征识别方法，涉及智能制造领域。该方法包括：获取目标加工实体模型，目标加工实体模型中包括至少一个加工特征；对目标加工实体模型进行节点特征提取，得到与目标加工实体模型对应的初始属性邻接图；基于碎面集合判定规则，确定属性邻接图中的至少一个碎面节点；对初始属性邻接图中的碎面节点进行筛除，得到与目标加工实体对应的属性邻接图；基于属性邻接图生成与目标加工实体模型对应的加工特征识别结果。在进行特征加工识别的过程当中，通过对于碎面的识别以及筛除，实现了对于目标加工实体中加工特征更为准确的识别，进而提高了在含碎面的三维模型上进行特征识别的准确率。
The present application is about a method for identifying processing features containing broken faces based on an attribute adjacency graph, and relates to the field of intelligent manufacturing. The method includes: obtaining a target processing entity model, which includes at least one processing feature; extracting node features from the target processing entity model to obtain an initial attribute adjacency graph corresponding to the target processing entity model; determining at least one broken face node in the attribute adjacency graph based on a broken face set judgment rule; screening the broken face nodes in the initial attribute adjacency graph to obtain an attribute adjacency graph corresponding to the target processing entity; and generating a processing feature recognition result corresponding to the target processing entity model based on the attribute adjacency graph. In the process of feature processing recognition, by identifying and screening broken faces, a more accurate recognition of the processing features in the target processing entity is achieved, thereby improving the accuracy of feature recognition on a three-dimensional model containing broken faces.
Description
Technical Field
The application relates to the field of intelligent manufacturing, in particular to a broken surface-containing processing characteristic identification method based on an attribute adjacency graph.
Background
The machining features are that the parts have geometric solid which can be machined and formed by basic machining modes, and are the preconditions for determining the machining process of the parts, and typically have holes, concave cavities, chamfers and the like. With the advent of the information age and the rapid development of Computer technology, computer aided design (Computer AIDED DESIGN, CAD), computer aided manufacturing (Computer Aided Manufacturing, CAM) and other technologies have been widely used in manufacturing industries. Because of the complexity of the actual parts, the selection of the processing features on the CAM software often requires the participation of process personnel, and the process has the problems of frequent human-computer interaction, long time consumption and the like. If the process of identifying the processing characteristics is automatically realized through an algorithm, the method has important practical significance for improving the operation system of numerical control processing, improving the production and manufacturing efficiency of enterprises and reducing the total manufacturing cost of parts.
In the related art, the processing characteristic recognition method is mainly divided into two routes based on boundary representation and based on volume decomposition according to the representation form of the model. Compared with the removed part of the blank, the method has higher characteristic dimension and increases the computational complexity based on the analysis model of the volume decomposition method, so the main stream method is a boundary-based method, and analysis and solution are carried out according to boundary representation information of the model. The processing feature recognition method can be further classified into graph-based (attribute adjacency graph), point cloud-based, mesh-based, and the like according to the type of the convenience representation information. Particularly, the application of the computer vision technology in the field of processing feature recognition is driven by the fire heat of artificial intelligence, and the advantages of the neural network that key features can be extracted from a large amount of geometric information promote the progress of technical methods such as point cloud, grid and the like.
In the related art, model features of an open source CAD part dataset such as MFINSTSEG are simpler, the number of model faces is smaller, and in the process of feature processing and recognition with broken faces, a neural network trained based on the dataset has poor effect on a complex model.
Disclosure of Invention
The application relates to a method for identifying the processing characteristics of a broken surface based on an attribute adjacency graph, which improves the identification effect on the processing characteristics of the broken surface, and is applied to computer equipment, and the method comprises the following steps:
Obtaining a target processing solid model, wherein the target processing solid model comprises at least one processing feature;
extracting node characteristics of the target processing entity model to obtain an initial attribute adjacency graph corresponding to the target processing entity model, wherein the initial attribute adjacency graph comprises at least two characteristic nodes, and the adjacent two characteristic nodes are connected through a characteristic connecting line;
determining at least one broken surface node in the attribute adjacency graph based on the broken surface set judgment rule;
Screening out broken surface nodes in the initial attribute adjacency graph to obtain an attribute adjacency graph corresponding to the target processing entity;
And generating a processing characteristic recognition result corresponding to the target processing entity model based on the attribute adjacency graph.
In an alternative embodiment, extracting node characteristics of the target processing solid model to obtain an initial attribute adjacency graph corresponding to the target processing solid model includes:
extracting node characteristics in the target processing solid model, wherein the node characteristics comprise at least one of plane node characteristics, cylindrical surface node characteristics, conical surface node characteristics, spherical surface node characteristics, circular ring surface node characteristics, spline surface node characteristics and other curved surface node characteristics;
Generating feature nodes in the initial attribute adjacency graph based on the node features;
Extracting edge features between two adjacent feature nodes in the target processing entity model, wherein the edge features comprise same-value directed edge features and different-value directed edge features;
generating feature connecting lines in the initial attribute adjacency graph based on the edge features;
and generating an initial attribute adjacency graph corresponding to the target processing entity model based on the characteristic connecting lines and the characteristic nodes.
In an alternative embodiment, extracting edge features between two adjacent feature nodes in the target processing solid model includes:
Determining a side curve type between two adjacent characteristic nodes in the target processing solid model, wherein the side curve type comprises at least one of a straight line type, an arc type, an elliptical arc type, a spiral line type, a spline curve type and other curve types;
Based on the type of the side curve and the in-plane shape assignment rule corresponding to the type of the side curve, 1 generating the side characteristic between two adjacent characteristic nodes.
In an alternative embodiment, the method further comprises:
And carrying out assignment numbering on the characteristic connecting lines based on the edge characteristics.
In an alternative embodiment, the broken surface set decision rules include a surface type restriction rule, an adjoining edge restriction rule, and a directed edge attribute restriction rule.
In an alternative embodiment, determining at least one broken surface node in the attribute adjacency graph based on a broken surface set decision rule includes:
and determining the adjacent at least two feature nodes as broken surface nodes and belonging to the same broken surface node set in response to the fact that the adjacent at least two feature nodes meet the broken surface set judging rule.
In an alternative embodiment, the feature connection lines further comprise broken surface feature connection lines;
the method further comprises the steps of:
and in response to the adjacent at least two feature nodes being broken surface nodes, modifying a connecting line for connecting the adjacent two broken surface nodes into broken surface feature connecting lines.
In an alternative embodiment, screening out broken surface nodes in the initial attribute adjacency graph to obtain an attribute adjacency graph corresponding to the target processing entity includes:
extracting key broken surface nodes in a broken surface node set;
and reserving the key broken surface nodes, and screening out other broken surface nodes in the broken surface node set to obtain an attribute adjacency graph corresponding to the target processing entity.
In an alternative embodiment, the method further comprises:
Determining association relations between broken surface nodes in the broken surface node set and other characteristic nodes in the initial attribute adjacency graph;
and adjusting the topological relation between the key broken surface nodes and other characteristic nodes in the initial attribute adjacency graph based on the association relation.
In an alternative embodiment, generating a process feature identification result corresponding to the target process entity model based on the attribute adjacency graph includes:
and generating a processing characteristic recognition result in a text form corresponding to the target processing entity model based on the attribute adjacency graph.
The technical effects included in each embodiment of the application at least include:
In the process of identifying the processing characteristics of the target processing entity, after an initial attribute adjacency graph corresponding to the target processing entity is generated, identifying broken surface nodes in the initial attribute adjacency graph, screening the broken surface nodes, and determining a processing characteristic identification result corresponding to the target processing entity model after screening. In the process of feature processing identification, through identification and screening of broken surfaces, more accurate identification of processing features in a target processing entity is realized, and further, the accuracy of feature identification on a three-dimensional model containing broken surfaces is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for identifying characteristics of broken-surface-containing processing based on an attribute adjacency graph according to an exemplary embodiment of the application.
FIG. 2 is a flow chart of another method for identifying a fracture-surface-containing processing feature based on an attribute adjacency graph according to an exemplary embodiment of the present application.
FIG. 3 illustrates a schematic representation of a target process mockup according to one exemplary embodiment of this application.
FIG. 4 illustrates a schematic representation of an initial attribute adjacency graph in accordance with an exemplary embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of a method for identifying a machined feature of a broken surface based on an attribute adjacency graph according to an exemplary embodiment of the present application, and the method is applied to a computer device for explanation, and includes:
And step 101, acquiring a target processing entity model.
In the embodiment of the application, the target machining solid model is a corresponding solid model obtained from the part to be machined. Alternatively, the target process entity model may be a model obtained based on artificial intelligence techniques, which corresponds to a part entity.
And 102, extracting node characteristics of the target processing entity model to obtain an initial attribute adjacency graph corresponding to the target processing entity model.
In an embodiment of the application, the initial attribute adjacency graph is implemented in a computer device in the form of a picture. The initial attribute adjacency graph comprises at least two feature nodes, and the two adjacent feature nodes are connected through a feature connecting line.
Step 103, determining at least one broken surface node in the attribute adjacency graph based on the broken surface set judgment rule.
In the embodiment of the application, the broken surface set judging rule is used for judging whether the node obtained by extracting the broken surface features is contained or not based on the initial attribute adjacency graph. In the embodiment of the application, the number of the broken surface characteristic nodes is usually more than 2, and the broken surface characteristic nodes are used for representing broken surfaces.
And 104, screening out broken surface nodes in the initial attribute adjacency graph to obtain an attribute adjacency graph corresponding to the target processing entity.
The process is the screening process of broken surface nodes. In some embodiments of the application, the broken surface nodes are completely screened out, in other embodiments of the application, the broken surface nodes are replaced by newly built feature nodes, and in other embodiments of the application, the broken surface nodes and the corresponding topological relations are consolidated to form the attribute adjacency graph. The present application is not limited to the actual form of the attribute adjacency graph.
Step 105, generating a processing feature recognition result corresponding to the target processing entity model based on the attribute adjacency graph.
In the embodiment of the application, the processing feature recognition result is a result corresponding to the target processing entity, and comprises the type, the content and the corresponding numerical value of the processing feature in the target processing entity. In one example, the processing feature recognition result can be implemented in text form.
In summary, in the method provided by the embodiment of the present application, in the process of identifying the processing characteristics of the target processing entity, after generating the initial attribute adjacency graph corresponding to the target processing entity, the broken surface nodes are identified in the initial attribute adjacency graph, and the broken surface nodes are screened out, and after screening out, the processing characteristic identification result corresponding to the target processing entity model is determined. In the process of feature processing identification, through identification and screening of broken surfaces, more accurate identification of processing features in a target processing entity is realized, and further, the accuracy of feature identification on a three-dimensional model containing broken surfaces is improved.
Fig. 2 is a schematic flow chart of another method for identifying characteristics of broken surface processing based on attribute adjacency graph according to an exemplary embodiment of the present application, where the method is applied to a computer device for illustration, and the method includes:
step 201, a target processing solid model is obtained.
This process corresponds to the process shown in step 101, and will not be described here.
And 202, extracting node characteristics in the target processing entity model.
It should be noted that, in the embodiment of the present application, before extracting the node features of the target processing entity model, the target processing entity model needs to be extracted as a wire frame model, that is, a model that only characterizes the line of the target processing entity, but not the color of the target processing entity, and in one example, the form of the target processing entity model 310 is shown in fig. 3.
In an embodiment of the present application, the node features include at least one of planar node features, cylindrical surface node features, conical surface node features, spherical surface node features, annular surface node features, spline surface node features, and other surface node features.
Step 203, generating feature nodes in the initial attribute adjacency graph based on the node features.
It should be noted that, the computer device assigns values corresponding to different node features, in one example, the values of the nodes are defined as n=0 to 5, where 1 to 5 corresponds to a plane/cylindrical surface/conical surface/spherical surface/circular surface, and 0 represents other planes not belonging to the above type.
And 204, extracting edge features between two adjacent feature nodes in the target processing entity model.
In the embodiment of the application, the edge features comprise the same-value directed edge features and different-value directed edge features.
In the embodiment of the application, the edge between two feature nodes has the type feature of the edge and the phase feature of the edge. The computer equipment firstly obtains the internal and external relation between the edges and the corresponding surfaces, the concave-convex state of the edges and the shapes of the edges, and finally generates edge characteristics. Optionally, the computer device defines the value e=xyz of the directed edge. X=1-2, Y=1-3, concave/convex/smooth, Z=0-4, wherein 1-4 corresponds to straight line/circular arc/elliptic arc/spiral line, 0 represents other directed edges not belonging to the geometric type. Optionally, the edge curve type includes at least one of a straight line type, an arc type, an elliptical arc type, a spiral type, a spline curve type, and other curve types.
In step 205, feature connection lines in the initial attribute adjacency graph are generated based on the edge features.
In the embodiment of the application, a process of assigning a value to a feature connection line based on an edge feature exists.
And 206, generating an initial attribute adjacency graph corresponding to the target processing entity model based on the characteristic connecting lines and the characteristic nodes.
In one embodiment of the application, the initial attribute adjacency graph is in the form of FIG. 4. In fig. 4, feature nodes 401 to 408 are included, and assigned feature connection lines exist between two adjacent feature nodes.
In step 207, in response to the at least two adjacent feature nodes meeting the broken surface set determination rule, the at least two adjacent feature nodes are determined to be broken surface nodes and belong to the same broken surface node set.
In the embodiment of the application, the broken surface set judging rule comprises a surface type limiting rule, an adjacent edge limiting rule and a directed edge attribute limiting rule. It corresponds to the full necessity of judging that two faces belong to one broken face set in the entity, and the two faces are the same in type and smooth in transition edge. And decomposing the corresponding node characteristics and the edge characteristics to obtain three conditions of identical surface types, smooth adjacent edges and identical directional edge attributes adjacent to the same surface, and judging that the corresponding nodes belong to broken surface nodes and the corresponding broken surface nodes belong to the same broken surface node set when the adjacent characteristic nodes meet at least three conditions.
In the embodiment of the application, in response to the fact that at least two adjacent characteristic nodes are broken surface nodes, a connecting line used for connecting the two adjacent broken surface nodes is modified into a broken surface characteristic connecting line. In the initial feature adjacency graph, the connecting lines between the broken surface nodes can be equivalently represented by a dotted line.
Step 208, extracting key broken surface nodes in the broken surface node set.
The process is based on the extraction process of the key broken surface nodes embodied in step 207.
And 209, reserving the key broken surface nodes, and screening out other broken surface nodes in the broken surface node set to obtain an attribute adjacency graph corresponding to the target processing entity.
In this process, the association relationship between the broken surface nodes in the broken surface node set and other characteristic nodes in the initial attribute adjacency graph needs to be determined, and the topological relationship between the key broken surface nodes and other characteristic nodes in the initial attribute adjacency graph is adjusted based on the association relationship, so that part of broken surface nodes are deleted, and at least one broken surface node in one broken surface node set is reserved to obtain the attribute adjacency graph corresponding to the target processing entity.
Step 210, generating a processing feature recognition result in a text form corresponding to the target processing entity model based on the attribute adjacency graph.
In the embodiment of the application, the processing characteristic recognition result can be realized in a text form. In one example, a database associated with the prior art process features is correspondingly stored in a computer device, and based on a comparison of database attribute adjacency graphs, the computer device generates at least one process feature corresponding to the target process entity and generates visual information in textual form for illustration.
In summary, in the method provided by the embodiment of the present application, in the process of identifying the processing characteristics of the target processing entity, after generating the initial attribute adjacency graph corresponding to the target processing entity, the broken surface nodes are identified in the initial attribute adjacency graph, and the broken surface nodes are screened out, and after screening out, the processing characteristic identification result corresponding to the target processing entity model is determined. In the process of feature processing identification, through identification and screening of broken surfaces, more accurate identification of processing features in a target processing entity is realized, and further, the accuracy of feature identification on a three-dimensional model containing broken surfaces is improved.
The foregoing description of the preferred embodiments of the present application is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements within the spirit and principles of the present application.
Claims (4)
1. A method for identifying a broken-surface-containing processing characteristic based on an attribute adjacency graph, which is applied to computer equipment and comprises the following steps:
obtaining a target processing solid model, wherein the target processing solid model comprises at least one processing feature;
Extracting node characteristics of the target processing entity model to obtain an initial attribute adjacency graph corresponding to the target processing entity model, wherein the initial attribute adjacency graph comprises at least two characteristic nodes, and the adjacent two characteristic nodes are connected through a characteristic connecting line;
determining at least one broken surface node in the attribute adjacency graph based on a broken surface set decision rule, wherein the broken surface set decision rule comprises a surface type limit rule, an adjacency edge limit rule and a directed edge attribute limit rule;
screening out broken surface nodes in the initial attribute adjacency graph to obtain an attribute adjacency graph corresponding to the target processing entity;
generating a processing feature recognition result corresponding to the target processing entity model based on the attribute adjacency graph;
wherein the determining at least one broken surface node in the attribute adjacency graph based on the broken surface set decision rule comprises:
Responding to the condition that at least two adjacent characteristic nodes accord with the broken surface set judging rule, determining the at least two adjacent characteristic nodes as broken surface nodes and belonging to the same broken surface node set;
Extracting node characteristics of the target processing entity model to obtain an initial attribute adjacency graph corresponding to the target processing entity model, wherein the node characteristic extraction comprises the following steps:
Extracting node characteristics in the target processing entity model, wherein the node characteristics comprise at least one of plane node characteristics, cylindrical surface node characteristics, conical surface node characteristics, spherical surface node characteristics, circular ring surface node characteristics and spline surface node characteristics;
Generating feature nodes in the initial attribute adjacency graph based on the node features;
extracting edge features between two adjacent feature nodes in the target processing entity model, wherein the edge features comprise same-value directed edge features and different-value directed edge features;
generating a feature connecting line in the initial attribute adjacency graph based on the edge feature;
generating an initial attribute adjacency graph corresponding to the target processing entity model based on the characteristic connecting lines and the characteristic nodes;
wherein the characteristic connecting lines further comprise broken surface characteristic connecting lines;
the method further comprises the steps of:
responding to the condition that at least two adjacent characteristic nodes are broken surface nodes, and modifying a connecting line for connecting the two adjacent broken surface nodes into a broken surface characteristic connecting line;
screening out broken surface nodes in the initial attribute adjacency graph to obtain an attribute adjacency graph corresponding to the target processing entity, wherein the screening out the broken surface nodes in the initial attribute adjacency graph comprises the following steps:
Extracting key broken surface nodes in the broken surface node set;
Reserving the key broken surface nodes, and screening out other broken surface nodes in the broken surface node set to obtain the attribute adjacency graph corresponding to the target processing entity;
the method further comprises the steps of:
Determining association relations between broken surface nodes in the broken surface node set and other characteristic nodes in the initial attribute adjacency graph;
and adjusting the topological relation between the key broken surface nodes and other characteristic nodes in the initial attribute adjacency graph based on the association relation.
2. The method according to claim 1, wherein the extracting edge features between two adjacent feature nodes in the target processing solid model includes:
Determining a side curve type between two adjacent characteristic nodes in the target processing solid model, wherein the side curve type comprises at least one of a straight line type, an arc type, an elliptical arc type, a spiral line type and a spline curve type;
And generating the edge characteristics between the two adjacent characteristic nodes based on the edge curve type and an in-plane shape assignment rule corresponding to the edge curve type.
3. The method according to claim 2, wherein the method further comprises:
and carrying out assignment numbering on the feature connecting lines based on the edge features.
4. The method of claim 1, wherein generating a process feature recognition result corresponding to the target process solid model based on the attribute adjacency graph comprises:
And generating a processing feature recognition result in a text form corresponding to the target processing entity model based on the attribute adjacency graph.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410627398.5A CN118279905B (en) | 2024-05-21 | 2024-05-21 | A method for identifying machining features of broken surfaces based on attributed adjacency graph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410627398.5A CN118279905B (en) | 2024-05-21 | 2024-05-21 | A method for identifying machining features of broken surfaces based on attributed adjacency graph |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118279905A CN118279905A (en) | 2024-07-02 |
| CN118279905B true CN118279905B (en) | 2025-08-26 |
Family
ID=91645383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410627398.5A Active CN118279905B (en) | 2024-05-21 | 2024-05-21 | A method for identifying machining features of broken surfaces based on attributed adjacency graph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118279905B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119129128A (en) * | 2024-08-13 | 2024-12-13 | 中国船舶集团有限公司第七一九研究所 | A method for optimizing the surface of a vane pump three-dimensional model |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104360634A (en) * | 2014-11-12 | 2015-02-18 | 南京航空航天大学 | Skin mirror image milling numerical control program fast generating method based on features |
| CN107577891A (en) * | 2017-09-19 | 2018-01-12 | 中国农业大学 | Automatic identification and correction method of broken surface defects of structural parts based on attribute adjacency graph |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7042451B2 (en) * | 2002-04-19 | 2006-05-09 | Geometric Software Solutions Co., Limited | Methods using specific attributes and graph grammars in graph-based techniques for feature recognition |
| CN105046020A (en) * | 2015-08-21 | 2015-11-11 | 北京航空航天大学 | Automatic identification and correction method used for broken surface defect of airplane complex structural component |
| CN115331022A (en) * | 2022-08-01 | 2022-11-11 | 北京蚂蚁非标科技有限公司 | A generalized feature recognition method based on quilt and multi-attribute adjacency graph |
-
2024
- 2024-05-21 CN CN202410627398.5A patent/CN118279905B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104360634A (en) * | 2014-11-12 | 2015-02-18 | 南京航空航天大学 | Skin mirror image milling numerical control program fast generating method based on features |
| CN107577891A (en) * | 2017-09-19 | 2018-01-12 | 中国农业大学 | Automatic identification and correction method of broken surface defects of structural parts based on attribute adjacency graph |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118279905A (en) | 2024-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7376233B2 (en) | Semantic segmentation of 2D floor plans using pixel-wise classifiers | |
| CN106096727B (en) | A kind of network model building method and device based on machine learning | |
| EP4388496A1 (en) | Methods and systems for generating segmentation masks | |
| CN118279905B (en) | A method for identifying machining features of broken surfaces based on attributed adjacency graph | |
| Zhang et al. | Generic face adjacency graph for automatic common design structure discovery in assembly models | |
| CN111914480A (en) | Intelligent processing characteristic identification method based on point cloud semantic segmentation | |
| US9886529B2 (en) | Methods and systems for feature recognition | |
| Gong et al. | A typification method for linear pattern in urban building generalisation | |
| EP4083913A1 (en) | Computer-implemented conversion of technical drawing data representing a map and object detection based thereupon | |
| CN116662628A (en) | A 3D CAD Model Retrieval Method Based on Complex Thin-walled Parts | |
| Xú et al. | STEP-NC based reverse engineering of in-process model of NC simulation | |
| CN108595631B (en) | Three-dimensional CAD model double-layer retrieval method based on graph theory | |
| CN119339374A (en) | A method for automatically generating dimension annotations of three-dimensional parts based on MBD | |
| CN118395528A (en) | CAD model generation method and system based on integral sketch | |
| Cui et al. | An efficient algorithm for recognizing and suppressing blend features | |
| CN109063271B (en) | Three-dimensional CAD model segmentation method and device based on ultralimit learning machine | |
| CN104808588B (en) | The broken face Automatic Combined and approximating method of feature based | |
| CN114219959A (en) | Rotary part feature recognition method | |
| CN111582053B (en) | Complex feature layered recognition method for blank model based on feature matrix | |
| CN108073136A (en) | A kind of processing domain computational methods of three-axis numerical control processing | |
| Zbiciak et al. | Feature recognition methods review | |
| CN115169122A (en) | A Multi-Stage Manufacturing Feature Recognition Method Based on Graph and Minimum Disjoint Feature Volume Suppression | |
| CN114925475B (en) | A machining feature recognition method for MBD model based on AAG | |
| CN119357425B (en) | A method for fast matching and searching of similar geometric bodies | |
| Zhang et al. | Research on an Intelligent Identification and Classification Method of Complex Holes in Triangle Meshes for 3D Printing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |