Method and system for intelligently generating sheet metal part process model

Abstract

The invention relates to the technical field of data mining, in particular to a method and system for intelligently generating a sheet metal part process model. The method comprises the following steps: acquiring structural data of a sheet metal part processing workshop, and carrying out topological structure analysis to generate a processing technology model; acquiring design data of sheet metal parts, establishing a three-dimensional model, and performing machining simulation by using a process model to obtain simulation data; integrating historical processing finished product feature data, extracting surface features, and obtaining actual finished product data; finished product parameterization description is carried out on the machining simulation data, surface defects of a finished product are evaluated, and defect data are obtained; the simulation machining stress distribution uniformity is evaluated, and surface quality influence factors are calculated; and optimizing the processing technology model according to the quality influence factor, and uploading to a management platform to execute a simulation generation task. The accuracy of the sheet metal part process model can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data mining, and in particular to a method and system for intelligently generating a process model for a sheet metal part. Background Art

[0002] In modern manufacturing, sheet metal parts have become an indispensable and important part of the production process because they are widely used in many fields such as automobiles, aerospace, and electronic equipment. These parts are usually made of metal sheets through a series of processes, including stamping, bending, welding, cutting, painting, etc. Sheet metal processing technology is widely used in the manufacturing process of various products due to its advantages in structural strength, light weight, and relatively low cost. The production of sheet metal parts involves complex process flows, including design, mold manufacturing, stamping, bending, welding, painting, and other links. The traditional sheet metal parts production process model mainly relies on manual experience and rule definition. Although this method can meet basic production needs, it has significant deficiencies in the face of increasingly complex design requirements and large-scale production needs. The traditional sheet metal production process model mainly relies on the experience and technical accumulation of workers. Although this method can meet basic needs, it is prone to errors and inconsistencies for complex design requirements. Traditional processes usually lack systematic and standardized process flows, resulting in greater arbitrariness and uncertainty in the production process. This may lead to unstable product quality and low production efficiency. Summary of the invention

[0003] Based on this, it is necessary for the present invention to provide a method and system for intelligently generating a sheet metal part process model to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a method for intelligently generating a sheet metal part process model comprises the following steps: Step S1: Acquire the sheet metal parts processing workshop structure data, and perform sheet metal parts processing flow topology structure analysis on the sheet metal parts processing workshop structure data, thereby obtaining the sheet metal parts processing flow topology structure; perform processing parameter mapping on the sheet metal parts processing flow topology structure, thereby obtaining the sheet metal parts processing process model; Step S2: obtaining the design data of the sheet metal part to be processed, and performing three-dimensional parameter modeling on the design data of the sheet metal part to be processed, thereby obtaining a three-dimensional model of the sheet metal part; performing sheet metal part processing simulation on the three-dimensional model of the sheet metal part through a sheet metal part processing process model, thereby obtaining sheet metal part processing simulation data; Step S3: integrating the features of the historical sheet metal parts processed by the design data of the sheet metal parts to be processed, thereby obtaining the data of the historical sheet metal parts processed by the finished products; extracting the surface features of the processed products according to the historical sheet metal parts processed by the finished products data, thereby obtaining the surface data of the actual processed products; Step S4: performing parameterized description of the sheet metal part processing simulation data to obtain processing simulation product data, and performing finished product surface defect evaluation on the processing simulation product data and the actual finished product surface data to obtain simulated processing surface finished product defect data; Step S5: evaluating the uniformity of simulated processing stress distribution on the sheet metal part processing simulation data, thereby obtaining simulated processing stress uniformity data, and calculating the surface quality influencing factor based on the simulated processing stress uniformity data and the simulated processing surface finished product defect data, thereby obtaining processing surface quality influencing factor data; Step S6: Optimize the processing parameter combination of the sheet metal part processing model according to the processing surface quality influencing factor data, so as to obtain the sheet metal part optimized processing model, and upload it to the sheet metal part processing management platform to execute the sheet metal part simulation generation task.

[0005] The present invention can systematically organize and organize the processing flow of sheet metal parts by acquiring workshop structure data and performing topological structure analysis. This makes the production process more controllable and can reduce errors caused by manual operation. The topological structure of the sheet metal parts processing flow obtained by analysis can help standardize the production process and clarify each processing step and parameter. This reduces production problems caused by lack of experience or irregular operation. By mapping the processing parameters to the process model, a scientific sheet metal parts processing process model can be generated to provide a reliable reference basis for subsequent processing processes and ensure the consistency and stability of production. Three-dimensional modeling can accurately reflect the design details of the parts to be processed, including size, shape and complex geometric features. This accurate modeling is crucial to the subsequent processing process and avoids the deviation between the design and the actual processing. Using the sheet metal parts processing process model to simulate the three-dimensional model, potential problems in the processing process can be predicted, so that adjustments can be made before the actual processing. This improves production efficiency and reduces the trial and error cost in actual processing. Integrating the data and features of historical processed products can help identify and summarize the problems encountered in the past processing process and their solutions. The analysis of such historical data helps to improve the current processing technology. By analyzing and extracting features from historical data, more accurate surface feature data of finished products can be obtained. This helps achieve higher quality control and reduce defect rates in new processing. Parametric description of simulation data and surface defect evaluation can predict and identify defects that may occur during processing. This provides data support for adjusting processing parameters and processes, reducing the non-conformity rate in actual processing. By evaluating the defects of simulated processing surfaces and actual finished product surfaces, the process can be adjusted in time to improve processing quality and product consistency. Evaluating the uniformity of processing stress distribution helps identify and correct stress concentration problems, thereby reducing the risk of deformation and cracking of parts and improving the strength and durability of products. By calculating the influencing factors of processing surface quality, the impact of different processing parameters on surface quality can be understood. This helps make scientific decisions in the process of optimizing processing to improve product quality. Optimizing the combination of processing parameters based on the influencing factor data can improve processing efficiency and product quality. The optimized process model can better meet the needs of complex design and large-scale production. Uploading the optimized process model to the processing management platform realizes the digital management and real-time update of process information. This improves the flexibility of process adjustment and production process and supports more efficient production management. In summary, through the implementation of these steps, the systematic and standardized level of the sheet metal parts production process can be significantly improved, the randomness and uncertainty in production can be reduced, thereby improving production efficiency and product quality.

[0006] Optionally, step S1 specifically includes: Step S11: Acquire the sheet metal parts processing workshop structure data, and extract the workshop processing component structure from the sheet metal parts processing workshop structure data, so as to obtain the processing workshop processing structure data; Step S12: performing a topological structure analysis of the sheet metal parts processing flow according to the processing structure data of the processing workshop, thereby obtaining a topological structure of the sheet metal parts processing flow; Step S13: classifying the processing structure according to the processing structure data of the processing workshop, thereby obtaining the laser processing component structure data and the bending processing component structure data; Step S14: simulating the sheet metal part processing conditions according to the laser processing component structure data and the bending processing component structure data, thereby obtaining a sheet metal part processing parameter set; Step S15: mapping the processing parameters of the sheet metal part processing flow topology structure according to the sheet metal part processing parameter set, thereby obtaining a sheet metal part processing process model.

[0007] The present invention obtains workshop structure data to fully understand the various components and their layout of the workshop, which lays the foundation for the subsequent optimization of the processing flow. After extracting the processing component structure, the specific configuration of each processing link can be accurately grasped, which helps to more accurately analyze and optimize the process. Through the analysis of the workshop structure data, potential problems in the workshop layout can be identified and optimized to improve the overall production efficiency. Analyzing the topological structure of the processing flow can reveal the relationship between the various processing links, help optimize the processing sequence and reduce unnecessary links. Through topological structure analysis, possible bottleneck links in the production process can be identified and improved in time to improve production efficiency. A clear process topological structure helps to accurately schedule resources and equipment, avoiding resource waste and waiting time in the production process. Structural classification of the processing technology can clearly distinguish the component data of different processes such as laser processing and bending processing, which is convenient for subsequent process analysis. Through classification, various processes can be specially optimized to improve the efficiency and quality of each process. The obtained component structure data can be customized according to different needs to improve the processing accuracy and performance of sheet metal parts. Working condition simulation can predict possible processing effects before actual processing, thereby avoiding problems in the processing process. The simulation results can help determine the best set of processing parameters, thereby improving processing quality and efficiency. Through simulation, adjustments can be made before actual processing, reducing trial and error costs and material waste. Through processing parameter mapping, the process parameters can be closely integrated with the processing flow to form a standardized process model and improve production consistency. The process model can help optimize the production process, making the processing process more efficient and stable. After the process model is established, it is easier to control and monitor the processing quality and reduce the product defect rate.

[0008] Optionally, step S12 is specifically: Step S121: extracting processing structure spatial features from processing structure data of the processing workshop, thereby obtaining processing component structure spatial position data; Step S122: performing processing structure spatial distribution analysis according to the processing component structure spatial position data, thereby obtaining processing structure spatial distribution data; Step S123: integrating the processing flow path according to the processing structure spatial distribution data, thereby obtaining the processing flow path data; Step S124: classifying the processing path data into process paths, thereby obtaining parallel processing path data and parallel processing path data; Step S125: performing parallel process topology analysis according to the parallel processing path data, thereby obtaining a parallel processing process topology structure; performing parallel process topology analysis according to the parallel processing path data, thereby obtaining a parallel processing process topology structure; Step S126: topologically associating the parallel processing flow topology structure and the parallel processing flow topology structure, thereby obtaining a sheet metal part processing flow topology structure.

[0009] The present invention can accurately obtain the spatial position of each processing component by extracting the spatial feature data of the processing structure of the processing workshop. This provides basic data for subsequent processing analysis and ensures the accuracy and efficiency of the processing process. Analyzing the spatial distribution data of the processing components can reveal the layout and mutual relationship of each processing component in the workshop, which helps to optimize the use of space and process arrangement, and reduce interference and collision. Integrating the processing process path data helps to build an efficient processing route. By optimizing the path, the processing time can be reduced and the production efficiency can be improved. Classifying the processing process paths can distinguish between parallel processing paths and parallel processing paths. This classification helps to formulate a more flexible processing plan and optimize resource allocation. Analyzing the topological structure of parallel and parallel processing paths helps to understand the topological characteristics of different paths and their mutual relationship, thereby optimizing the processing process and equipment configuration. By associating the topological structure of parallel and parallel processing processes, a complete sheet metal parts processing process topological structure can be constructed. In this way, the entire processing process can be fully understood, systematic optimization and improvement can be carried out, and production efficiency and processing quality can be improved.

[0010] Optionally, step S14 is specifically: Constructing a three-dimensional model of laser processing according to the structural data of the laser processing component, thereby obtaining a three-dimensional model of the laser processing component; Constructing a three-dimensional model of the bending process according to the structural data of the bending process component, thereby obtaining a three-dimensional model of the bending process component; Acquire sheet metal parts processing condition data, and classify the sheet metal parts processing condition data into processing condition data, so as to obtain laser processing condition data and bending processing condition data; Performing laser processing simulation on the three-dimensional model of the laser processing component according to the laser processing condition data, thereby obtaining laser processing simulation data; Perform bending simulation on the three-dimensional model of the bending component according to the bending working condition data, so as to obtain bending simulation data; Performing statistics on low-energy laser processing parameter combinations on laser processing simulation data to obtain a laser processing parameter set; Performing statistics on low-energy bending processing parameter combinations on the bending processing simulation data, thereby obtaining a bending processing parameter set; The sheet metal part processing parameters are integrated into the laser processing parameter set and the bending processing parameter set, so as to obtain the sheet metal part processing parameter set.

[0011] The present invention can design laser processing components more accurately through three-dimensional models, avoid errors in actual processing, test and optimize laser processing technology in a virtual environment, and reduce the number and cost of actual experiments. An intuitive component view is provided to facilitate communication and collaboration. The construction of a three-dimensional model for bending processing can help accurately analyze stress and deformation in bending processing and ensure processing accuracy. Verifying the bending process in a three-dimensional model can reduce problems in actual production, simplify the design and manufacturing process, and improve production efficiency. Acquiring and classifying processing condition data can help accurately understand the requirements and limitations of different processes and provide a basis for subsequent simulation and parameter optimization. Simulating the three-dimensional model of the laser and bending processing components can predict the performance in the actual processing process, discover potential problems, optimize the processing strategy, and reduce the cost of trial and error. By performing statistics on low-energy consumption parameter combinations on the simulation data, energy-saving and efficient processing parameters can be found, thereby reducing production costs and energy consumption and improving environmental benefits. Integrating the parameter sets of laser and bending processing can provide a comprehensive and optimized processing solution, improve overall production efficiency and processing quality, and ensure that parts meet design requirements.

[0012] Optionally, step S2 specifically includes: Step S21: obtaining design data of the sheet metal part to be processed, and performing sheet metal part feature extraction on the design data of the sheet metal part to be processed, thereby obtaining sheet metal part structure data and sheet metal part material data; Step S22: performing sheet metal part structural processing change statistics according to the sheet metal part structural data, thereby obtaining sheet metal part structural change data; Step S23: performing three-dimensional parametric modeling of the sheet metal part processing stage structure according to the sheet metal part structure change data, thereby obtaining a three-dimensional model of the sheet metal part; Step S24: performing material property analysis according to the material data of the sheet metal part, thereby obtaining the material property data of the sheet metal part, and filling the sheet metal part three-dimensional model with the part material property according to the material property data of the sheet metal part, thereby obtaining a sheet metal part parameter model; Step S25: simulating the sheet metal part processing stage on the sheet metal part parameter model through the sheet metal part processing process model, thereby obtaining sheet metal part processing simulation data.

[0013] By extracting design data, the present invention can clearly understand the structure and material of sheet metal parts, and provide accurate basic data for subsequent processing and modeling. Statistics on structural processing changes of sheet metal parts help analyze the impact of design modifications, optimize processing technology, and improve production efficiency. Three-dimensional parametric modeling provides an accurate three-dimensional model of sheet metal parts, which facilitates precise processing and inspection. Material property analysis and filling help create a parametric model that reflects the actual material properties and improves the accuracy and reliability of the simulation. The simulation of the processing technology model can predict problems in the actual processing process, optimize process parameters, reduce production costs, and improve the quality of the finished product.

[0014] Optionally, step S4 is specifically: Step S41: extracting structural features of the simulated finished product from the sheet metal part processing simulation data, thereby obtaining the simulated finished product structural data; Step S42: performing geometric parameter description according to the processing simulation finished product structure data, thereby obtaining the processing simulation finished product data; Step S43: extracting simulated finished product surface features from the processed simulated finished product data, thereby obtaining simulated finished product surface data; Step S44: Calculating the surface structure similarity of the simulated finished product surface data and the actual finished product surface data, thereby obtaining finished product surface similarity data; Step S45: clustering the simulated finished product surface data and the actual finished product surface data according to the finished product surface similarity data to obtain clustered finished product surface data; Step S46: Performing simulated finished product surface defect evaluation on the clustered finished product surface data, thereby obtaining simulated processed surface finished product defect data.

[0015] The present invention can obtain a detailed understanding of the simulation results and reveal the changes in the structure during the processing process by extracting the structural features of the finished product of the processing simulation. In this way, potential design problems or processing deviations can be identified at an early stage, which is helpful for timely adjustment of the design or processing technology. The geometric parameterization description converts the structural data of the simulated finished product into a parametric model, which helps to quantify and standardize the geometric features of the finished product. This description method makes the analysis of the geometric features of the finished product more systematic and scientific, which is helpful for subsequent data processing and comparison. Extracting surface features can provide detailed information about the surface quality of the finished product. These feature information is very important for evaluating the processing effect, identifying surface defects and performing quality control, and is helpful for improving the surface treatment process and optimizing the processing parameters. Calculating the surface structural similarity between the simulated finished product and the actual finished product can evaluate the accuracy of the simulation process and the effect of the actual processing. High similarity indicates that the simulation results are reliable, and low similarity indicates that there is a processing deviation or simulation error, which provides a basis for further adjustment. Finished products with similar surface structures are clustered to identify and classify finished products with different processing effects. This classification helps to carry out batch quality control, discover potential common problems, and optimize the production process to improve the overall product quality and consistency. Surface defect evaluation of clustered data can discover and quantify defects in the processing process. Understanding the defects that may occur during simulated machining helps optimize the machining process and formulate improvement measures in advance, thereby reducing the defect rate in actual production and improving the overall quality of the finished product.

[0016] Optionally, step S46 is specifically: Step S461: performing finished product surface error calculation on the clustered finished product surface data, thereby obtaining simulated finished product surface error data; Step S462: performing statistics on the error difference of the finished product surface area according to the simulated finished product surface error data, thereby obtaining high-error simulated finished product surface area data and low-error simulated finished product surface area data; Step S463: performing surface flatness fluctuation statistics according to the simulated finished product surface data, thereby obtaining high-fluctuation simulated finished product surface area data and low-fluctuation simulated finished product surface area data; Step S464: performing a surface area intersection operation on the surface area data of the high-error simulated finished product and the surface area data of the high-fluctuation simulated finished product, thereby obtaining the simulated finished product defect area data; performing a surface area intersection operation on the surface area data of the low-error simulated finished product and the surface area data of the low-fluctuation simulated finished product, thereby obtaining the simulated finished product normal area data; Step S465: merging the simulated finished product area data and the simulated finished product normal area data to obtain simulated processed surface finished product defect data.

[0017] The present invention calculates the surface error data of the finished product, which can reveal the actual error situation of the finished product surface and provide basic data for subsequent regional analysis and optimization. This is a key link to ensure that the quality of the finished product meets the standards. By performing regional statistics on the error data, high-error and low-error areas are distinguished, which helps to locate the problem areas on the surface of the finished product, making targeted repairs and improvements more targeted and efficient. Analyzing the height of the surface fluctuation helps to understand the stability of the surface flatness of the finished product. This process can identify surface fluctuation problems, thereby optimizing the production process and reducing problems caused by surface irregularities. By performing intersection operations on the error and fluctuation areas, the defective areas and normal areas on the surface of the finished product can be accurately identified. This analysis helps to further improve the production process and reduce the defect rate. The defective area and normal area data are combined to provide the final defect data, support decision-making and the implementation of improvement measures, thereby improving the quality and production efficiency of the final product.

[0018] Optionally, step S5 specifically includes: Step S51: extracting stress distribution features from sheet metal part processing simulation data to obtain stress distribution data in the simulation processing stage, and classifying the processing stages according to the stress distribution data in the simulation processing stage to obtain stress distribution data in the laser processing stage and stress distribution data in the bending processing stage; Step S52: classifying the stress distribution data of the laser processing stage into stress distribution data of the parts structure, thereby obtaining the stress concentration part structure data of the laser processing and the stress uniform part structure data of the laser processing; Step S53: classifying the stress distribution data of the bending process stage into parts structure stress distribution data, so as to obtain the bending process stress concentration part structure data and the bending process stress uniform part structure data; Step S54: performing part structure intersection operation on the laser processing stress concentration part structure data and the bending processing stress concentration part structure data, so as to obtain low stress uniformity part structure data; performing part structure intersection operation on the laser processing stress uniform part structure data and the bending processing stress uniform part structure data, so as to obtain high stress uniformity part structure data; Step S55: merging the low stress uniformity part structure data and the high stress uniformity part structure data to obtain simulated processing stress uniformity data; Step S56: Calculate the surface quality influencing factor based on the simulated processing stress uniformity data and the simulated processing surface finished product defect data, so as to obtain the processing surface quality influencing factor data.

[0019] The present invention can provide an in-depth understanding of the stress distribution of sheet metal parts in different processing stages (such as laser processing and bending processing). This provides basic data for subsequent processing optimization. By analyzing the stress distribution, stress concentration areas that may occur during the processing process can be identified, which is crucial for improving the processing quality and durability of parts. Classifying the stress distribution data according to the laser processing and bending processing stages helps to more clearly understand the specific impact of different processing stages on the stress distribution of parts. This classification can help optimize the processing parameters of each stage to reduce stress concentration and improve the overall performance and quality of parts. Classifying the stress distribution data in the laser processing stage into stress concentrated and stress uniform part structure data can identify which structures may experience stress concentration during the laser processing process. This classification helps to adjust the laser processing parameters or processes to reduce stress concentration and improve the structural stability and reliability of the parts. Similarly, classifying the stress distribution in the bending processing stage helps to identify which part structures will experience stress concentration during the bending process. This analysis can guide the optimization of the bending process to reduce stress concentration and enhance the mechanical properties and durability of the parts. By performing an intersection operation on the stress concentration data of the laser processing and bending processing stages, part structures with high stress concentration areas in both can be identified, so that the improvement of these structures can be focused on. Performing an intersection operation on the stress uniform part structures can find part structures with stress uniformity in both, which helps to design parts with more stability and reliability during processing. By merging the part structure data with low stress uniformity and high stress uniformity, the impact of different stress uniformities on part quality can be comprehensively considered to obtain more comprehensive stress uniformity data. This merger can help the design and manufacturing team identify which processing processes and parameters can best optimize stress uniformity, thereby improving the overall processing quality of the parts. By combining simulated processing stress uniformity data and surface finished product defect data, the impact of stress uniformity on the quality of the processed surface can be deeply understood. This analysis helps to identify the key factors that affect surface quality, thereby guiding the improvement of processing technology, reducing surface defects, and improving the appearance and functional quality of parts.

[0020] Optionally, step S56 is specifically: S561: extracting defect surface structure features from the simulated processed surface finished product defect data, thereby obtaining defect surface structure data; S562: extract stress concentration structure from simulated processing stress uniformity data, thereby obtaining stress concentration part structure data; S563: performing part structure intersection operation on the defect surface structure data and the stress concentration part structure data, thereby obtaining defect structure part data; S564: extracting defective structure processing simulation parameters from the sheet metal part processing simulation data according to the defective structure part data, thereby obtaining a defective structure processing simulation parameter group; S565: extracting stress application features according to the defect structure processing simulation parameter group, thereby obtaining processing stress application data; S566: Construct a defect influence factor mathematical model based on the processing stress application data and the defective structural part data, and calculate the structural surface defect influence factor based on the defect influence factor mathematical model to obtain the processing surface quality influence factor data.

[0021] The present invention can accurately identify and classify different types of surface defects by extracting the surface structural features of the defects. This helps to understand the formation mechanism and characteristics of the defects, thereby providing data support for subsequent corrective measures. Understanding the specific structural features of the defects can help optimize the processing process, reduce or eliminate the factors that cause these defects, and improve the quality of the finished product. The data obtained by feature extraction provides a basis for subsequent analysis and decision-making, making defect management and repair more scientific and efficient. Extracting stress concentration structures can help identify high stress areas in parts. This is very important for predicting the failure risk of parts, and measures can be taken in advance to avoid potential structural problems. By analyzing the stress concentration area, the part design can be optimized, the structure can be adjusted to reduce stress concentration, and the service life and reliability of the parts can be improved. The extracted stress concentration data helps to improve the accuracy of the processing simulation, thereby making the stress prediction more accurate and optimizing the stress distribution control during the processing process. By combining the defect data and the stress concentration data through the intersection operation, more comprehensive part structural defect information can be obtained. This helps to understand how defects are affected by stress distribution. The intersection data can guide how to repair defects in specific stress concentration areas, thereby improving the pertinence and effectiveness of the repair work. Comprehensive analysis of defects and stresses helps to optimize the processing process and design, and ultimately improve the overall quality of the parts. Extracting the processing simulation parameters of defective structures can help set the specific parameters required in the processing process to reduce the occurrence of defects. Through accurate simulation parameters, the accuracy of sheet metal parts processing simulation can be improved, so as to better predict the processing effect and defect situation. According to the extraction results of simulation parameters, the actual processing technology can be adjusted and optimized to improve production efficiency and product quality. Extracting stress application characteristics can help understand the influence of different stress conditions on the formation and development process of defects in actual processing. By analyzing the stress application characteristics, the strategy and parameters of stress application can be optimized to reduce the occurrence of defects in processing. The extraction of stress application characteristics helps to improve the production process and processing conditions, and improve the surface quality and overall performance of the product. Constructing a mathematical model can systematically describe the influence of defects on the quality of the processed surface, and provide theoretical support for understanding and predicting processing defects. Through the calculation of the influencing factor model, the most critical defect factors can be identified, and targeted measures can be taken to optimize them, so as to improve the stability of the processing process and the quality of the finished product. By calculating the influencing factor data of the processed surface quality, quality control can be carried out more scientifically and effective quality improvement strategies can be formulated.

[0022] Optionally, the present invention further provides a system based on intelligent generation of a sheet metal part process model, which is used to execute the method based on intelligent generation of a sheet metal part process model as described above. The system based on intelligent generation of a sheet metal part process model comprises: The topological structure analysis module is used to obtain the structural data of the sheet metal parts processing workshop, and perform the sheet metal parts processing flow topological structure analysis on the sheet metal parts processing workshop structural data, so as to obtain the sheet metal parts processing flow topological structure; perform processing parameter mapping on the sheet metal parts processing flow topological structure, so as to obtain the sheet metal parts processing process model; The sheet metal parts processing simulation module is used to obtain the design data of the sheet metal parts to be processed, and perform three-dimensional parameter modeling on the design data of the sheet metal parts to be processed, so as to obtain the three-dimensional model of the sheet metal parts; the sheet metal parts processing simulation is performed on the three-dimensional model of the sheet metal parts through the sheet metal parts processing process model, so as to obtain the sheet metal parts processing simulation data; The historical finished product feature integration module is used to integrate the historical finished product features of sheet metal parts with the design data of sheet metal parts to be processed, so as to obtain the historical finished product data of sheet metal parts; the finished product surface features are extracted based on the historical finished product data of sheet metal parts, so as to obtain the actual finished product surface data; The finished product surface defect evaluation module is used to perform parameterized description of the sheet metal parts processing simulation data to obtain the processing simulation finished product data, and to perform finished product surface defect evaluation on the processing simulation finished product data and the actual finished product surface data to obtain the simulated processing surface finished product defect data; The surface quality influencing factor calculation module is used to evaluate the uniformity of simulated processing stress distribution on the sheet metal parts processing simulation data, so as to obtain the simulated processing stress uniformity data, and calculate the surface quality influencing factor based on the simulated processing stress uniformity data and the simulated processing surface finished product defect data, so as to obtain the processing surface quality influencing factor data; The processing parameter combination optimization module is used to optimize the processing parameter combination of the sheet metal part processing process model according to the processing surface quality influencing factor data, so as to obtain the sheet metal part optimized processing process model, and upload it to the sheet metal part processing management platform to perform the sheet metal part simulation generation task.

[0023] The system of the present invention is based on intelligent generation of sheet metal part process models. The system can implement any one of the methods of the present invention based on intelligent generation of sheet metal part process models. It is used to combine the operation and signal transmission medium between various modules to complete the method based on intelligent generation of sheet metal part process models. The internal modules of the system cooperate with each other to improve the accuracy of the sheet metal part process model. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings: Figure 1 A schematic diagram of the steps of the method for intelligently generating a sheet metal part process model according to the present invention; Figure 2 Detailed step flow diagram of step S1 in the present invention; Figure 3 Detailed step flow diagram of step S2 in the present invention; The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0025] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0026] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0027] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0028] To achieve this, please refer to Figures 1 to 3 The present invention provides a method for intelligently generating a sheet metal part process model, the method comprising the following steps: Step S1: Acquire the sheet metal parts processing workshop structure data, and perform sheet metal parts processing flow topology structure analysis on the sheet metal parts processing workshop structure data, thereby obtaining the sheet metal parts processing flow topology structure; perform processing parameter mapping on the sheet metal parts processing flow topology structure, thereby obtaining the sheet metal parts processing process model; In this embodiment, first, the structural data of the sheet metal parts processing workshop is obtained through the sheet metal parts processing management platform of the processing workshop, including the location of each processing station, equipment type, workflow and other information. By performing topological structure analysis on these structural data, a topological diagram of the sheet metal parts processing process is drawn. This topological structure diagram will show the workflow and processing sequence between each station. Next, these topological structure diagrams are mapped with processing parameters, such as machine tool type, processing time, process steps and other parameters. These mapping results are used to construct a sheet metal parts processing process model, including specific processing requirements, processing steps and parameter settings for each station. For example, CAD software is used to model the workshop structure data, and a flowchart tool is used to analyze the workflow between stations, and finally a processing process topological diagram is generated. Then, the engineering management software is used to map the processing parameters of the machine tool to the topological diagram to generate a process model containing detailed processing steps and parameters.

[0029] Step S2: obtaining the design data of the sheet metal part to be processed, and performing three-dimensional parameter modeling on the design data of the sheet metal part to be processed, thereby obtaining a three-dimensional model of the sheet metal part; performing sheet metal part processing simulation on the three-dimensional model of the sheet metal part through a sheet metal part processing process model, thereby obtaining sheet metal part processing simulation data; In this embodiment, the design data of the sheet metal parts to be processed is obtained through the sheet metal parts processing management platform of the processing workshop, and the design data is three-dimensionally modeled using 3D modeling software (such as SolidWorks or CATIA) to obtain a three-dimensional model of the sheet metal parts. Next, the constructed three-dimensional model of the sheet metal parts is input into the processing simulation software (such as VERICUT or DEFORM), and the processing simulation is performed based on the obtained sheet metal parts processing process model. This simulation process generates sheet metal parts processing simulation data, including processing path, processing time, material removal amount and other information. For example, the design drawings are input into SolidWorks, and a detailed model of the sheet metal parts is generated by creating a three-dimensional model function. Then, this model is imported into VERICUT, and the processing simulation is run after setting the simulation parameters through the sheet metal parts processing process model to obtain detailed processing process data.

[0030] Step S3: integrating the features of the historical sheet metal parts processed by the design data of the sheet metal parts to be processed, thereby obtaining the data of the historical sheet metal parts processed by the finished products; extracting the surface features of the processed products according to the historical sheet metal parts processed by the finished products data, thereby obtaining the surface data of the actual processed products; In this embodiment, data is collected from historical sheet metal parts processing products, and the characteristic information of these products is integrated, including surface texture, dimensional tolerance, etc. By analyzing these data, the surface characteristics of the processed products, such as surface roughness, defect type, etc., are extracted. These characteristic data will be used to compare and evaluate the difference between the current processing simulation data and the actual finished product. Digital measurement tools can be used to perform surface inspection on historical finished products, and the measured data can be input into data analysis software to extract and record surface characteristic information, including surface roughness, dimensional deviation, etc.

[0031] Step S4: performing parameterized description of the sheet metal part processing simulation data to obtain processing simulation product data, and performing finished product surface defect evaluation on the processing simulation product data and the actual finished product surface data to obtain simulated processing surface finished product defect data; In this embodiment, the obtained sheet metal parts processing simulation data is parameterized, such as the surface roughness and dimensional error of the simulated finished product. Then, it is compared with the extracted actual finished product surface data to evaluate whether there are defects on the processing simulation surface. Using statistical analysis methods, the processing simulation surface defect data, such as surface unevenness, scratches, etc., are obtained. For example, in the data analysis software, the processing simulation data is compared with the actual finished product data, and the defect index is calculated using statistical tools to generate a defect report.

[0032] Step S5: evaluating the uniformity of simulated processing stress distribution on the sheet metal part processing simulation data, thereby obtaining simulated processing stress uniformity data, and calculating the surface quality influencing factor based on the simulated processing stress uniformity data and the simulated processing surface finished product defect data, thereby obtaining processing surface quality influencing factor data; In this embodiment, stress distribution analysis is performed on the processing simulation data to evaluate the stress uniformity during the simulated processing. This includes calculating the stress distribution and uniformity index. Based on the stress uniformity data and the obtained surface defect data, the factors affecting the processing surface quality are calculated, such as the influence of stress concentration, processing temperature and other factors on the surface quality of the finished product. Finite element analysis software (such as ANSYS) can be used to perform stress analysis and derive stress distribution diagrams. Combined with the surface defect data, a custom influencing factor calculation formula is used to obtain detailed data on the surface quality influencing factors.

[0033] Step S6: Optimize the processing parameter combination of the sheet metal part processing model according to the processing surface quality influencing factor data, so as to obtain the sheet metal part optimized processing model, and upload it to the sheet metal part processing management platform to execute the sheet metal part simulation generation task.

[0034] In this embodiment, the sheet metal parts processing process model is optimized according to the obtained surface quality influencing factor data. This includes adjusting the processing parameters and improving the process steps according to the surface quality influencing factors to improve the quality of the processed surface. The optimized process model will be uploaded to the sheet metal parts processing management platform, which will use the new process model to simulate and generate tasks for sheet metal parts to verify the optimization effect. In the process optimization software, the processing parameters, such as cutting speed, feed rate, etc., can be adjusted according to the influence of the processing parameters on the processing quality in the surface quality influencing factors, and the optimization results can be saved. After uploading the optimized process model through the management platform, the platform will automatically generate simulation tasks to verify the effectiveness of the new process model.

[0035] Optionally, step S1 specifically includes: Step S11: Acquire the sheet metal parts processing workshop structure data, and extract the workshop processing component structure from the sheet metal parts processing workshop structure data, so as to obtain the processing workshop processing structure data; In this embodiment, when obtaining the structural data of the sheet metal parts processing workshop, it is first necessary to measure and record all the processing equipment in the workshop in detail, including the size, location, function and working range of the equipment. Laser scanning technology can be used to obtain the three-dimensional model of the workshop, and then CAD software can be used to extract structural data to identify various processing components in the workshop, such as cutting machines, bending machines, welding machines, etc. Finally, these data are integrated to form a complete processing workshop structure data map. The structural composition of the entire sheet metal parts processing workshop can also be directly obtained through the sheet metal parts processing management platform.

[0036] Step S12: performing a topological structure analysis of the sheet metal parts processing flow according to the processing structure data of the processing workshop, thereby obtaining a topological structure of the sheet metal parts processing flow; In this embodiment, when performing topological structure analysis on the processing structure data of the sheet metal parts processing workshop, it is necessary to use graph theory methods to represent the various processing stages and processes in the processing process in the form of nodes and edges. The specific operation includes identifying each processing step (such as cutting, bending, welding) and arranging them in sequence to form a topological diagram of the processing flow. For example, the sequence of laser cutting and bending processes will determine the node connection method of the topological structure. Process modeling tools such as BPMN (Business Process Modeling Notation) can be used to analyze the workshop structure data to form a clear topological diagram of the sheet metal parts processing process.

[0037] Step S13: classifying the processing structure according to the processing structure data of the processing workshop, thereby obtaining the laser processing component structure data and the bending processing component structure data; In this embodiment, the processing technology is structurally classified based on the workshop processing structure data. The processing flow is divided into two categories: laser processing and bending processing, and the component structure data of these two types of processing are extracted respectively. The characteristics of different processing technologies can be automatically classified based on machine learning algorithms such as decision trees and random forests, thereby generating detailed structural data sets of laser processing components and bending processing components.

[0038] Step S14: simulating the sheet metal part processing conditions according to the laser processing component structure data and the bending processing component structure data, thereby obtaining a sheet metal part processing parameter set; In this embodiment, the structural data of the laser processing and bending processing components are used to simulate the processing conditions of sheet metal parts. Simulation software, such as ANSYS or SolidWorks Simulation, is used to simulate the parameter changes in the actual processing process, such as cutting speed, power and bending angle. The implementation method is to input the structural data in the simulation environment, adjust the processing parameters, verify and optimize the processing process, and finally obtain a set of accurate sheet metal parts processing parameter sets.

[0039] Step S15: mapping the processing parameters of the sheet metal part processing flow topology structure according to the sheet metal part processing parameter set, thereby obtaining a sheet metal part processing process model.

[0040] In this embodiment, according to the sheet metal parts processing parameter set, the sheet metal parts processing process topology structure is parameter mapped. The parameters of each processing step are integrated into the process topology structure to generate a detailed processing model. The processing parameter set is input into the engineering management software and mapped to the process model through the graph theory algorithm to ensure that the parameters of each step are consistent with the actual processing requirements, thereby forming a complete sheet metal parts processing process model.

[0041] Optionally, step S12 is specifically: Step S121: extracting processing structure spatial features from processing structure data of the processing workshop, thereby obtaining processing component structure spatial position data; In this embodiment, the processing structure data (such as workpiece position, shape, size, etc.) in the processing workshop is scanned and processed, and the spatial coordinate data of the processing components is obtained using a laser rangefinder or a 3D scanner. Then, the data is processed using spatial analysis software to extract the position and posture characteristics of the processing components in three-dimensional space. The spatial position data of the processing components can be extracted by performing coordinate transformation on the scanned point cloud data and converted into values ​​in the XYZ coordinate system.

[0042] Step S122: performing processing structure spatial distribution analysis according to the processing component structure spatial position data, thereby obtaining processing structure spatial distribution data; In this embodiment, the spatial distribution of the processing components is analyzed using a data analysis tool (such as a scientific computing library of MATLAB or Python) based on the obtained spatial position data. The spatial distribution map of the processing structure is generated by calculating the distance, angle and spatial distribution density between the components. A clustering algorithm, such as a K-means algorithm, can be applied to group the processing components to determine their spatial distribution characteristics and density distribution.

[0043] Step S123: integrating the processing flow path according to the processing structure spatial distribution data, thereby obtaining the processing flow path data; In this embodiment, based on the obtained processing structure spatial distribution data, the paths of each processing step are integrated. The processing flow is integrated using a path planning algorithm (such as an A* algorithm or a Dijkstra algorithm) to obtain an optimal processing path. The processing path data can be imported into a computer-aided design (CAD) software, and each processing step is simulated to finally generate a complete set of processing flow path data.

[0044] Step S124: classifying the processing path data into process paths, thereby obtaining parallel processing path data and parallel processing path data; In this embodiment, the generated processing flow path data is classified to determine the parallel processing path and the parallel processing path. The paths are analyzed and classified using a classification algorithm (such as a support vector machine or a decision tree algorithm). By analyzing the relationship between the paths, the parallel paths that need to be performed simultaneously and the parallel paths that need to rely on other paths can be distinguished, and finally the classified data are marked and saved. For example, the features of each path are extracted from the processing flow path data, including the start and end time of the path, the workpieces passed, the distance between the paths, the intersection of the paths, etc. A feature vector is constructed for each path, containing all the key attributes of the path, such as path length, processing sequence, dependency, etc. The SVM model is trained using a labeled training data set (including known parallel and parallel paths). The training data should include various types of paths and their classification labels. The classification model is trained using the SVM algorithm, and an appropriate kernel function (such as a linear kernel or a Gaussian kernel) is selected to better classify the paths. The constructed feature vector is input into the trained classification model to classify the paths. The SVM model will give the classification results for each path, while the decision tree model classifies the paths through the leaf nodes of the tree.

[0045] Step S125: performing parallel process topology analysis according to the parallel processing path data, thereby obtaining a parallel processing process topology structure; performing parallel process topology analysis according to the parallel processing path data, thereby obtaining a parallel processing process topology structure; In this embodiment, parallel process topology analysis is performed on the parallel processing path data, and parallel process topology analysis is performed on the parallel processing path data. The processing path data is modeled using a topology analysis tool in graph theory (such as Graphviz tool) to generate a topology diagram of the parallel and parallel processing flows. By analyzing the connection relationship of each processing path, the parallel and parallel process topology structures can be constructed, verified and optimized.

[0046] Step S126: topologically associating the parallel processing flow topology structure and the parallel processing flow topology structure, thereby obtaining a sheet metal part processing flow topology structure.

[0047] In this embodiment, the obtained parallel processing flow topology structure and parallel processing flow topology structure are associated to generate a comprehensive sheet metal parts processing flow topology structure. By combining the data of the parallel and parallel topology structures, the topology structures are integrated using a data fusion algorithm (such as a fusion weighted average algorithm) to generate a final sheet metal parts processing flow topology structure diagram. The data of the two topology structures are combined to generate an overall processing flow topology structure, and the topology structure is verified to ensure its accuracy and effectiveness.

[0048] Optionally, step S14 is specifically: Constructing a three-dimensional model of laser processing according to the structural data of the laser processing component, thereby obtaining a three-dimensional model of the laser processing component; In this embodiment, the geometric features and dimensional information are extracted from the structural data of the laser processed component, and a 3D model of the component is built using CAD software (such as AutoCAD or SolidWorks). Ensure that the model accurately reflects the design of the actual component, including hole positions, edges, and processing details. The ultimate goal of this step is to create a high-fidelity 3D model that can be used for subsequent simulation and analysis.

[0049] Constructing a three-dimensional model of the bending process according to the structural data of the bending process component, thereby obtaining a three-dimensional model of the bending process component; In this embodiment, information is extracted from the structural data of the bending processing component, and a three-dimensional model of the bending processing component is established using CAD software. Special attention is paid to key features such as bending angle, bending radius and material thickness in the model. The final model should have high precision to ensure that it can truly reproduce the actual bending effect during the simulation process.

[0050] Acquire sheet metal parts processing condition data, and classify the sheet metal parts processing condition data into processing condition data, so as to obtain laser processing condition data and bending processing condition data; In this embodiment, the sheet metal parts processing condition data, including material type, thickness, processing speed, etc., are collected and sorted through the sheet metal parts processing management platform. These data are classified according to the types of laser processing and bending processing to form two data sets: laser processing condition data and bending processing condition data. Each data set should record the corresponding condition parameters in detail to facilitate subsequent simulation and parameter optimization.

[0051] Performing laser processing simulation on the three-dimensional model of the laser processing component according to the laser processing condition data, thereby obtaining laser processing simulation data; In this embodiment, the three-dimensional model of the laser processing component is simulated using the laser processing condition data. According to the laser processing condition data, the laser power, cutting speed, focal length and other parameters are set in the simulation software, and the simulation is run on the three-dimensional model of the laser processing component to obtain the thermal impact, deformation and surface quality data that may be generated during the laser processing. These data can be used to optimize the processing process, reduce energy consumption and improve processing accuracy.

[0052] Perform bending simulation on the three-dimensional model of the bending component according to the bending working condition data, so as to obtain bending simulation data; In this embodiment, the three-dimensional model of the bending processing component is simulated based on the bending processing condition data. The bending angle, material rebound coefficient and mold parameters are set in the bending simulation software, and the simulation is run to obtain the stress distribution, deformation and surface quality data during the bending process. These data are helpful to improve the bending process and enhance production efficiency and quality.

[0053] Performing statistics on low-energy laser processing parameter combinations on laser processing simulation data to obtain a laser processing parameter set; In this embodiment, the laser processing simulation data is analyzed to calculate the energy consumption performance under different laser processing parameter combinations (such as power, speed, and focal length). The parameter set with the lowest energy consumption and meeting the processing quality requirements is selected. Multiple experiments are conducted to verify the stability and applicability of these parameter combinations, and finally a set of low-energy laser processing parameter sets is obtained.

[0054] Performing statistics on low-energy bending processing parameter combinations on the bending processing simulation data, thereby obtaining a bending processing parameter set; In this embodiment, the bending process simulation data is analyzed to calculate the energy consumption performance under different bending process parameter combinations (such as bending angle, speed, and mold pressure). The parameter set with the lowest energy consumption and meeting the processing accuracy requirements is selected. The effectiveness of these parameter combinations is verified through actual processing, and finally a low-energy-consumption bending process parameter set is obtained.

[0055] The sheet metal part processing parameters are integrated into the laser processing parameter set and the bending processing parameter set, so as to obtain the sheet metal part processing parameter set.

[0056] In this embodiment, the parameter sets of laser processing and bending processing are integrated to consider the comprehensive application of the two in sheet metal parts processing. During the integration process, it is necessary to consider the impact of each parameter on the overall processing effect to obtain the optimal processing parameter set. This parameter set will be used to guide actual production, optimize the processing process, and improve production efficiency and product quality.

[0057] Optionally, step S2 specifically includes: Step S21: obtaining design data of the sheet metal part to be processed, and performing sheet metal part feature extraction on the design data of the sheet metal part to be processed, thereby obtaining sheet metal part structure data and sheet metal part material data; In this embodiment, the design data of the sheet metal parts to be processed is obtained through the sheet metal parts processing management platform, which can be obtained by reading the drawing files and related parameters in the CAD system, such as dimensions, tolerances, and material specifications. Through automated software or manual extraction, the features of the sheet metal parts, such as edges, holes, bends, and shear areas, are identified. This generates structural data (such as thickness, shape) and material data (such as steel type, surface treatment) for subsequent processing.

[0058] Step S22: performing sheet metal part structural processing change statistics according to the sheet metal part structural data, thereby obtaining sheet metal part structural change data; In this embodiment, based on the structural data, the changes of the parts at different processing stages are counted. For example, the changes such as thickness reduction, hole position movement or edge trimming from the design drawing to the actual processing are recorded. The structural change data are generated using data analysis tools, which can be obtained by comparing the design model with the actual processing records to ensure that the processing changes at each stage are accurately recorded.

[0059] Step S23: performing three-dimensional parametric modeling of the sheet metal part processing stage structure according to the sheet metal part structure change data, thereby obtaining a three-dimensional model of the sheet metal part; In this embodiment, the structural change data is used to perform parametric modeling through 3D modeling software. A three-dimensional model with features such as bending and cutting is created based on the recorded structural changes. For example, the bending angle and aperture size are parameterized to ensure that the model can accurately reflect the changes during the processing. The final generated three-dimensional model will be used for subsequent material analysis and simulation.

[0060] Step S24: performing material property analysis according to the material data of the sheet metal part, thereby obtaining the material property data of the sheet metal part, and filling the sheet metal part three-dimensional model with the part material property according to the material property data of the sheet metal part, thereby obtaining a sheet metal part parameter model; In this embodiment, material property data is analyzed, such as obtaining information such as the strength, hardness, and corrosion resistance of sheet metal materials through experiments or material databases. These property data are filled into the three-dimensional model to generate a parametric model. This involves testing the mechanical properties of the material and applying the test results to the model to accurately reflect the performance of the actual material.

[0061] Step S25: simulating the sheet metal part processing stage on the sheet metal part parameter model through the sheet metal part processing process model, thereby obtaining sheet metal part processing simulation data.

[0062] In this embodiment, a sheet metal parts processing model is used to perform virtual processing simulation. The processing model is used to simulate various steps in the actual production process, such as bending, stamping, welding, etc. The simulation results generate processing simulation data, including the shape and size changes of the finished product, allowing analysis of potential process problems and optimization of the processing process.

[0063] Optionally, step S4 is specifically: Step S41: extracting structural features of the simulated finished product from the sheet metal part processing simulation data, thereby obtaining the simulated finished product structural data; In this embodiment, the sheet metal parts are first modeled in detail using computer-aided design (CAD) software. Then, the model is simulated using finite element analysis (FEA) tools, and the simulation process includes various processing operations such as stamping, bending, and cutting. The structural characteristics of the finished product are extracted through the simulation results, such as the thickness distribution and deformation degree of the sheet. These characteristic data include the processed geometric shape, stress distribution, and deformation, and finally form the structural data of the simulated finished product.

[0064] Step S42: performing geometric parameter description according to the processing simulation finished product structure data, thereby obtaining the processing simulation finished product data; In this embodiment, according to the obtained processing simulation finished product structure data, a parametric modeling tool is used to perform geometric parameter description of the data. For example, by defining size parameters, shape characteristics and tolerance ranges, the simulation data is converted into a parametric model. In this way, the geometric characteristics of the finished product structure can be described more flexibly, and detailed processing simulation finished product data can be generated, including the specific values ​​and variation ranges of each parameter.

[0065] Step S43: extracting simulated finished product surface features from the processed simulated finished product data, thereby obtaining simulated finished product surface data; In this embodiment, surface feature extraction is performed on the processing simulation finished product data. Image processing technology or three-dimensional scanning equipment is used to obtain data on the surface of the finished product, and surface features such as surface roughness, texture distribution, defects, etc. are extracted. By analyzing the surface data, such as using surface analysis software or algorithms, detailed data on the surface of the simulated finished product is obtained, including surface irregularities and defect types.

[0066] Step S44: Calculating the surface structure similarity of the simulated finished product surface data and the actual finished product surface data, thereby obtaining finished product surface similarity data; In this embodiment, the simulated finished product surface data is compared with the actual processed finished product surface data to calculate the similarity of the surface structure. This step involves calculating similarity indicators of surface features, such as mean square error (MSE), correlation coefficient or similarity score. Through these calculations, the finished product surface similarity data is obtained, which can reflect the degree of fit between the simulated finished product surface and the actual finished product surface.

[0067] Step S45: clustering the simulated finished product surface data and the actual finished product surface data according to the finished product surface similarity data to obtain clustered finished product surface data; In this embodiment, based on the finished product surface similarity data, cluster analysis is performed on the simulated finished product surface data and the actual finished product surface data. A clustering algorithm (such as K-means, hierarchical clustering, etc.) is used to divide the data into several groups to form clustered data of finished products with similar surface structures. In this way, groups of finished products with similar surface features can be identified, thereby helping to make more targeted adjustments and optimizations during the production process.

[0068] Step S46: Performing simulated finished product surface defect evaluation on the clustered finished product surface data, thereby obtaining simulated processed surface finished product defect data.

[0069] In this embodiment, defect assessment is performed on the clustered finished product surface data. The type and severity of surface defects are assessed using a defect detection algorithm or manual inspection. By comparing the simulated finished product surface defect data with the actual finished product surface data, simulated processed surface finished product defect data is obtained, including the specific location, type, and size of the defects. These data are helpful to further optimize the processing technology and improve product quality.

[0070] Optionally, step S46 is specifically: Step S461: performing finished product surface error calculation on the clustered finished product surface data, thereby obtaining simulated finished product surface error data; In this embodiment, a high-precision surface measurement device (such as a laser scanner or a three-dimensional coordinate measuring machine) is used to scan the surface of the clustered finished product to obtain surface point cloud data. These point cloud data (actual finished product surface data) are compared with the simulated finished product surface data, and the surface error data of the finished product is obtained by calculating the deviation value of each surface point. The least squares fitting method can be used to smooth the error data, or the interpolation method can be used to fill in the missing data. Specifically, for example, after scanning a batch of metal parts, the scanned data is compared point by point with the points on the surface of the simulated finished product of the design model, the error of each point is calculated, and the error is presented in the form of a grid to form the surface error data of the finished product.

[0071] Step S462: performing statistics on the error difference of the finished product surface area according to the simulated finished product surface error data, thereby obtaining high-error simulated finished product surface area data and low-error simulated finished product surface area data; In this embodiment, the surface of the finished product is divided into several regions according to the error data obtained. For example, the surface error data is grouped using the k-means clustering algorithm to identify high error regions and low error regions. Then, the mean and variance of the error are calculated for each region, and the error difference of each region is counted. For example, the region with an error greater than a certain threshold (e.g., 5 microns) is marked as a high error region, and the region with an error less than the threshold is marked as a low error region, and the specific error value of each region is recorded.

[0072] Step S463: performing surface flatness fluctuation statistics according to the simulated finished product surface data, thereby obtaining high-fluctuation simulated finished product surface area data and low-fluctuation simulated finished product surface area data; In this embodiment, the surface data of the finished product is subjected to fluctuation analysis. First, the surface point cloud data needs to be filtered to remove noise and abnormal points. The data is analyzed in the frequency domain using techniques such as Fourier transform or wavelet transform to extract the fluctuation characteristics of the surface flatness. According to the mean and variance of the fluctuation characteristics, high fluctuation areas and low fluctuation areas are divided. For example, if the standard deviation of the fluctuation is greater than a certain threshold (such as 1 micron), it is marked as a high fluctuation area, otherwise it is a low fluctuation area. The specific fluctuation values ​​of these areas are recorded to form high fluctuation and low fluctuation area data.

[0073] Step S464: performing a surface area intersection operation on the surface area data of the high-error simulated finished product and the surface area data of the high-fluctuation simulated finished product, thereby obtaining the simulated finished product defect area data; performing a surface area intersection operation on the surface area data of the low-error simulated finished product and the surface area data of the low-fluctuation simulated finished product, thereby obtaining the simulated finished product normal area data; In this embodiment, an intersection operation is required. First, the data of the high error area and the high fluctuation area are superimposed to identify the area with both high error and high fluctuation. Boolean operation or image processing technology (such as binarization and logical AND operation) is used to implement the intersection operation. Similarly, the data of the low error area and the low fluctuation area are subjected to intersection operation. In specific operation, GIS software or special surface analysis software can be used to complete the regional intersection operation to generate simulated finished product defect area data and simulated finished product normal area data.

[0074] Step S465: merging the simulated finished product area data and the simulated finished product normal area data to obtain simulated processed surface finished product defect data.

[0075] In this embodiment, it is necessary to merge the regions. Integrate the defect region data with the normal region data for subsequent analysis. For example, mark the defect region data in red on the surface map, and mark the normal region data in green. Use data merging tools or image processing software to merge the two regions of data into a complete finished product surface state map. For example, merge the point cloud data of the defect region and the normal region to generate a comprehensive finished product surface defect map for further quality control and improvement measures.

[0076] Optionally, step S5 specifically includes: Step S51: extracting stress distribution features from sheet metal part processing simulation data to obtain stress distribution data in the simulation processing stage, and classifying the processing stages according to the stress distribution data in the simulation processing stage to obtain stress distribution data in the laser processing stage and stress distribution data in the bending processing stage; In this embodiment, when processing the simulation data of the sheet metal parts, a stress distribution diagram is generated using finite element analysis software. The data can include stress conditions at different processing stages. For example, in the laser processing stage, the simulation results show that stress concentration is in a local area, while in the bending processing stage, the global stress distribution is uniform. These stress data are exported, and an algorithm is applied to classify the data into laser processing stress distribution data and bending processing stress distribution data.

[0077] Step S52: classifying the stress distribution data of the laser processing stage into stress distribution data of the parts structure, thereby obtaining the stress concentration part structure data of the laser processing and the stress uniform part structure data of the laser processing; In this embodiment, a clustering algorithm is used to classify the stress distribution data in the laser processing stage, assuming that the data is divided into two categories: "stress concentration" and "uniform stress". By analyzing the stress distribution diagram, it can be determined which parts have stress concentration after laser processing (for example, the edge part) and which parts maintain a relatively uniform stress distribution (for example, the central area).

[0078] Step S53: classifying the stress distribution data of the bending process stage into parts structure stress distribution data, so as to obtain the bending process stress concentration part structure data and the bending process stress uniform part structure data; In this embodiment, similar classification is performed on the stress distribution data of the bending process stage. For example, by analyzing the stress distribution of the parts after bending, it is found that stress is concentrated in some areas (such as at the bending edge), while stress is evenly distributed in other areas (such as near the bending centerline). The classification results should include stress concentration data and stress uniformity data of the bending process.

[0079] Step S54: performing part structure intersection operation on the laser processing stress concentration part structure data and the bending processing stress concentration part structure data, so as to obtain low stress uniformity part structure data; performing part structure intersection operation on the laser processing stress uniform part structure data and the bending processing stress uniform part structure data, so as to obtain high stress uniformity part structure data; In this embodiment, the stress concentration data of the laser processing and bending processing stages are subjected to intersection operations. Assuming that in the overlapped parts of the laser processing stress concentration area and the bending processing stress concentration area, these areas will show data with low stress uniformity. In contrast, similar operations are performed on the stress uniformity data to find the overlapping areas and obtain structural data with high stress uniformity.

[0080] Step S55: merging the low stress uniformity part structure data and the high stress uniformity part structure data to obtain simulated processing stress uniformity data; In this embodiment, the data of low stress uniformity and high stress uniformity are combined. For example, the overall stress uniformity of different part structures after simulated processing is calculated, which may involve integrating the data of high and low stress uniformity to obtain a comprehensive stress uniformity data set.

[0081] Step S56: Calculate the surface quality influencing factor according to the simulated processing stress uniformity data and the simulated processing surface finished product defect data, so as to obtain the processing surface quality influencing factor data.

[0082] In this embodiment, the obtained simulated processing stress uniformity data and the defect data of the finished surface (such as surface cracks, deformation, etc.) are used for analysis. Influencing factors are calculated, such as whether material stress concentration is significantly associated with the occurrence of defects, so as to obtain the influencing factor data of surface quality.

[0083] Optionally, step S56 is specifically: S561: extracting defect surface structure features from the simulated processed surface finished product defect data, thereby obtaining defect surface structure data; In this embodiment, a three-dimensional laser scanner is used to perform high-resolution scanning on the simulated processed metal surface to obtain detailed point cloud data of the surface. Data processing software is used to filter noise and reconstruct the surface of the scanned point cloud data, and feature extraction algorithms (such as normal-based feature extraction or curvature analysis) are used to identify various defect features on the surface. For example, by analyzing the changes in the surface normal, surface depressions, cracks and other defect types are extracted. Finally, defect surface structure data is generated, including features such as the location, size and shape of the defect. Features such as the defect location, size and shape can also be extracted from the finished defect data of the simulated processed surface that has been defined as a defect.

[0084] S562: extract stress concentration structure from simulated processing stress uniformity data, thereby obtaining stress concentration part structure data; In this embodiment, for the stress uniformity data in the simulated processing, finite element analysis software (such as ANSYS or Abaqus) is first used to simulate the stress field. Through stress field analysis, stress concentration areas can be identified. These areas are usually in places with complex geometric shapes or geometric discontinuities. The stress concentration detection algorithm is applied to extract the geometric features of the stress concentration area (such as hole edges, grooves, etc.). Finally, stress concentration part structure data is generated, including the location of the stress concentration point, the distribution of stress values, and the geometric shape of the stress concentration area.

[0085] S563: performing part structure intersection operation on the defect surface structure data and the stress concentration part structure data, thereby obtaining defect structure part data; In this embodiment, the obtained defect surface structure data and the obtained stress concentration part structure data are subjected to intersection operation. First, the two sets of data are converted into a unified coordinate system. Then, the two data sets are operated using an intersection operation algorithm (such as a Boolean operation) to find their intersection parts, which are the areas where defects and stress concentrations exist at the same time. This operation can be implemented through a specific software tool or programming algorithm, and finally the defect structure part data is obtained, indicating that defects and stress concentrations exist in these part areas at the same time.

[0086] S564: extracting defective structure processing simulation parameters from the sheet metal part processing simulation data according to the defective structure part data, thereby obtaining a defective structure processing simulation parameter group; In this embodiment, the processing simulation data of the sheet metal parts is analyzed based on the obtained defective structure part data. The defective structure data is input using processing simulation software (such as Simufact or DEFORM) to extract the parameters in the simulated processing process. Through simulation analysis, the process parameters (such as cutting speed, feed rate, tool angle, etc.) that may cause defects in the processing process are extracted. For example, in the sheet metal cutting simulation, the influence of stress and temperature on the formation of defects during the cutting process is extracted to obtain a defective structure processing simulation parameter group, including detailed data on the influence of each processing parameter on the defect.

[0087] S565: extracting stress application features according to the defect structure processing simulation parameter group, thereby obtaining processing stress application data; In this embodiment, the processing stress application feature extraction is performed based on the obtained defect structure processing simulation parameter group. Finite element analysis or special processing simulation software is used to simulate the stress application during the processing. The stress application characteristics related to the defect structure are extracted, such as stress distribution, maximum stress point and stress direction. By comparing the stress application characteristics under different processing parameters, the most critical stress factor for defect formation is determined, and processing stress application data is generated, including the specific value of stress application and the impact assessment on defect formation.

[0088] S566: Construct a defect influence factor mathematical model based on the processing stress application data and the defective structural part data, and calculate the structural surface defect influence factor based on the defect influence factor mathematical model to obtain the processing surface quality influence factor data.

[0089] In this embodiment, the obtained processing stress application data and the obtained defective structure part data are used to construct a mathematical model of defect influencing factors. The model can use regression analysis, neural network or other data modeling techniques. Through model calculation, the influence factor of each factor on the processing surface quality is obtained. The processing stress application data can be used as the input of the model, and the defective structure part data can be used as the output variable. The model is trained to identify the law of the influence of stress application on defects. Finally, the processing surface quality influencing factor data is obtained through model calculation. For example, the influence coefficient of each processing parameter on the surface quality is obtained through regression analysis, and a report is generated to guide future processing technology optimization.

[0090] Optionally, the present invention further provides a system based on intelligent generation of a sheet metal part process model, which is used to execute the method based on intelligent generation of a sheet metal part process model as described above. The system based on intelligent generation of a sheet metal part process model comprises: The topological structure analysis module is used to obtain the structural data of the sheet metal parts processing workshop, and perform the sheet metal parts processing flow topological structure analysis on the sheet metal parts processing workshop structural data, so as to obtain the sheet metal parts processing flow topological structure; perform processing parameter mapping on the sheet metal parts processing flow topological structure, so as to obtain the sheet metal parts processing process model; The sheet metal parts processing simulation module is used to obtain the design data of the sheet metal parts to be processed, and perform three-dimensional parameter modeling on the design data of the sheet metal parts to be processed, so as to obtain the three-dimensional model of the sheet metal parts; the sheet metal parts processing simulation is performed on the three-dimensional model of the sheet metal parts through the sheet metal parts processing process model, so as to obtain the sheet metal parts processing simulation data; The historical finished product feature integration module is used to integrate the historical finished product features of sheet metal parts with the design data of sheet metal parts to be processed, so as to obtain the historical finished product data of sheet metal parts; the finished product surface features are extracted based on the historical finished product data of sheet metal parts, so as to obtain the actual finished product surface data; The finished product surface defect evaluation module is used to perform parameterized description of the sheet metal parts processing simulation data to obtain the processing simulation finished product data, and to perform finished product surface defect evaluation on the processing simulation finished product data and the actual finished product surface data to obtain the simulated processing surface finished product defect data; The surface quality influencing factor calculation module is used to evaluate the uniformity of simulated processing stress distribution on the sheet metal parts processing simulation data, so as to obtain the simulated processing stress uniformity data, and calculate the surface quality influencing factor based on the simulated processing stress uniformity data and the simulated processing surface finished product defect data, so as to obtain the processing surface quality influencing factor data; The processing parameter combination optimization module is used to optimize the processing parameter combination of the sheet metal part processing process model according to the processing surface quality influencing factor data, so as to obtain the sheet metal part optimized processing process model, and upload it to the sheet metal part processing management platform to perform the sheet metal part simulation generation task.

[0091] The system of the present invention is based on intelligent generation of sheet metal part process models. The system can implement any one of the methods of the present invention based on intelligent generation of sheet metal part process models. It is used to combine the operation and signal transmission medium between various modules to complete the method based on intelligent generation of sheet metal part process models. The internal modules of the system cooperate with each other to improve the accuracy of the sheet metal part process model.

[0092] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0093] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for intelligently generating a process model for sheet metal parts, characterized in that: The following steps are involved: Step S1: Acquire the sheet metal parts processing workshop structure data, and perform sheet metal parts processing flow topology structure analysis on the sheet metal parts processing workshop structure data, thereby obtaining the sheet metal parts processing flow topology structure; perform processing parameter mapping on the sheet metal parts processing flow topology structure, thereby obtaining the sheet metal parts processing process model; Step S2: obtaining the design data of the sheet metal part to be processed, and performing three-dimensional parameter modeling on the design data of the sheet metal part to be processed, thereby obtaining a three-dimensional model of the sheet metal part; performing sheet metal part processing simulation on the three-dimensional model of the sheet metal part through a sheet metal part processing process model, thereby obtaining sheet metal part processing simulation data; Step S3: integrating the features of the historical sheet metal parts processed by the design data of the sheet metal parts to be processed, thereby obtaining the data of the historical sheet metal parts processed by the finished products; extracting the surface features of the processed products according to the historical sheet metal parts processed by the finished products data, thereby obtaining the surface data of the actual processed products; Step S4: performing parameterized description of the sheet metal part processing simulation data to obtain processing simulation product data, and performing finished product surface defect evaluation on the processing simulation product data and the actual finished product surface data to obtain simulated processing surface finished product defect data; Step S5: evaluating the uniformity of simulated processing stress distribution on the sheet metal part processing simulation data, thereby obtaining simulated processing stress uniformity data, and calculating the surface quality influencing factor based on the simulated processing stress uniformity data and the simulated processing surface finished product defect data, thereby obtaining processing surface quality influencing factor data; Step S6: Optimize the processing parameter combination of the sheet metal part processing model according to the processing surface quality influencing factor data, so as to obtain the sheet metal part optimized processing model, and upload it to the sheet metal part processing management platform to execute the sheet metal part simulation generation task.

2. The method for intelligently generating a sheet metal part process model according to claim 1, characterized in that: Step S1 is specifically as follows: Step S11: Acquire the sheet metal parts processing workshop structure data, and extract the workshop processing component structure from the sheet metal parts processing workshop structure data, so as to obtain the processing workshop processing structure data; Step S12: performing a topological structure analysis of the sheet metal parts processing flow according to the processing structure data of the processing workshop, thereby obtaining a topological structure of the sheet metal parts processing flow; Step S13: classifying the processing structure according to the processing structure data of the processing workshop, thereby obtaining the laser processing component structure data and the bending processing component structure data; Step S14: simulating the sheet metal part processing conditions according to the laser processing component structure data and the bending processing component structure data, thereby obtaining a sheet metal part processing parameter set; Step S15: mapping the processing parameters of the sheet metal part processing flow topology structure according to the sheet metal part processing parameter set, thereby obtaining a sheet metal part processing process model.

3. The method for intelligently generating a sheet metal part process model according to claim 2, characterized in that: Step S12 is specifically as follows: Step S121: extracting processing structure spatial features from processing structure data of the processing workshop, thereby obtaining processing component structure spatial position data; Step S122: performing processing structure spatial distribution analysis according to the processing component structure spatial position data, thereby obtaining processing structure spatial distribution data; Step S123: integrating the processing flow path according to the processing structure spatial distribution data, thereby obtaining the processing flow path data; Step S124: classifying the processing path data into process paths, thereby obtaining parallel processing path data and parallel processing path data; Step S125: performing parallel process topology analysis according to the parallel processing path data, thereby obtaining a parallel processing process topology structure; performing parallel process topology analysis according to the parallel processing path data, thereby obtaining a parallel processing process topology structure; Step S126: topologically associating the parallel processing flow topology structure and the parallel processing flow topology structure, thereby obtaining a sheet metal part processing flow topology structure.

4. The method for intelligently generating a sheet metal part process model according to claim 2, characterized in that: Step S14 is specifically as follows: Constructing a three-dimensional model of laser processing according to the structural data of the laser processing component, thereby obtaining a three-dimensional model of the laser processing component; Constructing a three-dimensional model of the bending process according to the structural data of the bending process component, thereby obtaining a three-dimensional model of the bending process component; Acquire sheet metal parts processing condition data, and classify the sheet metal parts processing condition data into processing condition data, so as to obtain laser processing condition data and bending processing condition data; Performing laser processing simulation on the three-dimensional model of the laser processing component according to the laser processing condition data, thereby obtaining laser processing simulation data; Perform bending simulation on the three-dimensional model of the bending component according to the bending working condition data, so as to obtain bending simulation data; Performing statistics on low-energy laser processing parameter combinations on laser processing simulation data to obtain a laser processing parameter set; Performing statistics on low-energy bending processing parameter combinations on the bending processing simulation data, thereby obtaining a bending processing parameter set; The sheet metal part processing parameters are integrated into the laser processing parameter set and the bending processing parameter set, so as to obtain the sheet metal part processing parameter set.

5. The method for intelligently generating a sheet metal part process model according to claim 1, characterized in that: Step S2 is specifically as follows: Step S21: obtaining design data of the sheet metal part to be processed, and performing sheet metal part feature extraction on the design data of the sheet metal part to be processed, thereby obtaining sheet metal part structure data and sheet metal part material data; Step S22: performing sheet metal part structural processing change statistics according to the sheet metal part structural data, thereby obtaining sheet metal part structural change data; Step S23: performing three-dimensional parametric modeling of the sheet metal part processing stage structure according to the sheet metal part structure change data, thereby obtaining a three-dimensional model of the sheet metal part; Step S24: performing material property analysis according to the material data of the sheet metal part, thereby obtaining the material property data of the sheet metal part, and filling the sheet metal part three-dimensional model with the part material property according to the material property data of the sheet metal part, thereby obtaining a sheet metal part parameter model; Step S25: simulating the sheet metal part processing stage on the sheet metal part parameter model through the sheet metal part processing process model, thereby obtaining sheet metal part processing simulation data.

6. The method for intelligently generating a sheet metal part process model according to claim 1, characterized in that: Step S4 is specifically as follows: Step S41: extracting structural features of the simulated finished product from the sheet metal part processing simulation data, thereby obtaining the simulated finished product structural data; Step S42: performing geometric parameter description according to the processing simulation finished product structure data, thereby obtaining the processing simulation finished product data; Step S43: extracting simulated finished product surface features from the processed simulated finished product data, thereby obtaining simulated finished product surface data; Step S44: Calculating the surface structure similarity of the simulated finished product surface data and the actual finished product surface data, thereby obtaining finished product surface similarity data; Step S45: clustering the simulated finished product surface data and the actual finished product surface data according to the finished product surface similarity data to obtain clustered finished product surface data; Step S46: Performing simulated finished product surface defect evaluation on the clustered finished product surface data, thereby obtaining simulated processed surface finished product defect data.

7. The method for intelligently generating a sheet metal part process model according to claim 6, characterized in that: Step S46 is specifically as follows: Step S461: performing finished product surface error calculation on the clustered finished product surface data, thereby obtaining simulated finished product surface error data; Step S462: performing statistics on the error difference of the finished product surface area according to the simulated finished product surface error data, thereby obtaining high-error simulated finished product surface area data and low-error simulated finished product surface area data; Step S463: performing surface flatness fluctuation statistics according to the simulated finished product surface data, thereby obtaining high-fluctuation simulated finished product surface area data and low-fluctuation simulated finished product surface area data; Step S464: performing a surface area intersection operation on the surface area data of the high-error simulated finished product and the surface area data of the high-fluctuation simulated finished product, thereby obtaining the simulated finished product defect area data; performing a surface area intersection operation on the surface area data of the low-error simulated finished product and the surface area data of the low-fluctuation simulated finished product, thereby obtaining the simulated finished product normal area data; Step S465: merging the simulated finished product area data and the simulated finished product normal area data to obtain simulated processed surface finished product defect data.

8. The method for intelligently generating a sheet metal part process model according to claim 1, characterized in that: Step S5 is specifically as follows: Step S51: extracting stress distribution features from sheet metal part processing simulation data to obtain stress distribution data in the simulation processing stage, and classifying the processing stages according to the stress distribution data in the simulation processing stage to obtain stress distribution data in the laser processing stage and stress distribution data in the bending processing stage; Step S52: classifying the stress distribution data of the laser processing stage into stress distribution data of the parts structure, thereby obtaining the stress concentration part structure data of the laser processing and the stress uniform part structure data of the laser processing; Step S53: classifying the stress distribution data of the bending process stage into parts structure stress distribution data, so as to obtain the bending process stress concentration part structure data and the bending process stress uniform part structure data; Step S54: performing part structure intersection operation on the laser processing stress concentration part structure data and the bending processing stress concentration part structure data, so as to obtain low stress uniformity part structure data; performing part structure intersection operation on the laser processing stress uniform part structure data and the bending processing stress uniform part structure data, so as to obtain high stress uniformity part structure data; Step S55: merging the low stress uniformity part structure data and the high stress uniformity part structure data to obtain simulated processing stress uniformity data; Step S56: Calculate the surface quality influencing factor based on the simulated processing stress uniformity data and the simulated processing surface finished product defect data, so as to obtain the processing surface quality influencing factor data.

9. The method for intelligently generating a sheet metal part process model according to claim 8, characterized in that: Step S56 is specifically as follows: S561: extracting defect surface structure features from the simulated processed surface finished product defect data, thereby obtaining defect surface structure data; S562: extract stress concentration structure from simulated processing stress uniformity data, thereby obtaining stress concentration part structure data; S563: performing part structure intersection operation on the defect surface structure data and the stress concentration part structure data, thereby obtaining the defect structure part data; S564: extracting defective structure processing simulation parameters from the sheet metal part processing simulation data according to the defective structure part data, thereby obtaining a defective structure processing simulation parameter group; S565: extracting stress application features according to the defect structure processing simulation parameter group, thereby obtaining processing stress application data; S566: Construct a defect influence factor mathematical model based on the processing stress application data and the defective structural part data, and calculate the structural surface defect influence factor based on the defect influence factor mathematical model to obtain the processing surface quality influence factor data.

10. A system for intelligently generating a process model for sheet metal parts, characterized in that: For executing the method for intelligently generating a sheet metal part process model according to claim 1, the system for intelligently generating a sheet metal part process model comprises: The topological structure analysis module is used to obtain the structural data of the sheet metal parts processing workshop, and perform the sheet metal parts processing flow topological structure analysis on the sheet metal parts processing workshop structural data, so as to obtain the sheet metal parts processing flow topological structure; perform processing parameter mapping on the sheet metal parts processing flow topological structure, so as to obtain the sheet metal parts processing process model; The sheet metal parts processing simulation module is used to obtain the design data of the sheet metal parts to be processed, and perform three-dimensional parameter modeling on the design data of the sheet metal parts to be processed, so as to obtain the three-dimensional model of the sheet metal parts; the sheet metal parts processing simulation is performed on the three-dimensional model of the sheet metal parts through the sheet metal parts processing process model, so as to obtain the sheet metal parts processing simulation data; The historical finished product feature integration module is used to integrate the historical finished product features of sheet metal parts with the design data of sheet metal parts to be processed, so as to obtain the historical finished product data of sheet metal parts; the finished product surface features are extracted based on the historical finished product data of sheet metal parts, so as to obtain the actual finished product surface data; The finished product surface defect evaluation module is used to perform parameterized description of the sheet metal parts processing simulation data to obtain the processing simulation finished product data, and to perform finished product surface defect evaluation on the processing simulation finished product data and the actual finished product surface data to obtain the simulated processing surface finished product defect data; The surface quality influencing factor calculation module is used to evaluate the uniformity of simulated processing stress distribution on the sheet metal parts processing simulation data, so as to obtain the simulated processing stress uniformity data, and calculate the surface quality influencing factor based on the simulated processing stress uniformity data and the simulated processing surface finished product defect data, so as to obtain the processing surface quality influencing factor data; The processing parameter combination optimization module is used to optimize the processing parameter combination of the sheet metal part processing process model according to the processing surface quality influencing factor data, so as to obtain the sheet metal part optimized processing process model, and upload it to the sheet metal part processing management platform to perform the sheet metal part simulation generation task.

Images