A process identification method, apparatus, equipment, and medium based on model features.

Abstract

This invention provides a process identification method based on model features, comprising: constructing a process knowledge graph by extracting relation node triples from standardized process description text; the node types of this graph include: feature nodes, process nodes, equipment nodes, tool nodes, and fixture nodes; the relationships between adjacent nodes include: "available process", "preceding process", "available equipment", "initial machining", "equipped tool", and "equipped fixture"; obtaining the geometric model of the mechanical part to be processed, extracting its geometric feature attributes and determining the feature topology relationships to obtain machining features; and using a reverse search method to start from the feature nodes corresponding to the machining features, filtering nodes that meet the machining requirements of the mechanical part to be processed from the process knowledge graph to obtain a complete process scheme. This invention can deeply explore the correlation between the geometric features of the part model and the machining process, improve the accuracy of process identification, and has wide applicability.

Description

Technical Field

[0001] This invention belongs to the field of process identification technology, and specifically relates to a process identification method, device, equipment and medium based on model features and based on process knowledge graph. Background Technology

[0002] Traditional industrial processes rely heavily on human experience, with design and analysis typically depending on the knowledge and experience of operators. More importantly, traditional methods lack the ability to deeply analyze process data, failing to uncover hidden patterns or correlations and limiting the scope for process optimization. As modern industry becomes increasingly diversified, customized, and complex, this approach struggles to meet the demands for high efficiency and precision, and is prone to errors, impacting production flexibility and timeliness. To effectively address these issues, knowledge graph technology has been introduced into the field of machining processes to optimize process identification and design workflows. Knowledge graphs, through computer systems storing part geometry information, machining process data, and their interrelationships, enable intelligent searching and automatic identification of required processes. As a structured semantic knowledge base, knowledge graphs can symbolically describe concepts and their relationships in the physical world. Their core unit is the "entity-relationship-entity" triple, which also includes relationships between entities and their associated attribute-value pairs. Through these relationships, entities form a network-like knowledge structure.

[0003] In machining processes, the application of knowledge graphs is particularly important. It can not only aggregate and organize complex process data, but also quickly respond to various process queries by analyzing part features, machining requirements, and historical data. Through intelligent reasoning and recommendations, it can effectively improve the efficiency and accuracy of process design, reduce reliance on manual labor, and enhance the automation level and decision support capabilities of the machining process.

[0004] Currently, some scholars have applied knowledge graph technology to the manufacturing field, but most research focuses on the construction technology of process knowledge graphs, failing to fully leverage its advantages for practical application. Patent application CN118468004A discloses a method for identifying machining processes of micro-roughness parts. Through dimensionality reduction, feature extraction and fusion, and combined with neural network technology, a model capable of effectively identifying machining processes is established, thereby improving the machining accuracy of micro-roughness parts. However, although this method improves the accuracy of process identification, its application is mainly concentrated in specific machining identification scenarios. Its "black box" nature makes the decision-making process opaque and unable to clearly explain the reasoning logic behind process identification. At the same time, the model cannot capture the deep semantic relationships between processes, limiting its application in complex process chains. Patent application CN117236432A discloses a method and system for constructing manufacturing process knowledge graphs for multimodal data. This invention establishes a solid model of the workpiece and its related features based on 3D CAD models and drawing data, enriching the data types of the knowledge graph and enhancing the accuracy and operability of the knowledge graph data. Although this invention integrates multimodal data from the knowledge graph, solving the problem of incomplete data coverage in the construction of previous manufacturing process knowledge graphs, it does not apply the manufacturing process knowledge graph further. Patent application CN116661389A discloses a method and system for identifying the "four new" elements in diesel engine component manufacturing processes. The "four new" elements refer to new processes, new materials, new equipment, and new technologies. This method traverses existing technology databases, statistically identifies the "four new" elements involved in the production process, and quickly confirms the application status of new technologies. While this patent can efficiently identify the "four new" elements in diesel engine manufacturing, it also fails to provide suggestions for subsequent processing schemes and lacks support for intelligent decision-making.

[0005] Overall, existing technologies have made significant progress in constructing manufacturing process knowledge graphs and in process identification. However, these technologies generally share a common shortcoming: a lack of in-depth application of process knowledge graphs, particularly in the recommendation of subsequent process solutions. Although knowledge graphs effectively organize and correlate large amounts of process data, they fail to fully utilize this information to generate intelligent process solutions. This deficiency limits the application potential of knowledge graphs in actual manufacturing. Further exploration and development of the decision support value of process knowledge graphs are needed to enhance their practicality and effectiveness in actual manufacturing processes. Summary of the Invention

[0006] To address the shortcomings of existing technologies, the present invention aims to provide a process identification method, apparatus, equipment, and medium based on model features, which can flexibly adapt to diverse process conditions, deeply explore the correlation between the geometric features of the mechanical part model to be processed and the processing technology, and improve the accuracy of process identification.

[0007] The technical solution adopted by the present invention to achieve the above objectives is as follows:

[0008] The first aspect of this invention provides a process identification method based on model features, comprising:

[0009] Acquire process-related data, preprocess it, and obtain standardized process description text;

[0010] A process knowledge graph is constructed by extracting relation node triples from the process description text. The node types constituting the process knowledge graph include: feature nodes, process nodes, equipment nodes, tool nodes, and fixture nodes. The relationships between two adjacent nodes include: "available process", "preceding process", "available equipment", "initial processing", "equipped tool", and "equipped fixture".

[0011] Obtain the geometric model of the mechanical part to be processed, extract its geometric feature attributes and determine the feature topology relationship to obtain the machining features of the mechanical part model;

[0012] A reverse search method is used to start from the feature nodes corresponding to the machining features and select nodes that meet the machining requirements of the mechanical parts to be processed from the process knowledge graph to obtain a complete process plan.

[0013] In some embodiments, the process-related data includes part machining features, material information, process requirements, and equipment parameters; the part machining features include specific requirements for the geometry, dimensional tolerances, and surface roughness of the mechanical part to be machined; the material information relates to the physical and chemical properties of the materials used in the part; the process requirements include the operating conditions during the machining process, including the process route, machining steps, and cutting tools used; and the equipment parameters include the type, specifications, and machining accuracy of the equipment.

[0014] In some embodiments, the process-related data is divided into two categories: structured process data and unstructured process data.

[0015] The preprocessing of structured process data includes: data cleaning, removing redundancy, correcting errors, and filling in missing values ​​to ensure data integrity and accuracy; standardization of data from different sources, unifying data formats from different sources, and converting categorical data into analyzable numerical forms; and normalization of numerical data to eliminate the influence of different units of measurement.

[0016] The preprocessing for unstructured process data includes, in order: word segmentation, part-of-speech tagging, regularization, and stop word filtering.

[0017] In some embodiments, in the process knowledge graph, the feature nodes represent features of the mechanical parts to be processed; the process nodes represent optional process procedures corresponding to the feature nodes, and the attributes maintained within each process node include machining accuracy and surface roughness; the equipment nodes represent available processing equipment that matches the process, and each equipment node maintains relevant attributes of its own equipment; the tool nodes represent available processing tools that match the equipment, and each tool node stores relevant attributes of its own tool; the fixture nodes represent available fixtures that match the equipment, and each fixture node stores the characteristics and applicable scope of its own fixture.

[0018] The term "available process" indicates that a certain feature of the mechanical part to be processed can be processed using a certain process; the term "preceding process" indicates the sequence of processes; the term "available equipment" indicates that a certain process can be processed using a certain equipment; the term "initial processing" indicates that a certain process is the first step in the processing route of a certain feature; the term "equipped with cutting tools" indicates that a certain equipment can be equipped with a certain cutting tool; and the term "equipped with fixtures" indicates that a certain equipment can be equipped with a certain fixture.

[0019] In some embodiments, the machining features of the mechanical part model to be processed are obtained according to the following steps:

[0020] Step S31: Import the geometric model of the mechanical part to be processed into a supported file format to ensure that the required geometric data is converted into a processable format;

[0021] Step S32: Extract all geometric features of the mechanical part to be processed from the geometric model, add solid attributes to each surface in the geometric model, and predefine the processing accuracy and surface roughness;

[0022] Step S33: According to the processing requirements, classify the extracted geometric features and identify the geometric features that meet the machining requirements as processing features;

[0023] Step S34: Extract the key attributes of the processing features, including dimensions, accuracy, and surface roughness;

[0024] Step S35: Detect adjacent features using normal vectors and boundary points for all extracted geometric features, construct topological relationships, use the unique identifier of the processing feature as a node, the connection relationship between adjacent processing features as an edge, and use the spatial location of the geometric features to analyze the dependency relationship between processing features and identify the processing order between adjacent processing features.

[0025] Step S36: Organize the extracted processing features and their related attributes and topological relationships into structured information to obtain the machining features of the mechanical part model to be processed.

[0026] In some embodiments, step S35, the specific steps for identifying the processing order between adjacent processing features, include:

[0027] Assuming the first and second processing features lie in a defined common plane, a topological analysis is performed on their closed curves: If the closed curve of the second processing feature is completely within the closed curve of the first processing feature, then the processing order of the first processing feature is superior to that of the second processing feature; if the closed curves of the first and second processing features only partially overlap, then the processing feature corresponding to the overlapping area or the processing feature with greater depth in three-dimensional space is processed first; if the closed curves of the first and second processing features do not overlap, it indicates that the first and second processing features are geometrically independent, and their processing order is arranged according to the overall process flow.

[0028] In some embodiments, the method of reverse search starts from the feature nodes corresponding to the machining features, and filters out nodes that meet the machining requirements of the mechanical parts to be processed from the process knowledge graph to obtain a complete process plan, specifically including:

[0029] The process knowledge graph is entered from the target feature node. The corresponding process nodes are found sequentially through the "available process" relationship. During this process, it is determined whether each process node meets the processing requirements. If it does not meet the requirements, the search of the current path is terminated directly. If it meets the requirements, the search is carried out in the next step according to the "preceding process" relationship. When the found process node has an "initial processing" relationship, the process method corresponding to the obtained node is determined to be the last process step. The path between the target feature node and the initial node corresponding to the last process step is found, thus forming a complete process solution.

[0030] A second aspect of the present invention provides an apparatus based on the process identification method described in any embodiment of the first aspect of the present invention, comprising:

[0031] The first module stores standardized process description text, which is obtained by preprocessing the acquired process-related data.

[0032] The second module is used to construct a process knowledge graph by extracting relation node triples from the process description text. The node types constituting the process knowledge graph include: feature nodes, process nodes, equipment nodes, tool nodes, and fixture nodes. The relationships between two adjacent nodes include: "available process", "preceding process", "available equipment", "initial processing", "equipped tool", and "equipped fixture".

[0033] The third module is used to obtain the geometric model of the mechanical part to be processed, extract its geometric feature attributes and determine the feature topology relationship to obtain the machining features of the mechanical part model.

[0034] The fourth module is used to start from the feature nodes corresponding to the machining features using a reverse search method, and select nodes that meet the machining requirements of the mechanical parts to be processed from the process knowledge graph to obtain a complete process plan.

[0035] A third aspect of the present invention provides an electronic device comprising:

[0036] At least one processor, and a memory communicatively connected to said at least one processor;

[0037] The memory stores instructions executable by the at least one processor, the instructions being configured to perform the process identification method according to any embodiment of the first aspect of the present invention.

[0038] A fourth aspect of the present invention provides a computer-readable storage medium storing computer instructions for causing the computer to perform the process identification method according to any embodiment of the first aspect of the present invention.

[0039] The beneficial effects of this invention are as follows:

[0040] Compared to traditional technologies, this invention combines process knowledge graphs to form a model-based process identification method, significantly improving the intelligence level of process selection. Traditional methods often rely on human experience, which is prone to subjective judgment and errors, while this system can quickly and accurately identify feasible process solutions, thereby reducing the error rate. This method can not only handle complex process information but also effectively integrate multi-source heterogeneous data, adapting to the needs of modern large-scale intelligent industrial production.

[0041] Compared with existing process identification schemes, this invention exhibits advantages in several aspects. First, traditional schemes typically rely on fixed rules and linear processes, failing to flexibly address complex and ever-changing processing requirements. In contrast, this invention utilizes knowledge graphs for process identification, enabling flexible adaptation to diverse process conditions and enhancing the system's flexibility and scalability. Furthermore, the process domain involved in this invention is at a deeper level, allowing for in-depth analysis of the correlation between geometric features and processing techniques, resulting in strong interpretability. This correlation not only expands the application scope but also improves the accuracy of process identification, ensuring superior processing results. Attached Figure Description

[0042] Figure 1 This is an overall flowchart of a process identification method based on model features provided in the first aspect embodiment of the present invention;

[0043] Figure 2 yes Figure 1 A schematic diagram of the node types in the process knowledge graph constructed by the process identification method shown;

[0044] Figure 3 This is a schematic diagram of a partial process knowledge graph generated using Neo4j Browser in a specific embodiment of the present invention;

[0045] Figure 4 In the middle (a) and (b), the topological relationship between the hole features and their constituent surfaces is shown respectively.

[0046] Figure 5 This is a schematic diagram illustrating the predefined processing feature attributes in an embodiment of the present invention;

[0047] Figure 6 This is a schematic diagram illustrating the determination of the topological relationships between processing features according to an embodiment of the present invention;

[0048] Figure 7 This is a schematic diagram illustrating the process selection route selection method used in an embodiment of the present invention;

[0049] Figure 8 This is a schematic diagram of the final process identification result obtained in an embodiment of the present invention;

[0050] Figure 9 This is a schematic diagram of the interactive software interface and its running effect designed based on the process identification method provided in the embodiments of the present invention.

[0051] Figure 10 This is a schematic diagram of the structure of an electronic device provided in a third aspect embodiment of the present invention. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this application clearer, the application will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely for explaining this application and are not intended to limit this application.

[0053] Conversely, this application covers any alternatives, modifications, equivalent methods, and schemes made within the spirit and scope of this application as defined by the claims. Furthermore, to provide the public with a better understanding of this application, certain specific details are described in detail below. However, this application can be fully understood by those skilled in the art even without these detailed descriptions.

[0054] See Figure 1 The first aspect of this invention provides a process identification method based on model features, comprising the following steps:

[0055] Step S1: Obtain process-related data, preprocess it, and obtain standardized process description text;

[0056] Step S2: Construct a process knowledge graph by extracting relation node triples from the process description text. The node types that constitute this process knowledge graph include: feature nodes, process nodes, equipment nodes, tool nodes, and fixture nodes. The relationships between two adjacent nodes include: available process, preceding process, available equipment, initial machining, equipped tool, and equipped fixture.

[0057] Step S3: Obtain the geometric model of the mechanical part to be processed, extract its geometric feature attributes and determine the feature topology relationship to obtain the machining features of the mechanical part model.

[0058] Step S4: Using a reverse search method, starting from the feature nodes corresponding to the machining features, select nodes that meet the machining requirements of the mechanical parts to be processed from the constructed process knowledge graph to obtain a complete process plan.

[0059] In some embodiments, the process-related data acquired in step S1 includes: part machining characteristics, material information, process requirements, equipment parameters, etc. Part machining characteristics include specific requirements such as the geometry, dimensional tolerances, and surface roughness of the mechanical part to be processed; this information directly affects the selection of the machining method. Material information involves the physical and chemical properties of the material used in the part, such as hardness, heat resistance, and ductility; different materials will impose different requirements on the setting of the machining process. Process requirements include the process route, machining steps, and operating conditions such as the tools used, ensuring that the part is manufactured efficiently while meeting design requirements. Equipment parameters refer to information related to the machining equipment, such as the type, specifications, and machining accuracy of the equipment. The accurate acquisition and analysis of this data is the foundation for constructing a process knowledge graph.

[0060] In some embodiments, in step S1, the acquired process-related data is divided into two categories: structured process data and unstructured process data, and different preprocessing methods are used for the two types of process data.

[0061] The preprocessing of structured process data includes: (1) data cleaning, removing redundancy, correcting errors, and filling in missing values ​​to ensure data integrity and accuracy; (2) standardizing data from different sources, unifying data formats from different sources, and converting categorical data into analyzable numerical forms; and (3) normalizing numerical data to eliminate the influence of different units of measurement. The preprocessed structured process data is directly stored in the form of triples for easy use in the subsequent construction of process knowledge graphs.

[0062] Preprocessing for unstructured process data specifically includes:

[0063] (1) Word segmentation: unstructured process statements or process descriptions are broken down into words or phrases. Since there are a lot of specific terms in the process field, the word segmentation results need to be adjusted in conjunction with the process field dictionary. For example, “high temperature treatment” is treated as a whole word instead of two separate words, “high temperature” and “treatment”. The process field dictionary is a collection of well-known words and terms in the process field.

[0064] (2) Part-of-speech tagging: The segmented text is tagged with part-of-speech tags to mark each word as a noun, verb or adjective, etc. Through part-of-speech tagging, the entity type corresponding to the node can be identified more accurately. For example, nouns are often material or equipment names, while verbs may be process steps.

[0065] (3) Regularization: In order to improve the consistency of entity recognition, the terminology in the process field must be regularized. For example, "aluminum alloy" should be unified as "aluminum alloy" to eliminate the differences in different word expressions (such as "aluminum" and "aluminum material"). In addition, it is also necessary to clean up noisy data in the text, such as symbols and useless stop words.

[0066] (4) Stop word filtering: Many words in the process description are irrelevant to entity recognition (such as "is", "of", "and", etc.). They can be removed by stop word filtering. The filtered text will be more concise and retain key information.

[0067] In some embodiments, in step S2, when extracting relation node triples from the process description text, for the preprocessed structured process data, the stored relation node triples are directly extracted. For the preprocessed unstructured process data, key information and relation nodes in the process description text are extracted through manual intervention and named entity recognition methods to form "entity-relationship-entity" triples. For example: "In the milling process, aluminum alloy parts are machined using high-speed steel tools, requiring a surface roughness Ra not exceeding 1.6." In such a process text, the identified entities include tools, materials, and processes; the relations include process methods and machining requirements; the final triples are ("aluminum alloy parts", "available processes", "milling") and ("milling", "machining requirements", "surface roughness Ra not exceeding 1.6"). Finally, the relation node triples formed from the processed data are organized and stored in a graph database to construct a process knowledge graph.

[0068] Further, see Figure 2 The process knowledge graph constructed in this embodiment mainly includes the following node types:

[0069] (1) Feature nodes: These represent the features of the mechanical parts to be processed, such as holes and planes. In the process knowledge graph, feature nodes are key elements; they define the geometry and processing requirements of the parts, ensuring the accuracy of process selection.

[0070] (2) Process node: Represents the optional process corresponding to the feature node. Each process node maintains two key attributes: machining accuracy IT and surface roughness Ra. These attributes help to evaluate the applicability of the process and provide a basis for process selection.

[0071] (3) Equipment node: Represents the available processing equipment that matches the process. Each equipment node maintains the relevant attributes of its own equipment, such as equipment type and applicable process, so as to ensure the matching of process and equipment.

[0072] (4) Tool node: Represents the available machining tools that match the equipment. Each tool node stores information such as the type, material, and diameter of the tool to support the implementation of the process.

[0073] (5) Fixture node: Represents the available fixtures that match the equipment. Each fixture node stores the characteristics and applicable range of the fixture to ensure the stability and safety of the workpiece during the processing.

[0074] The relationships between nodes in the process knowledge graph constructed in this embodiment include:

[0075] (1) Available process: indicates that a certain feature of the mechanical part to be processed can be processed by a certain process, ensuring the consistency between the process selection and the feature requirements;

[0076] (2) Preceding processes: Indicates the sequence of processes and clarifies the logical flow of processing steps;

[0077] (3) Available equipment: This indicates that the process can be carried out using a certain type of equipment, ensuring the compatibility between the equipment and the process;

[0078] (4) Initial processing: This indicates that the process is the first step in a certain characteristic processing route, which helps to determine the processing sequence;

[0079] (5) Equipped with cutting tools: This means that the equipment can be equipped with a certain type of cutting tool;

[0080] (6) Equipment fixture: This means that the equipment can be equipped with a certain fixture.

[0081] In one specific embodiment of the present invention, the relation node triples extracted from the standardized process description text are organized (partial results are shown in Tables 1-1 and 1-2), and stored in the Neo4j database. Using the Neo4j Browser, the node distribution and its relationships can be visualized, allowing users to intuitively understand the process route and the associations between nodes. The final process knowledge graph is shown below. Figure 3 .

[0082] Table 1-1 Relationship Node Triples

[0083]

[0084]

[0085] Table 1-2 Relationship Node Triples

[0086]

[0087] It is understandable that the process knowledge graph structure constructed in this embodiment has significant advantages. First, by meticulously defining feature nodes, process nodes, and equipment nodes, the accuracy of the nodes is improved, enabling them to accurately reflect the specific characteristics of the parts to be processed and related process information. Second, it comprehensively covers various relationships between nodes, deeply revealing the dependencies and sequences between processes, providing a more scientific basis for process selection. Users can intuitively understand the relationships between process routes and nodes, providing intelligent decision support and meeting the needs of modern manufacturing for efficient, flexible, and precise process management.

[0088] In some embodiments, the core of step S3 lies in how to accurately extract the corresponding machining features from the geometric model of the mechanical part to be processed. Although the application protocol STEP AP214 provides geometric information about the mechanical part model, such as the attributes and topological relationships of geometric features like surfaces and lines, these geometric features are not the same as machining features, which include planes, holes, fillets, etc. Figure 4 Taking the hole feature shown as an example, its components include plane F1 (the end plane of the part to be drilled) and plane F3 (the end plane of the hole), as well as cylindrical surface F2 (the diameter of which is the inner diameter of the hole). See [link to documentation]. Figure 4 In (a), topologically, cylindrical surface F2 is nested between planes F1 and F3, and the connectivity between the surfaces is as follows: Figure 4 As shown in (b), in terms of positional relationship, plane F3 is located inside plane F1. If plane F3 is located outside plane F1, then the geometric feature of the mechanical part to be processed is a boss. The attributes of machining features usually include dimensions, machining accuracy, and surface roughness. Although dimensions are closely related to geometric features, machining accuracy and surface roughness are attributes independent of geometric features, and therefore need to be predefined in the modeling stage of the mechanical part to be processed. The method used in this embodiment is to add solid attributes to each surface in the modeling stage, thereby defining the machining accuracy and surface roughness. Specifically, step S3 includes the following steps:

[0089] Step S31: Load the geometric model: Import the geometric model of the mechanical part to be processed through a supported file format, ensuring that the required geometric data is converted into a processable format;

[0090] Step S32: Extract geometric features: Extract all geometric features of the mechanical part to be processed from the loaded geometric model, including faces, edges, and vertices;

[0091] Step S33: Screening processing features: According to the processing requirements, classify the extracted geometric features and identify the geometric features that meet the machining requirements. For example, determine which features are holes, planes or other processing features to ensure that the key features that need to be processed are accurately found among many geometric shapes.

[0092] Step S34: Extracting Machining Feature Attributes: For the selected machining features, further extract their key attributes, including dimensions, accuracy, and surface roughness. Dimensions can be directly obtained from geometric features, while machining accuracy and surface roughness need to be predefined during the modeling stage. This is achieved by adding entity attributes to each surface in the geometric model, thereby defining machining accuracy and surface roughness. (See [link to relevant documentation]). Figure 5 ;

[0093] Step S35: Determination of Feature Topology and Arrangement of Processing Sequence: After extracting the types and attributes of each processing feature in the mechanical part model, it is necessary to determine the topology relationships between each processing feature in order to arrange the processing sequence of each processing feature. In this embodiment of the invention, all geometric features extracted in step S32 are used to detect adjacent processing features using normal vectors and boundary points to construct topology relationships. Using the unique identifier of the processing feature as a node and the connection relationship between adjacent processing features as an edge, the spatial position of the geometric features is used to analyze the dependencies between processing features and identify the processing sequence between adjacent processing features. For example, it determines which features are prerequisites to support the processing of other features. More specifically, in this embodiment, topology analysis is performed on the closed curves of processing features within a set common plane. If the closed curve of the second processing feature is completely located within the closed curve of the first processing feature, then the processing sequence of the first processing feature is superior to that of the second processing feature. Figure 6 Taking the feature set shown as an example, there are planar features and hole features, which coexist on geometric surface F1. On this surface, the closed curve L1 of the planar feature encloses the closed curve L2 of the hole feature. Therefore, the hole feature can be set as a child of the planar feature, meaning that in processing, the planar feature will be processed before the hole. For other cases, if the closed curves of two processing features are coplanar but only partially overlap, the processing feature corresponding to the overlapping area or the processing feature with greater depth in three-dimensional space will be processed first. This ensures the rationality of the processing order and avoids subsequent processing interference caused by improper processing order. If there is no overlap, it indicates that the first processing feature and the second processing feature are geometrically independent and there is no spatial interaction or conflict between them. The priority does not need to be judged by the overlap relationship of the closed curves and can be reasonably arranged according to the overall process flow.

[0094] Step S36: Output machining feature information: Organize the extracted machining features and their related attributes and topological relationships into structured information, that is, obtain the machining features of the mechanical part model to be processed, provide basic data for subsequent process analysis and decision-making, and ensure that suitable process solutions can be quickly responded to and recommended during the manufacturing process.

[0095] In some embodiments, the process selection algorithm in step S4 employs a reverse search approach, which helps improve the efficiency and accuracy of process selection, especially in complex process planning scenarios. The core reason is that machining processes often begin with the final machining requirements or product characteristics, with a clear final goal: the dimensional accuracy, surface roughness, etc., that the machining characteristics of the mechanical parts to be processed need to achieve. Achieving this goal may involve multiple machining paths and processes. Therefore, the reverse search proceeds backward from the feature nodes, gradually searching for corresponding process nodes and filtering each process method that meets the machining requirements. This method effectively avoids the "path blind spot" problem in forward search, preventing the waste of significant computational resources and reducing the exploration of unnecessary process steps. Simultaneously, by using path backtracking, it also helps operators intuitively understand the rationality of each process, providing a basis for subsequent process optimization.

[0096] To better illustrate the central idea of ​​the algorithm, see [link to algorithm]. Figure 7 First, the target feature node (e.g., "hole") is entered into the process knowledge graph. Through the "available processes" relationship, the corresponding process nodes are found sequentially, such as "hand reaming," "hole boring," "hole enlargement," and "hole drilling." During this process, it is determined whether each process node meets the processing requirements. If it does not meet the requirements, the search for the current path ends directly. If it does meet the requirements, the search proceeds to the next step based on the "preceding processes" relationship. When a process node is found with an "initial processing" relationship, the process method corresponding to that node is determined to be the final process step. By using the target feature node (the end node on the current path according to the processing sequence) and the initial node (the final process step), the path between the two can be effectively found, thus forming a complete processing flow, such as... Figure 7 A complete machining path is formed by the dark, thick arrowhead. The final formatted output, containing all process schemes that meet the machining requirements, serves as the process identification result. See [link / reference]. Figure 8 .

[0097] See Figure 9 This is a schematic diagram of the interactive software interface and its operation effect designed based on the process identification method provided in this invention. The mechanical part to be processed is a box, and the system realizes intelligent process scheme selection and output based on the part's features. First, the geometric model of the part to be processed is loaded, and its geometric feature information is extracted. These geometric features are used as input and entered into the process knowledge graph for feature node matching. Taking the "hole" feature as an example, the user selects the feature of the part model to be processed. Using the idea of ​​a reverse search algorithm, starting from the "hole" feature node, the system sequentially searches for process methods that match this feature, filtering out all process schemes that meet the processing conditions. Finally, a visual output is provided, displaying each process step and its corresponding processing conditions, providing operators with an intuitive reference for process selection.

[0098] A second aspect of the present invention provides a process identification device based on model features, comprising:

[0099] The first module stores standardized process description text, which is obtained by preprocessing the acquired process-related data.

[0100] The second module is used to construct a process knowledge graph by extracting relation node triples from the process description text. The node types constituting the process knowledge graph include: feature nodes, process nodes, equipment nodes, tool nodes, and fixture nodes. The relationships between two adjacent nodes include: "available process", "preceding process", "available equipment", "initial processing", "equipped tool", and "equipped fixture".

[0101] The third module is used to obtain the geometric model of the mechanical part to be processed, extract its geometric feature attributes and determine the feature topology relationship to obtain the machining features of the mechanical part model.

[0102] The fourth module is used to start from the feature nodes corresponding to the machining features using a reverse search method, and select nodes that meet the machining requirements of the mechanical parts to be processed from the process knowledge graph to obtain a complete process plan.

[0103] It should be noted that the foregoing explanation of the embodiments of the process identification method also applies to the process identification device of this embodiment, and will not be repeated here.

[0104] To implement the above embodiments, this invention also proposes a computer-readable storage medium storing a computer program thereon, which is executed by a processor to perform the process identification method of the above embodiments.

[0105] The following is for reference. Figure 10 The diagram illustrates a structural schematic of an electronic device suitable for implementing embodiments of the present invention. It should be noted that the electronic device in the embodiments of the present invention may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs, desktop computers, and servers. Figure 10 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0106] like Figure 10As shown, the electronic device may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 102 or a program loaded from a storage device 108 into a random access memory (RAM) 103. The RAM 103 also stores various programs and data required for the operation of the electronic device. The processing unit 101, ROM 102, and RAM 103 are interconnected via a bus 104. An input / output (I / O) interface 105 is also connected to the bus 104.

[0107] Typically, the following devices can be connected to I / O interface 105: input devices 106 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, etc.; output devices 107 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 108 including, for example, magnetic tapes, hard disks, etc.; and communication devices 109. Communication device 109 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 10 The electronic device is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0108] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, this embodiment includes a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device 109, or installed from a storage device 108, or installed from a ROM 102. When the computer program is executed by the processing device 101, it performs the functions defined in the methods of the embodiments of the present invention.

[0109] It should be noted that the computer-readable medium described above in this invention can be a computer-readable signal medium, a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0110] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0111] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the aforementioned process identification method.

[0112] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, C++, and Python—as well as conventional procedural programming languages—such as the "C-" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0113] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0114] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0115] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the function involved, as will be understood by those skilled in the art to which embodiments of this application pertain.

[0116] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0117] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0118] Those skilled in the art will understand that implementing all or part of the steps of the methods in the above embodiments can be accomplished by instructing related hardware through a program. The developed program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0119] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0120] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A process identification method based on model features, characterized in that, include: Acquire process-related data, preprocess it, and obtain standardized process description text; A process knowledge graph is constructed by extracting relation node triples from the process description text. The node types constituting the process knowledge graph include: feature nodes, process nodes, equipment nodes, tool nodes, and fixture nodes. The relationships between two adjacent nodes include: "available process", "preceding process", "available equipment", "initial processing", "equipped tool", and "equipped fixture". Obtain the geometric model of the mechanical part to be processed, extract its geometric feature attributes and determine the feature topology relationship to obtain the machining features of the mechanical part model; A reverse search method is used to start from the feature nodes corresponding to the machining features and select nodes that meet the machining requirements of the mechanical parts to be processed from the process knowledge graph to obtain a complete process plan. The machining features of the model of the mechanical part to be processed are obtained according to the following steps: Step S31: Import the geometric model of the mechanical part to be processed into a supported file format to ensure that the required geometric data is converted into a processable format; Step S32: Extract all geometric features of the mechanical part to be processed from the geometric model, add solid attributes to each surface in the geometric model, and predefine the processing accuracy and surface roughness; Step S33: According to the processing requirements, classify the extracted geometric features and identify the geometric features that meet the machining requirements as processing features; Step S34: Extract the key attributes of the processing features, including dimensions, accuracy, and surface roughness; Step S35: Detect adjacent features using normal vectors and boundary points for all extracted geometric features, construct topological relationships, use the unique identifier of the processing feature as a node, the connection relationship between adjacent processing features as an edge, and use the spatial location of the geometric features to analyze the dependency relationship between processing features and identify the processing order between adjacent processing features. Step S36: Organize the extracted processing features and their related attributes and topological relationships into structured information to obtain the machining features of the mechanical part model to be processed; In step S35, the specific steps for identifying the processing order between adjacent processing features include: Assuming the first and second processing features lie in a defined common plane, a topological analysis is performed on their closed curves: If the closed curve of the second processing feature is completely within the closed curve of the first processing feature, then the processing order of the first processing feature is superior to that of the second processing feature; if the closed curves of the first and second processing features only partially overlap, then the processing feature corresponding to the overlapping area or the processing feature with greater depth in three-dimensional space is processed first; if the closed curves of the first and second processing features do not overlap, it indicates that the first and second processing features are geometrically independent, and their processing order is arranged according to the overall process flow.

2. The process identification method according to claim 1, characterized in that, The process-related data includes part machining characteristics, material information, process requirements, and equipment parameters; the part machining characteristics include specific requirements for the geometry, dimensional tolerances, and surface roughness of the mechanical part to be processed; the material information involves the physical and chemical properties of the materials used in the part; the process requirements include the operating conditions during the processing, including the process route, processing steps, and cutting tools used; the equipment parameters include the type, specifications, and machining accuracy of the equipment.

3. The process identification method according to claim 1, characterized in that, The process-related data is divided into two categories: structured process data and unstructured process data. The preprocessing of structured process data includes: data cleaning, removing redundancy, correcting errors, and filling in missing values ​​to ensure data integrity and accuracy; standardization of data from different sources, unifying data formats from different sources, and converting categorical data into analyzable numerical forms; and normalization of numerical data to eliminate the influence of different units of measurement. The preprocessing for unstructured process data includes, in order: word segmentation, part-of-speech tagging, regularization, and stop word filtering.

4. The process identification method according to claim 1, characterized in that, In the process knowledge graph, the feature nodes represent the features of the mechanical parts to be processed; The process node represents an optional process corresponding to the feature node, and the attributes maintained within each process node include machining accuracy and surface roughness; the equipment node represents an available machining equipment that matches the process, and each equipment node maintains the relevant attributes of its own equipment; the tool node represents an available machining tool that matches the equipment, and each tool node stores the relevant attributes of its own tool; the fixture node represents an available fixture that matches the equipment, and each fixture node stores the characteristics and applicable scope of its own fixture. The term "available process" indicates that a certain feature of the mechanical part to be processed can be processed using a certain process; the term "preceding process" indicates the sequence of processes; the term "available equipment" indicates that a certain process can be processed using a certain equipment; the term "initial processing" indicates that a certain process is the first step in the processing route of a certain feature; the term "equipped with cutting tools" indicates that a certain equipment can be equipped with a certain cutting tool; and the term "equipped with fixtures" indicates that a certain equipment can be equipped with a certain fixture.

5. The process identification method according to claim 1, characterized in that, The method of reverse search starts from the feature nodes corresponding to the machining features, and selects nodes that meet the machining requirements of the mechanical parts to be processed from the process knowledge graph to obtain a complete process plan, specifically including: The process knowledge graph is entered from the target feature node. The corresponding process nodes are found sequentially through the "available process" relationship. During this process, it is determined whether each process node meets the processing requirements. If it does not meet the requirements, the search of the current path ends directly. If it meets the requirements, the search proceeds to the next step according to the "preceding process" relationship. When the found process node has an "initial processing" relationship, the process method corresponding to the obtained node is determined to be the last process step. The path between the target feature node and the initial node corresponding to the last process step is found, thus forming a complete process solution.

6. An apparatus based on the process identification method according to any one of claims 1 to 5, characterized in that, include: The first module stores standardized process description text, which is obtained by preprocessing the acquired process-related data. The second module is used to construct a process knowledge graph by extracting relation node triples from the process description text. The node types constituting the process knowledge graph include: feature nodes, process nodes, equipment nodes, tool nodes, and fixture nodes. The relationships between two adjacent nodes include: "available process", "preceding process", "available equipment", "initial processing", "equipped tool", and "equipped fixture". The third module is used to obtain the geometric model of the mechanical part to be processed, extract its geometric feature attributes and determine the feature topology relationship to obtain the machining features of the mechanical part model. The fourth module is used to start from the feature nodes corresponding to the machining features using a reverse search method, and select nodes that meet the machining requirements of the mechanical parts to be processed from the process knowledge graph to obtain a complete process plan.

7. An electronic device, characterized in that, include: At least one processor, and a memory communicatively connected to said at least one processor; The memory stores instructions executable by the at least one processor, the instructions being configured to perform the process identification method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the process identification method according to any one of claims 1 to 5.

Images