A method, system, computer and storage medium for online simulation processing of special-shaped products

Abstract

The present invention relates to an online simulation processing method, system, computer and storage medium for special-shaped products, wherein the method comprises: using an imported product design file as an input product to perform initial file simulation processing to obtain a product simulation model; performing multi-dimensional sensing recognition on a preset surface defect inspection position in the product simulation model to obtain a simulation recognition signal; performing secondary simulation on the product simulation model according to the simulation recognition signal to perform defect inspection, and forming a defect database with the obtained defect data; training each defect data in the defect database to obtain corresponding correction data and forming a model correction database to adjust product processing parameters. The present invention uses product design files as input products, can achieve rapid product design iteration, save product manufacturing time, and improve defect detection efficiency by performing defect detection marking, simulation recognition processing and defect data training on the product simulation model.

Description

Technical Field

[0001] The present invention relates to the technical field of simulation processing, and in particular to an online simulation processing method, system, computer and storage medium for special-shaped products. Background Art

[0002] At present, online simulation processing is one of the methods for producing complex structural products, which is used to detect defects in products in a timely manner and improve the yield rate. In the existing simulation processing technology, surface defects of products are detected by camera vision, and product processing adjustments are made through the establishment of CAD / CAE models and sample comparison. Due to the limitations of detection technology, 360° robot camera capture detection is required. During the detection, product processing will be temporarily stopped, that is, continuous production cannot be carried out while detection is carried out, resulting in low detection efficiency and poor flexibility in identifying new defects. Summary of the invention

[0003] In view of the above-mentioned shortcomings of the prior art, the object of the present invention is to provide an online simulation processing method, system, computer and storage medium for special-shaped products, so as to solve the technical problems of low defect detection efficiency and poor flexibility in the prior art.

[0004] To achieve the above-mentioned purpose and other related purposes, a technical solution adopted by an embodiment of the present invention is:

[0005] An online simulation processing method for special-shaped products, comprising:

[0006] Using the imported product design file as an input product to perform initial file simulation processing to obtain a product simulation model;

[0007] Performing multi-dimensional sensing recognition on a preset surface defect inspection position in the product simulation model to obtain a simulation recognition signal;

[0008] Performing secondary simulation on the product simulation model according to the simulation identification signal to perform defect inspection, and forming a defect database with the obtained defect data;

[0009] Each defect data in the defect database is trained to obtain corresponding correction data and form a model correction database to adjust product processing parameters.

[0010] As a preferred solution of the invention, the process of using the imported product design file as the input product to perform initial file simulation processing to obtain a product simulation model specifically includes:

[0011] Acquire a product design file according to the product information and import the product design file as an input product;

[0012] An initial file simulation process is performed on the product design file to construct a product simulation model including product production parameters according to the product design file, wherein a surface defect inspection position is preset in the product simulation model.

[0013] As a preferred solution of the invention, the multi-dimensional sensing recognition of the preset surface defect inspection position in the product simulation model to obtain the simulation recognition signal specifically includes:

[0014] In the product simulation model, defect detection positioning marks are made according to the preset surface defect detection positions to determine the key points of defect detection;

[0015] The product simulation model is identified by a multi-dimensional sensing identification method to generate a simulation identification signal containing defect detection key points according to the defect detection positioning mark.

[0016] As a preferred solution of the invention, the secondary simulation of the product simulation model according to the simulation identification signal to perform defect inspection specifically includes:

[0017] Perform dynamic simulation of product processing according to preset product processing parameters to obtain product simulation model middleware;

[0018] Comparing the defect detection positioning mark in the obtained simulation recognition signal with the product simulation model middleware to perform a simulation defect detection every time a feature matching the defect detection positioning mark is obtained in the product simulation model middleware;

[0019] After obtaining all the features that match the defect detection positioning marks, the product simulation model is simulated twice so that the final product simulation model includes the results of each simulation defect detection.

[0020] As a preferred solution of the invention, when performing dynamic simulation of product processing, the product simulation model is subjected to motion simulation control to simulate the motion state of the product during the processing;

[0021] As a preferred solution of the invention, when performing dynamic simulation of product processing, environmental parameters are also simulated and controlled to simulate the processing environment of the product during the processing.

[0022] As a preferred solution of the invention, the defect data includes the result of each simulation defect detection, and the training of each defect data in the defect database to obtain corresponding correction data and form a model correction database to adjust product processing parameters specifically includes:

[0023] Calculate and train each defect data according to a preset training model to obtain correction data according to the deviation between the defect data and the standard data;

[0024] The correction data and defect data are matched one by one to form a model correction database for adjusting the corresponding product processing parameters.

[0025] In order to solve the above technical problems, an embodiment of the present invention further provides an online simulation processing system for special-shaped products, comprising:

[0026] A model generation unit, used for performing initial file simulation processing on the imported product design file as an input product to obtain a product simulation model;

[0027] A simulation identification unit, used for performing multi-dimensional sensing identification on a preset surface defect inspection position in the product simulation model to obtain a simulation identification signal;

[0028] A simulation unit, used for performing secondary simulation on the product simulation model according to the simulation identification signal to perform defect inspection, and forming a defect database with the obtained defect data;

[0029] The correction processing unit is used to train each defect data in the defect database to obtain corresponding correction data and form a model correction database to adjust product processing parameters.

[0030] In order to solve the above technical problems, an embodiment of the present invention also provides a computer device, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the above-mentioned online simulation processing method for special-shaped products.

[0031] In order to solve the above technical problems, an embodiment of the present invention further provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the above-mentioned online simulation processing method for special-shaped products.

[0032] As described above, the present invention has the following beneficial effects:

[0033] The present invention uses product design files as input products. When performing product change iterations, it is only necessary to import new product design files, which can achieve rapid product design iterations and save product manufacturing time. By performing defect detection marking, simulation identification processing and defect data training on the product simulation model, a model correction database is formed. During the actual processing, the predetermined defect detection positions can be directly checked to improve the defect detection efficiency. When defects occur, the processing parameters can be adjusted in real time according to the model correction database, reducing downtime or even eliminating the need for downtime, and continuous production can be achieved while performing defect detection and correction. At the same time, when new defect situations occur, training and correction processing can also be performed simultaneously, and the flexibility of defect detection is higher. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 Shown is a method flow chart of the online simulation processing method of special-shaped products in an embodiment of the present invention.

[0036] Figure 2 Shown is a basic structural schematic diagram of an online simulation processing system for special-shaped products in an embodiment of the present invention.

[0037] Figure 3 Shown is a basic structural diagram of a computer in an embodiment of the present invention.

[0038] Figure 4 Shown is a structural schematic diagram of a specific online simulation processing system for special-shaped products in an embodiment of the present invention.

[0039] The numbers and letters in the figure represent the corresponding component names:

[0040] 501, model generation unit; 502, simulation identification unit; 503, simulation unit; 504, correction processing unit. DETAILED DESCRIPTION

[0041] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0042] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0043] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0044] See also Figure 1 The present invention provides an online simulation processing method for special-shaped products, comprising:

[0045] S100: using the imported product design file as an input product to perform initial file simulation processing to obtain a product simulation model.

[0046] S100 specifically includes:

[0047] S101. Obtain product design files according to product information and import the product design files as input products. Product design files can be uploaded by designers. Product information is associated with product design files. Product design files can be queried and obtained through product information. A product simulation model that is consistent with the actual product can be simulated and generated according to the product design files. Therefore, the product design files can be used as input products.

[0048] S102: Performing initial file simulation processing on the product design file to construct a product simulation model including product production parameters according to the product design file, wherein a surface defect inspection position is preset in the product simulation model.

[0049] In this embodiment, the existing 3D modeling software can be used to perform initial file simulation processing based on the product design files to obtain a product simulation model. The product production parameters contained in the product simulation model are consistent with the process parameters actually performed. The positions with a higher probability of product defects occurring in the actual production and processing process are usually fixed, because the surface defect detection positions can be preset according to the product characteristics as the key points for defect inspection.

[0050] S200, performing multi-dimensional sensing recognition on a preset surface defect inspection position in the product simulation model to obtain a simulation recognition signal.

[0051] S200 specifically includes:

[0052] S201. Defect detection positioning marks are made in the product simulation model according to preset surface defect detection positions to determine the key points of defect detection; the surface defect detection positions can be set by the designer according to the shape, structure, size and other characteristics of the product, combined with the defect records formed in the product pre-research, sample manufacturing and other stages. For example, defects are more likely to occur in the curved surface structure part, the sudden protrusion or groove structure part and other positions of the product, so these positions or areas can be set as surface defect detection positions. The purpose of defect positioning marking is to convert the surface defect detection position into an easily identifiable coordinate site in the product simulation model so as to accurately locate it during the defect detection process, and use these positions as the key points of defect detection and as the main detection objects during defect detection, and other positions as secondary detection objects, so that targeted defect detection can be carried out to improve detection efficiency.

[0053] S202. Identify the product simulation model through a multi-dimensional sensing recognition method to generate a simulation recognition signal containing defect detection key points according to the defect detection positioning mark; wherein, the multi-dimensional sensing recognition method refers to model recognition based on the actual sensor and camera layout of the product detection requirement pattern. In actual product inspection, a number of sensors and cameras are usually set around the product inspection station. By simulating the inspection conditions of the actual product, the collected defect detection key points can be more realistic and effective. By generating a simulation recognition signal for subsequent secondary simulation, targeted defect detection can be carried out through the defect detection key points during the simulation process, so that the formed defect database is more effective.

[0054] S300 , performing secondary simulation on the product simulation model according to the simulation identification signal to perform defect inspection, and forming a defect database with the obtained defect data.

[0055] S300 specifically includes:

[0056] S301. Perform dynamic simulation of product processing according to preset product processing parameters to obtain product simulation model middleware. The dynamic simulation of product processing can also be realized by existing modeling software, that is, simulate the processing process of the product from raw materials to finished products. A product simulation model middleware can be obtained after each processing step is simulated. Since product defect detection is usually divided into detection during the processing process and detection after the finished product is processed, defect detection in the product processing process can be simulated by generating a product simulation model middleware.

[0057] S302. Compare the defect detection positioning mark in the obtained simulation identification signal with the product simulation model middleware to perform a simulation defect detection every time a feature matching the defect detection positioning mark is obtained in the product simulation model middleware, that is, in the process of dynamic simulation of product processing, once the product model is formed to the position of the defect detection positioning mark, a simulation defect detection is performed. Preferably, a simulation defect detection can also be performed every time a process simulation is completed and a product simulation model middleware is obtained. In this way, when the product simulation model is completely formed, the defect detection of all parts is completed.

[0058] Among them, when performing dynamic simulation of product processing, the product simulation model is motion simulated and controlled to simulate the movement state of the product during the processing. Since the product will be transported to each processing station on the production line, the product will be in motion during the processing. During defect detection, the sensor and camera usually capture and shoot the product image information when the product moves through the inspection station. By comparing the image information with the preset standard image, defect comparison and judgment are performed. The motion state simulated by the motion model control can obtain more realistic image information, providing a more favorable reference for defect detection. At the same time, the environmental parameters are simulated and controlled to simulate the processing environment of the product during the processing. The processing environment can be conditions such as temperature and humidity that may cause product processing errors. By simulating the processing environment, image information matching the actual product can be further obtained.

[0059] S303. After obtaining all the features that match the defect detection positioning marks, the product simulation model is simulated a second time so that the final product simulation model includes the results of each simulation defect detection. After the second simulation, a complete product simulation model and the simulation defect results of the product simulation model are obtained, which can directly reflect the possible defects of the product directly processed through the previous product design files, so as to facilitate production adjustments.

[0060] S400, training each defect data in the defect database to obtain corresponding correction data and forming a model correction database to adjust product processing parameters.

[0061] S400 specifically includes:

[0062] S401. Calculate and train each defect data according to a preset training model to obtain correction data according to the deviation between the defect data and the standard data. The training model can be set according to product type, structural characteristics, etc., and is used to correct the defect data into standard data. For example, a corresponding mathematical model can be established by comparing a certain number of defect data with standard data, which is essentially an operation function.

[0063] S402. The correction data and the defect data are matched one by one to form a model correction database for adjusting the corresponding product processing parameters. Through the formed model correction database, when product defect detection is carried out in the actual production process, the corresponding correction data can be directly obtained without detecting any defect data, so that the product processing parameters can be directly adjusted, so as to achieve the purpose of simultaneous defect detection and timely correction of processing parameters.

[0064] The present invention uses product design files as input products. When performing product change iterations, it is only necessary to import new product design files, which can achieve rapid product design iterations and save product manufacturing time. By performing defect detection marking, simulation identification processing and defect data training on the product simulation model, a model correction database is formed. During the actual processing, the predetermined defect detection positions can be directly checked to improve the defect detection efficiency. When defects occur, the processing parameters can be adjusted in real time according to the model correction database, reducing downtime or even eliminating the need for downtime, and continuous production can be achieved while performing defect detection and correction. At the same time, when new defect situations occur, training and correction processing can also be performed simultaneously, and the flexibility of defect detection is higher.

[0065] In order to solve the above technical problems, an embodiment of the present invention further provides an online simulation processing system for special-shaped products, including: a model generation unit 501, used to use the imported product design file as the input product to perform initial file simulation processing to obtain a product simulation model; a simulation recognition unit 502, used to perform multi-dimensional sensing recognition on the preset surface defect inspection position in the product simulation model to obtain a simulation recognition signal; a simulation unit 503, used to perform a secondary simulation on the product simulation model according to the simulation recognition signal to perform defect inspection, and form a defect database with the obtained defect data; a correction processing unit 504, used to train each defect data in the defect database to obtain corresponding correction data and form a model correction database to adjust the product processing parameters.

[0066] The online simulation processing system for special-shaped products of the present invention uses product design files as input products when performing defect detection. When performing product change iterations, only new product design files need to be imported, which can achieve rapid product design iterations and save product manufacturing time. By performing defect detection marking, simulation recognition processing and defect data training on the product simulation model, a model correction database is formed. In the actual processing process, the predetermined defect detection positions can be directly checked to improve the defect detection efficiency. When defects occur, the processing parameters can be adjusted in real time according to the model correction database, reducing downtime or even eliminating the need for downtime, and continuous production can be achieved while performing defect detection and correction. At the same time, when new defect situations occur, training and correction processing can also be performed synchronously, and the flexibility of defect detection is higher.

[0067] To solve the above technical problems, the present invention also provides a computer. Figure 3 , Figure 3 This is a basic structural block diagram of the computer device in this embodiment.

[0068] like Figure 3 As shown, a schematic diagram of the internal structure of a computer device. The computer device includes a processor, a non-volatile storage medium, a memory, and a network interface connected via a system bus. Among them, the non-volatile storage medium of the computer device stores an operating system, a database, and computer-readable instructions. The database may store a control information sequence. When the computer-readable instructions are executed by the processor, the processor can implement an online simulation processing method for special-shaped products. The processor of the computer device is used to provide computing and control capabilities to support the operation of the entire computer device. The memory of the computer device may store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor can execute an online simulation processing method for special-shaped products. The network interface of the computer device is used to connect and communicate with a terminal. Those skilled in the art can understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0069] In this embodiment, the processor is used to execute Figure 2 The memory stores the program codes and various data required to execute the above modules. The network interface is used to transmit data between user terminals or servers. The memory in this embodiment stores the program codes and data required to execute all submodules in the face image key point detection device, and the server can call the program codes and data of the server to execute the functions of all submodules.

[0070] When performing defect detection, product design files are used as input products. When performing product change iterations, only new product design files need to be imported, which can achieve rapid product design iterations and save product manufacturing time. By performing defect detection marking, simulation identification processing and defect data training on the product simulation model, a model correction database is formed. During the actual processing, the predetermined defect detection positions can be directly checked to improve the defect detection efficiency. When defects occur, the processing parameters can be adjusted in real time according to the model correction database, reducing downtime or even eliminating the need for downtime, and achieving continuous production while performing defect detection and correction. At the same time, when new defects occur, training and correction processing can also be performed simultaneously, making defect detection more flexible.

[0071] The present invention also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the online simulation processing method for special-shaped products in any of the above-mentioned embodiments.

[0072] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0073] For ease of understanding, the following is an explanation using a specific online simulation processing system for special-shaped products:

[0074] like Figure 4As shown, the system specifically includes: a product information input module for inputting product information; an initial file simulation module connected to the product information input module, for obtaining a product design file according to the product information so as to use the product design file as the initial file for simulation training to obtain a product simulation model; a multi-sensor control system connected to the initial file simulation module, for identifying the product simulation model to obtain a simulation identification signal; an environmental control system connected to the initial file simulation module, the environmental control system is connected to the multi-sensor control system, for simulating the processing environment and forming an influencing parameter compensation for the product to the multi-sensor control system; a secondary simulation module connected to the multi-sensor control system, for performing a secondary simulation on the product simulation model to obtain a product simulation model containing a simulation defect detection result; a motion control system connected to the initial file simulation module and the secondary simulation module, for simulating the motion state of the control product and forming compensation data to be sent to the secondary simulation module; a data training module connected to the secondary simulation module, for performing model training on the obtained defect data to obtain correction data and form a model correction database for adjusting the product processing parameters; a result output module connected to the data training module, for outputting the defect data and the model correction database for adjusting the product processing parameters.

[0075] When performing defect detection, the product information input by the product information input module is used to obtain the product design file, the initial file simulation module simulates the product design file to obtain the product simulation model, and then the product simulation model is identified by the multi-sensor system. During the identification process, the environmental control system simulates the processing environment to form the parameters affecting the product and compensates them to the multi-sensor system, so that the obtained simulation identification parameters are more realistic. The secondary simulation model performs secondary simulation on the product simulation model. During the secondary simulation process, the product simulation model is subjected to defect detection to obtain defect data. At the same time, during the secondary simulation process, the motion control system simulates the motion state of the product, so that the final product simulation model is more in line with reality. The product simulation model after the secondary simulation includes the results of each simulation defect detection, and then the data training module trains the defect data to obtain the correction data and forms a model correction database. The result output module outputs the defect data and the model correction database. When defect detection is performed in the actual processing process, the product processing parameters can be directly adjusted according to the defect data actually detected, so that defect detection and product processing adjustment can be carried out simultaneously.

[0076] By using product design files as input products, only new product design files need to be imported when making product changes and iterations, which can achieve rapid product design iterations and save product manufacturing time. By performing defect detection marking, simulation identification processing and defect data training on the product simulation model, a model correction database is formed. During the actual processing, the predetermined defect detection positions can be directly checked to improve the defect detection efficiency. When defects occur, the processing parameters can be adjusted in real time according to the model correction database, reducing downtime or even eliminating the need for downtime, and achieving continuous production while performing defect detection and correction. At the same time, when new defects occur, training and correction processing can also be performed simultaneously, making defect detection more flexible.

[0077] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

Claims

1. An online simulation processing method for special-shaped products, characterized in that: include: Using the imported product design file as an input product to perform initial file simulation processing to obtain a product simulation model; Performing multi-dimensional sensing recognition on a preset surface defect inspection position in the product simulation model to obtain a simulation recognition signal; Performing secondary simulation on the product simulation model according to the simulation identification signal to perform defect inspection, and forming a defect database with the obtained defect data; Each defect data in the defect database is trained to obtain corresponding correction data and form a model correction database to adjust product processing parameters.

2. The online simulation processing method for special-shaped products according to claim 1 is characterized in that: The method of using the imported product design file as the input product to perform initial file simulation processing to obtain a product simulation model specifically includes: Acquire a product design file according to the product information and import the product design file as an input product; An initial file simulation process is performed on the product design file to construct a product simulation model including product production parameters according to the product design file, wherein a surface defect inspection position is preset in the product simulation model.

3. The online simulation processing method for special-shaped products according to claim 2 is characterized in that: The multi-dimensional sensing recognition of the preset surface defect inspection position in the product simulation model to obtain the simulation recognition signal specifically includes: In the product simulation model, defect detection positioning marks are made according to the preset surface defect detection positions to determine the key points of defect detection; The product simulation model is identified by a multi-dimensional sensing identification method to generate a simulation identification signal containing defect detection key points according to the defect detection positioning mark.

4. The online simulation processing method for special-shaped products according to claim 3 is characterized in that: The performing secondary simulation on the product simulation model according to the simulation identification signal to perform defect inspection specifically includes: Perform dynamic simulation of product processing according to preset product processing parameters to obtain product simulation model middleware; Comparing the defect detection positioning mark in the obtained simulation recognition signal with the product simulation model middleware to perform a simulation defect detection every time a feature matching the defect detection positioning mark is obtained in the product simulation model middleware; After obtaining all the features that match the defect detection positioning marks, the product simulation model is simulated twice so that the final product simulation model includes the results of each simulation defect detection.

5. The online simulation processing method for special-shaped products according to claim 4 is characterized in that: When performing dynamic simulation of product processing, motion simulation control is performed on the product simulation model to simulate the motion state of the product during the processing.

6. The online simulation processing method for special-shaped products according to claim 4 or 5, characterized in that: When conducting dynamic simulation of product processing, environmental parameters are also simulated and controlled to simulate the processing environment of the product during the processing.

7. The method for online simulation processing of special-shaped products according to claim 4, characterized in that: The defect data includes the result of each simulation defect detection, and the training of each defect data in the defect database to obtain corresponding correction data and form a model correction database to adjust product processing parameters specifically includes: Calculate and train each defect data according to a preset training model to obtain correction data according to the deviation between the defect data and the standard data; The correction data and defect data are matched one by one to form a model correction database for adjusting the corresponding product processing parameters.

8. An online simulation processing system for special-shaped products, characterized in that: include: A model generation unit, used for performing initial file simulation processing on the imported product design file as an input product to obtain a product simulation model; A simulation identification unit, used for performing multi-dimensional sensing identification on a preset surface defect inspection position in the product simulation model to obtain a simulation identification signal; A simulation unit, used for performing secondary simulation on the product simulation model according to the simulation identification signal to perform defect inspection, and forming a defect database with the obtained defect data; The correction processing unit is used to train each defect data in the defect database to obtain corresponding correction data and form a model correction database to adjust product processing parameters.

9. A computer comprising a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the online simulation processing method for special-shaped products as claimed in any one of claims 1 to 7.

10. A storage medium storing computer-readable instructions, which, when executed by one or more processors, enables the one or more processors to execute the steps of the online simulation processing method for special-shaped products as claimed in any one of claims 1 to 7.

Images