A method and system for optimizing machining performance of numerical control tools

Abstract

The present invention discloses a method and system for optimizing the machining performance of numerical control tools, which relates to the technical field of tool machining, including: searching and calling homologous application data for a target numerical control tool to determine an application data set; traversing the application data set to perform hierarchical clustering and defect point location, and performing fuzzy conversion of defect points through a fuzzy conversion model to determine an optimization target; performing a multi-scenario destruction morphology analysis on the target numerical control tool to determine a multi-limit coefficient based on machining performance; building an adaptive optimization module with multi-limit coefficients as constraints; based on the adaptive optimization module, performing multi-target optimization and iterative verification in combination with an initial machining plan to determine a machining optimization strategy; and optimizing machining control of the target numerical control tool based on the machining optimization strategy. The present invention solves the technical problems of low control accuracy and slow response speed in the prior art for numerical control tool machining, and achieves the technical effect of improving the control accuracy and response speed of numerical control tool machining.

Description

Technical Field

[0001] The present invention relates to the technical field of tool processing, and in particular to a method and system for optimizing the processing performance of a numerical control tool. Background Art

[0002] With the rapid development of industrial production and manufacturing technology, CNC tools have been widely used in many fields. However, with the continuous expansion of production scale and the increasing complexity of process flow, the monitoring and management of CNC tool processing are also facing greater challenges.

[0003] In practical applications, traditional CNC tool processing methods cannot respond to problems such as tool wear, temperature changes and vibration during processing in a timely manner, resulting in unstable processing quality and low efficiency. At the same time, traditional methods lack real-time monitoring and feedback mechanisms for key parameters during processing, and cannot achieve precise control and optimization of the processing process. Summary of the invention

[0004] The present application provides a method and system for optimizing the machining performance of a numerical control tool, which are used to solve the technical problems of low control accuracy and slow response speed in the prior art for numerical control tool machining.

[0005] In view of the above problems, the present application provides a method and system for optimizing CNC tool machining performance.

[0006] In a first aspect of the present application, a method for optimizing machining performance of a numerical control tool is provided, the method comprising:

[0007] For the target CNC tool, perform homologous application data retrieval and call to determine the application data set; traverse the application data set, perform hierarchical clustering and defect point location, and perform fuzzy transformation of defect points through a fuzzy transformation model to determine the optimization target; by performing multi-scenario destruction morphology analysis on the target CNC tool, determine the multi-limit coefficient based on the processing performance, and there is a corresponding relationship between the multi-limit coefficient and the performance index; use the multi-limit coefficient as a constraint to build an adaptive optimization module; based on the adaptive optimization module, in combination with the initial processing plan, perform multi-objective optimization and iterative verification based on the optimization target to determine the processing optimization strategy, wherein the optimized target is identified with a weight coefficient; based on the processing optimization strategy, optimize the processing control of the target CNC tool.

[0008] A second aspect of the present application provides a CNC tool processing performance optimization system, the system comprising:

[0009] A retrieval and calling unit, wherein the retrieval and calling unit performs a homologous application data retrieval and calling for a target CNC tool to determine an application data set; an optimization target determination unit, wherein the optimization target determination unit traverses the application data set to perform hierarchical clustering and defect point location, and performs fuzzy transformation of defect points through a fuzzy transformation model to determine an optimization target; a destruction morphology analysis unit, wherein the destruction morphology analysis unit determines a multi-limit coefficient based on processing performance by performing a multi-scenario destruction morphology analysis on the target CNC tool, and the multi-limit coefficient corresponds to a performance index; an adaptive optimization module building unit, wherein the adaptive optimization module building unit builds an adaptive optimization module with the multi-limit coefficient as a constraint; a processing optimization strategy determination unit, wherein the processing optimization strategy determination unit performs multi-target optimization and iterative verification based on the optimization target based on the adaptive optimization module and an initial processing plan to determine a processing optimization strategy, wherein the optimized target is identified with a weight coefficient; an optimized processing control unit, wherein the optimized processing control unit performs optimized processing control on the target CNC tool based on the processing optimization strategy.

[0010] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0011] This application searches and calls homologous application data for the target CNC tool to determine the application data set; traverses the application data set, performs hierarchical clustering and defect point location, and performs fuzzy conversion of defect points through a fuzzy conversion model to determine the optimization target; by performing a multi-scenario destruction morphology analysis on the target CNC tool, a multi-limit coefficient based on processing performance is determined, and there is a corresponding relationship between the multi-limit coefficient and the performance index; with the multi-limit coefficient as a constraint, an adaptive optimization module is built; based on the adaptive optimization module, combined with the initial processing plan, multi-objective optimization and iterative verification based on the optimization target are performed to determine the processing optimization strategy, wherein the optimized target identifier has a weight coefficient; based on the processing optimization strategy, the target CNC tool is optimized for processing control. The present invention solves the technical problems of low control accuracy and slow response speed in the prior art for CNC tool processing, and achieves the technical effect of improving the control accuracy and response speed of CNC tool processing by combining homologous application data retrieval, hierarchical clustering, defect point location, fuzzy conversion model, multi-scenario destruction morphology analysis, adaptive optimization module, multi-objective optimization and iterative verification technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] 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.

[0013] Figure 1 A schematic diagram of a process flow of a CNC tool machining performance optimization method provided in an embodiment of the present application;

[0014] Figure 2 A schematic diagram of the structure of a CNC tool machining performance optimization system provided in an embodiment of the present application.

[0015] Explanation of the accompanying drawings: retrieval and calling unit 11, optimization target determination unit 12, destruction morphology analysis unit 13, adaptive optimization module building unit 14, processing optimization strategy determination unit 15, optimization processing control unit 16. DETAILED DESCRIPTION

[0016] The present application provides a method and system for optimizing the performance of CNC tool processing, aiming to solve the technical problems of low control accuracy and slow response speed in the prior art for CNC tool processing. By combining homologous application data retrieval, hierarchical clustering, defect point location, fuzzy transformation model, closed-loop morphological analysis of multi-scenario, adaptive optimization module, multi-objective optimization and iterative verification technology, the technical effect of improving the control accuracy and response speed of CNC tool processing is achieved.

[0017] 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.

[0018] It should be noted that any variations of the terms "include" and "have" 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 inherent to these processes, methods, products or devices.

[0019] Embodiment 1

[0020] like Figure 1 As shown, the present application provides a method for optimizing the machining performance of a numerical control tool, the method comprising:

[0021] Step S100: for a target numerical control tool, perform a search and call for homologous application data to determine an application data set.

[0022] In the embodiment of the present application, the database or cloud data storage of the CNC equipment is used to identify and extract all historical data related to the target CNC tool. These data include but are not limited to tool usage records, processing parameters, tool wear, processing technology, environmental conditions, etc. Big data analysis technologies, such as SQL queries, NoSQL databases, data warehouses, etc., are used to retrieve and call application data of the same type of tools under similar processing conditions, and data preprocessing technologies, such as data cleaning, normalization, missing value processing, etc., are applied to the retrieved data to improve data quality. Finally, the processed data is integrated to form an application data set.

[0023] Step S200: traverse the application data set, perform hierarchical clustering and defect point location, perform fuzzy transformation of defect points through a fuzzy transformation model, and determine the optimization target.

[0024] In an embodiment of the present application, a comprehensive traversal of the application data set is performed to ensure that all data is read and analyzed. A hierarchical clustering algorithm, such as agglomerative hierarchical clustering or divisive hierarchical clustering, is applied to classify and aggregate the data set. In the clustering results, specific defect points are further identified and located. These defect points may be specific instances of problems such as tool wear, breakage, and reduced precision. Through data analysis techniques such as anomaly detection, outliers or problem points in the data set are found. Next, a fuzzy transformation model is constructed and applied to perform fuzzy transformation on the determined defect points. Through the processing of the fuzzy transformation model, the optimization target is determined. The optimization targets include improving the durability of the tool, reducing processing errors, optimizing processing parameters, etc.

[0025] Step S300: by performing a multi-scenario destruction morphology analysis on the target numerical control tool, a multi-limit coefficient based on machining performance is determined, and there is a corresponding relationship between the multi-limit coefficient and the performance index.

[0026] In an embodiment of the present application, a destruction morphology analysis is performed for a target CNC tool under various processing scenarios. Multivariate scenarios refer to different working conditions, materials, processing parameters, etc. The destruction morphology analysis includes a study of the wear, fracture, deformation, etc. of the tool under different conditions to obtain the performance of the tool under various conditions. Based on the results of the destruction morphology analysis, multiple limit coefficients related to the tool processing performance are determined. These coefficients reflect the changes and influencing factors of the tool performance under different scenarios. The limit coefficients include wear limit, cutting force limit, temperature threshold, etc. A correspondence is established between the multiple limit coefficients and specific performance indicators. Performance indicators include tool life, processing accuracy, surface quality, cutting efficiency, etc.

[0027] Step S400: constructing an adaptive optimization module with the multi-limit coefficients as constraints.

[0028] In an embodiment of the present application, according to the determined multi-limit coefficients, these coefficients include the wear limit of the tool under different processing conditions, the cutting force threshold, the temperature threshold, etc. The adaptive optimization module is constructed using these multi-limit coefficients as constraints. According to the nature of the problem and the constraints, a suitable optimization algorithm is selected. For multi-objective optimization problems, it is necessary to adopt a multi-objective optimization algorithm, such as a genetic algorithm, a particle swarm optimization algorithm, etc. Based on the selected optimization algorithm, an adaptive optimization module is constructed. This module can automatically adjust the optimization parameters and strategies to adapt to different processing conditions and performance requirements.

[0029] Step S500: Based on the adaptive optimization module and in combination with the initial processing plan, multi-objective optimization and iterative verification based on the optimization target are performed to determine the processing optimization strategy, wherein the optimized target is identified with a weight coefficient.

[0030] In the embodiment of the present application, the initial processing scheme is first read and loaded from the database or industrial control system. These schemes include initial processing parameters and tool configuration. In addition, the optimization targets determined in the previous steps are loaded. These targets include tool life, processing accuracy, surface quality, cutting efficiency, etc. At the same time, the weight coefficient of the optimization target is loaded, and the weight coefficient is pre-set by a technical expert. Next, the adaptive optimization module is used to establish a multi-objective optimization model. The model contains multiple objective functions, each objective function corresponds to an optimization target, and a weight coefficient is added to reflect the importance of different optimization targets. Through this model, multiple targets are optimized simultaneously. Select a suitable multi-objective optimization algorithm, such as a multi-objective genetic algorithm, a multi-objective particle swarm optimization algorithm, etc., and automatically configure the initial parameters of the algorithm. On the basis of the initial processing scheme, the multi-objective optimization algorithm is run to search for the best processing strategy that meets all optimization targets. During the optimization process, the comprehensive evaluation index is calculated according to the weight coefficient. After each optimization iteration, the optimization result is verified, and the feasibility and effect of the optimization scheme are verified by simulation or small batch test to ensure that it can be applied in practice. After multiple rounds of iterative optimization and verification, the final processing optimization strategy is determined. The strategy includes specific processing parameters, tool configuration and process flow.

[0031] Step S600: Based on the processing optimization strategy, the target CNC tool is optimized and controlled.

[0032] In the embodiment of the present application, the processing optimization strategy determined in the previous step is applied. The optimization strategy includes specific processing parameters, tool configuration and process flow. These optimization parameters are loaded into the control system of the CNC machine tool to ensure that the processing is carried out according to the optimization strategy. Through this process, the optimized processing control of the target CNC tool is completed.

[0033] Furthermore, step S200 in the method provided in the application embodiment also includes:

[0034] The application data set is traversed, and a first-layer clustering is performed based on the defect type to determine the first clustering result; based on the defect traceability point, the first clustering result is clustered in a second layer to determine the second clustering result; the second clustering result is traversed to identify and locate the defect features to determine the defect distribution set; based on the fuzzy conversion model, the defect distribution set is fuzzy converted to determine the optimization target.

[0035] In an embodiment of the present application, the application data set is first traversed, and a hierarchical clustering algorithm is applied to perform preliminary clustering on the application data set. The basis for clustering is the defect type, such as tool wear, fracture, and precision reduction. By calculating the distance matrix between the data points, the most similar defect data are gradually merged to form a tree-like hierarchical structure, and the first clustering result is finally determined. Next, based on the first-layer clustering results, subdivision clustering based on defect traceability points is performed. In this process, each type of defect data in the first-layer clustering results is further analyzed, and a second clustering is performed according to the traceability point information such as processing conditions, material type, and processing speed. The distance between data points is calculated by similarity measurement methods, such as Euclidean distance and Manhattan distance, to form a more refined classification and determine the second clustering result. Further traverse the second clustering results, extract the features of each defect category, and locate them. The feature recognition process includes calculating the statistical features of various types of defects, such as mean value, variance, etc., as well as identifying key feature parameters and determining the defect distribution set.

[0036] Finally, a fuzzy conversion model is constructed, and the characteristic data in the defect distribution set is input into the fuzzy model. The fuzzy logic system includes three steps: fuzzification, fuzzy reasoning, and defuzzification. Fuzzification converts the defect characteristic data into a fuzzy set and represents it through a membership function. Fuzzy reasoning performs reasoning based on the preset fuzzy rule base to obtain a fuzzy result. Defuzzification converts the fuzzy result into a specific optimization target. The final optimization target is determined by the output result of the fuzzy conversion model.

[0037] Furthermore, in the method provided in the embodiment of the application, based on the fuzzy conversion model, the defect distribution set is fuzzily converted, and further includes:

[0038] Based on fuzzy conversion logic, supervised training is performed on a bidirectional fuzzy conversion block, wherein the bidirectional fuzzy conversion block includes a fuzzy conversion branch and a defuzzification branch; based on the bidirectional fuzzy conversion block, the fuzzy conversion model is constructed; based on the fuzzy conversion branch of the fuzzy conversion model, the defect distribution set is fuzzy converted to determine the optimization target.

[0039] In an embodiment of the present application, firstly, the defect distribution set data is read from the database, and the data is cleaned and standardized to ensure data quality and consistency. Next, the supervised learning method is used to train the bidirectional fuzzy conversion block. Fuzzy sets and membership functions are defined to convert precise data into fuzzy data. For example, the degree of tool wear is represented by three fuzzy sets of "low", "medium" and "high". Use a defuzzification method, such as the centroid method, to convert fuzzy data into specific numerical values. For example, the fuzzy result of "medium wear" is converted into a specific numerical degree of wear. During the training process, the model parameters are adjusted according to the historical defect data and the corresponding optimization objectives to optimize the results of fuzzy conversion and defuzzification. Based on the trained bidirectional fuzzy conversion block, a complete fuzzy conversion model is constructed. In this process, the bidirectional fuzzy conversion block is integrated into the fuzzy conversion model. The model consists of multiple fuzzy rules and membership functions, and can handle complex defect data.

[0040] Finally, the constructed fuzzy conversion model is used to perform fuzzy conversion on the defect distribution set. The defect distribution set is input into the fuzzy conversion model, and the precise defect data is converted into fuzzy data through the fuzzy conversion branch to determine the optimization target. For example, the "wear rate" data is mapped into three fuzzy values ​​of "low, medium, and high", and then the corresponding optimization target is obtained through fuzzy rule reasoning.

[0041] Furthermore, step S300 in the method provided in the application embodiment also includes:

[0042] Based on the initial processing plan, a failure morphology analysis based on multivariate scenarios is performed to determine a first indicator matrix; based on expected performance standards, a second indicator matrix is ​​determined, and the expected performance standards are optimized performance indicators; the first indicator matrix and the second indicator matrix are mapped to determine multiple mapping groups; the multiple mapping groups are traversed to analyze and determine the multiple limit coefficients.

[0043] In the embodiment of the present application, when performing a damage morphology analysis based on a multivariate scenario, the damage trend and state of the product under different processing scenarios are analyzed by simulation and data mining technology. Use numerical simulation software, such as ANSYS and Abaqus, to simulate the product under different processing conditions, such as different cutting speeds, feed rates, cutting depths and material types, and collect the damage morphology data of the tool. Use big data analysis technology, such as, data mining tools to extract the damage trend and mode of the tool in various processing scenarios from historical data. Simulate and analyze data in different processing scenarios, record the wear, fracture, deformation and other conditions of the tool, and form a comprehensive damage morphology database. Next, perform statistical analysis on the damage morphology data and extract key performance indicators, such as tool life, wear rate, processing accuracy, and surface quality. According to different processing scenarios, a multidimensional first indicator matrix is ​​formed to reflect the performance of the tool under various conditions. According to the optimization goals set by the user or technical experts, define the expected performance standards of the tool, such as longer tool life, higher processing accuracy and better surface quality. Set the expected performance standards according to the optimization goals to form a second indicator matrix.

[0044] The first indicator matrix and the second indicator matrix are mapped correspondingly using a mapping algorithm and a mathematical model. In this process, the difference between the actual performance indicators and the expected performance indicators under different processing scenarios is calculated to form a mapping relationship. Multiple mapping groups are determined, each mapping group reflects the corresponding relationship between the actual indicators and the expected indicators.

[0045] Traverse the mapping groups one by one and analyze the performance indicator differences and trends in each group. Use data analysis methods such as regression analysis and variance analysis to identify key influencing factors and thresholds. By analyzing the results, determine multiple limit coefficients, which are used to describe the performance boundaries of the tool under different processing conditions.

[0046] Furthermore, in the method provided in the embodiment of the application, analyzing and determining the multi-limit coefficients further includes:

[0047] Traversing the multiple mapping groups, determining a first-layer limit coefficient based on the indicator difference; determining indicator associated parameters, wherein the associated process parameters of each indicator include at least one; based on the first-layer limit coefficient, performing extreme value analysis on the indicator associated parameters to determine a second-layer limit coefficient; mapping the first-layer limit coefficient and the second-layer limit coefficient and determining an adjustment response relationship, determining the multiple limit coefficients, wherein the adjustment response relationship is used to measure the global impact under unit amplitude modulation.

[0048] In an embodiment of the present application, each mapping group is traversed to read the data of the actual performance index and the expected performance index. The difference between the actual performance and the expected performance is calculated, and the performance deviation in each processing scenario is identified through the difference calculation. Next, based on the difference analysis, a statistical method such as percentile analysis is used to determine a layer of limit coefficients. A layer of limit coefficients is a limit value determined based on the indicator difference, which represents the limit value of the performance indicator under different processing conditions. By performing statistical analysis on the calculated difference, a layer of limit coefficients for each performance indicator is determined.

[0049] Based on process knowledge, determine the process parameters related to each performance indicator, such as cutting speed, feed rate, cutting depth, etc. Perform regression analysis or correlation analysis to verify and determine the associated parameters of each performance indicator. When performing extreme value analysis, use extreme value analysis techniques and statistical methods, such as maximum and minimum value analysis, to perform extreme value analysis on the associated process parameters and identify the limit value of each process parameter. Determine the optimal range of process parameters under different conditions through maximum and minimum value analysis. Based on the results of extreme value analysis, determine the second-level limit coefficient of each process parameter. The second-level limit coefficient reflects the optimal and critical values ​​of the process parameters under different processing conditions.

[0050] Map the first-layer limit coefficient and the second-layer limit coefficient to determine the relationship between the two. Use regression analysis and other methods to determine the adjustment response relationship, which is used to measure the global impact under unit amplitude modulation. Combining the above analysis results, the first-layer limit coefficient, the second-layer limit coefficient and the adjustment response relationship, the multi-limit coefficient is comprehensively determined. The multi-limit coefficient is used to describe the performance boundary of the tool under different processing conditions and guide the parameter optimization in the actual processing process.

[0051] Furthermore, in the method provided in the embodiment of the application, after determining the processing optimization strategy, it also includes:

[0052] In combination with the defuzzification branch of the fuzzy transformation model, the processing optimization strategy is defuzzified; the processing optimization strategy is verified by process derivation to determine the performance evaluation result; it is determined whether the performance evaluation result satisfies the second indicator matrix. If not, the processing optimization strategy is compensated in combination with the adjustment response relationship.

[0053] In the embodiment of the present application, the defuzzification technology in the fuzzy logic system, such as the centroid method, the maximum membership method, and the average method, is used to defuzzify the processing optimization strategy. In the fuzzy conversion model, the defuzzification branch is responsible for converting fuzzy data into precise data. Fuzzy data is a fuzzy set represented by a fuzzy membership function. The fuzzy optimization strategy is input into the defuzzification branch, and the specific value is determined by a predefined defuzzification method, such as the centroid method by calculating the centroid position of the membership curve under the fuzzy set, the maximum membership method selects the value corresponding to the fuzzy set with the maximum membership as the specific value, and the average method calculates the weighted average of all possible values ​​in the fuzzy set, and the fuzzy optimization strategy is converted into specific processing parameters. These parameters are used for actual processing control.

[0054] Next, the process of machining optimization strategy is derived and verified by numerical simulation method. In this process, based on the defuzzified machining optimization strategy, finite element analysis software such as ANSYS and Abaqus is used to simulate the machining process. The stress, deformation and thermal effects in actual machining are reproduced through simulation. The specific machining parameters are input into the simulation software for simulation analysis to verify the feasibility and effect of the optimization strategy. The results of the simulation include performance indicators such as tool wear, workpiece surface quality, and machining accuracy. The performance of the machining optimization strategy is evaluated based on these results. The performance evaluation results of the simulation are compared with the second indicator matrix to determine whether the expected goal is met. The evaluation results are analyzed using a decision algorithm, such as a threshold judgment algorithm. If the difference between the evaluation results and the expected standard is large, it is determined that the expected goal is not met. If the performance evaluation results do not meet the second indicator matrix, the machining optimization strategy is compensated in combination with the previously determined adjustment response relationship. The adjustment response relationship is determined by regression analysis and other methods to describe the impact of process parameter changes on overall performance. According to the adjustment response relationship, key process parameters such as cutting speed and feed rate are adjusted to optimize the machining strategy. Through the above process, the compensation of the machining optimization strategy is completed.

[0055] Furthermore, in the method provided in the embodiment of the application, after optimizing the processing control of the target CNC tool, it also includes:

[0056] Processing monitoring is carried out simultaneously, and abnormal control points are located based on control deviation and control lag, and the control deviation includes trend deviation and parameter deviation; over-limit judgment and traceability are performed on the abnormal control points to determine feedback control data; a digital feedback device responds to the feedback control data to perform feedback processing of the target CNC tool.

[0057] In an embodiment of the present application, after optimizing the processing control of the target CNC tool, synchronous processing monitoring is continued. Processing monitoring monitors the status and processing parameters of the tool in real time through various sensors installed on the CNC machine tool, such as vibration sensors, temperature sensors and force sensors. Control deviation refers to the system detecting changes in parameters during processing, including trend deviation and parameter deviation. Trend deviation is the phenomenon that the processing parameters gradually deviate from the expected value. Parameter deviation is the instant difference between the actual value and the target value. These monitoring data are used to locate abnormal control points that appear in the processing process, that is, those parameter points that exceed the normal range. When the abnormal control point is located, over-limit judgment and traceability positioning are performed. Over-limit judgment determines whether the abnormal control point exceeds the allowable range by setting the threshold or limit. Traceability positioning is to analyze the cause of the over-limit and determine the specific process parameters and operation steps that cause the abnormality. The data changes before and after the abnormal point are determined by time series analysis, the time when the abnormality occurs and the corresponding process parameter changes are identified, and the specific causes and steps that cause the abnormality are determined. According to the results of the traceability analysis, feedback control data are generated, which contain adjustment suggestions and correction parameters.

[0058] The digital feedback device is a feedback control device installed on the CNC machine tool, which can receive and respond to feedback control data in real time. The digital feedback device adjusts the processing parameters of the CNC tool, such as cutting speed and feed rate, according to the feedback control data to make real-time corrections to ensure that the processing process returns to normal and completes the feedback processing of the target CNC tool.

[0059] In the embodiments of the present application, in summary, the embodiments of the present application have at least the following technical effects:

[0060] This application searches and calls homologous application data for the target CNC tool to determine the application data set; traverses the application data set, performs hierarchical clustering and defect point location, and performs fuzzy conversion of defect points through a fuzzy conversion model to determine the optimization target; by performing a multi-scenario destruction morphology analysis on the target CNC tool, a multi-limit coefficient based on processing performance is determined, and there is a corresponding relationship between the multi-limit coefficient and the performance index; with the multi-limit coefficient as a constraint, an adaptive optimization module is built; based on the adaptive optimization module, combined with the initial processing plan, multi-objective optimization and iterative verification based on the optimization target are performed to determine the processing optimization strategy, wherein the optimized target identifier has a weight coefficient; based on the processing optimization strategy, the target CNC tool is optimized for processing control. The present invention solves the technical problems of low control accuracy and slow response speed in the prior art for CNC tool processing, and achieves the technical effect of improving the control accuracy and response speed of CNC tool processing by combining homologous application data retrieval, hierarchical clustering, defect point location, fuzzy conversion model, multi-scenario destruction morphology analysis, adaptive optimization module, multi-objective optimization and iterative verification technology.

[0061] Embodiment 2

[0062] Based on the same inventive concept as the method for optimizing machining performance of a numerical control tool in the aforementioned embodiment, Figure 2 As shown, the present application provides a CNC tool processing performance optimization system, and the system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0063] A search and call unit 11, wherein the search and call unit 11 searches and calls homologous application data for a target numerical control tool to determine an application data set;

[0064] An optimization target determination unit 12, wherein the optimization target determination unit 12 traverses the application data set, performs hierarchical clustering and defect point location, performs fuzzy conversion of defect points through a fuzzy conversion model, and determines an optimization target;

[0065] A damage morphology analysis unit 13, wherein the damage morphology analysis unit 13 determines a multi-limit coefficient based on machining performance by performing a multi-scenario damage morphology analysis on the target numerical control tool, wherein the multi-limit coefficient corresponds to a performance index;

[0066] An adaptive optimization module building unit 14, wherein the adaptive optimization module building unit 14 builds an adaptive optimization module with the multi-boundary coefficients as constraints;

[0067] A processing optimization strategy determination unit 15, wherein the processing optimization strategy determination unit 15 performs multi-objective optimization and iterative verification based on the optimization target based on the adaptive optimization module and the initial processing plan to determine the processing optimization strategy, wherein the optimized target is identified with a weight coefficient;

[0068] The optimized processing control unit 16 performs optimized processing control on the target numerical control tool based on the processing optimization strategy.

[0069] Furthermore, the system is also used to implement the following functions:

[0070] Traversing the application data set, performing a layer of clustering based on defect types, and determining a first clustering result;

[0071] Based on the defect traceability point, performing two-layer clustering on the first clustering result to determine a second clustering result;

[0072] Traversing the second clustering results, performing defect feature identification and positioning to determine a defect distribution set;

[0073] Based on the fuzzy conversion model, the defect distribution set is fuzzy converted to determine the optimization target.

[0074] Furthermore, the system is also used to implement the following functions:

[0075] Based on the fuzzy conversion logic, supervise the training of a bidirectional fuzzy conversion block, wherein the bidirectional fuzzy conversion block includes a fuzzy conversion branch and a defuzzification branch;

[0076] Based on the bidirectional fuzzy conversion block, construct the fuzzy conversion model;

[0077] Based on the fuzzy conversion branch of the fuzzy conversion model, the defect distribution set is fuzzy converted to determine the optimization target.

[0078] Furthermore, the system is also used to implement the following functions:

[0079] Based on the initial processing plan, a failure morphology analysis based on multiple scenarios is performed to determine a first indicator matrix;

[0080] Determining a second indicator matrix based on the expected performance standard, wherein the expected performance standard is the optimized performance indicator;

[0081] Mapping the first indicator matrix and the second indicator matrix to determine a plurality of mapping groups;

[0082] The multiple mapping groups are traversed to analyze and determine the multiple limit coefficients.

[0083] Furthermore, the system is also used to implement the following functions:

[0084] Traversing the plurality of mapping groups, and determining a layer of limit coefficients based on the indicator difference;

[0085] Determining index-related parameters, wherein the associated process parameters of each index include at least one;

[0086] Based on the first-layer limit coefficient, an extreme value analysis is performed on the indicator-related parameters to determine the second-layer limit coefficient;

[0087] The first-layer limit coefficient and the second-layer limit coefficient are mapped and an adjustment response relationship is determined to determine the multiple limit coefficients, and the adjustment response relationship is used to measure the global impact under unit amplitude modulation.

[0088] Furthermore, the system is also used to implement the following functions:

[0089] Defuzzification of the processing optimization strategy is performed in combination with the defuzzification branch of the fuzzy transformation model;

[0090] Performing process derivation and verification on the processing optimization strategy to determine the performance evaluation result;

[0091] Determine whether the performance evaluation result satisfies the second indicator matrix; if not, compensate the processing optimization strategy in combination with the adjustment response relationship.

[0092] Furthermore, the system is also used to implement the following functions:

[0093] Conduct processing monitoring simultaneously, locate abnormal control points based on control deviation and control lag, the control deviation includes trend deviation and parameter deviation;

[0094] Conduct over-limit determination and source tracing for the abnormal control point, and determine feedback control data;

[0095] The digital feedback device responds to the feedback control data to perform feedback processing of the target numerical control tool.

[0096] 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 and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0097] 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.

[0098] 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 optimizing the machining performance of a numerical control tool, characterized in that: The method comprises: For the target CNC tool, perform homologous application data retrieval and call to determine the application data set; Traversing the application data set, performing hierarchical clustering and defect point location, performing fuzzy transformation of defect points through a fuzzy transformation model, and determining optimization targets; By performing a multi-scenario destruction morphology analysis on the target numerical control tool, a multi-limit coefficient based on machining performance is determined, and the multi-limit coefficient has a corresponding relationship with the performance index; Taking the multi-limit coefficients as constraints, building an adaptive optimization module; Based on the adaptive optimization module, combined with the initial processing plan, multi-objective optimization and iterative verification based on the optimization target are performed to determine the processing optimization strategy, wherein the optimized target is identified with a weight coefficient; Based on the processing optimization strategy, optimizing processing control of the target CNC tool; Wherein, the determination of the multi-limit coefficient based on the processing performance includes: Based on the initial processing plan, a failure morphology analysis based on multiple scenarios is performed to determine a first indicator matrix; Determining a second indicator matrix based on the expected performance standard, wherein the expected performance standard is the optimized performance indicator; Mapping the first indicator matrix and the second indicator matrix to determine a plurality of mapping groups; Traversing the plurality of mapping groups, analyzing and determining the multi-boundary coefficients; Wherein, analyzing and determining the multiple limit coefficients includes: Traversing the plurality of mapping groups, and determining a layer of limit coefficients based on the indicator difference; Determining index-related parameters, wherein the associated process parameters of each index include at least one; Based on the first-layer limit coefficient, an extreme value analysis is performed on the indicator-related parameters to determine the second-layer limit coefficient; Mapping the first-layer limit coefficient and the second-layer limit coefficient and determining an adjustment response relationship, and determining the multiple limit coefficients, wherein the adjustment response relationship is used to measure the global impact under unit amplitude modulation; Wherein, after determining the processing optimization strategy, it includes: Defuzzification of the processing optimization strategy is performed in combination with the defuzzification branch of the fuzzy transformation model; Performing process derivation and verification on the processing optimization strategy to determine the performance evaluation result; Determine whether the performance evaluation result satisfies the second indicator matrix; if not, compensate the processing optimization strategy in combination with the adjustment response relationship.

2. A method for optimizing machining performance of a numerical control tool as claimed in claim 1, characterized in that: Determining the optimization target includes: Traversing the application data set, performing a layer of clustering based on defect types, and determining a first clustering result; Based on the defect traceability point, performing two-layer clustering on the first clustering result to determine a second clustering result; Traversing the second clustering results, performing defect feature identification and positioning to determine a defect distribution set; Based on the fuzzy conversion model, the defect distribution set is fuzzy converted to determine the optimization target.

3. A method for optimizing machining performance of a numerical control tool as claimed in claim 2, characterized in that: Based on the fuzzy conversion model, fuzzy conversion is performed on the defect distribution set, including: Based on the fuzzy conversion logic, supervise the training of a bidirectional fuzzy conversion block, wherein the bidirectional fuzzy conversion block includes a fuzzy conversion branch and a defuzzification branch; Based on the bidirectional fuzzy conversion block, construct the fuzzy conversion model; Based on the fuzzy conversion branch of the fuzzy conversion model, the defect distribution set is fuzzy converted to determine the optimization target.

4. A method for optimizing machining performance of a numerical control tool as claimed in claim 1, characterized in that: After optimizing the processing control of the target CNC tool, it includes: Conduct processing monitoring simultaneously, locate abnormal control points based on control deviation and control lag, the control deviation includes trend deviation and parameter deviation; Conduct over-limit determination and source tracing for the abnormal control point, and determine feedback control data; The digital feedback device responds to the feedback control data to perform feedback processing of the target numerical control tool.

5. A CNC tool processing performance optimization system, characterized in that: A method for optimizing machining performance of a numerical control tool according to any one of claims 1 to 4, the system comprising: A retrieval and calling unit, wherein the retrieval and calling unit performs a retrieval and calling of homologous application data for a target numerical control tool to determine an application data set; An optimization target determination unit, wherein the optimization target determination unit traverses the application data set, performs hierarchical clustering and defect point location, performs fuzzy conversion of defect points through a fuzzy conversion model, and determines an optimization target; A damage morphology analysis unit, wherein the damage morphology analysis unit determines a multi-limit coefficient based on machining performance by performing a multi-scenario damage morphology analysis on the target numerical control tool, wherein the multi-limit coefficient corresponds to a performance index; An adaptive optimization module building unit, wherein the adaptive optimization module building unit uses the multi-boundary coefficients as constraints to build an adaptive optimization module; A processing optimization strategy determination unit, wherein the processing optimization strategy determination unit performs multi-objective optimization and iterative verification based on the optimization target based on the adaptive optimization module and an initial processing plan to determine a processing optimization strategy, wherein the optimized target is identified with a weight coefficient; An optimized processing control unit is used to optimize the processing control of the target CNC tool based on the processing optimization strategy.

Images