A process simulation method and related equipment for machining training

Abstract

A simulation method and related equipment for machining process training are disclosed. The method includes: acquiring engineering data and process data of the target workpiece; extracting features from the engineering data and combining them with the process data to construct a case resource library; performing semantic association analysis between the pre-set knowledge resource library and the machining cases in the case resource library to generate a process knowledge network; constructing a virtual training environment based on the process knowledge network; collecting interaction data of learners in the virtual training environment and evaluating the interaction data to obtain evaluation results; and generating guidance animations based on the evaluation results and the process knowledge network. This application can improve the learning efficiency of simulation training.

Description

Technical Field

[0001] This application relates to the field of practical training and simulation, specifically to a process training and simulation method for mechanical processing and related equipment. Background Technology

[0002] With the transformation and upgrading of the manufacturing industry and the rapid development of intelligent manufacturing technology, higher demands are being placed on the cultivation of skilled personnel. As a crucial link in engineering education that combines theory and practice, the quality of process training directly impacts the effectiveness of talent cultivation. Currently, virtual simulation technology is widely used in process training, simulating actual production processes by constructing virtual environments.

[0003] In related technologies, learners can conduct practical training simulations in process training simulation systems. However, these simulations often only involve a single knowledge point related to workpiece processing, failing to establish an organic connection with other knowledge points related to the workpiece (such as related interdisciplinary knowledge points). This simulation method makes it difficult for learners to build a complete knowledge cognitive system, affecting the learning efficiency of simulation training. Summary of the Invention

[0004] This application provides a process simulation method and related equipment for machining, which can improve the learning efficiency of simulation training.

[0005] The first aspect of this application provides a process simulation method for machining, applied in a server, the method comprising:

[0006] Acquire engineering and process data of the target workpiece; extract features from the engineering data and combine them with the process data to construct a case resource library; perform semantic association analysis between the pre-set knowledge resource library and the processing cases in the case resource library to generate a process knowledge network; construct a virtual training environment based on the process knowledge network; collect interactive data of learners in the virtual training environment and evaluate the interactive data to obtain evaluation results; generate guidance animations based on the evaluation results and the process knowledge network.

[0007] Optionally, feature extraction can be performed on the engineering data, and combined with process data, to construct a case resource library, specifically including:

[0008] Extract workpiece feature data from engineering data, and combine it with processing steps and process parameters from process data to establish a feature-process correlation model. Based on the feature-process correlation model, divide the workpiece into feature regions to obtain multiple target feature regions, and extract the target process parameters for each target feature region to obtain a target process parameter set. According to the target process parameters, segment the process demonstration video in the process data to obtain process video segments for each target feature region. Construct a case resource library based on the feature-process correlation model, the target process parameter set, and the process video segments.

[0009] Optionally, a case resource library can be constructed based on the feature-process correlation model, the target process parameter set, and process video clips, specifically including:

[0010] Establish the correspondence between target process parameters and process video clips to generate a feature-process-demonstration association matrix; calculate the similarity between multiple target process parameters in the target process parameter set to obtain a process parameter similarity matrix; combine target feature regions, target process parameters, and process video clips to form processing cases; classify processing cases based on the feature-process-demonstration association matrix and the process parameter similarity matrix to construct a case knowledge base.

[0011] Optionally, semantic association analysis is performed on the processing cases in the preset knowledge resource base and the case resource base to generate a process knowledge network, specifically including:

[0012] Extract theoretical knowledge elements from the pre-set knowledge resource base; extract process knowledge elements from each processing case in the case resource base; based on pre-set knowledge association rules, associate theoretical knowledge elements with process knowledge elements to obtain a knowledge association matrix; based on the knowledge association matrix, determine the knowledge dependency of process knowledge elements on theoretical knowledge elements; construct a process knowledge network based on theoretical knowledge elements, process knowledge elements, and knowledge dependency.

[0013] Optionally, a virtual training environment can be constructed based on the process knowledge network, specifically including:

[0014] Extract target theoretical knowledge elements from the process knowledge network. Target theoretical knowledge elements are those with a knowledge dependency greater than a preset threshold. Determine the process training task sequence for the target workpiece based on the target theoretical knowledge elements and process knowledge elements. Construct a virtual process operation sequence based on the process training task sequence to obtain the virtual training environment for the target workpiece.

[0015] Optionally, a virtual process operation sequence is constructed based on the process training task sequence to obtain a virtual training environment for the target workpiece, specifically including:

[0016] The process training task sequence is decomposed into multiple process operation units, and execution constraints are set for each process operation unit based on the target theoretical knowledge elements. According to the execution constraints, a virtual workpiece processing state transition model of the target workpiece is constructed, and a detection threshold is set for each processing state in the virtual workpiece processing state transition model. Based on the processing state transition model, virtual simulation modeling is performed on the process operation units to obtain a virtual process operation sequence. The virtual process operation sequence is time-aligned with the process video clips to obtain a virtual training environment.

[0017] Optionally, guiding animations can be generated based on the evaluation results and the process knowledge network, specifically including:

[0018] Based on the operational deviations in the evaluation results, deviation theoretical knowledge elements and deviation process knowledge elements are extracted from the process knowledge network. Based on the deviation theoretical knowledge elements and deviation process knowledge elements, and combined with the process demonstration video in the process data, a correction strategy is generated. According to the correction strategy, a target demonstration case is selected from the case resource library, and the target process parameters of the target demonstration case are extracted. Based on the target demonstration case and the target process parameters, a guidance animation is generated.

[0019] A second aspect of this application provides a process simulation system for machining, comprising:

[0020] The acquisition module is used to acquire the engineering data and process data of the target workpiece;

[0021] The first construction module is used to extract features from engineering data and combine them with process data to build a case resource library;

[0022] The analysis module is used to perform semantic association analysis on the processing cases in the preset knowledge resource base and the case resource base to generate a process knowledge network;

[0023] The second construction module is used to build a virtual training environment based on the process knowledge network;

[0024] The evaluation module is used to collect learners' interaction data in the virtual training environment, evaluate the interaction data, and obtain evaluation results.

[0025] The generation module is used to generate guiding animations based on evaluation results and process knowledge networks.

[0026] A third aspect of this application provides an electronic device including a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described above.

[0027] In a fourth aspect, this application provides a computer-readable storage medium storing instructions that, when executed, perform the method described in any of the foregoing descriptions.

[0028] In summary, one or more technical solutions provided in this application have at least the following technical effects or advantages:

[0029] 1. By acquiring engineering and process data of workpieces and extracting features to construct a case resource library, the limitations of traditional simulations, which are limited to single knowledge points, are overcome. Semantic association analysis between the pre-set knowledge resource library and the case resource library generates a process knowledge network, achieving organic association of interdisciplinary knowledge. Based on this, a virtual training environment is constructed using a multi-dimensional process knowledge network, forming a complete knowledge cognition framework. By collecting learner interaction data for evaluation and generating targeted guidance animations, the technical problems of fragmented knowledge points and incomplete cognitive systems in traditional training systems are solved. This semantic association-based knowledge network construction mechanism enables the system to improve the learning efficiency of simulation training through intelligent association of interdisciplinary knowledge and collaborative presentation of multi-dimensional knowledge.

[0030] 2. By extracting workpiece feature data and combining it with processing steps and process parameters to establish a feature-process association model, a basic framework for process knowledge mapping was constructed. By partitioning the workpiece based on the association model and extracting target process parameters, a refined division of process knowledge was achieved. Based on this, process demonstration videos were segmented according to the target process parameters, forming video resources that precisely correspond to the feature regions. Finally, a case resource library was constructed by comprehensively building the association model, parameter set, and video segments, thus solving the technical problems of loose process knowledge structure and low feature correlation in traditional case libraries. This refined case construction mechanism based on feature partitioning enables the system to improve the structuring level of case resources and achieve precise location and rapid retrieval of process knowledge through accurate mapping and partition management of workpiece features and process knowledge.

[0031] 3. By extracting theoretical knowledge elements from a pre-defined knowledge resource base and process knowledge elements from a case resource base, a two-way foundation for knowledge association was established. A knowledge association matrix was obtained by associating elements based on pre-defined knowledge association rules, realizing a systematic mapping between theoretical and practical knowledge. On this basis, a quantitative evaluation mechanism for knowledge association was formed by determining the dependence of process knowledge elements on theoretical knowledge elements. Finally, a process knowledge network was constructed based on theoretical elements, process elements, and knowledge dependencies, thus solving the technical problem of the disconnect between theory and practice and the difficulty in quantifying the degree of association in traditional knowledge systems. This network construction mechanism based on knowledge dependencies enables the system to improve the integrity and relevance of the knowledge system through quantitative association and system integration of theoretical and practical knowledge.

[0032] 4. By decomposing the process training task sequence into process operation units and setting execution constraints, a refined control foundation for the training process was established. A dynamic monitoring mechanism for the processing status was realized by constructing a virtual workpiece processing state transition model and setting detection thresholds. Based on this, a virtual process operation sequence was obtained by virtual simulation modeling of the process operation units, forming a standardized operation process system. Finally, a virtual training environment was constructed by aligning the virtual operation sequence with the process video, thus solving the technical problem of lacking precise constraints and status monitoring in traditional virtual training. This virtual training construction mechanism based on state transitions enables the system to improve the standardization and controllability of training simulation through precise control of operation units and real-time monitoring of processing status. Attached Figure Description

[0033] Figure 1 This is a flowchart illustrating a process simulation method for machining in an embodiment of this application.

[0034] Figure 2 This is another flowchart illustrating a machining process training simulation method in the embodiments of this application;

[0035] Figure 3 This is a schematic diagram of the structure of a machining process training simulation system according to an embodiment of this application;

[0036] Figure 4 This is a schematic diagram of the structure of the electronic device in the embodiments of this application.

[0037] Explanation of reference numerals in the attached figures: 301, Acquisition module; 302, First construction module; 303, Analysis module; 304, Second construction module; 305, Evaluation module; 306, Generation module; 401, Processor; 402, Communication bus; 403, User interface; 404, Network interface; 405, Memory. Detailed Implementation

[0038] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0039] In the description of the embodiments of this application, the words "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design that is described as "for example" or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design options. Rather, the use of the words "for example" or "for instance" is intended to present the relevant concepts in a specific manner.

[0040] In the description of the embodiments of this application, the term "multiple" means two or more. For example, multiple systems means two or more systems, and multiple screen terminals means two or more screen terminals. 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 indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0041] Figure 1 This is a flowchart illustrating a process simulation method for machining in an embodiment of this application.

[0042] Please see Figure 1 This application provides a process simulation method for machining, applied in a server. The method includes:

[0043] S101. Obtain the engineering data and process data of the target workpiece;

[0044] In mechanical processing simulation training, the first step is to acquire the engineering and process data of the target workpiece to ensure that the subsequent simulation accurately reflects the actual machining process. Engineering data typically includes the workpiece's 3D model, dimensions, material properties, and tolerance requirements, while process data covers key information such as machining steps, process parameters (e.g., cutting speed, feed rate, spindle speed), tool selection, fixture design, and machining sequence. For example, in simulation training for CNC milling of a part, engineering data might include the part's CAD model, material information (e.g., aluminum alloy or stainless steel), and dimensional accuracy requirements, while process data might involve cutting parameters for roughing and finishing, the type of tool used (e.g., end mill or ball end mill), and clamping scheme. This data can come from CAD / CAM software, CNC programs, or actual production process documents and is entered into the system via data interfaces or file import.

[0045] S102. Extract features from engineering data and combine them with process data to build a case resource library;

[0046] After acquiring the engineering and process data of the target workpiece, in-depth analysis of the engineering data is required to extract key features of the workpiece. A case resource library is then established in conjunction with the process data to support subsequent simulation training. This process mainly includes workpiece feature extraction, feature-process correlation analysis, segmented processing of process demonstration videos, and the construction of the case resource library.

[0047] In one possible implementation, refer to Figure 2 , Figure 2 This is another flowchart illustrating a machining process training simulation method according to an embodiment of this application. Extracting features from engineering data and combining it with process data to construct a case resource library may include steps S201 to S204:

[0048] S201. Extract workpiece feature data from engineering data, and combine it with processing steps and process parameters from process data to establish a feature-process correlation model.

[0049] In step S201, feature extraction is required for the engineering data of the target workpiece, and a feature-process correlation model is established by combining the processing steps and process parameters in the process data, so as to provide data support for subsequent process analysis, case resource library construction and virtual simulation.

[0050] Specifically, the system analyzes the workpiece's engineering data, such as CAD models, dimensional information, and material properties, and extracts the workpiece's feature data. Workpiece feature data typically includes the workpiece's geometry (such as planes, cylindrical surfaces, holes, slots, chamfers, threads, etc.), topological relationships (such as adjacent faces, intersecting boundaries), dimensional information (such as diameter, depth, and length), and surface roughness requirements. For example, in a part containing threaded holes and countersunk holes, the system can identify key features such as the diameter, depth, and pitch of the threaded holes, and distinguish the shape and size of the countersunk holes.

[0051] Based on the extracted workpiece features, the system further integrates process data, namely the operations and process parameters involved in the machining process. This process data typically includes machining methods (such as turning, milling, drilling, tapping, etc.), tool types (such as end mills, ball end mills, drills), cutting parameters (such as spindle speed, feed rate, depth of cut), fixture scheme, and machining sequence. For example, for the aforementioned threaded hole, the system will match the corresponding machining operation (such as drilling before tapping) and associate it with process parameters such as drill diameter, drilling speed, feed rate for drilling, and tapping speed and lubrication method for tapping.

[0052] Based on the above analysis, the system establishes a feature-process association model, which matches the geometric features of the workpiece with the corresponding machining operations and process parameters to form a structured knowledge association. For example, this model can describe the process chain of "a threaded hole with a diameter of 10mm and a depth of 20mm → drilling (10mm diameter drill bit, 1200rpm rotation speed, 0.1mm / rev) → tapping (M10 tapping tool, 600rpm rotation speed, lubrication and cooling)". This model not only supports intelligent matching of machining cases but also provides data support for subsequent feature partitioning, process parameter extraction, and process video segmentation.

[0053] S202. Based on the feature-process correlation model, the workpiece is partitioned into multiple target feature regions, and the target process parameters of each target feature region are extracted to obtain the target process parameter set.

[0054] After establishing the feature-process correlation model, the system needs to further partition the workpiece into feature regions. That is, based on the geometric features of the workpiece and its corresponding processing technology, the workpiece is divided into multiple target feature regions, and the corresponding target process parameters of each target feature region are extracted to obtain the target process parameter set, which lays the foundation for subsequent process knowledge analysis, video segmentation processing and case resource library construction.

[0055] Specifically, the system first analyzes the geometric features of the workpiece and divides it into several target feature regions according to different machining processes. For example, in a part containing threaded holes, countersunk holes, stepped surfaces, and grooves, the system will divide "threaded holes" into one feature region because it involves drilling and tapping processes; "countersunk holes" into another feature region because it involves drilling and countersunk machining; "stepped surfaces" may involve milling and are also divided into a separate feature region; while "grooves" may require end milling and are therefore classified separately.

[0056] After completing the feature partitioning, the system further extracts the target process parameters for each target feature region. These parameters typically include: machining methods (such as drilling, milling, turning, tapping, etc.), tool type and specifications (such as Φ10mm twist drill, M10 tapping cutter, Φ6mm flat end mill, etc.), cutting parameters (such as cutting speed, feed rate, spindle speed, depth of cut, etc.), machining sequence (such as drilling before tapping, roughing before finishing, etc.), and fixture scheme and positioning method (such as workpiece clamping method, fixture type, machining datum, etc.). For example, for a threaded hole with a diameter of 10mm and a depth of 20mm, the target process parameters might include:

[0057] Processing method: Drill holes first, then tap;

[0058] Tool selection: Φ10mm twist drill, M10 tapping tool;

[0059] Cutting parameters (drilling): Drilling speed 1200 rpm, feed rate 0.1 mm / rev;

[0060] Cutting parameters (tapping): Tapping speed 600 rpm, lubrication and cooling method is emulsion spray;

[0061] Processing sequence: Drill holes first, then chamfer, and finally tap.

[0062] Fixture solution: V-block clamping is used, and a center drill is used for positioning during drilling.

[0063] The extraction of these target process parameters helps to standardize the processing and provides a basis for segmenting subsequent process demonstration videos, enabling learners to obtain corresponding process guidance information for different target feature areas in virtual simulation training.

[0064] S203. Based on the target process parameters, the process demonstration video in the process data is segmented to obtain a process video segment for each target feature region.

[0065] After completing the feature partitioning of the target workpiece and the extraction of the target process parameters, in order to enhance learners' understanding and operational experience, the system needs to segment the existing process demonstration videos so that each target feature area can correspond to a corresponding process operation video segment, thereby providing accurate multimedia teaching support in virtual simulation training.

[0066] Specifically, process demonstration videos typically include the complete workpiece machining process, such as all steps from raw material to final product. However, in practical teaching applications, learners often need to focus on learning specific machining features (such as drilling, tapping, milling specific areas, etc.). Therefore, the system intelligently segments these demonstration videos based on the target process parameters extracted in the previous step, allowing the machining process of each feature area to be displayed independently.

[0067] For example, for a part containing threaded holes, countersunk holes, stepped surfaces, and grooves, a process demonstration video might include the following complete machining process: drilling threaded holes, tapping, drilling countersunk holes, milling stepped surfaces, milling grooves, and deburring and surface treatment. The system will segment the video based on target process parameters (such as tool selection, machining method, and machining sequence), so that each machining feature corresponds to an independent video segment. For example, a process demonstration video usually contains the complete part machining process, but in order to accurately match different machining features, the system needs to segment the video according to the target process parameters, so that it can provide independent process guidance content for different machining feature areas. The system's segmentation criteria mainly include the following aspects:

[0068] Tool selection: Different machining features typically require different tools. For example, drills and taps are used to drill threaded holes, while end mills are used to mill stepped surfaces. Therefore, the system can identify the start and end points of video clips based on the tool type specified in the process parameters.

[0069] Machining methods: Different machining methods (such as drilling, tapping, milling, turning, etc.) correspond to different operation processes. The system can automatically segment different machining methods into independent video segments based on information such as the tool movement pattern and workpiece change characteristics in the video.

[0070] Processing sequence: In actual processing, the processing sequence is crucial. For example, when machining threaded holes, drilling is usually performed first, followed by chamfering, and finally tapping. Therefore, the system will split the video according to the processing sequence to ensure that each segment contains only content related to the current feature.

[0071] Suppose there is a complete machining demonstration video showing the entire machining process of a part from raw material to finished product, including the following steps: drilling threaded holes, tapping, drilling countersunk holes, milling stepped surfaces, milling grooves, and deburring and surface treatment. After partitioning the workpiece into features, the system has identified different feature areas (such as threaded holes, countersunk holes, stepped surfaces, etc.) and extracted the corresponding target process parameters. Next, the system will use these parameters to segment the video:

[0072] Related segments on threaded hole machining:

[0073] Segment 1: Drilling threaded holes (the system recognizes the tool as a drill bit and matches the drilling process).

[0074] Segment 2: Tapping (The system recognizes the tapping tool and matches the tapping process).

[0075] Related segments on countersunk hole machining:

[0076] Segment 3: Drilling countersunk holes (the system recognizes the countersunk drill and matches the countersunk hole process).

[0077] Relevant excerpts about step surface processing:

[0078] Segment 4: Milling the stepped surface (the system recognizes the end mill and matches the milling process).

[0079] Related excerpts on trenching:

[0080] Segment 5: Milling grooves (the system identifies a T-cut or end mill and matches the groove milling process).

[0081] To ensure the accuracy of segmentation, the system optimizes the segmented videos. The system analyzes key frames in the video, such as the moment the tool contacts the workpiece, the start and end of cutting, to ensure segmentation precision. Subtitles related to the target process parameters are embedded in the segmented videos, such as "Currently drilling with a Φ10mm drill bit, rotation speed 1200rpm, feed rate 0.1mm / rev," to help learners understand key process information. Simultaneously, the system can also precisely associate video clips with corresponding machining feature areas of the 3D workpiece model through visual analysis and timeline matching technology. For example, when playing a video on "threaded hole tapping," the system highlights the location of the threaded hole on the virtual workpiece.

[0082] After the above processing, the system finally generates a series of independent process video clips, each of which is matched with the corresponding target feature region and target process parameters.

[0083] S204. Construct a case resource library based on the feature-process correlation model, the target process parameter set, and process video clips.

[0084] Specifically, the correspondence between target process parameters and process video clips is established to generate a feature-process-demonstration association matrix; the similarity between multiple target process parameters in the target process parameter set is calculated to obtain a process parameter similarity matrix; the target feature regions, target process parameters, and process video clips are combined to form processing cases; based on the feature-process-demonstration association matrix and the process parameter similarity matrix, the processing cases are classified to construct a case knowledge base.

[0085] After segmenting the process demonstration videos, the system needs to establish a correspondence between target process parameters and video segments to ensure that each machining feature area is associated with the corresponding process demonstration content. To this end, the system constructs a feature-process-demonstration association matrix. Each row of the matrix represents a target feature area, each column represents a corresponding video segment, and the elements in the matrix indicate the strength or degree of association between the feature area and the video. For example, in a part containing "threaded hole," "countersunk hole," "stepped surface," and "groove," the system will establish a strong association between "threaded hole" and the video segments "drilling" and "tapping," while "stepped surface" will primarily be associated with the "milling" video segment. Furthermore, the system can assign different weights based on the importance of process parameters, ensuring that core process steps are prioritized for display in subsequent case recommendations and learning processes.

[0086] During machining, different target feature regions may have similar machining processes. For example, threaded holes of different sizes may use the same drilling-tapping process, and grooves of different depths may use similar milling strategies. To identify these similarities, the system calculates the similarity between target process parameters and generates a process parameter similarity matrix. Each row and column of the process parameter similarity matrix represents a target process parameter, and the elements in the matrix represent the degree of similarity between two parameters, which can be calculated using Euclidean distance, cosine similarity, or process rule-based matching algorithms. For example, if two threaded holes differ in diameter by only 1 mm and have the same tapping speed and tool type, their similarity score is high; while if one feature involves turning and the other involves milling, their similarity is low.

[0087] In building the case resource library, the system needs to integrate target feature regions, target process parameters, and process video clips to form complete machining cases. Each machining case represents a specific process operation step and includes detailed process information, such as: workpiece geometry, selected machining method, process parameters (tool type, spindle speed, feed rate, etc.), and corresponding process demonstration video. For example, a typical machining case might describe "machining M10 threaded holes on an aluminum alloy workpiece," and its content includes:

[0088] Target feature area: M10 threaded hole (10mm in diameter, 20mm in depth).

[0089] Target process parameters: Drilling: twist drill Φ10mm, rotation speed 1200rpm, feed rate 0.1mm / rev;

[0090] Tapping: M10 tapping tool, 600rpm speed, emulsion spray cooling method;

[0091] Related process video clips: "Drilling" video clip (demonstrating the drilling process); "Tapping" video clip (demonstrating the tapping process). Through this combination, each case study provides learners with complete machining knowledge.

[0092] S103. Perform semantic association analysis on the processing cases in the preset knowledge resource base and the case resource base to generate a process knowledge network;

[0093] Specifically, theoretical knowledge elements are extracted from the pre-set knowledge resource base; process knowledge elements are extracted from each processing case in the case resource base; theoretical knowledge elements and process knowledge elements are associated based on pre-set knowledge association rules to obtain a knowledge association matrix; based on the knowledge association matrix, the knowledge dependence of process knowledge elements on theoretical knowledge elements is determined; and a process knowledge network is constructed based on theoretical knowledge elements, process knowledge elements, and knowledge dependence.

[0094] In step S103, theoretical knowledge elements are first extracted from a pre-set knowledge resource base, covering core knowledge points from multiple disciplines. This pre-set knowledge resource base not only includes content related to machining (such as metal cutting principles, tool materials, and machining methods), but also integrates interdisciplinary knowledge such as materials science (such as metal mechanical properties and heat treatment technology), automation control (such as CNC programming and machining error compensation), and intelligent manufacturing (such as digital twins and process optimization algorithms). For example, when learning about the process of "high-speed milling," students not only need to understand the milling principles, but also need to master related theories such as "the heat resistance of tool materials," "rigidity control of the spindle system," and "the influence of cutting fluid on tool life," thus forming a complete cognitive system.

[0095] After extracting the theoretical knowledge elements, the system also needs to extract the process knowledge elements from the case resource library, which are the knowledge points related to specific machining operations, process parameters, and machining equipment. Each machining case typically includes information such as workpiece characteristics, machining methods, tool selection, cutting parameters, and machining sequence. These are all important components of process knowledge. For example, for the case of "machining M10 threaded holes," the system will extract the relevant process knowledge elements, such as "tool selection for drilling threaded bottom holes," "lubrication methods during tapping," and "thread dimensional accuracy control."

[0096] To further break down knowledge barriers between disciplines, the system uses knowledge association rules to link theoretical knowledge elements with technological knowledge elements, forming a knowledge association matrix. The purpose of this matrix is ​​to establish mapping relationships between interdisciplinary knowledge points, enabling students to automatically connect the learning of specific technological knowledge to relevant foundational theories. The pre-defined knowledge association rules are developed by industry experts and utilize big data analysis and machine learning techniques to determine which theoretical knowledge directly impacts specific technological knowledge. For example, when learning about "high-speed milling of aluminum alloys," the technological knowledge elements involved include: tool material selection, cutting parameter optimization, machining stability control, and coolant usage strategies. The system will automatically match the theoretical knowledge upon which this technological knowledge depends based on, according to the knowledge association rules.

[0097] The selection of tool materials may be related to "tool material properties" and "wear mechanism of high-speed cutting tools";

[0098] Optimization of cutting parameters may be related to "analysis of cutting force and cutting temperature" and "the influence of spindle rigidity on cutting stability";

[0099] Machining stability control may be related to "machine tool vibration and its suppression technology" and "cutting vibration and dynamic rigidity";

[0100] Coolant usage strategies may be related to "the type and function of cutting fluid" and "the heat-affected zone and the cooling mechanism of cutting fluid".

[0101] The system stores the relationships between all theoretical and technological knowledge in a knowledge association matrix. Each row represents a technological knowledge element, each column represents a theoretical knowledge element, and the elements in the matrix represent the strength of the association between them. For example, through methods such as text similarity calculation, case analysis, and expert scoring, the system can assign an association weight to each pair of knowledge elements (e.g., 0.8 indicates a strong association, and 0.3 indicates a weak association) to facilitate subsequent automated knowledge reasoning and personalized recommendations.

[0102] After establishing the knowledge association matrix, the system needs to further calculate the knowledge dependency of process knowledge elements on theoretical knowledge elements. This measures the degree to which a particular process knowledge point relies on relevant theoretical knowledge for understanding and application, thereby optimizing knowledge recommendation and learning paths. The calculation of knowledge dependency is typically based on multiple methods, such as expert scoring, machine learning analysis, and case data mining, to ensure the scientific validity and accuracy of the results. Specifically, knowledge dependency reflects which theoretical knowledge points require a higher level of mastery during the learning process of a particular process knowledge point, assigning corresponding weights. For example, when learning the process knowledge of "titanium alloy drilling," the system analyzes the key theoretical knowledge involved in the process, such as "thermal conductivity characteristics of titanium alloys," "tool wear mechanism," and "the influence of cutting fluid on high-temperature cutting," and calculates the degree of influence of these theoretical knowledge points on the drilling process based on historical learning data and case analysis, thus determining the weight of the dependency. If a theoretical concept is crucial to the technological operation, such as the direct impact of "tool wear mechanism" on "titanium alloy drilling tool selection," the system will assign it a high dependency weight (e.g., 0.9); conversely, if a concept has a relatively minor impact on the process, it will be assigned a lower weight (e.g., 0.3). Furthermore, the system can personalize its approach based on the learner's knowledge level. For instance, if the system detects that a learner lacks sufficient understanding of "tool coating technology" in the "high-speed milling" course, it will intelligently push relevant supplementary theoretical knowledge during the "high-speed milling process" simulation training to ensure the learner has the necessary knowledge base. This knowledge dependency-based optimization strategy makes the learning path more rational, preventing learners from directly entering complex process simulation training without sufficient theoretical support.

[0103] After calculating knowledge dependencies, the system ultimately constructs a process knowledge network. This network organizes and integrates process-related theoretical and practical knowledge in a structured manner, enabling learners to learn and apply process knowledge in a logically clear and dynamically scalable environment. The core of the process knowledge network is to use theoretical knowledge elements as foundational nodes and process knowledge elements as application nodes, establishing connections between them through knowledge dependencies. This allows learners to progress from basic theory to specific process simulation training in a scientifically sound order. This knowledge network not only provides a static knowledge structure but also supports dynamic adjustment and personalized recommendations. It can optimize knowledge paths and provide targeted learning content based on the needs of different learners. For example, when learning about "wear mechanisms of cemented carbide tools," the system automatically links to relevant theoretical knowledge such as "properties of cemented carbide materials," "cutting force analysis," and "the influence of cutting heat on tool life," and combines this with practical examples (such as "the application of cemented carbide tools in high-temperature alloy machining") to help learners understand how theoretical knowledge plays a role in actual machining processes.

[0104] S104. Construct a virtual training environment based on the process knowledge network;

[0105] Specifically, the target theoretical knowledge elements are extracted from the process knowledge network. These target theoretical knowledge elements are those with a knowledge dependency greater than a preset threshold. Based on the target theoretical knowledge elements and process knowledge elements, the process training task sequence for the target workpiece is determined. A virtual process operation sequence is constructed based on the process training task sequence to obtain the virtual training environment for the target workpiece.

[0106] In step S104, the system first needs to filter out the theoretical knowledge elements crucial to the machining of the target workpiece from the process knowledge network to ensure that learners can obtain the necessary theoretical support. To this end, the system extracts theoretical knowledge elements with a dependency greater than a preset threshold based on knowledge dependence; these are fundamental theories closely related to the target process knowledge and having a decisive impact on process practice. For example, when developing a training task on "high-precision milling of titanium alloy parts," the system analyzes the theoretical knowledge related to this process and filters out knowledge elements with high dependency, such as "cutting characteristics of titanium alloys," "tool wear mechanism in high-speed milling," and "the influence of cutting fluid on titanium alloy machining." If the knowledge dependence of a certain theoretical knowledge (such as "cutting mechanism of ordinary steel") is lower than the set threshold, this knowledge will not be included in the target theoretical knowledge elements to avoid learners wasting time on knowledge points irrelevant to the current task. Through this filtering process, the system ensures that the knowledge base of the process training accurately matches the machining requirements of the target workpiece, enabling learners to focus on core theoretical concepts and efficiently apply relevant theoretical knowledge in subsequent training simulations.

[0107] After determining the target theoretical knowledge elements, the system then needs to combine them with process knowledge elements to create a sequence of process training tasks for the target workpiece. This involves planning the process operation tasks that learners need to complete sequentially in a scientifically sound order. The creation of this task sequence is based on the machining characteristics of the target workpiece, the process flow, and the learner's knowledge level, ensuring a close integration of theoretical learning and practical operation. For example, in the process training task of "machining threaded holes in titanium alloy parts," the system will create a task sequence based on the correlation between target theoretical knowledge elements (such as "cutting mechanics analysis of thread machining") and process knowledge elements (such as "tapping tool selection" and "cooling strategy"). The task sequence may include: 1. Selecting a suitable drill bit for drilling the threaded hole; 2. Setting reasonable cutting parameters to optimize drilling quality; 3. Selecting an appropriate tapping tool and performing tapping; 4. Monitoring thread quality and performing error analysis; 5. Performing necessary surface treatment and subsequent quality optimization, etc. Each task step is matched with the corresponding theoretical knowledge and provides real-time knowledge support during task execution. For example, when tapping, the system can prompt "common tool breakage problems and their solutions during tapping" to help learners understand the application of theoretical knowledge in operation simulation.

[0108] After the process training task sequence is formulated, the system further transforms the task sequence into an executable virtual process operation sequence and simulates it in a virtual training environment to achieve an immersive process training experience.

[0109] Specifically, the process training task sequence is decomposed into multiple process operation units, and execution constraints are set for each process operation unit based on the target theoretical knowledge elements. According to the execution constraints, a virtual workpiece processing state transition model of the target workpiece is constructed, and a detection threshold is set for each processing state in the virtual workpiece processing state transition model. Based on the processing state transition model, virtual simulation modeling is performed on the process operation units to obtain a virtual process operation sequence. The virtual process operation sequence is then time-aligned with the process video clips to obtain a virtual training environment.

[0110] After determining the sequence of process training tasks for the target workpiece, the system needs to further break down the entire training task into multiple process operation units. This ensures that learners can gradually master the machining skills by following detailed steps. The system also sets execution constraints for each operation unit based on the target theoretical knowledge elements to ensure the standardization and rationality of the operation. For example, in the task of "high-precision drilling of aluminum alloy parts," the complete process training task may include several key steps such as drilling positioning, drill bit selection, cutting parameter setting, drilling operation, coolant usage, and drilling quality inspection. The system will break these down into independent process operation units and set execution constraints for each. For instance, the constraints for the "drill bit selection" unit might include "the tool material must meet the requirements for aluminum alloy machining" and "the drill bit diameter error must not exceed ±0.02mm," while the constraints for the "drilling operation" unit might include "the spindle speed should be controlled within the range of 3000-5000rpm" and "the feed rate should match the tool material," etc. These execution constraints not only regulate learners' operations but also enable real-time monitoring and correction during virtual training. For example, if a learner selects an unsuitable drill bit, the system can immediately issue a warning and provide correct tool recommendations, thereby ensuring that learners complete simulation operations while meeting process requirements and develop a good understanding of the process.

[0111] After decomposing the process operation units and setting the execution constraints, the system further constructs a virtual workpiece processing state transition model based on these conditions. This model dynamically simulates the state changes of the target workpiece at different processing stages and ensures that each processing operation conforms to process standards. The core of this model is establishing a mathematical description of the workpiece state, defining how different processing steps affect the workpiece's geometry, material properties, surface quality, etc., and setting rules for processing state transitions. For example, in the task of "CNC milling of copper alloy parts," the initial state of the workpiece might be a raw blank. After different processing operations, its state will gradually transform into "roughing state," "semi-finishing state," "finishing state," and "final finished product state," with each state transition influenced by execution constraints. In addition, the system will set detection thresholds for each machining state in the model to determine whether the machining meets the quality requirements. For example, in the "finishing mode" state, the system can set detection thresholds for "surface roughness Ra≤0.8μm" and "dimensional error≤±0.01mm". If the learner fails to meet these standards in the virtual training operation, the system will automatically prompt the reason for the error and suggest adjusting the cutting parameters or tool selection to ensure that the machining quality meets the requirements.

[0112] After establishing a complete virtual workpiece machining state transition model, the system will perform virtual simulation modeling for each process operation unit based on the model, constructing a dynamic virtual process operation sequence to achieve visualized machining process simulation in a virtual training environment. The core of virtual simulation modeling is to combine CAD / CAM modeling, finite element analysis (FEA), physics engines, and CNC simulation technology to accurately reproduce the physical changes of tools, workpieces, equipment, cutting forces, temperature distribution, and error accumulation during the process operation. For example, in the task of "CNC turning of parts with chamfers," the system will perform simulation calculations for parameters such as "tool infeed angle," "cutting speed," and "feed rate," and dynamically simulate how the tool removes material and forms the final chamfer shape. If the learner sets an infeed angle improperly, the system will simulate possible machining defects, such as "chamfer size too large" or "chamfer surface roughness not meeting standards," and provide visualized error analysis. Furthermore, virtual simulation modeling supports real-time interaction. Learners can adjust cutting parameters in the simulation environment and immediately observe changes in machining effects, thereby continuously optimizing the process plan and improving machining quality and operational proficiency in the training simulation.

[0113] After constructing the virtual process operation sequence, the sequence is time-aligned with real process video clips to ensure that the virtual training environment provides both interactive simulation and intuitive learning references based on real-world examples. The core of this time-alignment is to utilize computer vision, motion capture technology, and deep learning algorithms to automatically match the operation steps of the virtual simulation model with the actual operations in the process video clips, and then play them synchronously. For example, in the "High-Speed ​​Milling of Titanium Alloy Parts" task, the system compares the "real-time trajectory of the tool cutting path" in the virtual simulation with the "actual cutting path operated by the technician" in the process video, and synchronously plays key actions from the video at corresponding time points, such as "tool entry," "coolant spraying," and "spindle speed adjustment," allowing learners to observe the details of real machining while performing virtual operations. Furthermore, the system supports multi-view switching. For example, when learning "workpiece clamping," learners can try different clamping methods in the virtual environment while simultaneously watching the standard clamping operation in the video, helping them understand the correct process method.

[0114] S105. Collect learners' interaction data in the virtual training environment, evaluate the interaction data, and obtain evaluation results.

[0115] After learners enter the virtual training environment and begin process operation training, the system collects various interactive data from the learners in real time during the training process. This includes key behavioral information such as operation procedures, parameter settings, machining paths, equipment control, error correction, task completion time, and number of errors, to comprehensively assess the learners' mastery of process skills. This data collection process combines sensor technology, virtual reality (VR) or augmented reality (AR) interactive systems, machine vision, motion capture, and other technologies to achieve accurate recording of the learners' operations. For example, in the virtual training of "CNC milling," the system monitors the learners' tool selection, spindle speed setting, feed rate adjustment, workpiece clamping method, and other operations in real time, and records whether they follow the standard process flow. If the learner does not correctly align the workpiece during clamping, the system will mark this error and record the time and scope of the error.

[0116] After collecting interactive data, the system intelligently evaluates the learner's operations based on the process knowledge network and preset evaluation criteria. It analyzes dimensions such as operational standardization, rationality of process parameters, and stability of machining quality, generating a comprehensive evaluation result. For example, in "tapping process" training, the system uses data analysis to determine whether the learner correctly selected the tapping speed, used appropriate cutting fluid, and whether problems such as wire breakage or insufficient thread accuracy occurred during tapping. It then calculates a comprehensive score based on these indicators. Simultaneously, the system can also perform comparative analysis using the learner's historical data. For instance, if a learner's error in the "drilling positioning" task remains consistently large, the system further analyzes their operating patterns to determine if it's due to improper feed rate settings or incorrect tool selection, providing targeted optimization suggestions in subsequent intelligent guidance.

[0117] S106. Generate guiding animations based on evaluation results and process knowledge networks.

[0118] Specifically, based on the operational deviations in the evaluation results, deviation theoretical knowledge elements and deviation process knowledge elements are extracted from the process knowledge network; based on the deviation theoretical knowledge elements and deviation process knowledge elements, and combined with the process demonstration video in the process data, a correction strategy is generated; according to the correction strategy, a target demonstration case is selected from the case resource library, and the target process parameters of the target demonstration case are extracted; based on the target demonstration case and the target process parameters, a guidance animation is generated.

[0119] After learners complete virtual training tasks, the system intelligently analyzes the operation process based on the evaluation results, identifying operational deviations in each process unit—errors or deficiencies compared to the standard process flow. To accurately pinpoint the root cause, the system extracts theoretical and process knowledge elements directly related to the operational deviation from the process knowledge network, constructing a complete knowledge correction path. For example, during a learner's "CNC milling" training, the system detects that the feed rate is significantly lower than the standard value in the "cutting parameter setting" stage, resulting in low cutting efficiency and abnormal tool wear. In this case, the system extracts relevant theoretical knowledge elements (such as "cutting force calculation" and "tool wear mechanism") and process knowledge elements (such as "milling speed optimization strategy" and "the impact of cutting fluid on tool life") from the process knowledge network to ensure that the correction plan not only addresses the current error but also helps learners understand deeper process principles, thereby preventing similar problems from occurring in subsequent operations.

[0120] After extracting relevant deviation knowledge elements, the system further analyzes standard operating procedures by combining process demonstration videos from the process data, and formulates targeted correction strategies to help learners understand the correct operating methods. The formulation of correction strategies is based on technologies such as knowledge reasoning, case matching, and expert experience databases to ensure optimal corrective guidance for different types of operational deviations. For example, in the "thread machining" task, the system detects that the learner is not using cutting fluid correctly, resulting in excessive thread surface roughness and affecting thread accuracy. In this case, the system will analyze standard tapping operations by combining process demonstration videos and generate correction strategies, such as: "Select a suitable type of cutting fluid (e.g., water-soluble cutting fluid)," "Adjust the cutting fluid flow rate to ensure adequate lubrication," and "Reduce the tapping speed to reduce heat accumulation," while providing corresponding theoretical explanations (e.g., "The effect of cutting fluid on thread surface quality") to help learners optimize their operations based on understanding the principles.

[0121] After formulating a correction strategy, the system further matches the most relevant standard demonstration cases from the case resource library to the learner's operational deviations and extracts the target process parameters from those cases. This ensures that the learner can intuitively understand the correct operating method through comparative analysis. Case matching employs methods such as similarity calculation, case-based reasoning (CBR), and deep learning models to ensure that the selected cases are highly consistent with the current operational deviations in terms of process flow, material properties, and equipment type. For example, in the "CNC turning of external diameter" task, the system detects that the learner's cutting depth is too large, resulting in excessive tool load and significant vibration. In this case, the system selects a high-precision CNC turning demonstration case from the case resource library and extracts the target process parameters, such as "recommended cutting depth (0.2mm-0.4mm)," "reasonable spindle speed range (1200-1800rpm)," and "optimal feed rate (0.05mm / rev)." These parameters are then compared with the learner's incorrect parameters to help them understand the correct setting method. In addition, the system can provide further case studies, such as "comparison of surface quality of the same material at different cutting depths," enabling learners not only to correct current errors but also to acquire broader process experience.

[0122] After matching the target demonstration cases and extracting the target process parameters, the system generates guiding animations based on this data. These animations dynamically and visually demonstrate the correct process operations to learners and provide interactive prompts at key steps to enhance learning. The generation of these guiding animations combines 3D modeling, motion capture, virtual reality (VR), and augmented reality (AR) technologies to achieve highly realistic process demonstrations. For example, in the "Precision Hole Machining" task, if a learner causes the hole diameter to exceed tolerances due to excessive feed rate during drilling, the system will generate a guiding animation of "Correct Drilling Operation," including: 1. Correctly setting the feed rate (the animation dynamically adjusts the feed parameters and displays the changes); 2. Selecting the appropriate tool (the animation demonstrates the impact of different tools on hole diameter accuracy); 3. Optimizing with coolant (the animation shows the impact of coolant spraying methods on drilling temperature). Furthermore, the system can provide an error reproduction mode, where the animation first plays the learner's incorrect operation result (such as drilling too large, causing excessive clearance), and then switches to the standard operating procedure, allowing learners to clearly compare the differences between the incorrect and correct operations.

[0123] Please see Figure 3 , Figure 3 This application provides a schematic diagram of the structure of a machining process training simulation system 300, which specifically includes:

[0124] The acquisition module 301 is used to acquire the engineering data and process data of the target workpiece;

[0125] The first construction module 302 is used to extract features from engineering data and combine them with process data to build a case resource library;

[0126] Analysis module 303 is used to perform semantic association analysis on the processing cases in the preset knowledge resource base and the case resource base to generate a process knowledge network;

[0127] The second construction module 304 is used to construct a virtual training environment based on the process knowledge network;

[0128] The evaluation module 305 is used to collect the learner's interaction data in the virtual training environment, evaluate the interaction data, and obtain the evaluation results.

[0129] Module 306 is used to generate guiding animations based on evaluation results and process knowledge networks.

[0130] Optionally, the first building module 302 is specifically used for:

[0131] Extract workpiece feature data from engineering data, and combine it with processing steps and process parameters from process data to establish a feature-process correlation model. Based on the feature-process correlation model, divide the workpiece into feature regions to obtain multiple target feature regions, and extract the target process parameters for each target feature region to obtain a target process parameter set. According to the target process parameters, segment the process demonstration video in the process data to obtain process video segments for each target feature region. Construct a case resource library based on the feature-process correlation model, the target process parameter set, and the process video segments.

[0132] Optionally, the first building module 302 is also specifically used for:

[0133] Establish the correspondence between target process parameters and process video clips to generate a feature-process-demonstration association matrix; calculate the similarity between multiple target process parameters in the target process parameter set to obtain a process parameter similarity matrix; combine target feature regions, target process parameters, and process video clips to form processing cases; classify processing cases based on the feature-process-demonstration association matrix and the process parameter similarity matrix to construct a case knowledge base.

[0134] Optional, analysis module 303 is specifically used for:

[0135] Extract theoretical knowledge elements from the pre-set knowledge resource base; extract process knowledge elements from each processing case in the case resource base; based on pre-set knowledge association rules, associate theoretical knowledge elements with process knowledge elements to obtain a knowledge association matrix; based on the knowledge association matrix, determine the knowledge dependency of process knowledge elements on theoretical knowledge elements; construct a process knowledge network based on theoretical knowledge elements, process knowledge elements, and knowledge dependency.

[0136] Optionally, the second building block 304 is specifically used for:

[0137] Extract target theoretical knowledge elements from the process knowledge network. Target theoretical knowledge elements are those with a knowledge dependency greater than a preset threshold. Determine the process training task sequence for the target workpiece based on the target theoretical knowledge elements and process knowledge elements. Construct a virtual process operation sequence based on the process training task sequence to obtain the virtual training environment for the target workpiece.

[0138] Optionally, the second building block 304 is also specifically used for:

[0139] The process training task sequence is decomposed into multiple process operation units, and execution constraints are set for each process operation unit based on the target theoretical knowledge elements. According to the execution constraints, a virtual workpiece processing state transition model of the target workpiece is constructed, and a detection threshold is set for each processing state in the virtual workpiece processing state transition model. Based on the processing state transition model, virtual simulation modeling is performed on the process operation units to obtain a virtual process operation sequence. The virtual process operation sequence is time-aligned with the process video clips to obtain a virtual training environment.

[0140] Optionally, module 306 is generated, specifically for:

[0141] Based on the operational deviations in the evaluation results, deviation theoretical knowledge elements and deviation process knowledge elements are extracted from the process knowledge network. Based on the deviation theoretical knowledge elements and deviation process knowledge elements, and combined with the process demonstration video in the process data, a correction strategy is generated. According to the correction strategy, a target demonstration case is selected from the case resource library, and the target process parameters of the target demonstration case are extracted. Based on the target demonstration case and the target process parameters, a guidance animation is generated.

[0142] It should be noted that the above embodiments of the apparatus are only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0143] This embodiment also discloses an electronic device, as shown in the reference. Figure 4 The electronic device may include: at least one processor 401, at least one communication bus 402, user interface 403, network interface 404, and at least one memory 405.

[0144] The communication bus 402 is used to enable communication between these components.

[0145] The user interface 403 may include a display screen and a camera. Optionally, the user interface 403 may also include a standard wired interface and a wireless interface.

[0146] The network interface 404 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0147] The processor 401 may include one or more processing cores. The processor 401 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 405, and by calling data stored in memory 405. Optionally, the processor 401 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 401 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also be implemented as a separate chip without being integrated into the processor 401.

[0148] The memory 405 may include random access memory (RAM) or read-only memory. Optionally, the memory 405 may include a non-transitory computer-readable storage medium. The memory 405 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 405 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 405 may also be at least one storage device located remotely from the aforementioned processor 401. Figure 4 As shown, the memory 405, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a process simulation method for machining.

[0149] exist Figure 4 In the electronic device shown, the user interface 403 is mainly used to provide an input interface for the user and to obtain the user input data; while the processor 401 can be used to call an application program stored in the memory 405 for a mechanical processing process training simulation method. When executed by one or more processors 401, the electronic device executes one or more methods as described in the above embodiments.

[0150] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0151] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0152] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the shown or discussed mutual couplings or direct couplings or communication connections may be through some service interfaces; indirect couplings or communication connections between apparatuses or units may be electrical or other forms.

[0153] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0154] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0155] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory 405 and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory 405 includes various media capable of storing program code, such as a USB flash drive, external hard drive, magnetic disk, or optical disk.

[0156] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Other embodiments of this disclosure will be readily apparent to those skilled in the art upon consideration of the disclosure in this specification. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A process simulation method for machining, characterized in that, When applied to a server, the method includes: Obtain engineering and process data for the target workpiece; Feature extraction is performed on the engineering data, and a case resource library is constructed by combining the process data; Semantic association analysis is performed between the preset knowledge resource base and the processing cases in the case resource base to generate a process knowledge network; A virtual training environment is constructed based on the aforementioned process knowledge network; Collect learners' interaction data in the virtual training environment, evaluate the interaction data, and obtain evaluation results; Based on the evaluation results and the process knowledge network, a guiding animation is generated. The step of performing semantic association analysis between the preset knowledge resource base and the processing cases in the case resource base to generate a process knowledge network specifically includes: Extract theoretical knowledge elements from the preset knowledge resource base; Extract the process knowledge elements of each processing case from the case resource library; Based on preset knowledge association rules, the theoretical knowledge elements are associated with the process knowledge elements to obtain a knowledge association matrix; Based on the knowledge association matrix, the knowledge dependence of the process knowledge elements on the theoretical knowledge elements is determined; A process knowledge network is constructed based on the theoretical knowledge elements, the process knowledge elements, and the knowledge dependency. The generation of the guidance animation based on the evaluation results and the process knowledge network specifically includes: Based on the operational deviations in the evaluation results, deviation theoretical knowledge elements and deviation process knowledge elements are extracted from the process knowledge network. Based on the aforementioned deviation theory knowledge elements and deviation process knowledge elements, and combined with the process demonstration video in the process data, a correction strategy is generated. According to the correction strategy, a target demonstration case is selected from the case resource library, and the target process parameters of the target demonstration case are extracted. Based on the target demonstration case and the target process parameters, a guiding animation is generated.

2. The method according to claim 1, characterized in that, The step of extracting features from the engineering data and combining them with the process data to construct a case resource library specifically includes: Extract workpiece feature data from the engineering data, and combine it with the processing steps and process parameters from the process data to establish a feature-process correlation model; Based on the feature-process correlation model, the workpiece is partitioned into multiple target feature regions, and the target process parameters of each target feature region are extracted to obtain a target process parameter set. Based on the target process parameters, the process demonstration video in the process data is segmented to obtain a process video segment for each target feature region. The case resource library is constructed based on the feature-process correlation model, the target process parameter set, and the process video clips.

3. The method according to claim 2, characterized in that, The construction of the case resource library based on the feature-process correlation model, the target process parameter set, and the process video clips specifically includes: Establish the correspondence between the target process parameters and the process video segments, and generate a feature-process-demonstration association matrix; Calculate the similarity among multiple target process parameters in the target process parameter set to obtain a process parameter similarity matrix; The target feature region, the target process parameters, and the process video clip are combined to form the processing case. Based on the feature-process-demonstration association matrix and the process parameter similarity matrix, the processing cases are classified to construct a case knowledge base.

4. The method according to claim 3, characterized in that, The construction of the virtual training environment based on the process knowledge network specifically includes: Extract target theoretical knowledge elements from the process knowledge network, wherein the target theoretical knowledge elements are the theoretical knowledge elements whose knowledge dependence is greater than a preset threshold; Based on the target theoretical knowledge elements and the process knowledge elements, determine the process training task sequence for the target workpiece; A virtual process operation sequence is constructed based on the process training task sequence to obtain the virtual training environment for the target workpiece.

5. The method according to claim 4, characterized in that, The step of constructing a virtual process operation sequence based on the process training task sequence to obtain the virtual training environment for the target workpiece specifically includes: The process training task sequence is decomposed into multiple process operation units, and execution constraints for each process operation unit are set based on the target theoretical knowledge elements. Based on the execution constraints, a virtual workpiece processing state transition model for the target workpiece is constructed, and a detection threshold is set for each processing state in the virtual workpiece processing state transition model. Based on the processing state transition model, the process operation unit is virtually simulated and modeled to obtain a virtual process operation sequence; The virtual process operation sequence is time-aligned with the process video clips to obtain the virtual training environment.

6. A process simulation system for machining, characterized in that, include: The acquisition module is used to acquire the engineering data and process data of the target workpiece; The first construction module is used to extract features from the engineering data and, in conjunction with the process data, construct a case resource library. The analysis module is used to perform semantic association analysis between the preset knowledge resource base and the processing cases in the case resource base to generate a process knowledge network; The second construction module is used to construct a virtual training environment based on the process knowledge network; The evaluation module is used to collect the learner's interaction data in the virtual training environment, evaluate the interaction data, and obtain the evaluation results. The generation module is used to generate a guidance animation based on the evaluation results and the process knowledge network; The analysis module is specifically used for: extracting theoretical knowledge elements from the preset knowledge resource base; and extracting process knowledge elements for each processing case in the case resource base. Based on preset knowledge association rules, the theoretical knowledge elements are associated with the process knowledge elements to obtain a knowledge association matrix; Based on the knowledge association matrix, the knowledge dependency of the process knowledge elements on the theoretical knowledge elements is determined; a process knowledge network is constructed based on the theoretical knowledge elements, the process knowledge elements, and the knowledge dependency. The generation module is specifically used to extract deviation theoretical knowledge elements and deviation process knowledge elements from the process knowledge network based on the operational deviations in the evaluation results. Based on the aforementioned deviation theory knowledge elements and deviation process knowledge elements, and combined with the process demonstration video in the process data, a correction strategy is generated. According to the correction strategy, a target demonstration case is selected from the case resource library, and the target process parameters of the target demonstration case are extracted. Based on the target demonstration case and the target process parameters, a guiding animation is generated.

7. An electronic device, characterized in that, include: One or more processors and memory; The memory is coupled to the one or more processors, the memory being used to store computer program code, the computer program code including computer instructions, the one or more processors invoking the computer instructions to cause the electronic device to perform the method as described in any one of claims 1-5.

8. A computer-readable storage medium comprising instructions, characterized in that, When the instructions are executed on an electronic device, the electronic device causes the electronic device to perform the method as described in any one of claims 1-5.

Images