Method and device for determining cavity processing track, electronic equipment and storage medium
By obtaining the processing information of the cavity to be cut and using pre-trained machine learning models to determine the target processing trajectory, combined with PID algorithm and machine learning functions, the problem of low machining accuracy of high-end molds is solved, achieving more efficient and more accurate cavity Body processing.
Patent Information
- Application Number
- CN202411419723.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-11
- Publication Date
- 2024-12-31
AI Technical Summary
When processing detailed structures such as small holes, deep concaves, grooves and other high-end molds, the processing accuracy is low, the quality stability is poor, the batch consistency is poor, and the technical parameters assessment assumptions of the machine tool are inconsistent, resulting in the actual processing accuracy is much lower than the parameters. grade.
By obtaining the processing information of the cavity to be cut, including feed rate and feed direction, the target processing trajectory is determined using a pre-trained machine learning model, combining PID algorithm and machine learning functions, correcting errors, establishing a processing trajectory model, and real-time real-time Update compensation.
It improves the accuracy and cutting efficiency of the cavity processing trajectory, reduces measurement errors and artificial errors, and improves the stability and consistency of processing quality.
Smart Images
Figure CN119225276A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of mold processing technology, and in particular to a method, device, electronic device and storage medium for determining a cavity processing trajectory. Background Art
[0002] At present, the small holes, deep recesses, grooves and other detailed structures of high-end molds are difficult to process, with low processing accuracy, poor processing quality stability, and poor batch processing consistency. The technical parameter evaluation of machine tools is based on the assumption that the machine tool has the same accuracy at different feed rates and different feed directions. In fact, it is impossible to be consistent, that is, the position dispersion of the tool moving from different directions or at different speeds to the same point must be much greater than the position dispersion of moving from the same direction at the same speed to the same point, and there is no need to be consistent. When processing molds, after the program setting is completed, this specific trajectory is used for processing, that is, the accuracy after the processing elements converge is the actual requirement for processing the part, which is far lower than the parameter evaluation level of the machine tool. How to improve the accuracy of trajectory processing is an urgent problem to be solved. Summary of the invention
[0003] The purpose of some embodiments of the present application is to provide a method, device, electronic device and storage medium for determining the processing trajectory of a cavity. Through the technical solution of the embodiments of the present application, by obtaining the processing information of the cavity to be cut, wherein the processing information at least includes a feed rate and a feed direction; according to the processing information of the cavity to be cut and a pre-trained processing trajectory model, a target processing trajectory corresponding to the processing information is determined, wherein: the pre-trained processing trajectory model is obtained by training a machine learning model using sample processing information of the cavity. The embodiments of the present application add a machine learning function, establish a processing trajectory model according to processing trajectories of different shapes, treat the processing trajectory feed direction and feed rate as error-related factors for error correction, and use the processing trajectory model to determine the target processing trajectory according to the feed rate and feed direction in the processing information of the cavity to be cut, so that each processing trajectory is similar, improving cutting efficiency and accuracy.
[0004] In a first aspect, some embodiments of the present application provide a method for determining a cavity processing trajectory, comprising: Acquire processing information of the cavity to be cut, wherein the processing information at least includes a feed rate and a feed direction; According to the processing information of the cavity to be cut and the pre-trained processing trajectory model, a target processing trajectory corresponding to the processing information is determined, wherein: The pre-trained processing trajectory model is obtained by training the machine learning model using the sample processing information of the cavity. Some embodiments of the present application establish a processing trajectory model according to processing trajectories of different shapes by adding a machine learning function, taking the processing trajectory feed direction and feed rate as error-related factors for error correction, and using the processing trajectory model to determine the target processing trajectory according to the feed rate and feed direction in the processing information of the cavity to be cut, so that each processing trajectory is similar, improving cutting efficiency and accuracy.
[0005] Optionally, the processing trajectory model is obtained by: Obtain sample processing information of the cavity; Determining training data corresponding to the sample processing information according to the sample processing information of the cavity; According to the training data and the preset processing trajectory, the machine learning network model is trained to obtain the processing trajectory model. Some embodiments of the present application train the machine learning network model according to the training data and the preset processing trajectory to obtain the processing trajectory model, add a machine learning function, establish a learning library according to processing trajectories of different shapes, and realize continuous learning and real-time update compensation.
[0006] Optionally, determining the training data corresponding to the sample processing information according to the sample processing information of the cavity includes: Acquiring a feeding direction and a feeding rate from sample processing information of the cavity; Using preset PID parameters, the feed direction and the feed rate are adjusted to obtain a processing trajectory corresponding to the preset PID parameters; The preset PID parameters, the feed direction, the feed rate and the processing trajectory are determined as the training data. Some embodiments of the present application use the PID algorithm to identify the processing code, perform processing trajectory compensation, and output a new code. The PID can first obtain the difference between the theoretical value and the measured value, and then use the two parameters KI and KD to compensate for the difference. For linear / circular interpolation, the theoretical and actual differences are calculated and compensated respectively to obtain the compensated training data, thereby reducing the measurement error in the model training process.
[0007] Optionally, the preset PID parameters include at least a proportional parameter, a differential parameter and an integral parameter. Optionally, the training of the machine learning network model according to the training data and the preset processing trajectory to obtain the processing trajectory model includes: Inputting the training data into the machine learning model to obtain a model training result; Comparing the model training result with the preset processing trajectory; When the difference between the model training result and the preset processing trajectory is less than a preset value, the machine learning model corresponding to the training data is determined as the processing trajectory model.
[0008] Some embodiments of the present application compare the model training results with a preset processing trajectory, i.e., a standard processing trajectory. When the difference is less than the preset value, the machine learning model corresponding to the training data is determined as the processing trajectory model, thereby improving the accuracy of trajectory processing.
[0009] Optionally, the method further comprises: updating the processing trajectory model according to the target processing trajectory. Some embodiments of the present application add a machine learning function to establish a learning library according to processing trajectories of different shapes, realize continuous learning and real-time update compensation, and improve the accuracy of trajectory processing.
[0010] In a second aspect, some embodiments of the present application provide a device for determining a cavity processing trajectory, including: An acquisition module, used for acquiring processing information of the cavity to be cut, wherein the processing information at least includes a feed rate and a feed direction; A determination module is used to determine a target processing trajectory corresponding to the processing information of the cavity to be cut and a pre-trained processing trajectory model, wherein the pre-trained processing trajectory model is obtained by training a machine learning model using sample processing information of the cavity.
[0011] Some embodiments of the present application add a machine learning function to establish a processing trajectory model according to processing trajectories of different shapes, use the processing trajectory feed direction and feed rate as error-related factors for error correction, and use the processing trajectory model to determine the target processing trajectory based on the feed rate and feed direction in the processing information of the cavity to be cut. This makes the processing trajectory similar each time, thereby improving cutting efficiency and accuracy.
[0012] Optionally, the device further comprises a training module, wherein the training module is used to: Obtain sample processing information of the cavity; Determining training data corresponding to the sample processing information according to the sample processing information of the cavity; The machine learning network model is trained according to the training data and the preset processing trajectory to obtain the processing trajectory model. Some embodiments of the present application train a machine learning network model according to training data and preset processing trajectories to obtain a processing trajectory model, add a machine learning function, establish a learning library according to processing trajectories of different shapes, and achieve continuous learning and real-time update compensation.
[0013] Optionally, the training module is used to: Acquiring a feeding direction and a feeding rate from sample processing information of the cavity; Using preset PID parameters, the feed direction and the feed rate are adjusted to obtain a processing trajectory corresponding to the preset PID parameters; The preset PID parameters, the feed direction, the feed rate and the processing trajectory are determined as the training data. Some embodiments of the present application use the PID algorithm to identify the processing code, perform processing trajectory compensation, and output a new code. The PID can first obtain the difference between the theoretical value and the measured value, and then use the two parameters KI and KD to compensate for the difference. For linear / circular interpolation, the theoretical and actual differences are calculated and compensated respectively to obtain the compensated training data, thereby reducing the measurement error in the model training process.
[0014] Optionally, the preset PID parameters include at least a proportional parameter, a differential parameter and an integral parameter. Optionally, the training module is used to: Inputting the training data into the machine learning model to obtain a model training result; Comparing the model training result with the preset processing trajectory; When the difference between the model training result and the preset processing trajectory is less than a preset value, the machine learning model corresponding to the training data is determined as the processing trajectory model.
[0015] Some embodiments of the present application compare the model training results with a preset processing trajectory, i.e., a standard processing trajectory. When the difference is less than the preset value, the machine learning model corresponding to the training data is determined as the processing trajectory model, thereby improving the accuracy of trajectory processing.
[0016] Optionally, the training module is used to update the processing trajectory model according to the target processing trajectory.
[0017] Some embodiments of the present application add a machine learning function to establish a learning library according to processing trajectories of different shapes, so as to achieve continuous learning and real-time update compensation, thereby improving the accuracy of trajectory processing.
[0018] In a third aspect, some embodiments of the present application provide an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for determining a cavity processing trajectory as described in any embodiment of the first aspect can be implemented.
[0019] In a fourth aspect, some embodiments of the present application provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, can implement the method for determining a cavity processing trajectory as described in any embodiment of the first aspect.
[0020] In a fifth aspect, some embodiments of the present application provide a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for determining a cavity processing trajectory as described in any embodiment of the first aspect can be implemented. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] In order to more clearly illustrate the technical solutions of some embodiments of the present application, the drawings required for use in some embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0022] Figure 1 A schematic flow chart of a method for determining a cavity machining trajectory provided in an embodiment of the present application; Figure 2 is a flow chart of the real contour processing method described in the embodiment of the present application; Figure 3 It is a flow chart of the machining trajectory modification steps of the real contour machining method described in the embodiment of the present application; Figure 4 is a flow chart of the machining trajectory modification steps described in the embodiment of the present application; Figure 5 is a flow chart of the machining trajectory modification steps described in the embodiment of the present application; Figure 6 It is a structural schematic diagram of the installation of the machining trajectory modification method described in the embodiment of the present application; Figure 7 is a schematic diagram of the machining trajectory modification method described in an embodiment of the present application; Figure 8 A schematic diagram of the structure of a device for determining a cavity processing trajectory provided in an embodiment of the present application; Fig. 9 A schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0023] The technical solutions in some embodiments of the present application will be described below in conjunction with the drawings in some embodiments of the present application.
[0024] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0025] At present, the small holes, deep recesses, grooves and other detailed structures of high-end molds are difficult to process, with low processing accuracy, poor processing quality stability, and poor batch processing consistency. The technical parameter evaluation of machine tools is based on the assumption that the machine tool has consistent accuracy at different feed rates and different feed directions. In fact, it is impossible to be consistent, that is, the position dispersion of the tool moving from different directions or at different speeds to the same point must be much greater than the position dispersion of moving from the same direction to the same point at the same speed, and there is no need to be consistent. When processing the mold, after the program setting is completed, this specific trajectory is used for processing, that is, the accuracy after the processing elements converge is the actual requirement for processing the part, which is far lower than the parameter evaluation level of the machine tool. How to improve the accuracy of trajectory processing is an urgent problem to be solved. In view of this, some embodiments of the present application provide a method for determining a cavity processing trajectory, the method includes obtaining processing information of a cavity to be cut, wherein the processing information at least includes a feed rate and a feed direction; according to the processing information of the cavity to be cut and a pre-trained processing trajectory model, a target processing trajectory corresponding to the processing information is determined, wherein: the pre-trained processing trajectory model is obtained by training a machine learning model using sample processing information of the cavity. The embodiment of the present application adds a machine learning function, establishes a processing trajectory model according to processing trajectories of different shapes, takes the processing trajectory feed direction and feed rate as error-related factors for error correction, and uses the processing trajectory model to determine the target processing trajectory based on the feed rate and feed direction in the processing information of the cavity to be cut, so that the processing trajectory each time is similar, thereby improving the cutting efficiency and accuracy.
[0026] like Figure 1 As shown, an embodiment of the present application provides a method for determining a cavity processing trajectory, the method comprising: S101, obtaining processing information of a cavity to be cut, wherein the processing information at least includes a feed rate and a feed direction; Specifically, the terminal device obtains processing information of the cavity to be cut, and the processing information at least includes a feed rate and a feed direction; S102. Determine a target processing trajectory corresponding to the processing information according to the processing information of the cavity to be cut and a pre-trained processing trajectory model, wherein the pre-trained processing trajectory model is obtained by training a machine learning model using sample processing information of the cavity.
[0027] The terminal device pre-acquires sample processing information of multiple cavities, which sample processing information includes at least a feed rate and a feed direction, as well as a standard processing trajectory, and then performs PID algorithm adjustment on the feed rate and the feed direction to obtain an adjusted processing trajectory, and trains the machine learning model on the standard processing trajectory and the adjusted processing trajectory to obtain a processing trajectory model. The machine learning model may be a neural network model, etc., and the type of the machine learning model is not specifically limited in the embodiment of the present application.
[0028] During actual use, the terminal device obtains the processing information of the cavity to be cut, which includes at least the feed rate and feed direction, and inputs the feed rate and feed direction into the pre-trained processing trajectory model to obtain the target processing trajectory. Through the trained processing trajectory model, the obtained processing trajectory is made consistent with the standard processing trajectory as much as possible. like Figure 2 As shown, the embodiment of the present application proposes a real contour processing method for mold forming, and machine learning compensation is applied to mold processing, which can also obtain the optimal trajectory feed direction and feed rate, and improve the accuracy of the processed workpiece, specifically including: S0, recording the tool path, feed direction and feed rate of the machine tool head by laser interference tracking; S1, storing the tool path, feed direction, and feed rate of the machine tool head in a processing trajectory library according to different shapes; S2, processing the data in the machining trajectory library, and analyzing the trajectory differences under certain feed directions and feed rates; S3. Through PID algorithm, PID algorithm, i.e. proportional, integral, differential algorithm, is a control algorithm used in industrial control systems and various applications that require continuous modulation control. It identifies the processing code, performs processing trajectory compensation, and outputs a new code. PID can first obtain the difference between the theoretical value and the measured value, and then use the two parameters KI and KD to compensate for the difference. For linear / circular interpolation, the theoretical and actual differences are calculated and compensated respectively, and the new G code, i.e. the adjusted feed direction and feed rate, is obtained. S4, saving the adjusted feed rate and feed direction of the tool to the processing trajectory library; Under the premise of meeting the machining technology, the optimal feed rate and feed direction are implemented.
[0029] Machine learning will achieve real-time updates and continuously improve its mold processing trajectory compensation library.
[0030] Some embodiments of the present application add a machine learning function to establish a processing trajectory model according to processing trajectories of different shapes, use the processing trajectory feed direction and feed rate as error-related factors for error correction, and use the processing trajectory model to determine the target processing trajectory based on the feed rate and feed direction in the processing information of the cavity to be cut. This makes the processing trajectory similar each time, thereby improving cutting efficiency and accuracy.
[0031] Another embodiment of the present application further supplements the method for determining the cavity processing trajectory provided in the above embodiment.
[0032] Optionally, the processing trajectory model is obtained by: Obtain sample processing information of the cavity; Determining training data corresponding to the sample processing information according to the sample processing information of the cavity; According to the training data and the preset processing trajectory, the machine learning network model is trained to obtain the processing trajectory model.
[0033] Some embodiments of the present application train a machine learning network model according to training data and preset processing trajectories to obtain a processing trajectory model, add a machine learning function, establish a learning library according to processing trajectories of different shapes, and achieve continuous learning and real-time update compensation.
[0034] Optionally, determining training data corresponding to the sample processing information according to the sample processing information of the cavity includes: Obtaining the feed direction and feed rate from the sample processing information of the cavity; Using the preset PID parameters, the feed direction and feed rate are adjusted to obtain the machining trajectory corresponding to the preset PID parameters; The preset PID parameters, feed direction, feed rate and processing trajectory are determined as training data. Some embodiments of the present application use the PID algorithm to identify the processing code, perform processing trajectory compensation, and output a new code. The PID can first obtain the difference between the theoretical value and the measured value, and then use the two parameters KI and KD to compensate for the difference. For linear / circular interpolation, the theoretical and actual differences are calculated and compensated respectively to obtain the compensated training data, thereby reducing the measurement error in the model training process.
[0035] Optionally, the preset PID parameters include at least a proportional parameter, a differential parameter and an integral parameter. Optionally, the machine learning network model is trained according to the training data and the preset processing trajectory to obtain a processing trajectory model, including: Input the training data into the machine learning model to obtain the model training results; Compare the model training results with the preset processing trajectory; When the difference between the model training result and the preset processing trajectory is less than the preset value, the machine learning model corresponding to the training data is determined as the processing trajectory model.
[0036] Some embodiments of the present application compare the model training results with a preset processing trajectory, i.e., a standard processing trajectory. When the difference is less than the preset value, the machine learning model corresponding to the training data is determined as the processing trajectory model, thereby improving the accuracy of trajectory processing.
[0037] Optionally, the method further includes: updating the processing trajectory model according to the target processing trajectory.
[0038] Some embodiments of the present application add a machine learning function to establish a learning library according to processing trajectories of different shapes, so as to achieve continuous learning and real-time update compensation, thereby improving the accuracy of trajectory processing.
[0039] The laser interference tracking method in the embodiment of the present application can be divided into internal memory and external memory, the internal memory can detect the position movement of the nut of its motion mechanism, and the external Figure 5 and Figure 6 ; The acquisition functional components include: laser transmitter, beam splitter, linear optical lens group, turning mirror; The base station includes: a numerical control system, a display, and post-processing software. The post-processing software performs steps such as processing trajectory tracking map generation, comparison, feedback, and correction; obtains three-dimensional coordinate points and generates processing trajectory tracking. The main installation components include: tool fixing seat 1 worktable fixture 2 processing workpiece 3 clamping table 4 laser tracker 5 tool 6; The tool fixing seat 1, the worktable fixture 2, the workpiece 3, the clamping table 4, and the tool 5 are machine tool parts; the clamping table 4 can move in the X and Y axis directions, and the tool 6 can move in the Z axis; The tool running trajectory includes: tool trajectory entry point 6, tool trajectory 7, and tool trajectory exit point 8; The tool running trajectory recording method tool comprises: a laser transmitter 9, a three-way direction-changing mirror 10, an interference mirror 11, and a direction-changing mirror 12; The present application embodiment is applied to Figure 5 and Figure 6 The structure of the tool trajectory 8 is corrected. In the process of machine tool movement, there is a machine tool geometric error, and the trajectory offset is corrected to improve the processing accuracy; Track deviation is corrected according to the error: the machine tool moves on a specific track to process the surface of its parts. It is driven by G code commands and has a specific processing track. Its track is tracked and recorded, and the error between the ideal stroke and the actual stroke is compared to obtain the error and correct it to improve the processing accuracy. like Figure 3 As shown, the specific tracking and revision steps are as follows: Step A1, perform machining programming for the machined parts and write G code; Step A 2. The machine tool performs an empty cut for a specific trajectory and runs the set machining trajectory; Step A 3, the laser tracker tracks the processing trajectory to obtain coordinate points; Step A 4. Track and measure to generate the tool path processing trajectory, so as to compare it with the processing trajectory set by the machine tool; Determine whether the error is within the processing error. If it does not meet the error requirement, proceed to step A5; if it meets the error requirement, proceed to step A6; Step A 5. If the error requirement is not met, the error is corrected; Step A 6. When the error requirement is met, the revised machining trajectory is output, such as Figure 7 As shown; like Figure 4 As shown, the error correction steps are as follows: S1051, comparing the tracked measurement trajectory with the original set trajectory of the machine tool to determine the difference between the two; S1052, correct and compensate for the difference; S1053, generating a revised processing trajectory; S1054, generating its G code; Use the revised G code to improve the parts processing technology; Exemplarily, the embodiment of the present application determines the difference between two trajectories, corrects the compensation, and implements the process of modifying the processing trajectory. Taking the cutting straight line as an example, the coordinate origin is defined as A (0.0) trajectory point B (260.0) C (260.120).
[0040] The original processing trajectory G code is as follows: G17 G00G90G54 X0 Y0 M03 G01 Z-0.1 F300 G01 X260 Y0 G01 X260 Y120 G01 Z10 G04 The original processing trajectory is as follows Figure 5 No. 13, an error occurs during the processing, and the running trajectory is as follows Figure 5No. 14, the coordinates obtained are Bf (Xb, Yb), the error amount X axis: 260-|Xb|, Y axis: 0-|Yb|, the machining trajectory coordinate points are corrected (260+(260-|Xb|), 0+(0-|Yb|)), and the final corrected trajectory is as follows Figure 5 Serial number 15.
[0041] The embodiment of the present application provides a method for processing the true contour of a mold cavity, and performs error correction. It can provide accuracy in part processing, reduce the generation of scrap rate, perform mold cavity processing trajectory correction, reduce machine tool geometric errors, reduce the measurement process of the processed workpiece, reduce human errors caused by repeated clamping, and improve efficiency and accuracy; it is low-cost and convenient to install and adjust, and can achieve rapid feedback on the errors caused by the machine tool, and continue to learn and accumulate.
[0042] The embodiments of the present application provide a method for processing parts with high processing accuracy requirements, which is suitable for similar three-axis machine tools and machining centers and is conducive to the development of high-precision machine tools.
[0043] It should be noted that each implementable method in this embodiment may be implemented separately, or may be implemented in combination in any combination without conflict, and this application is not limited thereto.
[0044] Another embodiment of the present application provides a cavity processing trajectory determination device, which is used to execute the cavity processing trajectory determination method provided in the above embodiment.
[0045] like Figure 8 , which is a schematic diagram of the structure of a device for determining a cavity processing trajectory provided in an embodiment of the present application. The device for determining a cavity processing trajectory includes an acquisition module 801 and a determination module 802, wherein: The acquisition module 801 is used to acquire processing information of the cavity to be cut, wherein the processing information at least includes a feed rate and a feed direction; The determination module 802 is used to determine the target processing trajectory corresponding to the processing information based on the processing information of the cavity to be cut and the pre-trained processing trajectory model, wherein the pre-trained processing trajectory model is obtained by training the machine learning model using the sample processing information of the cavity.
[0046] Regarding the device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0047] Some embodiments of the present application add a machine learning function to establish a processing trajectory model according to processing trajectories of different shapes, use the processing trajectory feed direction and feed rate as error-related factors for error correction, and use the processing trajectory model to determine the target processing trajectory based on the feed rate and feed direction in the processing information of the cavity to be cut. This makes the processing trajectory similar each time, thereby improving cutting efficiency and accuracy.
[0048] Another embodiment of the present application further supplements the device for determining the cavity processing trajectory provided in the above embodiment.
[0049] Optionally, the device further comprises a training module, the training module being used for: Obtain sample processing information of the cavity; Determining training data corresponding to the sample processing information according to the sample processing information of the cavity; According to the training data and the preset processing trajectory, the machine learning network model is trained to obtain the processing trajectory model. Some embodiments of the present application train a machine learning network model according to training data and preset processing trajectories to obtain a processing trajectory model, add a machine learning function, establish a learning library according to processing trajectories of different shapes, and achieve continuous learning and real-time update compensation.
[0050] Optionally, the training module is used to: Obtaining the feed direction and feed rate from the sample processing information of the cavity; The preset PID parameters are used to adjust the feed direction and feed rate to obtain a machining trajectory corresponding to the preset PID parameters; The preset PID parameters, feed direction, feed rate and processing trajectory are determined as training data. Some embodiments of the present application use the PID algorithm to identify the processing code, perform processing trajectory compensation, and output a new code. The PID can first obtain the difference between the theoretical value and the measured value, and then use the two parameters KI and KD to compensate for the difference. For linear / circular interpolation, the theoretical and actual differences are calculated and compensated respectively to obtain the compensated training data, thereby reducing the measurement error in the model training process.
[0051] Optionally, the preset PID parameters include at least a proportional parameter, a differential parameter and an integral parameter. Optionally, the training module is used to: Input the training data into the machine learning model to obtain the model training results; Compare the model training results with the preset processing trajectory; When the difference between the model training result and the preset processing trajectory is less than the preset value, the machine learning model corresponding to the training data is determined as the processing trajectory model.
[0052] Some embodiments of the present application compare the model training results with a preset processing trajectory, i.e., a standard processing trajectory. When the difference is less than the preset value, the machine learning model corresponding to the training data is determined as the processing trajectory model, thereby improving the accuracy of trajectory processing.
[0053] Optionally, the training module is used to update the processing trajectory model according to the target processing trajectory.
[0054] Some embodiments of the present application add a machine learning function to establish a learning library according to processing trajectories of different shapes, so as to achieve continuous learning and real-time update compensation, thereby improving the accuracy of trajectory processing.
[0055] Regarding the device in this embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0056] It should be noted that each implementable method in this embodiment may be implemented separately, or may be implemented in combination in any combination without conflict, and this application is not limited thereto.
[0057] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the operation of the method corresponding to any embodiment of the method for determining the cavity processing trajectory provided in the above embodiments can be implemented.
[0058] An embodiment of the present application also provides a computer program product, which includes a computer program, wherein when the computer program is executed by a processor, it can implement the operations corresponding to any embodiment of the method for determining the cavity processing trajectory provided in the above embodiments.
[0059] like Fig. 9 As shown, some embodiments of the present application provide an electronic device 900, which includes: a memory 910, a processor 920, and a computer program stored in the memory 910 and executable on the processor 920, wherein the processor 920 can implement any of the methods of the above-mentioned method for determining the cavity processing trajectory when reading the program from the memory 910 through a bus 930 and executing the program.
[0060] Processor 920 can process digital signals and can include various computing structures, such as complex instruction set computer structure, reduced instruction set computer structure, or a structure that implements a combination of multiple instruction sets. In some examples, processor 920 can be a microprocessor.
[0061] The memory 910 may be used to store instructions executed by the processor 920 or data related to the execution of instructions. These instructions and / or data may include codes for implementing some or all functions of one or more modules described in the embodiments of the present application. The processor 920 of the disclosed embodiment may be used to execute instructions in the memory 910 to implement the method shown above. The memory 910 includes a dynamic random access memory, a static random access memory, a flash memory, an optical memory, or other memory known to those skilled in the art.
[0062] The above are only embodiments of the present application and are not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.
[0063] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0064] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.
Claims
1. A method for determining a cavity processing trajectory, characterized in that: The method comprises: Acquire processing information of the cavity to be cut, wherein the processing information at least includes a feed rate and a feed direction; According to the processing information of the cavity to be cut and the pre-trained processing trajectory model, a target processing trajectory corresponding to the processing information is determined, wherein: The pre-trained processing trajectory model is obtained by training a machine learning model using sample processing information of the cavity.
2. The method for determining the cavity machining trajectory according to claim 1, characterized in that: The processing trajectory model is obtained by: Obtaining sample processing information of the cavity; Determining training data corresponding to the sample processing information according to the sample processing information of the cavity; The machine learning network model is trained according to the training data and the preset processing trajectory to obtain the processing trajectory model.
3. The method for determining the cavity machining trajectory according to claim 2, characterized in that: The determining, according to the sample processing information of the cavity, training data corresponding to the sample processing information comprises: Acquiring a feeding direction and a feeding rate from sample processing information of the cavity; Using preset PID parameters, the feed direction and the feed rate are adjusted to obtain a processing trajectory corresponding to the preset PID parameters; The preset PID parameters, the feeding direction, the feeding rate and the processing trajectory are determined as the training data.
4. The method for determining the cavity machining trajectory according to claim 3, characterized in that: The preset PID parameters include at least a proportional parameter, a differential parameter and an integral parameter.
5. The method for determining the cavity machining trajectory according to claim 4, characterized in that: The step of training the machine learning network model according to the training data and the preset processing trajectory to obtain the processing trajectory model includes: Inputting the training data into the machine learning model to obtain a model training result; Comparing the model training result with the preset processing trajectory; When the difference between the model training result and the preset processing trajectory is less than a preset value, the machine learning model corresponding to the training data is determined as the processing trajectory model.
6. The method for determining the cavity machining trajectory according to claim 2, characterized in that: The method further comprises: The processing trajectory model is updated according to the target processing trajectory.
7. A device for determining a cavity processing trajectory, characterized in that: The device comprises: An acquisition module, used for acquiring processing information of the cavity to be cut, wherein the processing information at least includes a feed rate and a feed direction; A determination module is used to determine a target processing trajectory corresponding to the processing information of the cavity to be cut and a pre-trained processing trajectory model, wherein the pre-trained processing trajectory model is obtained by training a machine learning model using sample processing information of the cavity.
8. The device for determining the cavity machining trajectory according to claim 7, characterized in that: The device also includes a training module, which is used to: Obtain sample processing information of the cavity; Determining training data corresponding to the sample processing information according to the sample processing information of the cavity; The machine learning network model is trained according to the training data and the preset processing trajectory to obtain the processing trajectory model.
9. An electronic device, characterized in that: It comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, it can implement the method for determining the cavity processing trajectory as described in any one of claims 1 to 6.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the program is executed by a processor, the method for determining a cavity processing trajectory as described in any one of claims 1 to 6 can be implemented.