Self-adaptive optimization method and device for control parameters of gantry machine tool

Abstract

The invention provides a self-adaptive optimization method and device for control parameters of a gantry machine tool, and relates to the technical field of gantry machine tools. A control parameter sequence is obtained according to processing design and processing quality analysis; the gantry machine tool is operated through the control parameter sequence to process the machining raw materials, and production of the solid structural part of the structural part is executed; and monitoring the gantry machine tool based on the control deviation window, generating a process self-adaptive compensation parameter, and performing compensation control on the operation process of the gantry machine tool by adopting the process self-adaptive compensation parameter. The technical problem that in the prior art, the automation degree of the production process of the complex structural parts is low due to the fact that the dependence on manual operation is high in the machining process of producing the complex structural parts through a gantry machine tool is solved. The gantry machine tool achieves the technical effects that the gantry machine tool is automatic and intelligent in the machining process of complex structural parts, and the production efficiency and quality control quality of the structural parts are improved.

Description

Technical Field

[0001] The invention relates to the technical field of gantry machine tools, and in particular to a control parameter adaptive optimization method and device for a gantry machine tool. Background Art

[0002] In mechanical manufacturing, gantry machine tools are often used to process customized structural parts of machinery, which often have complex structures. Due to the complexity and diversity of customized structural parts, operators need to constantly manually adjust the cutting speed, feed rate and tool selection according to the processing situation to adapt to the material properties and geometric shapes of different areas.

[0003] This reliance on manual operations not only limits production efficiency, but also makes the processing process susceptible to human factors, making quality control more difficult.

[0004] In summary, in the prior art, there is a technical problem that the processing process of complex structural parts production using gantry machine tools is highly dependent on manual operation, resulting in a low degree of automation in the production process of complex structural parts. Summary of the invention

[0005] The present application provides a method and device for adaptively optimizing the control parameters of a gantry machine tool, which is used to solve the technical problem in the prior art that the processing process of complex structural parts production using a gantry machine tool is highly dependent on manual operation, resulting in a low degree of automation in the complex structural parts production process.

[0006] In view of the above problems, the present application provides a method and device for adaptively optimizing control parameters of a gantry machine tool.

[0007] In a first aspect of the present application, a control parameter adaptive optimization method for a gantry machine tool is provided, the method comprising: interactively obtaining an expected processing specification of an expected structural part, wherein the expected processing specification includes an expected processing design and an expected processing requirement; performing processing control parameter optimization according to the expected processing design to obtain a target control parameter sequence; performing raw material selection and calling according to the expected processing requirement to obtain a target processing raw material; operating a gantry machine tool to process the target processing raw material using the target control parameter sequence to execute production of a physical structural part of the expected structural part; presetting a control deviation window, and monitoring the gantry machine tool based on the control deviation window to obtain a machine tool operating parameter group for the production process of the physical structural part; analyzing the machine tool operating parameter group to generate a process adaptive compensation parameter, and using the process adaptive compensation parameter to execute compensation control of the operation process of the gantry machine tool.

[0008] According to a second aspect of the present application, there is provided a control parameter adaptive optimization device for a gantry machine tool, the device comprising: an expected information interaction module, for interactively obtaining an expected processing specification of an expected structural part, wherein the expected processing specification includes an expected processing design and an expected processing requirement; a control parameter optimization module, for performing processing control parameter optimization according to the expected processing design to obtain a target control parameter sequence; a processing raw material extraction module, for performing raw material selection and calling according to the expected processing requirement to obtain a target processing raw material; a production control execution module, for operating a gantry machine tool to process the target processing raw material using the target control parameter sequence to execute production of a physical structural part of the expected structural part; an operation deviation identification module, for presetting a control deviation window, and monitoring the gantry machine tool based on the control deviation window to obtain a machine tool operation parameter group for the production process of the physical structural part; a compensation control execution module, for analyzing the machine tool operation parameter group, generating a process adaptive compensation parameter, and using the process adaptive compensation parameter to perform compensation control of the operation process of the gantry machine tool.

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

[0010] The method provided in the embodiment of the present application obtains the expected processing specification of the expected structural part through interaction, wherein the expected processing specification includes the expected processing design and the expected processing requirements; performs processing control parameter optimization according to the expected processing design to obtain the target control parameter sequence; performs raw material selection and call according to the expected processing requirements to obtain the target processing raw material; uses the target control parameter sequence to operate the gantry machine tool to process the target processing raw material, and executes the production of the physical structural part of the expected structural part; presets a control deviation window, and monitors the gantry machine tool based on the control deviation window to obtain the machine tool operation parameter group of the physical structural part production process; analyzes the machine tool operation parameter group, generates process adaptive compensation parameters, and uses the process adaptive compensation parameters to perform compensation control on the gantry machine tool during the operation process. The adaptive optimization of control parameters in the gantry machine tool processing parameter setting dimension and the gantry machine tool production operation control dimension is realized, achieving the automation and intelligence of the gantry machine tool in the complex structural part processing process, and improving the production efficiency and quality control quality of the structural parts. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic flow chart of a control parameter adaptive optimization method for a gantry machine tool provided in this application;

[0012] Figure 2 A schematic diagram of a flow chart of obtaining a target control parameter sequence in a control parameter adaptive optimization method for a gantry machine tool provided in the present application;

[0013] Figure 3 A schematic diagram of the structure of a control parameter adaptive optimization device for a gantry machine tool provided in this application.

[0014] Explanation of the reference numerals: expected information interaction module 11, control parameter optimization module 12, processing raw material extraction module 13, production control execution module 14, operation deviation identification module 15, compensation control execution module 16. DETAILED DESCRIPTION

[0015] The present application provides a control parameter adaptive optimization method and device for a gantry machine tool, which is used to solve the technical problem in the prior art that the processing process of complex structural parts produced by gantry machine tools is highly dependent on manual operation, resulting in a low degree of automation in the production process of complex structural parts. The method realizes adaptive optimization of control parameters in the dimension of gantry machine tool processing parameter setting and the dimension of gantry machine tool production operation control, achieving the automation and intelligence of the gantry machine tool processing process of complex structural parts, and improving the production efficiency and quality control quality of structural parts.

[0016] Below, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited to the example embodiments described herein. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. It should also be noted that, for the convenience of description, only the parts related to the present invention are shown in the accompanying drawings, rather than all of them.

[0017] Embodiment 1

[0018] like Figure 1 As shown, the present application provides a control parameter adaptive optimization method for a gantry machine tool, the method comprising:

[0019] A100: Interactively obtain expected processing specifications of expected structural parts, wherein the expected processing specifications include expected processing design and expected processing requirements.

[0020] Specifically, in this embodiment, the expected structural part is an unspecified component that has not yet been produced, and the expected structural part can be obtained by processing through a gantry machine tool.

[0021] The expected processing specification is the design requirement of the expected structural part. Specifically, the expected processing specification includes the expected processing design characterizing the size and shape of the structural part and the expected processing requirement characterizing the material performance state of the expected processed part.

[0022] The expected processing design and the expected processing requirements are combined to analyze and restore the production control parameters of the gantry machine tool for producing the expected structural parts; the expected processing requirements are used to select and call raw materials for processing and producing the expected structural parts.

[0023] A200: Optimize the processing control parameters according to the expected processing design to obtain a target control parameter sequence.

[0024] In one embodiment, Figure 2 As shown, according to the expected processing design, processing control parameter optimization is performed to obtain a target control parameter sequence. The method step A200 provided in the present application also includes:

[0025] A210: Perform modeling and restoration according to the expected processing design to obtain a structural part model.

[0026] A220: Perform structural feature analysis based on the structural component model to obtain a processing array, wherein the processing array includes multiple processing units.

[0027] A230: Perform process overlap sequence analysis based on the processing technology array to obtain a target process sequence.

[0028] A240: Execute processing control parameter optimization according to the target process sequence to obtain a target control parameter sequence.

[0029] In one embodiment, structural feature analysis is performed based on the structural component model to obtain a processing array, and the method step A220 provided in the present application further includes:

[0030] A221: Interactively obtain a modeling space of the structural component model, and use 1 / 20 of the modeling space as a discrete grid size.

[0031] A222: discretize the structural part model using the discrete grid size, and extract and obtain a processing unit array based on the discretization result, wherein the processing unit array includes a plurality of discrete processing units.

[0032] A223: Pre-built machining process identification unit.

[0033] A224: Synchronize the processing unit array to the processing technology identification unit to perform process identification to obtain the processing technology array.

[0034] In one embodiment, the processing technology identification unit is pre-built, and the method step A223 provided in the present application further includes:

[0035] A223-1: Interactive gantry machine tool obtains multiple sample processing images, multiple sample processing processes, multiple sample processing designs and multiple sample processing parameters of associated mapping.

[0036] A223-2: Construct a processing technology identification branch based on the multiple sample processing images and the multiple sample processing technologies.

[0037] A223-3: Aggregate the multiple sample processing techniques to obtain multiple machine tool processing techniques, and reorganize the multiple sample processing designs and multiple sample processing parameters according to the multiple machine tool processing techniques to obtain multiple sample processing design sets and multiple sample processing parameter sets mapped to the multiple machine tool processing techniques.

[0038] A223-4: Construct multiple processing parameter analysis branches based on the multiple sample processing design sets and the multiple sample processing parameter sets.

[0039] A223-5: Connect the multiple processing parameter analysis branches in parallel, and connect the output end of the processing technology identification branch to the input end of the multiple processing parameter analysis branches to complete the construction of the processing technology identification unit.

[0040] In one embodiment, the processing unit array is synchronized to the processing technology identification unit to perform process identification to obtain the processing technology array. The method step A224 provided in the present application also includes:

[0041] A224-1: Synchronize the processing unit array to the processing technology identification unit to perform process identification to obtain an initial process array, wherein the initial process array includes multiple initial processing technology parameters mapped to the multiple discrete processing units.

[0042] A224-2: Randomly select multiple merging starting point units from the multiple discrete processing units, and based on the principles of process consistency and processing parameter consistency, perform merging judgment of adjacent discrete processing units in the multiple merging starting point units until the multiple initial processing parameters are traversed, the merging processing of the initial process array is completed, and the processing process array is obtained.

[0043] In one embodiment, process overlap sequence analysis is performed based on the processing array to obtain a target process sequence. The method step A230 provided in the present application further includes:

[0044] A231: Extract and obtain multiple process overlapping units based on the processing technology array.

[0045] A232: Perform process retention integrity analysis on the multiple process overlapping units to obtain multiple process execution sequences.

[0046] A233: Aggregate the multiple process execution sequences to obtain the target process sequence, wherein the target process sequence includes K real-time processing processes, and K is a positive integer.

[0047] In one embodiment, the process control parameter optimization is performed according to the target process sequence to obtain the target control parameter sequence. The method step A240 provided in the present application further includes:

[0048] A241: Extract and obtain a first real-time processing technology based on the target process sequence, wherein the first real-time processing technology is the first process among K real-time processing technologies in the target process sequence.

[0049] A242: Use the first real-time processing technology to traverse the processing technology array and extract M real-time processing parameters of M processing technology units.

[0050] A243: Interactively obtain the first standard processing parameters of the first real-time processing process, and obtain M processing deviation coefficients of the M real-time processing parameters and the first standard processing parameters based on Euclidean distance calculation.

[0051] A244: Sequence the M processing units according to the M processing deviation coefficients to obtain a first real-time processing control trajectory.

[0052] A245: Similarly, K real-time processing control trajectories of the K real-time processing processes in the target process sequence are obtained.

[0053] A246: Connect the K real-time processing control trajectories based on the target process sequence to obtain the target control parameter sequence.

[0054] Specifically, in this embodiment, based on step A100, it can be known that the expected processing design represents the size and shape of the structural part, and may specifically include surface features of the structural part such as curves and hole positions. Therefore, this embodiment performs modeling and restoration according to the expected processing design based on existing CAD modeling technology to obtain a structural part model, and the structural part model reflects the structural features such as the size and shape of the expected structural part from a three-dimensional space dimension.

[0055] It should be understood that the parameter design of any structural component area can be easily extracted based on the structural component model. In this embodiment, based on the acquisition of the structural component model, the modeling space is automatically created through the tools in the CAD software. The size of the modeling space is appropriate to accommodate the structural component model.

[0056] The modeling space is a cube, and 1 / 20 of the length, width and height of the modeling space is taken as the length, width and height of the discrete grid size. The discrete grid size is then used to grid the structural part model, and the overall gridding of the structural part model is divided into multiple discrete processing units to complete the discretization processing of the structural part model.

[0057] The plurality of discrete processing units are spatially marked to ensure the restoration of the plurality of discrete processing units to the structural component model. The plurality of discrete processing units with spatial position marks constitute the processing unit array, wherein the processing unit array includes a plurality of discrete processing units.

[0058] A processing technology identification unit is pre-constructed, and the processing technology identification unit can accurately detect the processing technology of the non-segmented surface (the component surface of the structural surface model, the discretized additional surface) of each discrete processing unit and the control parameters under the specific processing technology.

[0059] The construction process of the processing technology identification unit is as follows:

[0060] Based on the characteristics that properties such as material hardness affect processing control parameters, this embodiment uses the expected processing requirements as constraints, and obtains multiple sample processing images, multiple sample processing processes, multiple sample processing designs and multiple sample processing parameters of associated mappings through the historical processing log of the interactive gantry machine tool, wherein the meaning of each group of sample processing images, sample processing processes, sample processing designs and sample processing parameters is as follows: the sample processing process is a specific machine tool processing process used to realize the sample processing image, the sample processing design is a specific shape and size design parameter of the sample processing image, which is used for reference to generate the sample processing parameters, and the corresponding processing equipment is called according to the sample processing process, the sample processing parameters are generated according to the sample processing design, and the sample processing parameters are used to execute the operation control of the processing equipment, so as to obtain the sample processing image.

[0061] This embodiment constructs a processing technology identification branch based on a back propagation neural network, and the processing technology identification branch is used to analyze and determine the specific machine tool processing technology used to realize the processing image after obtaining the processing image, including but not limited to milling, drilling, and cutting.

[0062] Multiple groups of multiple sample processing images - multiple sample processing technologies are divided into training set, test set and verification set using a data volume identifier of 17:2:1, and the training set and the test set are used to perform supervised training of the processing technology recognition branch to provide input images and correct process labels so that the neural network can learn how to correctly classify processes. The verification set is used to verify the process analysis recognition accuracy of the processing technology recognition branch until the process analysis recognition accuracy of the processing technology recognition branch meets the preset requirements. This embodiment uses a large amount of image data training to enable the processing technology recognition branch to intelligently identify and classify different processing technologies, thereby improving the efficiency and accuracy of process recognition.

[0063] The same type of processes are aggregated for the multiple sample processing techniques to obtain a plurality of machine tool processing techniques covering all machine tool processing techniques.

[0064] Furthermore, based on the data characteristics that there is a mapping relationship between the multiple sample processing images, multiple sample processing processes, multiple sample processing designs and multiple sample processing parameters in the previous text, the multiple sample processing designs and multiple sample processing parameters are reorganized according to the multiple machine tool processing processes to obtain multiple sample processing design sets and multiple sample processing parameter sets mapped to the multiple machine tool processing processes.

[0065] The same method of constructing the processing technology identification branch is adopted to obtain multiple processing parameter analysis branches based on the multiple sample processing design sets and the multiple sample processing parameter sets. Each processing parameter analysis can realize the processing technology control parameters of the structural part apparent design parameters according to the input structural part apparent design parameter analysis output.

[0066] Each processing parameter analysis branch has a processing technology identification. The purpose of constructing multiple processing parameter analysis branches is to ensure that no matter what process type the output of the identification branch is, there is a corresponding parameter analysis branch that can analyze and provide processing parameters.

[0067] The multiple processing parameter analysis branches are connected in parallel, and the output end of the processing technology identification branch is connected to the input ends of the multiple processing parameter analysis branches to complete the construction of the processing technology identification unit.

[0068] The processing technology identification unit constructed in this embodiment realizes rapid analysis and determination of the required processing technology after obtaining the processing simulation image, and rapid determination of specific required control parameters under the required processing technology after obtaining the processing design parameters.

[0069] The specific method of using the processing technology identification unit is as follows:

[0070] Since the implementation method of analyzing and determining the required processing parameters for multiple discrete processing units in the processing unit array is consistent, this embodiment takes the processing parameters of the randomly selected first discrete processing unit as an example to elaborate on the specific use method of the processing technology identification unit.

[0071] A first non-segmented surface image is extracted based on the first discrete processing unit; and then modeling parameters of the first discrete processing unit are extracted with reference to the first non-segmented surface image to obtain a first discrete processing design.

[0072] The first non-segmented surface image is input into the processing technology identification branch of the processing technology identification unit to obtain the first processing technology, and then the multiple processing technology identifiers of the multiple processing parameter analysis branches are traversed according to the first processing technology, and a target processing parameter analysis branch is selected, and then the first discrete processing design is input into the target processing parameter analysis branch to obtain the first initial processing technology parameters for realizing the processing to obtain the first non-segmented surface image, wherein the first initial processing technology parameters use the first processing technology identifier.

[0073] By analogy, the processing unit array is synchronized to the processing technology identification unit to perform technology identification to obtain an initial technology array, wherein the initial technology array includes multiple initial processing technology parameters mapped to the multiple discrete processing units, and each initial processing technology parameter has a processing technology identifier.

[0074] The processing technology and processing control parameters of each discrete processing unit are recorded and sorted to form a data list, and the merging criteria are clearly defined, that is, two discrete processing units can only be merged if they are adjacent in the processing unit array and have consistent processes and processing parameters.

[0075] The adjacent relationship of multiple discrete processing units is obtained according to the processing unit array, and then an adjacency list is created for each discrete processing unit based on the adjacent relationship, listing all adjacent discrete processing units and their corresponding initial processing parameters and processing identifiers.

[0076] One or more discrete processing units are randomly selected from the plurality of discrete processing units as starting points for merging, to obtain the plurality of merging starting points.

[0077] Starting from multiple merged starting point units, traverse their adjacency lists, compare the processing technology identifiers and initial processing technology parameters, merge the consistent ones, obtain multiple expanded starting point units, use the inconsistent multiple discrete processing units as multiple updated merged starting point units, repeat the above process for the multiple expanded starting point units and the multiple updated merged starting point units, until the multiple initial processing technology parameters and multiple processing technology identifiers of the multiple discrete processing units are traversed, and the multiple discrete processing units are merged into multiple processing technology units with consistent initial processing technology parameters and processing technology identifiers. The multiple processing technology units constitute the processing technology array in space.

[0078] It should be understood that there are process overlaps in the processing process units. Specifically, a process consistency unit includes multiple sets of processing processes-combined processing process parameters. Processing equipment is called and operation controlled based on the multiple sets of processing processes-initial processing process parameters to achieve processing of the process consistency unit to the required processing design.

[0079] Based on this, this embodiment counts the processing technology types of each processing technology unit in the processing technology array, extracts and processes the processing technology units with different processing technology types, and obtains the multiple process overlapping units.

[0080] Since the process retention integrity analysis is performed on the process overlapping units, the method for obtaining the process execution sequence is consistent, and this embodiment randomly extracts the first process overlapping unit from the multiple process overlapping units, wherein the first process overlapping unit records multiple sets of processing technology-merged processing technology parameters.

[0081] A plurality of sets of processing technology-initial processing technology parameters are respectively used to perform processing technology control fitting in the first process overlapping unit to obtain a plurality of fitting processing design images.

[0082] The first process overlapping unit is subjected to non-segmented surface image extraction to obtain a first process overlapping non-segmented surface image, and then based on the existing image similarity comparison technology, the first process overlapping non-segmented surface image is compared with the multiple fitting processing design images to obtain multiple similarity coefficients.

[0083] It should be understood that the higher the similarity coefficient, the later the corresponding processing technology is executed and the more complete the processing traces are preserved. Based on this, this embodiment adopts a small to large sorting rule according to the multiple similarity coefficients to serialize the multiple processing technologies in the multiple groups of processing technology-initial processing technology parameters to obtain the first process execution sequence of the first process overlapping unit.

[0084] By analogy, multiple process execution sequences of the multiple process overlapping units are obtained, and then the repeated process steps of the multiple process execution sequences are identified, and then the multiple process execution sequences are aligned based on the identification results, and the sorting position of each processing step in the target process sequence is determined, and the aggregation of the multiple process execution sequences is completed to obtain the target process sequence, wherein the target process sequence includes K real-time processing processes with sequence identifiers, K is a positive integer, and the real-time processing process has the same meaning as the processing process in the previous text, and is only distinguished here. The target process sequence is the order of scheduling the processing processes of the gantry machine tool when the expected workpiece is obtained through processing.

[0085] A first real-time machining process is extracted based on the target process sequence, where the first real-time machining process is the first process among K real-time machining processes in the target process sequence.

[0086] The processing technology array is traversed with the first real-time processing technology to extract M processing technology units using the first real-time processing technology, and initial processing technology parameters of the M processing technology units corresponding to the first real-time processing technology are extracted to obtain M real-time processing parameters.

[0087] Interactively obtain the first standard processing parameters of the first real-time processing process, where the first standard processing parameters are the operating parameters of the first real-time processing process when the corresponding processing equipment is started and run, and obtain M processing deviation coefficients of the M real-time processing parameters and the first standard processing parameters based on Euclidean distance calculation.

[0088] According to the M processing deviation coefficients, the M processing units are serialized to obtain a first real-time processing control trajectory. Based on the first real-time processing control trajectory, processing control parameters of the M processing units are adjusted to achieve a smaller parameter adjustment amount and reduce the complexity of parameter adjustment.

[0089] By analogy, K real-time machining control trajectories of the K real-time machining processes in the target process sequence are obtained. The K real-time machining control trajectories are connected based on the target process sequence to obtain the target control parameter sequence.

[0090] It should be understood that by using the target control parameter sequence to perform three-dimensional processing on the expected structural part blank, a structural part entity that meets the expected processing design can be obtained.

[0091] This embodiment achieves the technical effect of reducing the dependence of the expected structural part processing technology analysis process on human experience based on the expected structural part design information, improving the restoration of the processing control parameters to the expected structural part design, and achieving that the processing control parameters obtained by analysis will more accurately reflect the design intent of the expected processing design.

[0092] A300: Execute raw material selection and call according to the expected processing requirements to obtain target processing raw materials.

[0093] A400: Using the target control parameter sequence to operate the gantry machine tool to process the target processing raw material, and execute the production of the physical structural part of the expected structural part.

[0094] Specifically, based on step A100, it can be known that the expected processing requirement is the material performance state requirement for the expected processed part, and thus this embodiment uses the expected processing requirement as a constraint to perform raw material selection and call to obtain the target processing raw material.

[0095] After the gantry machine tool clamps the target raw material in a directional manner, the gantry machine tool is operated to process the target raw material using the target control parameter sequence to execute the production of the physical structural part of the expected structural part.

[0096] A500: Preset a control deviation window, and monitor the gantry machine tool based on the control deviation window to obtain a machine tool operating parameter group for the solid structural part production process.

[0097] A600: Analyze the machine tool operation parameter group, generate process adaptive compensation parameters, and use the process adaptive compensation parameters to perform compensation control on the operation process of the gantry machine tool.

[0098] Specifically, it should be understood that as the gantry machine tool operates continuously, the temperature and amplitude performance of the gantry machine tool will change. If the changes are irregular, there is a risk of processing deviation.

[0099] Based on this, the present embodiment presets a control deviation window, and illustratively, the control deviation window is 15 minutes. Based on the control deviation window, the gantry machine tool is monitored to obtain a machine tool operation parameter group of the solid structural part production process, each machine tool operation parameter group includes an amplitude change sequence and a temperature change sequence that synchronously fall into the control deviation window.

[0100] The amplitude change sequence and the temperature change sequence are processed in an image-based manner, and the temperature-amplitude change law is analyzed based on the image to obtain the temperature-amplitude stable change period and the periodic stable change feature, and then the fused image of the amplitude change sequence and the temperature change sequence is segmented based on the temperature-amplitude stable change period, and the periodic stable change feature is used to traverse the segmentation result to locate the unstable change time node, which is the time node when the amplitude change sequence and the temperature change sequence no longer show periodic stable data changes.

[0101] The time span between the unstable change time node and the start time of the control deviation window is taken as the process adaptive compensation period, and the local amplitude change sequence and the local temperature change sequence falling into the process adaptive compensation period are extracted from the amplitude change sequence and the temperature change sequence, and then the mean of the local amplitude change sequence is calculated to obtain the amplitude adaptive compensation parameter, and the mean of the local temperature change sequence is calculated to obtain the temperature adaptive compensation parameter.

[0102] The temperature adaptive compensation parameters, amplitude adaptive compensation parameters and process adaptive compensation cycle constitute the process adaptive compensation parameters, and the process adaptive compensation parameters are used to perform compensation control on the operation process of the gantry machine tool. The specific compensation control is that during the production of physical structural parts, the temperature and vibration state of the gantry machine tool are adjusted by using the temperature adaptive compensation parameters and the amplitude adaptive compensation parameters at intervals of the process adaptive compensation cycle to eliminate the control deviation of the continuous operation of the gantry machine tool.

[0103] This embodiment achieves the technical effect of automating and intelligentizing the complex structural parts processing process of the gantry machine tool and improving the production efficiency and quality control quality of the structural parts by performing adaptive optimization of the control parameters in the gantry machine tool processing parameter setting dimension and the gantry machine tool production operation control dimension.

[0104] Embodiment 2

[0105] Based on the same inventive concept as the control parameter adaptive optimization method of a gantry machine tool in the aforementioned embodiment, Figure 3 As shown, the present application provides a control parameter adaptive optimization device for a gantry machine tool, wherein the device comprises:

[0106] The expected information interaction module 11 is used to interactively obtain the expected processing specifications of the expected structural parts, wherein the expected processing specifications include the expected processing design and the expected processing requirements.

[0107] The control parameter optimization module 12 is used to perform machining control parameter optimization according to the expected machining design to obtain a target control parameter sequence.

[0108] The processing raw material extraction module 13 is used to execute raw material selection and call according to the expected processing requirements to obtain target processing raw materials.

[0109] The production control execution module 14 is used to operate the gantry machine tool to process the target processing raw material using the target control parameter sequence to execute the production of the physical structural part of the expected structural part.

[0110] The operation deviation identification module 15 is used to preset a control deviation window, and monitor the gantry machine tool based on the control deviation window to obtain a machine tool operation parameter group of the solid structure part production process.

[0111] The compensation control execution module 16 is used to analyze the machine tool operation parameter group, generate process adaptive compensation parameters, and use the process adaptive compensation parameters to perform compensation control on the operation process of the gantry machine tool.

[0112] In one embodiment, the control parameter optimization module 12 further includes:

[0113] Modeling and restoration are performed according to the expected processing design to obtain a structural component model; structural feature analysis is performed based on the structural component model to obtain a processing technology array, wherein the processing technology array includes multiple processing technology units; process overlap sequence analysis is performed based on the processing technology array to obtain a target process sequence; processing control parameter optimization is performed according to the target process sequence to obtain a target control parameter sequence.

[0114] In one embodiment, the control parameter optimization module 12 further includes:

[0115] Interactively obtain a modeling space of the structural part model, and use 1 / 20 of the modeling space as a discrete grid size; discretize the structural part model using the discrete grid size, and extract and obtain a processing unit array based on the discretization result, wherein the processing unit array includes a plurality of discrete processing units; pre-construct a processing technology identification unit; synchronize the processing unit array to the processing technology identification unit to perform process identification to obtain the processing technology array.

[0116] In one embodiment, the control parameter optimization module 12 further includes:

[0117] The interactive gantry machine tool obtains multiple sample processing images, multiple sample processing techniques, multiple sample processing designs and multiple sample processing parameters of associated mapping; constructs a processing technique identification branch based on the multiple sample processing images and multiple sample processing techniques; aggregates the multiple sample processing techniques to obtain multiple machine tool processing techniques, and reorganizes the multiple sample processing designs and multiple sample processing parameters according to the multiple machine tool processing techniques to obtain multiple sample processing design sets and multiple sample processing parameter sets mapped to the multiple machine tool processing techniques; constructs multiple processing parameter analysis branches based on the multiple sample processing design sets and multiple sample processing parameter sets; connects the multiple processing parameter analysis branches in parallel, and connects the output end of the processing technique identification branch with the input end of the multiple processing parameter analysis branches to complete the construction of the processing technique identification unit.

[0118] In one embodiment, the control parameter optimization module 12 further includes:

[0119] The processing unit array is synchronized to the processing technology identification unit to perform process identification to obtain an initial process array, wherein the initial process array includes multiple initial processing technology parameters mapped to the multiple discrete processing units; a plurality of merging starting point units are randomly selected from the multiple discrete processing units, and based on the principles of process consistency and processing parameter consistency, adjacent discrete processing unit merging judgments are performed in the multiple merging starting point units until the multiple initial processing technology parameters are traversed and the merging processing of the initial process array is completed to obtain the processing technology array.

[0120] In one embodiment, the control parameter optimization module 12 further includes:

[0121] Based on the processing technology array, multiple process overlapping units are extracted to obtain; process retention integrity analysis is performed on the multiple process overlapping units to obtain multiple process execution sequences; the multiple process execution sequences are aggregated to obtain the target process sequence, wherein the target process sequence includes K real-time processing technologies, and K is a positive integer.

[0122] In one embodiment, the control parameter optimization module 12 further includes:

[0123] A first real-time processing technology is extracted based on the target process sequence, wherein the first real-time processing technology is the first process among the K real-time processing technologies in the target process sequence; the first real-time processing technology is used to traverse the processing technology array to extract M real-time processing parameters of M processing technology units; the first standard processing parameters of the first real-time processing technology are interactively obtained, and M processing deviation coefficients of the M real-time processing parameters and the first standard processing parameters are obtained based on Euclidean distance calculation; the M processing technology units are serialized according to the M processing deviation coefficients to obtain a first real-time processing control trajectory; and so on, K real-time processing control trajectories of the K real-time processing technologies in the target process sequence are obtained; the K real-time processing control trajectories are connected based on the target process sequence to obtain the target control parameter sequence.

[0124] Any of the methods or steps described above may be stored as computer instructions or programs in various types of computer memories, and the computer instructions or programs may be recognized by various types of computer processors to implement any of the methods or steps described above.

[0125] Based on the above specific embodiments of the present invention, any improvements and modifications made to the present invention by those skilled in the art without departing from the principles of the present invention shall fall within the patent protection scope of the present invention.

Claims

1. A control parameter adaptive optimization method for a gantry machine tool, characterized in that: The method comprises: interactively obtaining an expected processing specification of an expected structural part, wherein the expected processing specification includes an expected processing design and an expected processing requirement; Optimize the processing control parameters according to the expected processing design to obtain a target control parameter sequence; Execute raw material selection and call according to the expected processing requirements to obtain target processing raw materials; Using the target control parameter sequence to operate the gantry machine tool to process the target processing raw material, and to execute the production of the physical structural part of the expected structural part; Presetting a control deviation window, and monitoring the gantry machine tool based on the control deviation window to obtain a machine tool operating parameter group for the production process of the solid structural part; The machine tool operation parameter group is analyzed to generate process adaptive compensation parameters, and the process adaptive compensation parameters are used to perform compensation control on the operation process of the gantry machine tool.

2. A control parameter adaptive optimization method for a gantry machine tool as claimed in claim 1, characterized in that: Optimizing the machining control parameters according to the expected machining design to obtain a target control parameter sequence, the method further comprising: Perform modeling and restoration according to the expected processing design to obtain a structural component model; Performing structural feature analysis based on the structural component model to obtain a processing array, wherein the processing array includes a plurality of processing units; Performing process overlap sequence analysis based on the processing technology array to obtain a target process sequence; The processing control parameter optimization is performed according to the target process sequence to obtain the target control parameter sequence.

3. A control parameter adaptive optimization method for a gantry machine tool as claimed in claim 2, characterized in that: Structural feature analysis is performed based on the structural component model to obtain a processing technology array, and the method further includes: Interactively obtain a modeling space of the structural component model, and use 1 / 20 of the modeling space as a discrete grid size; The structural component model is discretized using the discrete grid size, and a processing unit array is extracted based on the discretization result, wherein the processing unit array includes a plurality of discrete processing units; Pre-built processing technology identification unit; The processing unit array is synchronized to the processing technology identification unit to perform technology identification to obtain the processing technology array.

4. A control parameter adaptive optimization method for a gantry machine tool as claimed in claim 3, characterized in that: A processing technology identification unit is pre-built, and the method further comprises: The interactive gantry machine tool obtains multiple sample processing images, multiple sample processing processes, multiple sample processing designs and multiple sample processing parameters of the associated mapping; Constructing a processing technology recognition branch based on the multiple sample processing images and the multiple sample processing technologies; Aggregating the plurality of sample processing techniques to obtain a plurality of machine tool processing techniques, and reorganizing the plurality of sample processing designs and a plurality of sample processing parameters according to the plurality of machine tool processing techniques to obtain a plurality of sample processing design sets and a plurality of sample processing parameter sets mapped to the plurality of machine tool processing techniques; Constructing and obtaining multiple processing parameter analysis branches based on the multiple sample processing design sets and the multiple sample processing parameter sets; The multiple processing parameter analysis branches are connected in parallel, and the output end of the processing technology identification branch is connected to the input ends of the multiple processing parameter analysis branches to complete the construction of the processing technology identification unit.

5. A control parameter adaptive optimization method for a gantry machine tool as claimed in claim 3, characterized in that: The processing unit array is synchronized to the processing technology identification unit to perform technology identification to obtain the processing technology array, and the method further includes: Synchronizing the processing unit array to the processing technology identification unit to perform technology identification to obtain an initial technology array, wherein the initial technology array includes a plurality of initial processing technology parameters mapped to the plurality of discrete processing units; A plurality of merging starting point units are randomly selected from the plurality of discrete processing units, and based on the principle of process consistency and processing parameter consistency, adjacent discrete processing unit merging judgment is performed in the plurality of merging starting point units until the plurality of initial processing parameters are traversed, the merging processing of the initial process array is completed, and the processing process array is obtained.

6. A control parameter adaptive optimization method for a gantry machine tool as claimed in claim 5, characterized in that: Performing process overlap sequence analysis based on the processing technology array to obtain a target process sequence, the method further includes: Extract and obtain a plurality of process overlapping units based on the processing technology array; Performing process retention integrity analysis on the multiple process overlapping units to obtain multiple process execution sequences; Aggregate the multiple process execution sequences to obtain the target process sequence, wherein the target process sequence includes K real-time machining processes, and K is a positive integer.

7. A control parameter adaptive optimization method for a gantry machine tool as claimed in claim 6, characterized in that: Optimizing the processing control parameters according to the target process sequence to obtain a target control parameter sequence, the method further comprising: Extracting and obtaining a first real-time machining process based on the target process sequence, wherein the first real-time machining process is the first process among K real-time machining processes in the target process sequence; Traversing the processing technology array with the first real-time processing technology to extract and obtain M real-time processing parameters of M processing technology units; Interactively obtaining a first standard processing parameter of the first real-time processing process, and obtaining M processing deviation coefficients of the M real-time processing parameters and the first standard processing parameters based on Euclidean distance calculation; Sequencing the M processing units according to the M processing deviation coefficients to obtain a first real-time processing control trajectory; By analogy, K real-time processing control trajectories of the K real-time processing processes in the target process sequence are obtained; The K real-time machining control trajectories are connected based on the target process sequence to obtain the target control parameter sequence.

8. A control parameter adaptive optimization device for a gantry machine tool, characterized in that: A method for adaptively optimizing control parameters of a gantry machine tool according to any one of claims 1 to 7, the device comprising: An expected information interaction module, used to interactively obtain an expected processing specification of an expected structural part, wherein the expected processing specification includes an expected processing design and an expected processing requirement; A control parameter optimization module, used to perform machining control parameter optimization according to the expected machining design to obtain a target control parameter sequence; A processing raw material extraction module is used to execute raw material selection and call according to the expected processing requirements to obtain target processing raw materials; A production control execution module, used to operate a gantry machine tool to process the target processing raw material using the target control parameter sequence, and to execute the production of the physical structural part of the expected structural part; An operation deviation identification module is used to preset a control deviation window, and monitor the gantry machine tool based on the control deviation window to obtain a machine tool operation parameter group for the production process of the solid structural part; The compensation control execution module is used to analyze the machine tool operation parameter group, generate process adaptive compensation parameters, and use the process adaptive compensation parameters to perform compensation control on the operation process of the gantry machine tool.

Images