Adaptive machining method and device for numerical control die and storage medium

Abstract

The invention relates to a numerical control mold self-adaptive machining method and device and a storage medium, and relates to the technical field of numerical control machining. Determining a key surface which can influence the durability and the precision of the numerical control die in the machining process according to the structural characteristics and the machining process flow; obtaining a machining compensation scheme according to the key surface, the structural characteristics and the machining process flow, wherein the machining compensation scheme comprises a compensation axis direction and compensation parameters; dynamic variable data in the machining process of the numerical control mold are obtained; and the machining process is compensated in real time according to the dynamic variable data and the machining compensation scheme. The numerical control die has the effect of improving the durability and the machining precision of the numerical control die.

Description

Technical Field

[0001] The present application relates to the technical field of numerical control machining, and in particular to a numerical control mold adaptive machining method, equipment and storage medium. Background Art

[0002] CNC machining is a process method for processing parts on CNC machine tools. CNC machine tool processing uses digital information to control the displacement of parts and tools. It can solve problems such as varied types of parts, small batches, complex shapes, and high precision, and can achieve efficient and refined part processing.

[0003] The CNC machining process usually requires the cooperation of CNC tools and molds. However, in actual use, there may be inaccuracies in the manufacturing and assembly process of various parts of CNC machine tools. Friction heat, cutting heat and ambient temperature changes during the machining process will cause uneven temperatures of various parts of the machine tool, resulting in thermal deformation. Loads such as cutting force and clamping force during the machining process act on the workpiece and machine tool, which may cause elastic deformation of the workpiece and machine tool structure. The lack of control accuracy of the servo system, such as positioning accuracy and repeated positioning accuracy, may cause deviations between the actual position and posture during the machining process and the design value. At the same time, the hardness, toughness and other characteristics of the mold material may change during the machining process, especially when the machining conditions are not suitable for the material characteristics, which may lead to a decrease in the durability of the mold. Improper selection of machining parameters such as cutting speed, feed rate, and cutting depth, and unreasonable arrangement of process flows such as machining sequence and cooling method may lead to increased tool wear. When the above problems occur for a long time, it may cause excessive wear of the mold, thereby affecting the durability and machining accuracy of the CNC mold. Summary of the invention

[0004] The purpose of this application is to provide a CNC mold adaptive processing method, equipment and storage medium, which can improve the durability and processing accuracy of the CNC mold.

[0005] In the first aspect, the present application provides a CNC mold adaptive processing method using the following technical solutions: A CNC mold adaptive processing method, comprising: Obtain the structural characteristics and processing process of CNC molds; Determine the key surfaces that will affect the durability and precision of CNC molds during processing based on structural features and processing technology; Obtaining a machining compensation scheme according to the key surface, structural features and machining process flow, wherein the machining compensation scheme includes a compensation axis direction and compensation parameters; Obtain dynamic variable data during CNC mold processing; The machining process is compensated in real time based on dynamic variable data and machining compensation scheme.

[0006] By adopting the above-mentioned technical scheme, the present application combines the structural characteristics of the CNC mold and the processing process to determine the key surfaces that are most susceptible to wear during the processing and thus affect the durability and processing accuracy of the mold, and compensates for the key surfaces. By real-time monitoring of the dynamic variable data during the processing, the CNC processing is adaptively adjusted, which can effectively improve the durability and processing accuracy of the CNC mold.

[0007] Furthermore, a machining compensation scheme is obtained according to the key surface, structural features and machining process flow, including obtaining the compensation axis direction according to the key surface, specifically including: Obtain the motion axis when machining the key surface according to the machining process; The moving direction of the moving axis is defined as the compensation axis direction.

[0008] By adopting the above technical solution, the present application determines the direction of the machining tool axis through the machining process flow, thereby establishing the machining compensation scheme and the direction of the compensation axis. The compensation axis selected is usually the axis that moves when machining the critical surface, such as the x-axis, y-axis, z-axis or b-axis, so as to more accurately perform machining compensation on the CNC mold.

[0009] Furthermore, obtaining a processing compensation scheme according to the key surface, structural features and processing flow also includes obtaining compensation parameters according to the structural features and processing flow, specifically including: According to the structural characteristics and processing flow, the deformation error value in the processing process is obtained; A compensation parameter prediction model is constructed, and the deformation error value is input into the compensation parameter prediction model to obtain the compensation parameter.

[0010] By adopting the above-mentioned technical solution, the present application obtains the deformation error value that may cause the mold durability and processing accuracy to decrease during the processing through the structural characteristics and processing process of the CNC mold, and performs processing compensation based on the compensation parameters predicted by the deformation error value to ensure the accuracy of the processing compensation.

[0011] Furthermore, the construction of the compensation parameter prediction model, inputting the deformation error value into the compensation parameter prediction model, and obtaining the compensation parameter specifically includes: Constructing an initial model for predicting compensation parameters; Obtaining deformation error value samples and corresponding compensation parameter samples in several machining compensation processes in a compensation parameter prediction database; The deformation error value samples are used as input features, and the compensation parameter samples are used as output features to construct a sample set; The initial compensation parameter prediction model is trained according to the sample set to obtain a trained compensation parameter prediction model; The deformation error value is input into the trained compensation parameter prediction model to obtain the compensation parameter.

[0012] By adopting the above-mentioned technical solution, the present application predicts the compensation parameters by constructing a compensation parameter prediction model. The compensation parameter prediction model learns the characteristic relationship between deformation error value samples and compensation parameter samples during the training stage, so that the compensation parameters can be predicted according to the deformation error values, thereby effectively improving the intelligence and accuracy of processing compensation.

[0013] Furthermore, the real-time adjustment of the machining process according to the dynamic variable data and the machining compensation scheme includes: Adjust the cutting depth in the compensation axis direction in real time according to dynamic variable data and compensation parameters; The accelerated convergence method is used to improve the convergence speed of cutting depth adjustment.

[0014] By adopting the above-mentioned technical solution, the present application adjusts the cutting depth in the direction of the compensation axis through real-time monitored dynamic variable data and predicted compensation parameters, thereby achieving precise processing compensation, and improving the convergence speed of the cutting depth adjustment through an accelerated convergence method, ensuring real-time adjustment during the processing process to adapt to changes in the characteristics of the mold material and processing conditions.

[0015] Furthermore, the obtaining of the structural features of the CNC mold specifically includes: Acquire basic data of the CNC mold, wherein the basic data includes geometric shape, size and material properties; Obtain key data and processing difficulties based on basic data; According to the key data and processing difficulties, the structural data that may cause errors in the processing process are determined as structural features.

[0016] By adopting the above-mentioned technical scheme, this application obtains the key data and processing difficulties in the CNC mold processing process based on the basic data of the mold, and then determines the structural data that may cause errors in the processing process through the key data and processing difficulties, and performs targeted compensation based on the structural features that may cause errors, thereby improving the accuracy of processing compensation.

[0017] Furthermore, the obtaining of the structural features and processing flow of the CNC mold also includes optimizing the processing flow, specifically including: Optimize each process parameter in the processing flow according to the standard process parameters in the knowledge base to obtain the processing flow of standard process parameters; Taking the minimum repetitive work as the optimization goal, the processing technology flow of standard process parameters is optimized to obtain the optimized processing technology flow.

[0018] By adopting the above technical solution, the present application optimizes the processing technology to ensure that repetitive work can be reduced, thereby reducing unnecessary wear on the mold, improving mold durability and improving processing efficiency.

[0019] Furthermore, after the processing is adjusted in real time according to the dynamic variable data and the processing compensation scheme, the method further includes: Obtain the structural features of CNC molds after real-time compensation; Compare the structural features after real-time compensation with the standard structural features to determine whether the real-time compensation is qualified; When the real-time compensation is qualified, a qualified feedback signal is generated; When the real-time compensation fails to meet the standards, an unqualified feedback signal is generated and the processing compensation plan is adjusted.

[0020] By adopting the above technical solution, the present application ensures the accuracy of the processing compensation process by providing feedback on the processing compensation results and making real-time adjustments, and can adapt to changes in the environment or actual conditions.

[0021] In a second aspect, the present application provides a computer device that adopts the following technical solution: A computer device comprises a memory and a processor, wherein the memory stores a CNC mold adaptive processing method as described in the first aspect which can be loaded and executed by the processor.

[0022] In a third aspect, the present application provides a computer-readable storage medium that adopts the following technical solution: A computer-readable storage medium stores a computer program that can be loaded by a processor and executed by a CNC mold adaptive processing method as described in the first aspect.

[0023] In summary, the present application includes at least one of the following beneficial technical effects: 1. This application combines the structural characteristics of the CNC mold and the processing process to determine the key surfaces that are most susceptible to wear during the processing, which affects the durability and processing accuracy of the mold, and compensates for the key surfaces. By real-time monitoring of the dynamic variable data during the processing, the CNC processing is adaptively adjusted, which can effectively improve the durability and processing accuracy of the CNC mold; 2. This application obtains the deformation error value that may cause the mold durability and processing accuracy to decrease during the processing through the structural characteristics and processing process of the CNC mold, and performs processing compensation based on the compensation parameters predicted by the deformation error value to ensure the accuracy of the processing compensation; 3. This application obtains the key data and processing difficulties in the CNC mold processing process based on the basic data of the mold, and then determines the structural data that may cause errors in the processing process through the key data and processing difficulties, and performs targeted compensation based on the structural features that may cause errors, thereby improving the accuracy of processing compensation; 4. This application optimizes the processing technology to ensure that repetitive work can be reduced, thereby reducing unnecessary wear on the mold, improving mold durability and improving processing efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a method flow chart of an embodiment of the present application; Figure 2 It is a flow chart of the compensation parameter prediction model construction method of the embodiment of the present application. DETAILED DESCRIPTION

[0025] The following is combined with Figure 1 -Attached Figure 2 , further details of this application are given.

[0026] The CNC machining process usually requires the CNC tools and molds to cooperate with each other. However, in actual use, there may be inaccuracies in the manufacturing and assembly process of the various components of the CNC machine tools. The friction heat, cutting heat and ambient temperature changes during the machining process will cause uneven temperatures of the various components of the machine tool, resulting in thermal deformation. The cutting force, clamping force and other loads during the machining process act on the workpiece and the machine tool, which may cause elastic deformation of the workpiece and the machine tool structure. The lack of control accuracy of the servo system, such as positioning accuracy and repeated positioning accuracy, may cause deviations between the actual position and posture during the machining process and the design values. At the same time, the hardness, toughness and other properties of the mold material may change during the machining process. In particular, when the machining conditions are not suitable for the material properties, the durability of the mold may decrease. Improper selection of machining parameters such as cutting speed, feed rate, and cutting depth, and unreasonable arrangement of process flows such as machining sequence and cooling method may lead to increased tool wear. When the above problems occur for a long time, the mold may be excessively worn, thereby affecting the durability and machining accuracy of the CNC mold. Therefore, the embodiment of the present application provides a CNC mold adaptive machining method, referring to Figure 1 ,include: S1. Obtain the structural characteristics and processing process of the CNC mold.

[0027] Specifically, the basic data of the CNC mold is obtained, including the geometric shape, size and material properties of the CNC mold. The key data and processing difficulties are obtained based on the basic data. The structural data that may cause errors in the processing process are determined based on the key data and processing difficulties, such as thin walls, long overhangs, complex curved surfaces and other structures that may cause deformation errors, as structural features. In the specific implementation process, the image data of the CNC mold can be collected by visual inspection equipment, and the structural features of the CNC mold can be obtained by image recognition based on the image data. The structural features can also be obtained by manually inputting the basic data of the CNC mold for analysis.

[0028] S2. Determine the key surfaces that will affect the durability and accuracy of the CNC mold during processing based on the structural characteristics and processing process.

[0029] Specifically, the surface that is easily worn during the processing and thus affects the durability and processing accuracy of the CNC mold is obtained as the key surface for processing compensation.

[0030] S3. Obtain a processing compensation plan based on key surfaces, structural features and processing technology flow.

[0031] Specifically, the processing compensation scheme includes the direction of the compensation axis and the compensation parameters. The direction of the compensation axis is usually obtained according to the key surface, which specifically includes: obtaining the moving axis when processing the key surface according to the processing process, and setting the moving direction of the moving axis as the direction of the compensation axis. In the specific implementation process, the selection of the compensation axis is usually the axis that moves when processing the key surface, such as the x-axis, y-axis, z-axis or b-axis. The compensation parameters are also obtained according to the structural characteristics and the processing process, which specifically includes: obtaining the deformation error value in the processing process according to the structural characteristics and the processing process, constructing a compensation parameter prediction model, and inputting the deformation error value into the compensation parameter prediction model to obtain the compensation parameters. In the specific implementation process, the deformation error value that may cause the mold durability and processing accuracy to decrease during the processing process is obtained through the structural characteristics and the processing process of the CNC mold. The deformation error value includes thermal deformation error, elastic deformation error, etc. The compensation parameters include thermal expansion coefficient, elastic modulus, cutting force coefficient, etc.

[0032] S4. Obtain dynamic variable data during CNC mold processing.

[0033] Specifically, the online measurement function of the CNC machining center is used to measure the machining benchmark of the CNC mold online, obtain dynamic variable data, and the measurement data is automatically transferred to the machine tool parameters for storage for subsequent machining compensation.

[0034] S5. Perform real-time compensation on the machining process according to dynamic variable data and machining compensation scheme.

[0035] Specifically, the cutting depth in the direction of the compensation axis is adjusted in real time according to the dynamic variable data and the compensation parameters, and the convergence speed of the cutting depth adjustment is improved by using the accelerated convergence method. In the specific implementation process, a dynamic processing program can be compiled according to the processing compensation plan and the dynamic variable data, and the collected dynamic variable data can be used to realize multi-axis linkage processing. An adaptive dynamic compensation processing program is formed to ensure real-time adjustment during the processing process to adapt to the characteristics of different molds and changes in processing conditions. The dynamic processing program can bend with the shape. For example, if the processed part is a curve shape, the processing program is also a curve shape; if the processed part is a wave shape, the processing program is also a wave shape, to achieve adaptive processing, to ensure that the dimensional characteristics of the part such as wall thickness or depth meet the part processing quality requirements, and the processing quality is optimal.

[0036] The implementation principle of the embodiment of the present application is: combining the structural characteristics of the CNC mold and the processing process to determine the key surfaces that are most susceptible to wear during the processing and thus affect the durability and processing accuracy of the mold, and compensate for the key surfaces. By real-time monitoring of the dynamic variable data during the processing, the CNC processing is adaptively adjusted, which can effectively improve the durability and processing accuracy of the CNC mold.

[0037] This application can also improve the durability and processing accuracy of CNC molds by optimizing the processing technology, including: S11. Optimize each process parameter in the processing flow according to the standard process parameters in the knowledge base to obtain the processing flow of the standard process parameters.

[0038] Specifically, the knowledge base stores standard process parameters obtained according to previous processing procedures.

[0039] S12. Taking the minimum repetitive work as the optimization goal, the processing technology flow of standard process parameters is optimized to obtain the optimized processing technology flow.

[0040] Specifically, by optimizing the processing technology, we can ensure that repetitive work can be reduced, thereby reducing unnecessary wear on the mold. like Figure 2 As shown, the embodiment of the present application constructs a compensation parameter prediction model, inputs the deformation error value into the compensation parameter prediction model, and obtains the compensation parameter, which specifically includes: S31. Construct an initial model for predicting compensation parameters.

[0041] Specifically, a compensation parameter prediction initial model is constructed based on LSTM, and model parameters of the compensation parameter prediction initial model are configured, where the model parameters include but are not limited to the number of LSTM units, activation function, and input sequence length.

[0042] S32, obtaining deformation error value samples and corresponding compensation parameter samples in several machining compensation processes in the compensation parameter prediction database.

[0043] Specifically, the compensation parameter prediction database stores deformation error value samples and corresponding compensation parameter samples acquired and stored during previous CNC machining compensation. The deformation error value samples include thermal deformation samples, elastic deformation samples, etc., and the compensation parameter samples include thermal expansion coefficient samples, elastic modulus samples, cutting force coefficient samples, etc.

[0044] S33. Using deformation error value samples as input features and compensation parameter samples as output features to construct a sample set.

[0045] S34. Train the initial compensation parameter prediction model according to the sample set to obtain a trained compensation parameter prediction model.

[0046] Specifically, 70% of the samples in the sample set are used as the training set to train the initial model for compensation parameter prediction, where the deformation error value samples are used as input data and the compensation parameter samples are used as output data, so that the model can learn the characteristic relationship between the deformation error value samples and the compensation parameter samples during the training process.

[0047] S35, inputting the deformation error value into the trained compensation parameter prediction model to obtain compensation parameters.

[0048] Specifically, the compensation parameter prediction model predicts the corresponding compensation parameter prediction result according to the input deformation error value based on the learned feature relationship, and outputs the compensation parameter prediction result.

[0049] In the process of model construction, in addition to training the model, it is also necessary to determine whether the accuracy of the model meets the standard through testing. Therefore, step S33 of the embodiment of the present application specifically includes: S331, dividing the sample set into a training set and a test set, and presetting the number of training rounds.

[0050] Specifically, 70% of the sample set is usually used as a training set and 30% as a test set.

[0051] S332: Input the training set into the compensation parameter prediction initial model, and perform training according to a preset number of training rounds.

[0052] Specifically, during training, deformation error samples of the training set are used as input data, and compensation parameter samples are used as output data to train the initial model for predicting compensation parameters.

[0053] S333: When the compensation parameter prediction initial model reaches a preset number of training rounds, a trained compensation parameter prediction model is obtained.

[0054] S334, input the deformation error samples in the test set into the trained compensation parameter prediction model to obtain compensation parameter prediction result prediction samples.

[0055] Specifically, after the model is trained, the output results of the model are tested using input data in a sample set of known output data.

[0056] S335. Obtain a mean square error of the compensation parameter prediction result based on the compensation parameter samples in the test set and the corresponding compensation parameter prediction result prediction samples.

[0057] Specifically, mean-square error (MSE) is a measure of the difference between the estimator and the estimated quantity, that is, the compensation parameter sample and the corresponding compensation parameter prediction result prediction sample. The difference between the compensation parameter sample and the corresponding compensation parameter prediction result prediction sample is judged based on the mean-square error, so as to judge whether the trained compensation parameter prediction model meets the requirements.

[0058] S336. When the mean square error of the compensation parameter prediction result is greater than the preset error value, the model parameters of the compensation parameter prediction model are cyclically adjusted until the mean square error of the compensation parameter prediction result is less than the preset error value.

[0059] Specifically, if the mean square error of the compensation parameter prediction result is greater than the preset error value, the accuracy of the trained compensation parameter prediction model is low and does not meet the requirements, and the model parameters need to be adjusted.

[0060] S337. When the mean square error of the compensation parameter prediction result is less than the preset error value, a trained compensation parameter prediction model is obtained according to the current model parameters.

[0061] Specifically, the model parameters of the compensation parameter prediction model are adjusted according to the compensation parameter samples in the test set and the corresponding compensation parameter prediction result prediction samples, and the trained compensation parameter prediction model is obtained according to the adjusted model parameters.

[0062] The implementation principle of the embodiment of the present application is: the compensation parameters are predicted by constructing a compensation parameter prediction model. The compensation parameter prediction model learns the characteristic relationship between the deformation error value samples and the compensation parameter samples during the training stage, so that the compensation parameters can be predicted according to the deformation error values, thereby effectively improving the intelligence and accuracy of processing compensation.

[0063] In order to further improve the accuracy of the machining compensation process, the embodiment of the present application also includes feedback on the machining compensation results and real-time adjustment, specifically including: S61. Obtain structural features of the CNC mold after real-time compensation.

[0064] Specifically, the structural features of the mold after machining compensation are automatically measured through the online measurement function of the CNC machining center.

[0065] S62: Compare the structural features after real-time compensation with the standard structural features to determine whether the real-time compensation is qualified.

[0066] Specifically, the standard structural features may be data such as standard drawings pre-stored in the memory, and a reasonable error range may be preset according to the accuracy requirements. When the error between the structural features after real-time compensation and the standard structural features exceeds the error range, it indicates that the current real-time compensation is unqualified, otherwise it is qualified.

[0067] S63. When the real-time compensation is qualified, a qualified feedback signal is generated.

[0068] Specifically, if the real-time compensation is qualified, it means that the current processing compensation solution is accurate enough and no adjustment is needed.

[0069] S64. When the real-time compensation is unqualified, an unqualified feedback signal is generated, and the processing compensation plan is adjusted.

[0070] Specifically, failure of real-time compensation indicates that the current processing compensation solution is not accurate enough and needs to be adjusted.

[0071] The embodiment of the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and executed by a method for adaptive processing of a numerical control mold, specifically including: S1. Obtain the structural characteristics and processing process of the CNC mold.

[0072] S2. Determine the key surfaces that will affect the durability and accuracy of the CNC mold during processing based on the structural characteristics and processing process.

[0073] S3. Obtain a processing compensation plan based on key surfaces, structural features and processing technology.

[0074] S4. Obtain dynamic variable data during CNC mold processing.

[0075] S5. Perform real-time compensation on the machining process according to dynamic variable data and machining compensation scheme.

[0076] The computer is a server, and the computer device includes a processor, a memory, a network interface and a database connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store basic data of CNC molds, processing process flow, online measurement function program of CNC machining center, knowledge base, compensation parameter prediction model, compensation parameter prediction database, etc. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for adaptive processing of CNC molds can be provided.

[0077] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: S1. Obtain the structural characteristics and processing process of the CNC mold.

[0078] S2. Determine the key surfaces that will affect the durability and accuracy of the CNC mold during processing based on the structural characteristics and processing process.

[0079] S3. Obtain a processing compensation plan based on key surfaces, structural features and processing technology.

[0080] S4. Obtain dynamic variable data during CNC mold processing.

[0081] S5. Perform real-time compensation on the machining process according to dynamic variable data and machining compensation scheme.

[0082] In addition, the processor in the computer device executes all the steps of the above-mentioned CNC mold adaptive processing method when executing the computer program.

[0083] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM).

[0084] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0085] The embodiments of this specific implementation are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. The same components are represented by the same figure marks. Therefore, any equivalent changes made based on the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A CNC mold adaptive processing method, characterized in that: include: Obtain the structural characteristics and processing process of CNC molds; Determine the key surfaces that will affect the durability and precision of CNC molds during processing based on structural features and processing technology; Obtaining a machining compensation scheme according to the key surface, structural features and machining process flow, wherein the machining compensation scheme includes a compensation axis direction and compensation parameters; Obtain dynamic variable data during CNC mold processing; The machining process is compensated in real time based on dynamic variable data and machining compensation scheme.

2. A CNC mold adaptive processing method according to claim 1, characterized in that: The machining compensation scheme is obtained according to the key surface, structural features and machining process, including the direction of the compensation axis according to the key surface, including: Obtain the motion axis when machining the key surface according to the machining process; The moving direction of the moving axis is defined as the compensation axis direction.

3. A CNC mold adaptive processing method according to claim 2, characterized in that: The method of obtaining a processing compensation scheme according to the key surface, structural features and processing flow also includes obtaining compensation parameters according to the structural features and processing flow, specifically including: According to the structural characteristics and processing flow, the deformation error value in the processing process is obtained; A compensation parameter prediction model is constructed, and the deformation error value is input into the compensation parameter prediction model to obtain the compensation parameter.

4. A CNC mold adaptive processing method according to claim 3, characterized in that: The compensation parameter prediction model is constructed, and the deformation error value is input into the compensation parameter prediction model to obtain the compensation parameter, specifically including: Constructing an initial model for predicting compensation parameters; Obtaining deformation error value samples and corresponding compensation parameter samples in several machining compensation processes in a compensation parameter prediction database; The deformation error value samples are used as input features, and the compensation parameter samples are used as output features to construct a sample set; The initial compensation parameter prediction model is trained according to the sample set to obtain a trained compensation parameter prediction model; The deformation error value is input into the trained compensation parameter prediction model to obtain the compensation parameter.

5. The method for adaptive machining of a CNC mold according to claim 1, characterized in that: The real-time adjustment of the machining process according to the dynamic variable data and the machining compensation scheme includes: Adjust the cutting depth in the compensation axis direction in real time according to dynamic variable data and compensation parameters; The accelerated convergence method is used to improve the convergence speed of cutting depth adjustment.

6. A CNC mold adaptive processing method according to claim 1, characterized in that: The obtaining of the structural features of the CNC mold specifically includes: Acquire basic data of the CNC mold, wherein the basic data includes geometric shape, size and material properties; Obtain key data and processing difficulties based on basic data; According to the key data and processing difficulties, the structural data that may cause errors in the processing process are determined as structural features.

7. A CNC mold adaptive processing method according to claim 6, characterized in that: The obtaining of the structural features and processing flow of the CNC mold also includes optimizing the processing flow, specifically including: Optimize each process parameter in the processing flow according to the standard process parameters in the knowledge base to obtain the processing flow of standard process parameters; Taking the minimum repetitive work as the optimization goal, the processing technology flow of standard process parameters is optimized to obtain the optimized processing technology flow.

8. A CNC mold adaptive processing method according to any one of claims 1 to 7, characterized in that: After the processing process is adjusted in real time according to the dynamic variable data and the processing compensation scheme, it also includes: Obtain the structural features of CNC molds after real-time compensation; Compare the structural features after real-time compensation with the standard structural features to determine whether the real-time compensation is qualified; When the real-time compensation is qualified, a qualified feedback signal is generated; When the real-time compensation fails to meet the standards, an unqualified feedback signal is generated and the processing compensation plan is adjusted.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a CNC mold adaptive processing method as described in any one of claims 1 to 8 which can be loaded and executed by the processor.

10. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and executes a CNC mold adaptive processing method as described in any one of claims 1 to 8.

Images