Intelligent optimization technology and application of precision CNC machining
By building a digital twin model and simulation environment, selecting the best CNC tool path and optimizing it in real time in actual processing, the problem of traditional CNC machining technology relying on experience is solved, and the accuracy, efficiency and quality of precision CNC machining is improved.
Patent Information
- Application Number
- CN202411238780.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-05
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-09-05
AI Technical Summary
Traditional CNC machining technology relies on the experience of operators in process parameter setting and processing path planning, making it difficult to achieve optimal processing effects, especially in the field of precision CNC machining, and the requirements for machining accuracy, surface quality and production efficiency are difficult to meet.
By building a digital twin model, generating a CNC simulation environment, simulating and comprehensively analyzing multiple CNC tool simulation paths, selecting the best path for CNC processing, and monitoring and optimizing in real time during the actual processing process, using preset cycles and thresholds Perform path optimization value judgment and automatically adjust parameters to improve machining accuracy and efficiency.
It effectively ensures the accuracy, cost and quality of CNC machining, promptly detects and optimizes actual machining abnormalities, realizes automated monitoring and optimization, and improves the overall performance of precision CNC machining.
Smart Images

Figure CN118760104B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of numerical control machining, and more specifically, to an intelligent optimization process and application of precision numerical control machining. Background Art
[0002] CNC machining technology is an important part of modern manufacturing industry, and is of great significance for improving production efficiency, product quality and reducing production costs. However, traditional CNC machining often relies on the experience of operators in terms of process parameter setting and machining path planning, and it is difficult to achieve the optimal machining effect. Especially in the field of precision CNC machining, the requirements for machining accuracy, surface quality and production efficiency are higher, and traditional methods are difficult to meet the needs. Summary of the invention
[0003] In view of the deficiencies in the prior art, the purpose of the present invention is to provide an intelligent optimization process and application of precision CNC machining.
[0004] To achieve the above object, the present invention provides the following technical solutions:
[0005] The intelligent optimization process of precision CNC machining includes the following steps:
[0006] Step 1: Obtain basic parameters and target parameters of the processing target, combine the basic parameters and the target parameters into a parameter data set, input the parameter data set into a processing parameter preset model, and obtain preset parameters for CNC processing;
[0007] Step 2: Build a digital twin model based on the basic parameters of the machining target, the target parameters of the machining target, and the preset parameters of the NC machining, generate the NC simulation environment of the machining target, and then obtain multiple NC tool simulation paths;
[0008] Step 3: Simulate each CNC tool simulation path in turn. After each CNC tool simulation path is simulated, obtain the simulation path evaluation value of each CNC tool simulation path, and mark the CNC tool simulation path with the largest simulation path evaluation value as the final selected path;
[0009] Step 4: Perform CNC machining on the machining target according to the preset parameters of CNC machining and the final selected path. In the actual machining process, based on the preset cycle, a final selected path analysis record of the final selected path is generated at each cycle node of the preset cycle;
[0010] Step 5: When a final path analysis record is generated each time, the path optimization value of the final path is obtained, and based on the comparison result between the path optimization value and its threshold, it is determined whether to optimize the parameters and the path.
[0011] Furthermore, during the simulation process of each numerical control tool simulation path, based on a preset cycle, a simulation path analysis record of the numerical control tool simulation path is generated at each cycle node of the preset cycle.
[0012] Furthermore, the simulation path analysis record includes a path number, a path analysis value, a node number, and a node time.
[0013] Furthermore, the path analysis value is obtained by: collecting various types of CNC machining data of the current cycle, obtaining CNC machining monitoring models of various types of CNC machining data, inputting each type of CNC machining data into the corresponding CNC machining monitoring model, obtaining machining monitoring values of various types of CNC machining data, obtaining machining monitoring thresholds of various types of CNC machining data, summing up the machining monitoring values of various types of CNC machining data, and obtaining machining monitoring sum values. , compare the processing monitoring value of the same type of CNC processing data with the processing monitoring threshold. When the processing monitoring value is greater than or equal to the processing monitoring threshold, the type of CNC processing data is marked as standard normal data. When the processing monitoring value is less than the processing monitoring threshold, the type of CNC processing data is marked as standard abnormal data. The total number of standard normal data is marked as , the total number of standard abnormal data is marked as , calculate the difference between the processing monitoring value of the standard abnormal data and the processing monitoring threshold and take the absolute value to obtain the processing monitoring difference, set the processing monitoring threshold difference, compare the processing monitoring difference with the processing monitoring threshold difference, when the processing monitoring difference is greater than or equal to the processing monitoring threshold difference, mark the standard abnormal data as prominent abnormal data, when the processing monitoring difference is less than the processing monitoring threshold difference, do not process it, obtain the CNC processing data spectrum, compare all prominent abnormal data in pairs, when two prominent abnormal data have an interaction relationship in the CNC processing data spectrum, do not process it, when two prominent abnormal data do not have an interaction relationship in the CNC processing data spectrum, increase the number of prominent abnormal actions by one, sum up all the number of prominent abnormal actions, and obtain the sum of the number of prominent abnormal actions. , using the formula The path analysis value Ek is obtained, where L1 is the processing monitoring and value coefficient, L2 is the standard normal data total coefficient, L3 is the standard abnormal data total coefficient, and L4 is the highlight abnormal effect and number coefficient.
[0014] Furthermore, the final selected path analysis record includes a path analysis value, a node number, and a node time.
[0015] Furthermore, the path optimization value of the final path is obtained in the following manner: obtain all final path analysis records generated by the final path before the current time of the system, obtain the node number of the final path analysis record, obtain the simulation path analysis record of the same node number of the final path in the simulation environment, obtain the path analysis value of the simulation path analysis record, compare the path analysis value of the final path analysis record with the same node number with the path analysis value of the simulation path analysis record, when the path analysis value of the final path analysis record is greater than the path analysis value of the simulation path analysis record, increase the number of path deviations by one, and at the same time perform a difference calculation between the path analysis value of the final path analysis record and the path analysis value of the simulation path analysis record to obtain a path deviation value When the path analysis value of the final path analysis record is less than or equal to the path analysis value of the simulation path analysis record, no processing is performed, and the number of path deviations is summed to obtain the total number of path deviations. , using the formula The path optimization value Ae of the final selected path is obtained, where t1 is the path deviation value coefficient and t2 is the total number of path deviation coefficients.
[0016] Furthermore, the simulation path evaluation is obtained by the following method: obtaining all simulation path analysis records of the same CNC tool simulation path, summing up the path analysis values of all simulation path analysis records and taking the average, to obtain the path analysis average value , sort all simulation path analysis records in the order of node time, calculate the difference between the path analysis values of two adjacent simulation path analysis records after sorting, and get the path analysis fluctuation value, set the path analysis fluctuation limit (the path analysis fluctuation limit is the system setting threshold, which can be modified according to actual needs), when the path analysis fluctuation value is greater than the path analysis fluctuation limit, calculate the difference between the path analysis fluctuation value and the path analysis fluctuation limit to get the prominent fluctuation value, when the path analysis fluctuation value is less than or equal to the path analysis fluctuation limit, no processing is performed, and all prominent fluctuation values are summed to get the prominent fluctuation sum value , using the formula The simulation path evaluation value PY of the CNC tool simulation path is obtained, where k1 is the path analysis mean coefficient and k2 is the prominent fluctuation sum coefficient.
[0017] Furthermore, based on the comparison result between the path optimization value and its threshold, it is determined whether to optimize the parameters and the path, specifically: a path optimization threshold is set, when the path optimization value of the final selected path is greater than the path optimization threshold, the basic parameters of the current processing target are obtained and marked as actual basic parameters, the actual basic parameters and target parameters of the processing target are input into the processing parameter preset model, the preset parameters of the CNC processing are obtained again, the preset parameters of the CNC processing obtained again are marked as optimization parameters, the digital twin model is rebuilt according to the actual basic parameters of the processing target, the target parameters of the processing target, and the optimization parameters of the CNC processing, and multiple optimization simulation paths are obtained, the optimization simulation path with the largest simulation path evaluation value is marked as the optimized selected path, and the processing target is CNC processed according to the optimization parameters and the optimized selected path of the CNC processing;
[0018] When the path optimization value of the final selected path is less than or equal to the path optimization threshold, no processing is performed.
[0019] Compared with the prior art, the present invention has the following beneficial effects:
[0020] 1. Through steps 1 to 3, by building a CNC simulation environment, multiple CNC tool simulation paths are simulated, and a three-dimensional comprehensive analysis is performed on each CNC tool simulation path. After the comprehensive analysis, the best CNC tool simulation path is selected for CNC machining, effectively ensuring the accuracy, cost, efficiency and quality of CNC machining;
[0021] 2. The present invention can compare and analyze the actual processing and the simulated processing during the actual CNC processing through steps 4 and 5. When abnormalities are found in the actual processing, the CNC simulation and analysis can be re-performed in a timely manner, the actual processing process can be fully monitored, and the actual processing can be automatically optimized. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] Figure 1 A flowchart of the intelligent optimization process for precision CNC machining;
[0023] Figure 2 A flowchart for obtaining path analysis values;
[0024] Figure 3 A flowchart for obtaining path optimization values. DETAILED DESCRIPTION
[0025] Reference Figures 1 to 3
[0026] The intelligent optimization process of precision CNC machining includes the following steps:
[0027] Step 1: Obtain the basic parameters of the processing target (i.e., the material to be processed) (the basic parameters are the current parameters of the processing target, including but not limited to geometric dimensions, material hardness, and material toughness) and the target parameters (the target parameters are the expected parameters of the processing target after the processing is completed, including but not limited to expected dimensions and expected shapes), form a parameter data set with the basic parameters and the target parameters, input the parameter data set into the processing parameter preset model, and obtain the preset parameters of CNC processing (the preset parameters include but are not limited to the position of the tool, cutting force, and cutting speed);
[0028] Step 2: Build a digital twin model according to the basic parameters of the processing target, the target parameters of the processing target, and the preset parameters of the CNC processing (build a digital twin model corresponding to the actual CNC machine tool in a virtual environment. The types of simulation processing supported by the digital twin model of this embodiment include but are not limited to turning, three-axis processing, and five-axis processing), generate a CNC simulation environment for the processing target, and then obtain multiple CNC tool simulation paths;
[0029] Step 3: Simulate each CNC tool simulation path in turn. During the simulation process of each CNC tool simulation path, based on a preset cycle (the interval between periodic nodes of the preset cycle can be adjusted according to actual needs), a simulation path analysis record of the CNC tool simulation path is generated at each periodic node of the preset cycle. The simulation path analysis record includes a path number (each CNC tool simulation path corresponds to a unique number, and there will be no duplicate numbers), a path analysis value, a node number (i.e., the number corresponding to the periodic node, the node number is i, i=1, 2, ..., n, and the node number increases in sequence with the change of the node time), and a node time (the time corresponding to the current periodic node). After the simulation of each CNC tool simulation path is completed, obtain the simulation path evaluation value of each CNC tool simulation path, and mark the CNC tool simulation path with the largest simulation path evaluation value as the final selected path;
[0030] The present invention constructs a numerical control simulation environment through steps one to three, simulates multiple numerical control tool simulation paths, and performs a three-dimensional comprehensive analysis on each numerical control tool simulation path. After the comprehensive analysis, the best numerical control tool simulation path is selected for numerical control machining, thereby effectively ensuring the accuracy, cost, efficiency and quality of numerical control machining.
[0031] Step 4: Perform CNC machining on the machining target according to the preset parameters and the final selected path of CNC machining (the CNC machine tool performs CNC machining on the machining target based on the preset parameters and the final selected path). In the actual machining process, based on the preset cycle (the preset cycle in the simulation process is always kept the same as the preset cycle in the actual machining process), at each cycle node of the preset cycle, a final selected path analysis record of the final selected path is generated. The final selected path analysis record includes a path analysis value, a node number, and a node time.
[0032] Step 5: Each time a final path analysis record is generated, the path optimization value of the final path is obtained, and the path optimization threshold is set (the path optimization threshold is a system-set threshold and can be modified according to actual needs). When the path optimization value of the final path is greater than the path optimization threshold, the basic parameters of the current processing target are obtained and marked as actual basic parameters, and the actual basic parameters and target parameters of the processing target are input into the processing parameter preset model to obtain the preset parameters of CNC processing again, and the preset parameters of CNC processing again are marked as optimization parameters. The digital twin model is rebuilt according to the actual basic parameters of the processing target, the target parameters of the processing target, and the optimization parameters of CNC processing, and multiple optimized simulation paths are obtained. The optimized simulation path with the largest simulation path evaluation value is marked as the optimized selected path, and the processing target is CNC processed according to the optimization parameters of CNC processing and the optimized selected path;
[0033] When the path optimization value of the final selected path is less than or equal to the path optimization threshold, no processing is performed.
[0034] Through step four and step five, the present invention can compare and analyze the actual processing and the simulated processing during the actual CNC processing process. When abnormalities in the actual processing are detected, the CNC simulation and analysis can be re-performed in a timely manner, the actual processing process can be fully monitored, and the actual processing can be automatically optimized.
[0035] The path optimization value of the final path is obtained in the following way: obtain all final path analysis records generated before the current time of the system for the final path, obtain the node number of the final path analysis record, obtain the simulation path analysis record of the same node number of the final path in the simulation environment, obtain the path analysis value of the simulation path analysis record, compare the path analysis value of the final path analysis record with the same node number with the path analysis value of the simulation path analysis record, when the path analysis value of the final path analysis record is greater than the path analysis value of the simulation path analysis record, increase the number of path deviations by one, and calculate the difference between the path analysis value of the final path analysis record and the path analysis value of the simulation path analysis record to obtain the path deviation value When the path analysis value of the final path analysis record is less than or equal to the path analysis value of the simulation path analysis record, no processing is performed, and the number of path deviations is summed to obtain the total number of path deviations. , using the formula The path optimization value Ae of the final selected path is obtained, where t1 is the path deviation value coefficient, t2 is the total number of path deviation coefficients, the value of t1 is 2.52, and the value of t2 is 1.02.
[0036] The path analysis value is obtained in the following way: collect various types of CNC machining data of the current cycle (CNC machining data include but are not limited to tool wear data, cutting temperature data, machining target surface roughness data, machining target size accuracy data, machining target shape accuracy, tool wear data and machining target surface roughness data can be obtained through visual inspection technology, visual inspection technology is not the research and development focus of this application, so it is not introduced. The above-mentioned CNC machining data will affect the accuracy, cost, efficiency and quality of CNC machining), obtain CNC machining monitoring models for various types of CNC machining data (each type of CNC machining data corresponds to a CNC machining monitoring model), input each type of CNC machining data into the corresponding CNC machining monitoring model, obtain the machining monitoring value of each type of CNC machining data, obtain the machining monitoring threshold of each type of CNC machining data (each type of CNC machining data corresponds to a machining monitoring threshold, the machining monitoring threshold is the system setting threshold, which can be modified according to actual needs), sum the machining monitoring values of each type of CNC machining data to obtain the machining monitoring sum value , compare the processing monitoring value of the same type of CNC processing data with the processing monitoring threshold. When the processing monitoring value is greater than or equal to the processing monitoring threshold, the type of CNC processing data is marked as standard normal data. When the processing monitoring value is less than the processing monitoring threshold, the type of CNC processing data is marked as standard abnormal data. The total number of standard normal data is marked as , the total number of standard abnormal data is marked as , calculate the difference between the processing monitoring value of the standard abnormal data and the processing monitoring threshold and take the absolute value to obtain the processing monitoring difference, set the processing monitoring threshold difference (the processing monitoring threshold difference is the system setting threshold, which can be modified according to actual needs), compare the processing monitoring difference with the processing monitoring threshold difference, when the processing monitoring difference is greater than or equal to the processing monitoring threshold difference, mark the standard abnormal data as prominent abnormal data, when the processing monitoring difference is less than the processing monitoring threshold difference, do not process it, obtain the CNC processing data spectrum, compare all prominent abnormal data in pairs, when two prominent abnormal data have an interaction relationship in the CNC processing data spectrum, do not process it, when two prominent abnormal data do not have an interaction relationship in the CNC processing data spectrum, increase the number of prominent abnormal actions by one, sum up all the number of prominent abnormal actions, and obtain the sum of the number of prominent abnormal actions. , using the formula The path analysis value Ek is obtained, where L1 is the processing monitoring and value coefficient, L2 is the total coefficient of standard normal data, L3 is the total coefficient of standard abnormal data, and L4 is the coefficient of highlighting abnormal effects and times. The value of L1 is 0.87, the value of L2 is 0.91, the value of L3 is 0.93, and the value of L4 is 3.59.
[0037] The CNC machining data spectrum includes various types of CNC machining data (each type of CNC machining data is displayed in the form of a block diagram). The CNC machining data spectrum can display the interaction relationship between various types of CNC machining data, such as tool wear data and cutting temperature data. As the cutting temperature increases, the tool will undergo thermal expansion, changing the original geometric shape and dimensional accuracy, and intensifying the wear of the tool and the machining target. At the same time, as the tool wears, the cutting edge becomes blunt, and the deformation and friction generated during cutting increase, which will cause the cutting temperature to increase. Therefore, there is an interaction relationship between tool wear data and cutting temperature data in the CNC machining data spectrum.
[0038] The following will take cutting temperature data as an example to introduce the construction method of the CNC machining monitoring model: collect a group of cutting temperature data, each group of cutting temperature data includes but is not limited to the average cutting temperature, the peak cutting temperature, and the valley cutting temperature, build a neural network model, use a group of cutting temperature data as the training data of the neural network model, assign an environmental monitoring value to each group of cutting temperature data, divide the training data into a training set and a validation set in a ratio of 3:5, perform neural network iterative training on the training set and the validation set, and obtain a CNC machining monitoring model. Among them, the range of the machining monitoring value is (0~3), the larger the value of the machining monitoring value, the more the group of cutting temperature data meets the CNC machining standard (meeting the CNC machining standard means that the accuracy, cost, efficiency and quality can be guaranteed), and the smaller the value of the machining monitoring value, the less the group of cutting temperature data does not meet the CNC machining standard (not meeting the CNC machining standard means that the accuracy, cost, efficiency and quality cannot be guaranteed).
[0039] The above introduces the construction method of the CNC machining monitoring model taking cutting temperature data as an example. The construction method of the CNC machining monitoring model for other types of CNC machining data is the same as above. You only need to replace the training data to obtain the CNC machining monitoring model of different types of CNC machining data. The value range of the machining monitoring values of all CNC machining monitoring models is the same.
[0040] The machining parameter preset model is obtained in the following way: obtain multiple groups of parameter data sets, build a deep learning model, use the parameter data sets as training data for the deep learning model, assign preset parameters for CNC machining to each training data, divide all training data into training set and validation set according to a set ratio of 2:3, perform neural network iterative training on the training set and validation set, and obtain the machining parameter preset model.
[0041] The simulation path evaluation is obtained by the following method: obtain all simulation path analysis records of the same CNC tool simulation path, sum up the path analysis values of all simulation path analysis records and take the average value to obtain the path analysis average value. , sort all simulation path analysis records in the order of node time, calculate the difference between the path analysis values of two adjacent simulation path analysis records after sorting, and get the path analysis fluctuation value, set the path analysis fluctuation limit (the path analysis fluctuation limit is the system setting threshold, which can be modified according to actual needs), when the path analysis fluctuation value is greater than the path analysis fluctuation limit, calculate the difference between the path analysis fluctuation value and the path analysis fluctuation limit to get the prominent fluctuation value, when the path analysis fluctuation value is less than or equal to the path analysis fluctuation limit, no processing is performed, and all prominent fluctuation values are summed to get the prominent fluctuation sum value , using the formula The simulation path evaluation value PY of the CNC tool simulation path is obtained, where k1 is the path analysis mean coefficient, k2 is the prominent fluctuation sum coefficient, the value of k1 is 0.72, and the value of k2 is 0.66.
[0042] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.
[0043] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.
[0044] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.
[0045] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0046] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0047] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0048] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.
[0049] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
Claims
1. Intelligent optimization process of precision CNC machining, characterized by: The steps include: Step 1: Obtain basic parameters and target parameters of the processing target, combine the basic parameters and the target parameters into a parameter data set, input the parameter data set into a processing parameter preset model, and obtain preset parameters for CNC processing; Step 2: Build a digital twin model based on the basic parameters of the machining target, the target parameters of the machining target, and the preset parameters of the NC machining, generate a NC simulation environment for the machining target, and then obtain multiple NC tool simulation paths; Step 3: Simulate each CNC tool simulation path in turn. After each CNC tool simulation path is simulated, obtain the simulation path evaluation value of each CNC tool simulation path, and mark the CNC tool simulation path with the largest simulation path evaluation value as the final selected path; Step 4: Perform CNC machining on the machining target according to the preset parameters of CNC machining and the final selected path. In the actual machining process, based on the preset cycle, a final selected path analysis record of the final selected path is generated at each cycle node of the preset cycle; Step 5: When each final path analysis record is generated, the path optimization value of the final path is obtained, and based on the comparison result between the path optimization value and its threshold, it is determined whether to optimize the parameters and the path; The path optimization value of the final path is obtained in the following way: obtain all final path analysis records generated before the current time of the system for the final path, obtain the node number of the final path analysis record, obtain the simulation path analysis record of the same node number of the final path in the simulation environment, obtain the path analysis value of the simulation path analysis record, compare the path analysis value of the final path analysis record with the same node number with the path analysis value of the simulation path analysis record, when the path analysis value of the final path analysis record is greater than the path analysis value of the simulation path analysis record, increase the number of path deviations by one, and calculate the difference between the path analysis value of the final path analysis record and the path analysis value of the simulation path analysis record to obtain the path deviation value When the path analysis value of the final path analysis record is less than or equal to the path analysis value of the simulation path analysis record, no processing is performed, and the number of path deviations is summed to obtain the total number of path deviations. , using the formula The path optimization value Ae of the final selected path is obtained, where t1 is the path deviation value coefficient and t2 is the total number of path deviation coefficients; The simulation path evaluation is obtained by the following method: obtain all simulation path analysis records of the same CNC tool simulation path, sum up the path analysis values of all simulation path analysis records and take the average value to obtain the path analysis average value. , sort all simulation path analysis records in the order of node time, calculate the difference between the path analysis values of two adjacent simulation path analysis records after sorting, and get the path analysis fluctuation value, set the path analysis fluctuation limit, when the path analysis fluctuation value is greater than the path analysis fluctuation limit, calculate the difference between the path analysis fluctuation value and the path analysis fluctuation limit, and get the prominent fluctuation value, when the path analysis fluctuation value is less than or equal to the path analysis fluctuation limit, no processing is done, and all prominent fluctuation values are summed to get the prominent fluctuation sum value , using the formula The simulation path evaluation value PY of the CNC tool simulation path is obtained, where k1 is the path analysis mean coefficient and k2 is the prominent fluctuation sum coefficient.
2. The intelligent optimization process for precision CNC machining according to claim 1 is characterized in that: During the simulation process of each numerical control tool simulation path, based on a preset cycle, a simulation path analysis record of the numerical control tool simulation path is generated at each cycle node of the preset cycle.
3. The intelligent optimization process for precision CNC machining according to claim 2 is characterized in that: The simulation path analysis record includes the path number, path analysis value, node number, and node time.
4. The intelligent optimization process for precision CNC machining according to claim 3 is characterized in that: The path analysis value is obtained in the following way: collect various types of CNC machining data of the current cycle, obtain CNC machining monitoring models of various types of CNC machining data, input each type of CNC machining data into the corresponding CNC machining monitoring model, obtain machining monitoring values of various types of CNC machining data, obtain machining monitoring thresholds of various types of CNC machining data, sum the machining monitoring values of various types of CNC machining data, and obtain machining monitoring sum values , compare the processing monitoring value of the same type of CNC processing data with the processing monitoring threshold. When the processing monitoring value is greater than or equal to the processing monitoring threshold, the type of CNC processing data is marked as standard normal data. When the processing monitoring value is less than the processing monitoring threshold, the type of CNC processing data is marked as standard abnormal data. The total number of standard normal data is marked as , the total number of standard abnormal data is marked as , calculate the difference between the processing monitoring value of the standard abnormal data and the processing monitoring threshold and take the absolute value to obtain the processing monitoring difference, set the processing monitoring threshold difference, compare the processing monitoring difference with the processing monitoring threshold difference, when the processing monitoring difference is greater than or equal to the processing monitoring threshold difference, mark the standard abnormal data as prominent abnormal data, when the processing monitoring difference is less than the processing monitoring threshold difference, do not process it, obtain the CNC processing data spectrum, compare all prominent abnormal data in pairs, when two prominent abnormal data have an interaction relationship in the CNC processing data spectrum, do not process it, when two prominent abnormal data do not have an interaction relationship in the CNC processing data spectrum, increase the number of prominent abnormal actions by one, sum up all the number of prominent abnormal actions, and obtain the sum of the number of prominent abnormal actions. , using the formula The path analysis value Ek is obtained, where L1 is the processing monitoring and value coefficient, L2 is the standard normal data total coefficient, L3 is the standard abnormal data total coefficient, and L4 is the highlight abnormal effect and number coefficient.
5. The intelligent optimization process for precision CNC machining according to claim 1 is characterized in that: The final path analysis record includes the path analysis value, node number, and node time.
6. The intelligent optimization process for precision CNC machining according to claim 1 is characterized in that: Based on the comparison result of the path optimization value and its threshold, determine whether to optimize the parameters and the path, specifically: set the path optimization threshold, when the path optimization value of the final selected path is greater than the path optimization threshold, obtain the basic parameters of the current processing target and mark them as actual basic parameters, input the actual basic parameters and target parameters of the processing target into the processing parameter preset model, and re-obtain the preset parameters of CNC processing, mark the re-obtained preset parameters of CNC processing as optimization parameters, reconstruct the digital twin model according to the actual basic parameters of the processing target, the target parameters of the processing target, and the optimization parameters of CNC processing, and obtain multiple optimized simulation paths, mark the optimized simulation path with the largest simulation path evaluation value as the optimized selected path, and perform CNC processing on the processing target according to the optimization parameters and the optimized selected path of CNC processing; When the path optimization value of the final selected path is less than or equal to the path optimization threshold, no processing is performed.
7. Intelligent optimization application of precision CNC machining, characterized by: An intelligent optimization process for executing the precision CNC machining described in any one of claims 1-6.
Citation Information
Patent Citations
Tool path generation and optimization method based on reinforcement learning
CN109491320A
Robot grinding track optimization method based on digital twinning and visual communication technology
CN116276328A
Optimized machining control method and system for numerical control machine tool
CN117047556A
Distributed Additive Manufacturing Platform for Value Chain Networks
US20230080545A1
