High-precision part process route planning method and system based on knowledge reuse network
By constructing a process knowledge reuse network and virtual simulation evaluation, the problem of existing process planning systems relying on human experience for complex and high-precision parts has been solved, realizing efficient and intelligent process route planning and ensuring the accuracy and consistency of the process route.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- NINGXIA BOXU LAB EQUIP CO LTD
- Filing Date
- 2026-04-16
- Publication Date
- 2026-06-19
AI Technical Summary
Existing process planning systems rely on manual experience for planning process routes for complex and high-precision parts, lacking the ability to automatically analyze and match features of 3D CAD models, and thus cannot automatically generate feasible process routes.
A high-precision parts process route planning method based on knowledge reuse networks is proposed. By analyzing part drawings and CAD models, a process knowledge reuse network is constructed. Combined with virtual simulation evaluation and iterative optimization, the process route is generated and optimized.
It improves the accuracy and intelligence of process planning, reduces manpower and time costs, ensures that process routes comply with national and industry standards, and enhances the efficiency and precision of process planning.
Smart Images
Figure CN122242161A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of process planning technology, specifically relating to a method and system for planning process routes for high-precision parts based on knowledge reuse networks. Background Technology
[0002] Complex and high-precision parts are widely used in high-end manufacturing fields such as precision instruments, aerospace, automobiles, and medical devices. They have complex geometries and are mostly made of difficult-to-machine materials such as titanium alloys and high-temperature alloys. The process route planning is difficult and the requirements for precision and economy are extremely high.
[0003] Existing process planning systems rely too heavily on human experience for process route planning and lack the ability to automatically analyze and match features from 3D CAD models, thus failing to automatically generate feasible process routes. Summary of the Invention
[0004] Based on this, this application provides a method and system for high-precision parts process route planning based on knowledge reuse networks, in order to solve the problems of existing process planning systems that rely too much on human experience for process route planning, lack the ability to automatically analyze and match features of 3D CAD models, and cannot automatically generate feasible process routes.
[0005] The technical solution to the above-mentioned technical problems in this application is as follows:
[0006] A high-precision parts process route planning method based on knowledge reuse networks includes:
[0007] Step S1: Obtain the part drawings and CAD models, parse them, and output information parameters;
[0008] Step S2: Obtain historical process information, equipment information, standard parameter information, and feature information to establish a process knowledge reuse network;
[0009] Step S3: Based on process knowledge, reuse network and information parameters to output the initial process route.
[0010] Preferably, it further includes:
[0011] Step S4: Based on the virtual simulation evaluation model, perform simulation evaluation on the initial process route and output the simulation evaluation results;
[0012] Step S5: Based on the simulation evaluation results, determine whether it is not less than the threshold.
[0013] If so, perform iterative optimization, output the optimal process route, and execute step S6;
[0014] If not, repeat steps S3-S5 and issue a prompt for a professional to perform process route planning, and input the process route planning processed by the professional into the updated process knowledge reuse network;
[0015] Step S6: Based on the simulation evaluation results, the initial process route is sent to the physical equipment for optimization, and the simulation evaluation results and the corresponding optimal process route are fed back to update the process knowledge reuse network.
[0016] Preferably, the virtual simulation evaluation model includes any one or more of the following evaluation dimensions: machining deformation, tool path, equipment load, energy consumption, and carbon emissions.
[0017] Preferably, the initial process route includes process route generation and processing flow.
[0018] Preferably, in step S2, the process knowledge reuse network includes the reuse of processing method knowledge and the reuse of process decision knowledge.
[0019] Preferably, the initial process route in step S3 includes at least one initial process.
[0020] Preferably, step S4 involves simulation evaluation of the initial process route, including the following steps:
[0021] Step S41: Based on the virtual simulation evaluation model, perform simulation evaluation on one of the initial processes in the initial process route;
[0022] Step S42: Output the simulation evaluation results of the initial process;
[0023] Step S43: Determine if any parts of the initial process route have not been simulated and evaluated.
[0024] If so, repeat steps S41 to S43;
[0025] If not, then the simulation evaluation results of all initial processes in the initial process route are sorted.
[0026] Preferably, it is applicable to the process route planning of any one or more complex shafts and irregularly shaped parts made of 40CrMo, titanium alloy, and high-temperature alloy.
[0027] A high-precision parts process route planning system based on knowledge reuse networks, characterized in that it is applied to the execution of any of the above-described high-precision parts process route planning methods based on knowledge reuse networks, including:
[0028] The model parsing module is used to parse part drawings and CAD models and output information parameters.
[0029] The knowledge management module is used to acquire historical process information, equipment information, standard parameter information, and feature information to establish a process knowledge reuse network.
[0030] The route generation module, based on the model parsing module and the knowledge management module, outputs the initial process route.
[0031] Preferably, it further includes:
[0032] The simulation evaluation module is used to perform simulation evaluation on the initial process route based on the virtual simulation evaluation model and output the simulation evaluation results.
[0033] The optimization output module is used to iteratively optimize the initial process route and output the optimal process route;
[0034] The equipment execution module is used to execute the optimal process route based on the optimization output module.
[0035] The technical solution adopted in this application can achieve the following beneficial effects:
[0036] 1. By analyzing part drawings and CAD models, comprehensive information parameters such as geometry, materials, structure, and process requirements are extracted. Combined with process knowledge, historical processes matched by network retrieval are reused and adaptively adjusted to avoid blind planning. This ensures that the initial process route fits the specific processing requirements of complex and high-precision parts, reduces process deviations caused by missing parameters or improper matching, and improves the accuracy and adaptability of process planning. At the same time, it solves the problem that existing process planning systems rely too much on human experience for process route planning and lack the ability to automatically analyze and match features of 3D CAD models, thus failing to automatically generate feasible process routes.
[0037] 2. Construct a process knowledge reuse network that includes information on historical processes, equipment, standards, and features. This allows for the structured storage and retrieval of past mature process experience, eliminating the need for repeated process design, reducing repetitive work by professionals, shortening process planning cycles, and lowering labor and time costs. It is particularly suitable for the efficient planning of complex and high-precision parts, while also enabling efficient reuse of process knowledge and reducing planning costs.
[0038] 3. By building a knowledge reuse network based on graph neural networks, dynamic updates and associated calls of knowledge can be realized. Combined with standardized information parameter processing procedures, this replaces the traditional planning mode that relies on human experience, improves the intelligence level of process planning, and ensures that the planning process complies with national and industry standards, guaranteeing the standardization and consistency of process routes, thereby enhancing the intelligence and standardization of process planning.
[0039] 4. The output initial process route clearly defines the core contents such as the sequence of operations, processing equipment, and parameters. Moreover, the information parameters are stored in a standardized dataset, which can be directly connected to subsequent virtual simulation evaluation, iterative optimization, and other stages, providing reliable data support and a clear optimization direction for improving process accuracy and optimizing processing efficiency. Attached Figure Description
[0040] Figure 1 This is a flowchart of the high-precision parts process route planning method based on knowledge reuse networks described in this application.
[0041] Figure 2 This is a schematic diagram of the precision attenuation repair system for high-precision machining equipment based on quality correlation networks as described in this application. Detailed Implementation
[0042] To facilitate understanding of this application, a more complete description will be provided below with reference to the accompanying drawings. Preferred embodiments of this application are shown in the drawings. However, this application can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the disclosure of this application.
[0043] It should be noted that when an element is referred to as being "set on" another element, it can be directly on the other element or there may be an intervening element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or there may be an intervening element. The terms "vertical," "horizontal," "left," "right," "top," "bottom," "end," "top," and similar expressions used herein are for illustrative purposes only and do not represent the only possible implementation.
[0044] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the specification of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.
[0045] Please see Figure 1 This application provides a high-precision parts process route planning method based on a knowledge reuse network, including: step S1, acquiring part drawings and CAD models, parsing them, and outputting information parameters; step S2, acquiring historical process information, equipment information, standard parameter information, and feature information, and establishing a process knowledge reuse network; step S3, outputting an initial process route based on the process knowledge reuse network and information parameters.
[0046] Specifically, the information parameters include, but are not limited to, geometric features, tolerance requirements, material properties, and machining constraints. In step S1, the part drawings include two-dimensional engineering drawings and three-dimensional assembly drawings. The CAD model adopts common formats such as STEP and IGES. The parsing process is completed through professional CAD parsing software, focusing on extracting the geometric features of the part (such as dimensional accuracy, geometric tolerances, and surface roughness), material properties (such as material composition, hardness, and toughness), structural features (such as the distribution and dimensions of complex structures such as holes, slots, threads, and curved surfaces), and process requirements (such as machining accuracy level, surface quality requirements, and assembly fit requirements). The output information parameters are stored in the form of standardized datasets to facilitate subsequent process knowledge reuse, network access, and processing.
[0047] In step S2, historical process information includes process routes, processing parameters, tooling and fixture selection, processing time, quality inspection results, and fault handling records for similar or comparable complex high-precision parts in the past; equipment information includes the model, processing range, precision level, operating parameters, maintenance status, and available time periods of existing processing equipment; standard parameter information includes national and industry-related high-precision part processing standards, process specifications, and quality acceptance standards; feature information includes typical processing methods and process parameters corresponding to various geometric and structural features of the parts; the process knowledge reuse network is constructed through a graph neural network (GNN), using the above types of information as nodes, and the relationships between nodes (such as the correspondence between features and processing methods, the matching relationship between equipment and processing parameters, and the similarity association between historical processes and current parts) as edges, to achieve structured storage, associated retrieval, and dynamic updating of knowledge.
[0048] In step S3, historical process knowledge matching the current part information parameters is retrieved through the process knowledge reuse network. Combined with the geometric features, material properties and process requirements of the part, the retrieved historical process is adaptively adjusted (such as adjusting processing parameters, changing suitable equipment, and optimizing the process sequence) to generate an initial process route that meets the current part processing requirements. The initial process route clearly defines the sequence of each processing step, processing equipment, processing parameters, tooling fixtures, processing time and quality inspection nodes.
[0049] This application employs a high-precision parts process route planning method based on knowledge reuse networks, and the resulting technical solution achieves the following beneficial effects:
[0050] 1. By analyzing part drawings and CAD models, comprehensive information parameters such as geometry, materials, structure, and process requirements are extracted. Combined with process knowledge, historical processes matched by network retrieval are reused and adaptively adjusted to avoid blind planning. This ensures that the initial process route fits the specific processing requirements of complex and high-precision parts, reduces process deviations caused by missing parameters or improper matching, and improves the accuracy and adaptability of process planning. At the same time, it solves the problem that existing process planning systems rely too much on human experience for process route planning and lack the ability to automatically analyze and match features of 3D CAD models, thus failing to automatically generate feasible process routes.
[0051] 2. Construct a process knowledge reuse network that includes information on historical processes, equipment, standards, and features. This allows for the structured storage and retrieval of past mature process experience, eliminating the need for repeated process design, reducing repetitive work by professionals, shortening process planning cycles, and lowering labor and time costs. It is particularly suitable for the efficient planning of complex and high-precision parts, while also enabling efficient reuse of process knowledge and reducing planning costs.
[0052] 3. By building a knowledge reuse network based on graph neural networks, dynamic updates and associated calls of knowledge can be realized. Combined with standardized information parameter processing procedures, this replaces the traditional planning mode that relies on human experience, improves the intelligence level of process planning, and ensures that the planning process complies with national and industry standards, guaranteeing the standardization and consistency of process routes, thereby enhancing the intelligence and standardization of process planning.
[0053] 4. The output initial process route clearly defines the core contents such as the sequence of operations, processing equipment, and parameters. Moreover, the information parameters are stored in a standardized dataset, which can be directly connected to subsequent virtual simulation evaluation, iterative optimization, and other stages, providing reliable data support and a clear optimization direction for improving process accuracy and optimizing processing efficiency.
[0054] Based on the above scheme, the high-precision parts process route planning method based on knowledge reuse networks also includes:
[0055] Step S4: Based on the virtual simulation evaluation model, perform simulation evaluation on the initial process route and output the simulation evaluation results. The virtual simulation evaluation model is constructed by combining finite element analysis (FEA) and digital twin technology. It can simulate the entire process of part processing in a real processing environment. During the simulation, it restores the operating status of the processing equipment, the cutting trajectory of the tool, the constraint effect of the tooling fixture, and physical phenomena such as force, heat, and vibration during the processing. Finally, it outputs multi-dimensional simulation evaluation indicators to provide data support for judging the rationality of the initial process route.
[0056] Step S5: Based on the simulation evaluation results, determine whether it is not less than the threshold; where the threshold is a preset process route qualification standard, which is set by professional technicians in combination with the processing requirements of complex high-precision parts, industry standards and actual production needs. The threshold covers the minimum qualified value of core evaluation indicators such as processing accuracy, processing efficiency, energy consumption and cost.
[0057] If so, iterative optimization is performed to output the optimal process route and execute step S6. The iterative optimization process uses a genetic algorithm to adjust the process sequence, processing parameters, equipment selection, etc. of the initial process route multiple times with the goal of optimizing the simulation evaluation index. After each iteration, virtual simulation evaluation is performed again until a process route that meets all evaluation indexes and has the best overall performance is obtained.
[0058] If not, repeat steps S3-S5 and issue a prompt for professionals to plan the process route. The process route plan processed by the professionals will be input into and updated in the process knowledge reuse network. The prompt message will be sent to the relevant professionals through system pop-ups, sound alarms, etc. The professionals will manually adjust and optimize the process route based on their own experience and actual production. The optimized process route, along with the corresponding evaluation results and adjustment basis, will be entered into the process knowledge reuse network to supplement and update knowledge, thereby improving the accuracy and efficiency of subsequent process route planning.
[0059] Step S6: Based on the simulation evaluation results, the initial process route is distributed to the physical equipment for optimization, and the simulation evaluation results and the corresponding optimal process route are fed back to update the process knowledge reuse network. The distribution process is realized through the industrial internet platform, which synchronizes the relevant parameters of the optimal process route (such as processing steps, equipment parameters, and cutting parameters) to the corresponding processing equipment. The equipment performs processing operations according to the distributed parameters. At the same time, the virtual simulation evaluation results, data from the actual processing process (such as actual processing accuracy, processing time, and energy consumption), and the optimal process route are bound and stored, and fed back to the process knowledge reuse network to enrich the knowledge reserves in the network, optimize the correlation between nodes, and improve the reliability of knowledge reuse.
[0060] In the above scheme, the virtual simulation evaluation model includes any one or more of the following evaluation dimensions: machining deformation, tool path, equipment load, energy consumption, and carbon emissions. The machining deformation evaluation dimension is used to detect the deformation of parts during machining due to factors such as cutting force and thermal stress, determining whether the deformation is within the allowable tolerance range to avoid substandard part accuracy caused by deformation. The tool path evaluation dimension is used to verify the rationality of the tool movement trajectory, detecting any trajectory deviations or interference, ensuring smooth tool movement, and reducing tool wear and surface scratches on parts. The equipment load evaluation dimension is used to monitor parameters such as spindle speed, feed rate, and cutting force during machining, determining whether the equipment load is within a reasonable range to avoid malfunctions caused by equipment overload. The energy consumption and carbon emissions evaluation dimension is used to statistically analyze electrical energy consumption, cutting fluid consumption, etc., during machining, calculating total carbon emissions to achieve green machining evaluation and contribute to low-carbon production. Each evaluation dimension has a corresponding evaluation weight, and the weight ratio of each dimension can be flexibly adjusted according to the machining priority and production needs of the parts, ultimately outputting a comprehensive simulation evaluation result.
[0061] In another embodiment of this application, the initial process route includes process route generation and machining process flow. Process route generation is based on process knowledge reuse networks and part information parameters to determine the overall machining path of the part from blank to finished product, and to clarify the sequence and core requirements of each machining stage (such as roughing, semi-finishing, finishing, and finishing). The machining process flow refines the specific operations of each machining stage in the process route, including the machining methods, selection of machining equipment, machining parameters (such as cutting speed, feed rate, depth of cut), tooling and fixture configuration, quality inspection methods and acceptance standards, and clarifies the connection requirements between each process to ensure that the machining process is orderly and efficient, and to meet the machining accuracy and quality requirements of complex and high-precision parts.
[0062] In another embodiment of this application, in step S2, the process knowledge reuse network includes machining method knowledge reuse and process decision knowledge reuse. Machining method knowledge reuse stores typical machining methods, machining parameters, and applicable scenarios corresponding to various part features, such as drilling, boring, and reaming for hole features, and milling and grinding for surface features. It can quickly retrieve suitable machining methods and related parameters based on the current part's feature information, reducing redundant design. Process decision knowledge reuse stores the decision logic in the process route planning process, including process sequence arrangement principles (such as roughing before finishing, datum before others, surface before hole), equipment selection criteria, tooling and fixture matching rules, and quality inspection node setting logic. It can automatically call relevant decision knowledge based on the current part's information parameters and production conditions to assist in generating a reasonable process route, improving the intelligence level and decision efficiency of process planning.
[0063] In another embodiment of this application, the initial process route in step S3 includes at least one initial process. An initial process is an independent processing plan for different processing stages and features of the part. Each initial process corresponds to a specific processing step or a set of related steps. For example, the initial process for the roughing stage may include rough turning and rough milling of the blank, while the initial process for the finishing stage may include finish turning, finish grinding, and polishing. Multiple initial processes are combined according to the sequence of the process route to form a complete initial process route. When the part structure is complex and has diverse features, the number of initial processes can be increased according to actual processing needs. Each initial process must meet the processing requirements of the corresponding feature of the part, and the initial processes must maintain smooth connection to avoid process conflicts or repeated processing.
[0064] Based on the above scheme, step S4 performs simulation evaluation of the initial process route, including the following steps:
[0065] Step S41: Based on the virtual simulation evaluation model, perform simulation evaluation on an initial process in the initial process route; specifically, extract the processing parameters, equipment information, tooling and fixture information and part feature information corresponding to the initial process, input them into the virtual simulation evaluation model, simulate the complete processing of the initial process, focus on monitoring the evaluation dimensions corresponding to the process (such as processing deformation, tool path, etc.), and record various data during the simulation process.
[0066] Step S42: Output the simulation evaluation results of the initial process; the evaluation results include the specific values of each evaluation dimension of the initial process, the judgment of the qualification status, and the existing problems (such as excessive processing deformation, tool path interference, abnormal equipment load, etc.). At the same time, generate a simulation report, which records the simulation process, data and analysis conclusions in detail, and provides a basis for subsequent optimization.
[0067] Step S43: Determine if there are any initial processes in the initial process route that have not been simulated and evaluated: The system numbers and counts all initial processes in the initial process route, compares the number of initial processes that have been simulated and evaluated with the total number, and determines if there are any initial processes that have not been evaluated.
[0068] If so, repeat steps S41 to S43; perform the same simulation evaluation process for the next unevaluated initial process to ensure that each initial process is fully simulated and verified.
[0069] If not, the simulation evaluation results of all initial processes in the initial process route are sorted. The sorting criteria can be based on the preset evaluation weights, calculating the comprehensive evaluation score of each initial process, and sorting them from high to low or low to high scores. Initial processes with higher comprehensive evaluation scores are retained first, providing a clear optimization direction for subsequent iterative optimization, and facilitating professionals to quickly locate problematic initial processes.
[0070] In the above scheme, the intelligent planning method for process routes of complex high-precision parts using knowledge reuse networks is applicable to the planning of process routes for any one or more complex shafts and irregularly shaped parts made of 40CrMo, titanium alloy, and high-temperature alloy. 40CrMo alloy parts possess high strength, high toughness, good hardenability, and wear resistance, and are often used to manufacture complex shaft parts that withstand impacts and heavy loads. This method can optimize machining parameters based on their material properties, reduce machining deformation, and ensure machining accuracy. Titanium alloy parts have the characteristics of low density, high strength, and strong corrosion resistance, but they are difficult to machine and have poor machinability. This method uses a knowledge reuse network to retrieve specific machining knowledge for titanium alloy parts, optimize tool selection and cutting parameters, reduce machining difficulty, and improve machining efficiency. High-temperature alloy parts have excellent high-temperature strength, oxidation resistance, and corrosion resistance, and are often used in complex irregular-shaped parts in high-end fields such as aerospace. This method uses virtual simulation evaluation and iterative optimization to solve problems such as cracks and deformation that are prone to occur during the machining of high-temperature alloys. Complex shaft parts include multi-step shafts, crankshafts, camshafts, etc., and irregular-shaped parts include irregular curved surface parts and irregular structural parts. This method can generate reasonable process sequences and machining schemes based on their complex structural characteristics, adapting to the machining needs of various complex parts.
[0071] This application also provides a high-precision parts process route planning system based on knowledge reuse networks, characterized in that it is applied to the high-precision parts process route planning method based on knowledge reuse networks described in any of the above claims, including:
[0072] The model parsing module is used to acquire and parse part drawings and CAD models, and output information parameters. The model parsing module integrates professional CAD parsing algorithms and data processing units, supports the import of part drawings and CAD models in various formats, and can automatically identify the geometric features, structural features, material properties and process requirements of parts. It standardizes and classifies the parsed information, generates a structured information parameter dataset, and has a data verification function to detect errors and omissions in the parsing process, ensuring the accuracy and completeness of the output information parameters and providing reliable data support for subsequent modules.
[0073] The knowledge management module is used to acquire historical process information, equipment information, standard parameter information, and feature information to establish a process knowledge reuse network. The module includes a data acquisition unit, a knowledge modeling unit, and a knowledge update unit. The data acquisition unit interfaces with the enterprise production management system, equipment management system, and historical process database to automatically collect various relevant information, while also supporting manual input and supplementation. The knowledge modeling unit uses a graph neural network algorithm to construct a structured process knowledge reuse network from the collected information, enabling associative storage and efficient retrieval of knowledge. The knowledge update unit receives feedback from the optimization output module, equipment execution module, and professionals, dynamically updating the process knowledge reuse network to continuously enrich the knowledge reserve and improve the accuracy of knowledge reuse.
[0074] The route generation module, based on the model parsing module and the knowledge management module, outputs an initial process route. The route generation module has a built-in process planning algorithm that can call the information parameters output by the model parsing module and the process knowledge reuse network built by the knowledge management module. Through similarity retrieval, adaptive adjustment and other processes, it automatically generates an initial process route that meets the current part processing requirements. It also has process route preview and editing functions, which makes it convenient for professionals to manually adjust and modify the initial process route to ensure the rationality and feasibility of the initial process route.
[0075] The simulation evaluation module is used to perform simulation evaluation of the initial process route based on a virtual simulation evaluation model and output the simulation evaluation results. The simulation evaluation module integrates finite element analysis and digital twin simulation engine, which can simulate the real processing environment and processing, perform multi-dimensional simulation evaluation of each initial process in the initial process route, generate detailed simulation evaluation reports, clarify the advantages and problems of each initial process, and support the visualization of simulation results, so that professionals can intuitively understand the rationality of the process route and provide data support for subsequent optimization.
[0076] The optimization output module is used to iteratively optimize the initial process route and output the optimal process route. The optimization output module has built-in optimization algorithms such as genetic algorithm and particle swarm optimization. Based on the simulation evaluation results, and with the goal of optimizing the comprehensive performance in terms of processing accuracy, efficiency, cost, and energy consumption, it performs multiple iterative adjustments to the process sequence, processing parameters, equipment selection, tooling and fixture configuration of the initial process route. After each iteration, the optimized process route is sent to the simulation evaluation module for re-evaluation until the optimal process route is obtained. At the same time, this module has the function of storing and exporting the optimal process route for easy subsequent calling and traceability.
[0077] The equipment execution module is used to execute the optimal process route based on the optimization output module. The equipment execution module communicates with the workshop processing equipment through the industrial internet interface, and can synchronously send the relevant parameters of the optimal process route (such as processing steps, cutting parameters, and equipment operating parameters) to the corresponding processing equipment, controlling the equipment to execute processing operations according to the preset process route. At the same time, this module can collect the equipment's operating data and processing data in real time, and feed them back to the knowledge management module and the optimization output module for updating the process knowledge reuse network and optimizing subsequent process routes, realizing closed-loop management of process planning, simulation evaluation, and equipment execution.
[0078] Based on the above implementation plan, the parameters of the repaired high-precision parts are input into the above method to plan a new process route and output the optimal process route again. Similarly, the high-precision parts that need repair are replaced, and the replaced mechanical parts in the instrument are precisely repaired. After the precision repair is completed, the process planning for each component is re-planned, and the above steps are repeated. This ensures assembly accuracy and the overall structural stability of the equipment.
[0079] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.
Claims
1. A method for planning the process route of high-precision parts based on knowledge reuse networks, characterized in that, include: Step S1: Obtain the part drawings and CAD models, parse them, and output information parameters; Step S2: Obtain historical process information, equipment information, standard parameter information, and feature information to establish a process knowledge reuse network; Step S3: Based on process knowledge, reuse network and information parameters to output the initial process route.
2. The high-precision parts process route planning method based on knowledge reuse networks as described in claim 1, characterized in that, Also includes: Step S4: Based on the virtual simulation evaluation model, perform simulation evaluation on the initial process route and output the simulation evaluation results; Step S5: Based on the simulation evaluation results, determine whether it is not less than the threshold. If so, perform iterative optimization, output the optimal process route, and execute step S6; If not, repeat steps S3-S5 and issue a prompt for a professional to perform process route planning, and input the process route planning processed by the professional into the updated process knowledge reuse network; Step S6: Based on the simulation evaluation results, the initial process route is sent to the physical equipment for optimization, and the simulation evaluation results and the corresponding optimal process route are fed back to update the process knowledge reuse network.
3. The high-precision parts process route planning method based on knowledge reuse networks as described in claim 2, characterized in that, The virtual simulation evaluation model includes any one or more of the following evaluation dimensions: machining deformation, tool path, equipment load, energy consumption, and carbon emissions.
4. The high-precision parts process route planning method based on knowledge reuse networks as described in claim 1, characterized in that, The initial process route includes process route generation and processing technology flow.
5. The high-precision parts process route planning method based on knowledge reuse networks as described in claim 1, characterized in that, In step S2, the process knowledge reuse network includes the reuse of processing method knowledge and the reuse of process decision knowledge.
6. The high-precision parts process route planning method based on knowledge reuse networks as described in claim 2, characterized in that, The initial process route in step S3 includes at least one initial process.
7. The high-precision parts process route planning method based on knowledge reuse networks as described in claim 6, characterized in that, Step S4 involves simulation evaluation of the initial process route, including the following steps: Step S41: Based on the virtual simulation evaluation model, perform simulation evaluation on one of the initial processes in the initial process route; Step S42: Output the simulation evaluation results of the initial process; Step S43: Determine if any parts of the initial process route have not been simulated and evaluated. If so, repeat steps S41 to S43; If not, then the simulation evaluation results of all initial processes in the initial process route are sorted.
8. The high-precision parts process route planning method based on knowledge reuse networks as described in claim 2, characterized in that, It is applicable to process route planning for any one or more complex shafts and irregularly shaped parts made of 40CrMo, titanium alloy, and high-temperature alloy.
9. A high-precision parts process route planning system based on knowledge reuse networks, characterized in that, The method for planning the process route of high-precision parts based on knowledge reuse networks, applied to any one of claims 1-8, includes: The model parsing module is used to parse part drawings and CAD models and output information parameters. The knowledge management module is used to acquire historical process information, equipment information, standard parameter information, and feature information to establish a process knowledge reuse network. The route generation module, based on the model parsing module and the knowledge management module, outputs the initial process route.
10. The high-precision parts process route planning system based on knowledge reuse networks as described in claim 9, characterized in that, Also includes: The simulation evaluation module is used to perform simulation evaluation on the initial process route based on the virtual simulation evaluation model and output the simulation evaluation results. The optimization output module is used to iteratively optimize the initial process route and output the optimal process route; The equipment execution module is used to execute the optimal process route based on the optimization output module.