A mold processing parameter adaptive control method and device

Abstract

The present invention discloses a method and device for adaptively controlling mold processing parameters, and relates to the field of intelligent control technology. The method comprises: receiving basic processing data; performing processing parameter analysis to generate a first processing parameter; performing cutter head wear state identification, and performing processing parameter influence identification to generate a parameter penalty factor; optimizing the first processing parameter to generate a second processing parameter; constructing a processing simulation model, simulating the second processing parameter, and generating predetermined processing feature data; performing mold processing to generate real-time processing feature data; comparing the real-time processing feature data with the predetermined processing feature data, optimizing the second processing parameter, generating a third processing parameter, and performing continuous processing control. The method solves the technical problem in the prior art that the cutter head wear affects the processing quality during mold processing, and by adaptively adjusting the processing parameters, the influence of wear on the processing accuracy is reduced, thereby achieving the technical effect of improving processing efficiency and quality.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a method and device for adaptively controlling mold processing parameters. Background Art

[0002] With the rapid development of modern manufacturing, mold processing is a key link in the product manufacturing process, and its processing accuracy and efficiency directly affect the quality and market competitiveness of the final product. However, mold processing often faces many challenges, especially the problem of cutter head wear. During mold processing, the cutter head is a tool that directly contacts the material. As the processing time increases, the cutter head will gradually wear, resulting in a decrease in its cutting performance, which in turn affects the accuracy and stability of the processing parameters, and ultimately reduces the quality of the processed products. In addition, traditional processing parameter adjustment methods often rely on experience judgment or regular shutdown inspections, lack real-time and adaptability, and are difficult to meet the needs of modern efficient and precise processing. Summary of the invention

[0003] The present application provides a method and device for adaptively controlling mold processing parameters, which solves the technical problem in the prior art that tool head wear affects processing quality during mold processing.

[0004] In view of the above problems, the present application provides a method and device for adaptively controlling mold processing parameters.

[0005] In a first aspect of the present application, a method for adaptively controlling mold processing parameters is provided, the method comprising:

[0006] Receive basic processing data, wherein the basic processing data includes the characteristics of the blank to be processed and the processing target characteristics of the process node to which the target machine tool belongs; input the characteristics of the blank to be processed and the processing target characteristics into the control terminal of the target machine tool for processing parameter analysis to generate a first processing parameter; collect the tool head status data of the target machine tool, identify the tool head wear status, and perform processing parameter influence identification under the tool head wear status to generate a parameter penalty factor; call an adaptive coupling regulator to optimize the first processing parameter with the parameter penalty factor to generate a second processing parameter; collect modeling data of the target machine tool, build a processing simulation model, simulate the second processing parameter in combination with the tool head wear status, and generate predetermined processing feature data, wherein the predetermined processing feature data includes cutting force characteristics, vibration characteristics and temperature characteristics under continuous time series nodes; control the target machine tool to perform mold processing according to the second processing parameter, and monitor the processing characteristics through a processing monitoring module to generate real-time processing feature data; compare the real-time processing feature data with the predetermined processing feature data, and based on the comparison result, optimize the second processing parameter through the adaptive coupling regulator to generate a third processing parameter for continuous processing control.

[0007] A second aspect of the present application provides a mold processing parameter adaptive control device, the device comprising:

[0008] A data receiving module, the data receiving module is used to receive basic processing data, wherein the basic processing data includes the characteristics of the blank to be processed and the processing target characteristics of the process node to which the target machine tool belongs; a parameter analysis module, the parameter analysis module is used to input the characteristics of the blank to be processed and the processing target characteristics into the control terminal of the target machine tool for processing parameter analysis, and generate a first processing parameter; an identification module, the identification module is used to collect the tool head state data of the target machine tool, identify the tool head wear state, and perform processing parameter influence identification under the tool head wear state to generate a parameter penalty factor; a first optimization module, the first optimization module is used to call an adaptive coupling regulator, optimize the first processing parameter with the parameter penalty factor, and generate a second processing parameter; a simulation module The simulation module is used to collect the modeling data of the target machine tool, build a processing simulation model, simulate the second processing parameter in combination with the wear state of the tool head, and generate predetermined processing feature data, wherein the predetermined processing feature data includes cutting force characteristics, vibration characteristics and temperature characteristics under continuous timing nodes; the control module is used to control the target machine tool to perform mold processing according to the second processing parameter, and monitor the processing characteristics through the processing monitoring module to generate real-time processing feature data; the second optimization module is used to compare the real-time processing feature data with the predetermined processing feature data, and based on the comparison result, optimize the second processing parameter through the adaptive coupling regulator to generate a third processing parameter for continuous processing control.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] First, the basic processing data is received, wherein the basic processing data includes the characteristics of the blank to be processed and the processing target characteristics of the process node to which the target machine tool belongs. Then, the characteristics of the blank to be processed and the processing target characteristics are input into the control terminal of the target machine tool for processing parameter analysis to generate the first processing parameter. By collecting the tool head status data of the target machine tool, the tool head wear state is identified, and the processing parameter influence identification under the tool head wear state is performed to generate the parameter penalty factor. Further, the adaptive coupling regulator is called to optimize the first processing parameter with the parameter penalty factor to generate the second processing parameter. Next, the modeling data of the target machine tool is collected, a processing simulation model is constructed, and the second processing parameter is simulated in combination with the tool head wear state to generate the predetermined processing feature data, wherein the predetermined processing feature data includes the cutting force characteristics, vibration characteristics and temperature characteristics under the continuous time series node. Then, the target machine tool is controlled to perform mold processing according to the second processing parameter, and the processing feature monitoring is performed through the processing monitoring module to generate real-time processing feature data. Finally, the real-time processing feature data and the predetermined processing feature data are compared, and based on the comparison result, the second processing parameter is optimized through the adaptive coupling regulator to generate the third processing parameter for continuous processing control. The invention solves the technical problem that the tool head wear affects the processing quality during the mold processing in the prior art, reduces the influence of wear on the processing accuracy by adaptively adjusting the processing parameters, and achieves the technical effect of improving the processing efficiency and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0012] Figure 1 A schematic diagram of a process flow of a mold processing parameter adaptive control method provided in an embodiment of the present application;

[0013] Figure 2 A schematic diagram of the structure of a mold processing parameter adaptive control device provided in an embodiment of the present application.

[0014] Explanation of the reference numerals: data receiving module 11 , parameter analysis module 12 , identification module 13 , first optimization module 14 , simulation module 15 , control module 16 , second optimization module 17 . DETAILED DESCRIPTION

[0015] The present application solves the technical problem in the prior art that tool head wear affects processing quality during mold processing by providing a mold processing parameter adaptive control method and device.

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0017] It should be noted that the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or are inherent to these processes, methods, products or devices.

[0018] Embodiment 1, as Figure 1 As shown, the present application provides a method for adaptively controlling mold processing parameters, wherein the method comprises:

[0019] The basic processing data is received, wherein the basic processing data includes the characteristics of the blank to be processed and the processing target characteristics of the process node to which the target machine tool belongs.

[0020] By receiving basic processing data, a solid foundation is provided for subsequent processing parameter analysis and optimization. Among them, basic processing data includes the characteristics of the blank to be processed and the processing target characteristics of the process node to which the target machine tool belongs; the characteristics of the blank to be processed include the physical and chemical properties of the blank such as material, size, shape, hardness, surface roughness, etc., which directly affect the setting of parameters such as cutting force, cutting speed, feed rate, etc. required in the processing process; the processing target characteristics of the process node to which the target machine tool belongs refer to the processing accuracy, surface roughness, dimensional tolerance and other target requirements that the machine tool needs to achieve at a certain process stage, such as rough processing, semi-finishing or finishing.

[0021] The features of the blank to be processed and the features of the processing target are input into the control terminal of the target machine tool to perform processing parameter analysis to generate first processing parameters.

[0022] The received basic processing data, including the features of the blank to be processed and the processing target features, are input into the control terminal of the target machine tool for processing parameter analysis, so as to generate a processing parameter plan based on the current processing task, including but not limited to spindle speed, cutting depth, feed speed, cutting force limit, etc. These parameters together constitute the first processing parameters.

[0023] The tool head status data of the target machine tool is collected, the tool head wear status is identified, and the influence of the machining parameters under the tool head wear status is identified to generate a parameter penalty factor.

[0024] As a component directly involved in the cutting process, the wear state of the cutter head will directly affect the selection of processing parameters and processing effects. Based on the sensors on the machine tool, the state data of the cutter head of the target machine tool, such as cutting force, vibration, temperature, etc., are collected. These data can indirectly reflect the wear of the cutter head. Based on the wear state of the cutter head, the influence of the wear state on the processing parameters is further analyzed. For example, the wear of the cutter head will lead to a decrease in cutting performance, such as increased cutting force and increased cutting temperature, and a parameter penalty factor is generated accordingly. The parameter penalty factor is used to correct the processing parameters to ensure the stability and processing quality of the processing process. For example, for the cutting speed, if the cutter head is severely worn, it may be necessary to reduce the cutting speed to reduce the cutting force and cutting temperature, thereby protecting the machine tool and the tool. At this time, a corresponding cutting speed penalty factor can be generated according to the degree of wear to adjust the set value of the cutting speed. Similarly, for other processing parameters such as feed rate and cutting depth, corresponding penalty factors can also be generated for adjustment.

[0025] Furthermore, the tool head status data of the target machine tool is collected, the tool head wear status is identified, and the machining parameter influence identification under the tool head wear status is performed to generate a parameter penalty factor, including:

[0026] The tool head of the target machine tool is imaged by a high-precision camera to generate high-precision tool head image data; point cloud modeling is performed based on the high-precision tool head image data to generate a tool head point cloud model; the tool head point cloud model is aligned and compared with a predetermined tool head model, and the parameter penalty factor is generated according to the comparison result; wherein the predetermined tool head model is a tool head point cloud model in an unworn state.

[0027] Preferably, a high-precision camera is used to perform multi-angle and high-resolution image acquisition of the tool head of the target machine tool to obtain high-precision tool head image data; the acquired high-precision tool head image data is imported into the three-dimensional modeling software, and the two-dimensional image information is converted into point cloud data in three-dimensional space through image processing and point cloud generation algorithms, so as to construct a tool head point cloud model; the generated tool head point cloud model is aligned and compared with the predetermined tool head point cloud model in an unworn state, that is, when the two models are ensured to be consistent in spatial position, the two models are compared point by point or region by region to quantify the degree and distribution of tool head wear; based on the result of the model comparison, that is, according to the specific situation of tool head wear, a corresponding parameter penalty factor is generated.

[0028] Furthermore, the tool head point cloud model is aligned and compared with a predetermined tool head model, and the parameter penalty factor is generated according to the comparison result, including:

[0029] The tool head point cloud model is aligned and compared with a predetermined tool head model to establish a tool head wear vector set; wherein the tool head wear vector set includes wear characteristic values ​​corresponding to multiple wear angles; and a processing parameter influence analysis is performed based on the tool head wear vector set to generate the parameter penalty factor.

[0030] Preferably, after aligning and comparing the tool head point cloud model with the predetermined tool head model (i.e., the tool head point cloud model in an unworn state), a tool head wear vector set can be established to quantify the wear state of the tool head, wherein the tool head wear vector set contains wear characteristic values ​​corresponding to multiple wear angles, and these characteristic values ​​can comprehensively describe the wear of the tool head in different directions and degrees. Specifically, multiple angles of tool head wear are determined according to the geometric shape of the tool head, the way of use, and common wear patterns. For example, for a rotary tool, the axial, radial, and multiple circumferential angles of the tool can be selected for analysis; for each selected wear angle, by comparing the difference between the aligned tool head point cloud model and the predetermined tool head model, the wear characteristic value at the angle is calculated, and these characteristic values ​​can be distance difference, volume difference, surface area difference, etc.; the wear characteristic values ​​corresponding to each wear angle are combined to form a multi-dimensional tool head wear vector set, which can comprehensively reflect the wear state of the tool head in different directions. After the tool head wear vector set is established, the impact analysis of the machining parameters can be performed based on the tool head wear vector set to evaluate the specific impact of tool head wear on the machining process and generate corresponding parameter penalty factors accordingly.

[0031] Furthermore, the machining parameter impact analysis is performed based on the tool head wear vector set to generate the parameter penalty factor, including:

[0032] Extract multiple parameter types from the first processing parameters; establish a multidimensional wear impact analyzer based on the multiple parameter types, wherein the multidimensional wear impact analyzer includes multiple wear impact analysis branches corresponding to the multiple parameter types; wherein the multiple wear impact analysis branches are constructed by training a wear impact sample library, and the wear impact sample library includes tool head wear vector samples and identification information of image indicators that identify the multiple parameter types; analyze the tool head wear vector set through the multidimensional wear impact analyzer to generate the parameter penalty factor.

[0033] Specifically, multiple parameter types are extracted from the first processing parameters, including but not limited to cutting speed, cutting depth, feed rate, etc.; based on the extracted parameter types, a multidimensional wear impact analyzer can be constructed, which consists of multiple wear impact analysis branches corresponding to the parameter types, and each branch is specifically used to analyze the impact of a specific parameter type on the wear of the tool head. Specifically, each branch in the multidimensional wear impact analyzer can use machine learning or deep learning algorithms to train the prediction model of each branch using the data in the wear impact sample library, so that it can accurately predict the wear of the tool head under different parameter combinations; wherein the wear impact sample library includes tool head wear vector samples and identification information of image indicators that identify multiple parameter types; the tool head wear vector samples record the quantitative indicators of tool head wear under different processing parameter combinations, such as wear amount, wear morphology, etc.; the identification information of the image indicator is the processing parameter value corresponding to each sample, which is used to identify the specific impact of each parameter type on wear. The tool head wear vector set is analyzed by the multidimensional wear impact analyzer to generate a parameter penalty factor, which reflects the sensitivity and influence of different processing parameters on tool head wear.

[0034] An adaptive coupling regulator is called to optimize the first processing parameter with the parameter penalty factor to generate a second processing parameter.

[0035] The adaptive coupling regulator can dynamically adjust the cutting speed, feed rate, cutting depth and other processing parameters according to the parameter penalty factor and the current processing conditions to reduce the wear of the tool head and improve the processing quality and efficiency. The parameter penalty factor generated by the multidimensional wear impact analyzer is passed as input to the adaptive coupling regulator. The adaptive coupling regulator will iteratively optimize the first processing parameter according to the input parameter penalty factor and the current processing conditions, and output the second processing parameter, wherein the second processing parameter is adjusted based on the combination of tool head wear and processing conditions, which is more in line with the actual processing requirements.

[0036] Furthermore, the steps of constructing the adaptive coupling regulator include:

[0037] Taking the first parameter type among the multiple parameter types as the independent variable, taking the other parameter types as the quantitative variables, taking the control targets respectively corresponding to the multiple parameter types as the dependent variables, a coupling effect analysis between the multiple parameter types is performed, and a coupling parameter group whose coupling effect index is greater than a preset coupling effect index is established, and the coupling parameter group has a coupling effect relationship mark; based on the coupling parameter group and the coupling effect relationship mark, the adaptive coupling regulator is established, wherein the adaptive coupling regulator performs parameter feedback adjustment according to the coupling effect relationship mark.

[0038] Specifically, one parameter type is selected from multiple parameter types as the first parameter type, and the first parameter type is used as the independent variable (for example, cutting speed is first selected as the independent variable), and the remaining parameter types are used as quantitative (that is, they are kept unchanged in these analyses); for each change in the independent variable, the changes in the control objectives (dependent variables) corresponding to the other parameter types are observed and recorded; the above process is repeated, but a different parameter type is selected as the independent variable each time, while the other parameters are kept as quantitative; in this way, the mutual influence and coupling effects between the parameters can be fully analyzed. Based on the results of the coupling effect analysis, a coupling effect index is defined to measure the degree of coupling between parameters; those coupling parameter groups whose coupling effect index is greater than the preset coupling effect index are identified, that is, the parameter changes in these combinations have a significant impact on the control target, and the coupling effect relationship is marked for each coupling parameter group for subsequent management and optimization; based on the coupling parameter group and the coupling effect relationship mark, the adjustment logic of the adaptive coupling regulator is designed, which should be able to automatically identify and respond to the coupling effect according to the current processing conditions and parameter status, and optimize the control target by adjusting the parameter value; a parameter feedback adjustment mechanism is set in the adaptive coupling regulator, which should be able to monitor the key parameters and the status of the control target in the processing process in real time, and automatically adjust the parameter value according to the coupling effect relationship mark and the preset adjustment strategy to compensate for the adverse effects brought by the coupling effect, thereby realizing dynamic optimization of the processing parameters.

[0039] Further, calling the adaptive coupling regulator to optimize the first processing parameter with the parameter penalty factor to generate the second processing parameter includes:

[0040] The first processing parameter is adjusted with the parameter penalty factor to generate multiple parameter adjustment steps corresponding to multiple parameter types; the adaptive coupling regulator is called to perform coupling effect analysis based on the multiple parameter adjustment steps to generate a real-time coupling effect; with the real-time coupling effect, the multiple parameter adjustment steps are reversely adjusted by the adaptive coupling regulator until the deviation between the reverse coupling effect and the real-time coupling effect meets the preset deviation, thereby generating an optimal parameter adjustment step; the first processing parameter is adjusted with the optimal parameter adjustment step to generate the second processing parameter.

[0041] The first machining parameter is adjusted according to the parameter penalty factor generated by the multidimensional wear impact analyzer. The parameter penalty factor reflects the sensitivity and influence of different parameter types on tool head wear. Therefore, an adjustment step can be determined for each parameter type. The adjustment step indicates the direction (increase or decrease) and the amplitude of adjustment for each parameter. Multiple parameter adjustment steps are input into the adaptive coupling regulator. Based on these steps, the regulator combines the coupling effect model established internally and the real-time machining conditions to perform coupling effect analysis between multiple parameters to evaluate the influence of the interaction between the parameters on the machining process under the current adjustment step, especially whether they will produce adverse coupling effects. The adaptive coupling regulator generates a real-time coupling effect, which quantifies the strength and direction of the coupling effect between parameters under the current adjustment step. If the real-time coupling effect does not meet the expected goal (for example, it causes increased tool wear or decreased machining efficiency), reverse parameter adjustment is required. Reverse parameter adjustment refers to adjusting the parameter adjustment step according to the result of the real-time coupling effect to reduce or eliminate the adverse coupling effect. Through continuous iteration, when the reverse parameter adjustment makes the deviation between the real-time coupling effect and the expected goal meet the preset deviation threshold, it is considered that the optimal parameter adjustment step is found. The optimal parameter adjustment step is applied to the first processing parameter to generate the optimized second processing parameter.

[0042] The modeling data of the target machine tool is collected, a machining simulation model is constructed, the second machining parameter is simulated in combination with the wear state of the tool head, and predetermined machining feature data is generated, wherein the predetermined machining feature data includes cutting force characteristics, vibration characteristics, and temperature characteristics under continuous time series nodes.

[0043] By collecting the modeling data of the target machine tool, including but not limited to the machine tool structure parameters, power system data, tool and workpiece information, etc., a machining simulation model is constructed using mechanical machining simulation software. The tool head wear model is integrated into the machining simulation model to simulate the second machining parameter so as to generate predetermined machining feature data, which includes cutting force characteristics, vibration characteristics and temperature characteristics under continuous time series nodes. The cutting force characteristics reflect the changes of the cutting force over time during the cutting process, including the size, direction and fluctuation of the cutting force; the vibration characteristics refer to the vibration of the machine tool and the tool during the machining process, including the vibration amplitude, frequency and phase; the temperature characteristics refer to the temperature changes in the cutting area, including the cutting temperature, tool temperature and workpiece temperature.

[0044] The target machine tool is controlled to perform mold processing according to the second processing parameter, and the processing feature is monitored through the processing monitoring module to generate real-time processing feature data.

[0045] The second processing parameter is input into the CNC system of the target machine tool, and the processing program is started. The CNC system will control the various axes of the machine tool to move precisely according to the input parameters, and drive the tool to cut the mold. During the processing, the processing monitoring module will monitor the various features of the processing in real time, so as to obtain real-time processing feature data, including real-time cutting force data, real-time vibration data, real-time temperature data, etc. Among them, the processing monitoring module includes a variety of sensors, such as cutting force sensors, vibration sensors, temperature sensors, etc.

[0046] The real-time processing characteristic data and the predetermined processing characteristic data are compared, and based on the comparison result, the second processing parameter is optimized by the adaptive coupling regulator to generate a third processing parameter for continuous processing control.

[0047] The predetermined processing feature data is usually set according to the simulation before processing, and represents the expected processing state and performance indicators; by comparing the real-time processing feature data with the predetermined processing feature data, the differences and deviations between the two can be identified; based on the identified deviation, the adaptive coupling regulator is called to optimize the second processing parameter to generate the third processing parameter, which is a fine-tuning or resetting of the second processing parameter, aiming to reduce the difference between the real-time processing feature data and the predetermined processing feature data, so as to make the processing process closer to the ideal state; the third processing parameter is used to control the machine tool to improve the processing quality and efficiency.

[0048] Further, comparing the real-time processing characteristic data with the predetermined processing characteristic data, and optimizing the second processing parameter through the adaptive coupling regulator based on the comparison result to generate a third processing parameter, comprises:

[0049] A mapping relationship between processing features and processing parameter control deviations is established; based on the mapping relationship, the comparison result is matched with processing parameter deviations to generate matching processing parameter deviations; the second processing parameter is adjusted with the matching processing parameter deviation, and after calling the adaptive coupling regulator to perform coupling effect analysis, reverse parameter adjustment is performed to generate the third processing parameter.

[0050] Preferably, a mapping relationship between processing features and processing parameter control deviations is established based on corresponding processing features under different processing parameter combinations; in the real-time processing process, after comparing the real-time processing feature data with the predetermined processing feature data, the comparison result is matched with the processing parameter deviation according to the established mapping relationship, so as to identify the processing parameter deviation that causes the current processing feature deviation; based on matching the processing parameter deviation, the second processing parameter is adjusted, and at the same time, the adaptive coupling regulator is called to perform coupling effect analysis and perform reverse parameter adjustment, thereby generating the third processing parameter.

[0051] In summary, the embodiments of the present application have at least the following technical effects:

[0052] First, the basic processing data is received, wherein the basic processing data includes the characteristics of the blank to be processed and the processing target characteristics of the process node to which the target machine tool belongs. Then, the characteristics of the blank to be processed and the processing target characteristics are input into the control terminal of the target machine tool for processing parameter analysis to generate the first processing parameter. By collecting the tool head status data of the target machine tool, the tool head wear state is identified, and the processing parameter influence identification under the tool head wear state is performed to generate the parameter penalty factor. Further, the adaptive coupling regulator is called to optimize the first processing parameter with the parameter penalty factor to generate the second processing parameter. Next, the modeling data of the target machine tool is collected, a processing simulation model is constructed, and the second processing parameter is simulated in combination with the tool head wear state to generate the predetermined processing feature data, wherein the predetermined processing feature data includes the cutting force characteristics, vibration characteristics and temperature characteristics under the continuous time series node. Then, the target machine tool is controlled to perform mold processing according to the second processing parameter, and the processing feature monitoring is performed through the processing monitoring module to generate real-time processing feature data. Finally, the real-time processing feature data and the predetermined processing feature data are compared, and based on the comparison result, the second processing parameter is optimized through the adaptive coupling regulator to generate the third processing parameter for continuous processing control. The invention solves the technical problem that the tool head wear affects the processing quality during the mold processing in the prior art, reduces the influence of wear on the processing accuracy by adaptively adjusting the processing parameters, and achieves the technical effect of improving the processing efficiency and quality.

[0053] Embodiment 2 is based on the same inventive concept as a method for adaptively controlling mold processing parameters in the above embodiment. Figure 2 As shown, the present application provides a mold processing parameter adaptive control device, wherein the device includes:

[0054] A data receiving module 11, the data receiving module 11 is used to receive basic processing data, wherein the basic processing data includes the characteristics of the blank to be processed and the processing target characteristics of the process node to which the target machine tool belongs; a parameter analysis module 12, the parameter analysis module 12 is used to input the characteristics of the blank to be processed and the processing target characteristics into the control terminal of the target machine tool for processing parameter analysis, and generate a first processing parameter; an identification module 13, the identification module 13 is used to collect the tool head state data of the target machine tool, identify the tool head wear state, and perform processing parameter influence identification under the tool head wear state to generate a parameter penalty factor; a first optimization module 14, the first optimization module 14 is used to call an adaptive coupling regulator, optimize the first processing parameter with the parameter penalty factor, and generate a second processing parameter; a module A simulation module 15, the simulation module 15 is used to collect modeling data of the target machine tool, construct a processing simulation model, simulate the second processing parameter in combination with the wear state of the tool head, and generate predetermined processing feature data, wherein the predetermined processing feature data includes cutting force characteristics, vibration characteristics and temperature characteristics under continuous time series nodes; a control module 16, the control module 16 is used to control the target machine tool to perform mold processing according to the second processing parameter, and monitor the processing characteristics through the processing monitoring module to generate real-time processing feature data; a second optimization module 17, the second optimization module 17 is used to compare the real-time processing feature data with the predetermined processing feature data, and based on the comparison result, optimize the second processing parameter through the adaptive coupling regulator to generate a third processing parameter for continuous processing control.

[0055] Furthermore, the identification module 13 is used to execute the following method:

[0056] The tool head of the target machine tool is imaged by a high-precision camera to generate high-precision tool head image data; point cloud modeling is performed based on the high-precision tool head image data to generate a tool head point cloud model; the tool head point cloud model is aligned and compared with a predetermined tool head model, and the parameter penalty factor is generated according to the comparison result; wherein the predetermined tool head model is a tool head point cloud model in an unworn state.

[0057] Furthermore, the identification module 13 is used to execute the following method:

[0058] The tool head point cloud model is aligned and compared with a predetermined tool head model to establish a tool head wear vector set; wherein the tool head wear vector set includes wear characteristic values ​​corresponding to multiple wear angles; and a processing parameter influence analysis is performed based on the tool head wear vector set to generate the parameter penalty factor.

[0059] Furthermore, the identification module 13 is used to execute the following method:

[0060] Extract multiple parameter types from the first processing parameters; establish a multidimensional wear impact analyzer based on the multiple parameter types, wherein the multidimensional wear impact analyzer includes multiple wear impact analysis branches corresponding to the multiple parameter types; wherein the multiple wear impact analysis branches are constructed by training a wear impact sample library, and the wear impact sample library includes tool head wear vector samples and identification information of image indicators that identify the multiple parameter types; analyze the tool head wear vector set through the multidimensional wear impact analyzer to generate the parameter penalty factor.

[0061] Furthermore, the first optimization module 14 is used to execute the following method:

[0062] Taking the first parameter type among the multiple parameter types as the independent variable, taking the other parameter types as the quantitative variables, taking the control targets respectively corresponding to the multiple parameter types as the dependent variables, a coupling effect analysis between the multiple parameter types is performed, and a coupling parameter group whose coupling effect index is greater than a preset coupling effect index is established, and the coupling parameter group has a coupling effect relationship mark; based on the coupling parameter group and the coupling effect relationship mark, the adaptive coupling regulator is established, wherein the adaptive coupling regulator performs parameter feedback adjustment according to the coupling effect relationship mark.

[0063] Furthermore, the first optimization module 14 is used to execute the following method:

[0064] The first processing parameter is adjusted with the parameter penalty factor to generate multiple parameter adjustment steps corresponding to multiple parameter types; the adaptive coupling regulator is called to perform coupling effect analysis based on the multiple parameter adjustment steps to generate a real-time coupling effect; with the real-time coupling effect, the multiple parameter adjustment steps are reversely adjusted by the adaptive coupling regulator until the deviation between the reverse coupling effect and the real-time coupling effect meets the preset deviation, thereby generating an optimal parameter adjustment step; the first processing parameter is adjusted with the optimal parameter adjustment step to generate the second processing parameter.

[0065] Furthermore, the second optimization module 17 is used to perform the following method:

[0066] A mapping relationship between processing features and processing parameter control deviations is established; based on the mapping relationship, the comparison result is matched with processing parameter deviations to generate matching processing parameter deviations; the second processing parameter is adjusted with the matching processing parameter deviation, and after calling the adaptive coupling regulator to perform coupling effect analysis, reverse parameter adjustment is performed to generate the third processing parameter.

[0067] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0068] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

[0069] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for adaptively controlling mold processing parameters, characterized in that: The method comprises: Receiving basic processing data, wherein the basic processing data includes characteristics of a blank to be processed and processing target characteristics of a process node to which a target machine tool belongs; Inputting the to-be-processed blank feature and the processing target feature into the control terminal of the target machine tool to perform processing parameter analysis to generate first processing parameters; Collecting the tool head status data of the target machine tool, identifying the tool head wear status, and performing the identification of the influence of the machining parameters under the tool head wear status to generate a parameter penalty factor; calling an adaptive coupling regulator to optimize the first processing parameter with the parameter penalty factor to generate a second processing parameter; Collecting modeling data of the target machine tool, constructing a machining simulation model, simulating the second machining parameter in combination with the wear state of the tool head, and generating predetermined machining feature data, wherein the predetermined machining feature data includes cutting force characteristics, vibration characteristics, and temperature characteristics at continuous time series nodes; Control the target machine tool to perform mold processing according to the second processing parameters, and monitor the processing characteristics through the processing monitoring module to generate real-time processing characteristic data; Comparing the real-time processing characteristic data with the predetermined processing characteristic data, optimizing the second processing parameter through the adaptive coupling regulator based on the comparison result, generating a third processing parameter, and performing continuous processing control; The tool head status data of the target machine tool is collected to identify the tool head wear status, and the machining parameter influence identification under the tool head wear status is performed to generate a parameter penalty factor, including: Capturing an image of a tool head of the target machine tool by using a high-precision camera to generate high-precision tool head image data; Performing point cloud modeling based on the high-precision tool head image data to generate a tool head point cloud model; Aligning and comparing the tool head point cloud model with a predetermined tool head model, and generating the parameter penalty factor according to the comparison result; Wherein, the predetermined cutter head model is a cutter head point cloud model in an unworn state; The step of aligning and comparing the tool head point cloud model with a predetermined tool head model and generating the parameter penalty factor according to the comparison result includes: Aligning and comparing the tool head point cloud model with a predetermined tool head model to establish a tool head wear vector set; Wherein, the tool head wear vector set includes wear characteristic values ​​corresponding to multiple wear angles; Performing a machining parameter impact analysis based on the tool head wear vector set to generate the parameter penalty factor; The process of performing a machining parameter impact analysis based on the tool head wear vector set and generating the parameter penalty factor comprises: extracting a plurality of parameter types from the first processing parameters; Establishing a multidimensional wear impact analyzer based on the multiple parameter types, wherein the multidimensional wear impact analyzer includes multiple wear impact analysis branches corresponding to the multiple parameter types; The plurality of wear impact analysis branches are constructed by training a wear impact sample library, wherein the wear impact sample library includes tool head wear vector samples and identification information of image indicators identifying the plurality of parameter types; Analyzing the tool head wear vector set by the multidimensional wear impact analyzer to generate the parameter penalty factor; The steps of constructing the adaptive coupling regulator include: Taking the first parameter type among the multiple parameter types as an independent variable, taking the other parameter types as quantitative, taking the control targets respectively corresponding to the multiple parameter types as dependent variables, performing coupling effect analysis between the multiple parameter types, establishing a coupling parameter group whose coupling effect index is greater than a preset coupling effect index, and the coupling parameter group has a coupling effect relationship mark; Establishing the adaptive coupling regulator based on the coupling parameter group and the coupling effect relationship mark, wherein the adaptive coupling regulator performs parameter feedback adjustment according to the coupling effect relationship mark; The step of calling the adaptive coupling regulator to optimize the first processing parameter with the parameter penalty factor to generate the second processing parameter includes: The first processing parameter is adjusted by the parameter penalty factor to generate a plurality of parameter adjustment steps corresponding to a plurality of parameter types; Calling the adaptive coupling regulator to perform coupling effect analysis based on the multiple parameter adjustment steps to generate real-time coupling effect; Using the real-time coupling effect, the adaptive coupling regulator performs reverse parameter adjustment on the multiple parameter adjustment steps until the deviation between the reverse coupling effect and the real-time coupling effect meets a preset deviation, thereby generating an optimal parameter adjustment step; The first processing parameter is adjusted with the optimal parameter adjustment step to generate the second processing parameter.

2. A mold processing parameter adaptive control method according to claim 1, characterized in that: Comparing the real-time processing characteristic data with the predetermined processing characteristic data, and optimizing the second processing parameter through the adaptive coupling regulator based on the comparison result to generate a third processing parameter, including: Establish the mapping relationship between processing features and processing parameter control deviations; Based on the mapping relationship, matching the comparison results with processing parameter deviations to generate matching processing parameter deviations; The second processing parameter is adjusted with the matching processing parameter deviation, and after calling the adaptive coupling regulator to perform coupling effect analysis, reverse parameter adjustment is performed to generate the third processing parameter.

3. A mold processing parameter adaptive control device, characterized in that: The device is used to implement a mold processing parameter adaptive control method according to any one of claims 1 to 2, comprising: A data receiving module, the data receiving module is used to receive basic processing data, wherein the basic processing data includes the characteristics of the blank to be processed and the processing target characteristics of the process node to which the target machine tool belongs; A parameter analysis module, wherein the parameter analysis module is used to input the characteristics of the blank to be processed and the processing target characteristics into the control terminal of the target machine tool to perform processing parameter analysis and generate a first processing parameter; An identification module, the identification module is used to collect the tool head status data of the target machine tool, identify the tool head wear status, and perform the identification of the influence of the machining parameters under the tool head wear status to generate a parameter penalty factor; A first optimization module, the first optimization module is used to call an adaptive coupling regulator to optimize the first processing parameter with the parameter penalty factor to generate a second processing parameter; A simulation module, the simulation module is used to collect modeling data of the target machine tool, build a machining simulation model, simulate the second machining parameter in combination with the wear state of the tool head, and generate predetermined machining feature data, wherein the predetermined machining feature data includes cutting force characteristics, vibration characteristics, and temperature characteristics at continuous time series nodes; A control module, the control module is used to control the target machine tool to perform mold processing according to the second processing parameters, and monitor the processing characteristics through the processing monitoring module to generate real-time processing characteristic data; The second optimization module is used to compare the real-time processing feature data with the predetermined processing feature data, and based on the comparison result, optimize the second processing parameter through the adaptive coupling regulator to generate the third processing parameter for continuous processing control.

Images