Fine machining method and device of double-sided numerical control milling machine

Abstract

The invention provides a fine machining method and device of a double-face numerical control milling machine, and relates to the technical field of milling machine numerical control. The method comprises the steps that target numerical control machining tools are obtained, and the target numerical control machining tools comprise the first tool and the second tool; traversing and matching the target workpiece characteristic parameters to obtain a target milling machine control scheme; acquiring a processing monitoring record; obtaining a first project parameter and a second project parameter; establishing a target comparison deviation set based on the first project comparison deviation; a prediction synchronization index is obtained through analysis of the processing synchronization prediction model; and when the predicted synchronization index is not in the synchronization index limit value, sending a dynamic adjustment instruction to carry out dynamic adjustment and optimization. The technical targets of intelligentization, automation and datamation of the double-sided numerical control machining process are achieved, and the technical effects that the problem of asynchronous double-sided machining is found in time, targeted adjustment is conducted in time, and finally the machining precision is improved are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of CNC milling machines, and in particular to a fine processing method and device for a double-sided CNC milling machine. Background Art

[0002] With the rapid development of modern manufacturing industry, CNC machining technology is being used more and more widely in industrial production. In the process of CNC machining, how to improve machining efficiency and machining accuracy and ensure the stability of the machining process has always been the goal pursued by the manufacturing industry. The traditional CNC machining process mainly relies on the experience and technical level of the operator, and the machining efficiency and machining accuracy are subject to certain limitations. In order to solve this problem, researchers have proposed many solutions based on computer technology and artificial intelligence, such as CNC machining database, neural network model, etc. CNC machining database is a system for storing and managing various data and information required in the machining process. It can provide the optimal machining plan and parameter settings according to the characteristics and machining requirements of the workpiece. The neural network model is a computational model that simulates the structure of neurons in the human brain. It can realize intelligent control and optimization of the machining process through learning and training.

[0003] However, in the actual CNC machining process, due to the influence of various factors, such as tool wear, cutting heat and cutting vibration, the machining process may become unstable and asynchronous. Summary of the invention

[0004] The purpose of this application is to provide a fine processing method and device for a double-sided CNC milling machine, so as to solve the technical problem that in the existing double-sided CNC processing process, it is impossible to timely discover the problem of double-sided processing asynchrony and take corrective adjustment measures in time, thereby affecting the processing control accuracy and causing unstable processing quality of the double-sided CNC milling machine.

[0005] In view of the above problems, the present application provides a fine processing method and device for a double-sided CNC milling machine.

[0006] In the first aspect, the present application provides a fine processing method for a double-sided CNC milling machine, which is implemented by a fine processing device for a double-sided CNC milling machine, wherein the fine processing method for a double-sided CNC milling machine comprises: obtaining a target CNC processing tool, wherein the target CNC processing tool comprises a first tool for a first CNC surface and a second tool for a second CNC surface of the target double-sided CNC milling machine; traversing and matching target workpiece feature parameters obtained by multi-dimensional feature collection of the target workpiece in a fine processing database to obtain a target milling machine control scheme; obtaining a processing monitoring record, wherein the processing monitoring record refers to predetermined monitoring items when the first tool and the second tool process the target workpiece under the target milling machine control scheme. Purpose record, the processing monitoring record includes a first record and a second record; extracting the first monitoring item in the predetermined monitoring items, and matching parameters in the first record and the second record in turn to obtain first item parameters and second item parameters respectively; forming a target comparison deviation set based on the first item comparison deviation obtained by comparing the first item parameters and the second item parameters; analyzing the target comparison deviation set through a processing synchronization prediction model to obtain a predicted synchronization index, the processing synchronization prediction model is an intelligent model trained based on a neural network model; when the predicted synchronization index is not within the synchronization index limit, issuing a dynamic adjustment instruction, and dynamically adjusting and optimizing the target milling machine control scheme based on the dynamic adjustment instruction.

[0007] In the second aspect, the present application also provides a fine processing device for a double-sided CNC milling machine, which is used to execute the fine processing method for a double-sided CNC milling machine as described in the first aspect, wherein the fine processing device for a double-sided CNC milling machine includes: a tool acquisition module, the tool acquisition module is used to acquire a target CNC processing tool, the target CNC processing tool includes a first tool for the first CNC surface and a second tool for the second CNC surface of the target double-sided CNC milling machine; a scheme acquisition module, the scheme acquisition module is used to traverse and match the target workpiece feature parameters obtained by multi-dimensional feature collection of the target workpiece in a fine processing database to obtain a target milling machine control scheme; a monitoring and recording module, the monitoring and recording module is used to acquire a processing monitoring record, the processing monitoring record refers to a record of predetermined monitoring items when the first tool and the second tool process the target workpiece under the target milling machine control scheme, and the processing monitoring record includes The invention comprises a first record and a second record; a parameter matching module, wherein the parameter matching module is used to extract the first monitoring item in the predetermined monitoring items, and perform parameter matching in the first record and the second record in turn to obtain the first item parameter and the second item parameter respectively; a comparison analysis module, wherein the comparison analysis module is used to form a target comparison deviation set based on the first item comparison deviation obtained by comparing the first item parameter and the second item parameter; a synchronization index prediction module, wherein the synchronization index prediction module is used to analyze the target comparison deviation set through a processing synchronization prediction model to obtain a predicted synchronization index, and the processing synchronization prediction model is an intelligent model trained based on a neural network model; a dynamic adjustment module, wherein the dynamic adjustment module is used to issue a dynamic adjustment instruction when the predicted synchronization index is not within the synchronization index limit, and dynamically adjust and optimize the target milling machine control scheme based on the dynamic adjustment instruction.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: By acquiring a target CNC machining tool, the target CNC machining tool includes a first tool for a first CNC surface and a second tool for a second CNC surface of a target double-sided CNC milling machine; traversing and matching the target workpiece feature parameters obtained by multi-dimensional feature collection of the target workpiece in a fine machining database to obtain a target milling machine control scheme; acquiring a machining monitoring record, the machining monitoring record refers to a record of a predetermined monitoring item when the first tool and the second tool process the target workpiece under the target milling machine control scheme, the machining monitoring record includes a first record and a second record; extracting a first monitoring item from the predetermined monitoring items, and matching parameters in the first record and the second record in turn to obtain a first item parameter and a second item parameter respectively; forming a target comparison deviation set based on a first item comparison deviation obtained by comparing the first item parameter and the second item parameter; analyzing the target comparison deviation set through a machining synchronization prediction model to obtain a predicted synchronization index, the machining synchronization prediction model is an intelligent model trained based on a neural network model; when the predicted synchronization index is not at the synchronization index limit, issuing a dynamic adjustment instruction, and dynamically adjusting and optimizing the target milling machine control scheme based on the dynamic adjustment instruction. In other words, by integrating advanced monitoring technology, data analysis, intelligent models and automated control technology, the technical goals of intelligent, automated and data-based double-sided CNC machining processes have been achieved, and the problem of double-sided machining asynchrony has been discovered in a timely manner, and timely and targeted adjustments have been made, ultimately improving the technical effect of machining accuracy.

[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0011] Figure 1 A schematic flow chart of a fine processing method of a double-sided CNC milling machine for this application; Figure 2 This is a structural schematic diagram of a fine processing device of a double-sided CNC milling machine according to the present application.

[0012] Description of reference numerals: Tool acquisition module 11, solution acquisition module 12, monitoring and recording module 13, parameter matching module 14, comparison and analysis module 15, synchronization index prediction module 16, dynamic adjustment module 17. DETAILED DESCRIPTION

[0013] This application provides a fine processing method and device for a double-sided CNC milling machine, which solves the technical problem that the existing double-sided CNC machining process cannot timely detect the problem of double-sided machining asynchrony and take corrective adjustment measures, thereby affecting the machining control accuracy and causing the unstable machining quality of the double-sided CNC milling machine. By performing real-time analysis and prediction of the monitoring data during the machining process, the asynchrony phenomenon in the machining process can be timely discovered and adjusted, thereby ensuring the stability and machining quality of the machining process.

[0014] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0015] For example, please refer to the attached Figure 1 The present application provides a fine processing method for a double-sided CNC milling machine, wherein the method is implemented by executing a fine processing device for a double-sided CNC milling machine, and the fine processing method for a double-sided CNC milling machine specifically includes the following steps: Step 1: Obtain a target CNC machining tool, wherein the target CNC machining tool comprises a first tool on a first CNC surface and a second tool on a second CNC surface of a target double-sided CNC milling machine.

[0016] Specifically, first determine the specific model and processing requirements of the target double-sided CNC milling machine, which includes a detailed analysis of the processing characteristics and requirements of the first CNC surface and the second CNC surface. Then, based on these characteristics, select the appropriate tool material, size and shape to adapt to different processing tasks. Next, design the specific structure of the first tool and the second tool to ensure that they can adapt to the processing requirements of the first CNC surface and the second CNC surface respectively. In addition, it is also necessary to consider the installation and replacement methods of the tools to ensure the convenience and safety of operation on the CNC milling machine. Finally, through professional manufacturing processes, produce the first tool and the second tool that meet the requirements, and conduct quality inspections to ensure that they can meet the processing requirements of the double-sided CNC milling machine.

[0017] In summary, by configuring a special first tool and a second tool for the double-sided CNC milling machine, customized processing for different CNC surfaces can be achieved, thereby improving processing efficiency and quality. Such a configuration can not only improve processing accuracy, but also help to extend the service life of the tool and reduce production costs.

[0018] Step 2: Traverse and match the target workpiece feature parameters obtained by multi-dimensional feature collection in the fine processing database to obtain the target milling machine control solution.

[0019] Specifically, first, the characteristic parameters of the target workpiece are obtained through multi-dimensional feature collection, and traversal matching is performed in the fine processing database to obtain the target milling machine control scheme suitable for the workpiece, so as to achieve accurate matching between the workpiece characteristic parameters and the milling machine control scheme, thereby improving processing accuracy and efficiency.

[0020] Specifically, first, multi-dimensional features of the target workpiece are collected, including the size, shape, material properties and other information of the workpiece. Then, these feature parameters are input into the fine processing database. Next, the database system will traverse and match these parameters to find the most suitable milling machine control solution. In addition, the database may contain a variety of pre-stored milling machine control solutions, which are pre-set according to different types of workpiece characteristics and processing requirements. The matching process will take into account various factors, such as processing speed, cutting depth, tool path, etc. Finally, the milling machine control solution that best matches the target workpiece characteristics is output.

[0021] In summary, customized milling machine control for specific workpieces can be achieved by matching the multi-dimensional feature parameters of the target workpiece with the control scheme in the fine machining database.

[0022] Step three: Obtain a processing monitoring record, wherein the processing monitoring record refers to a record of predetermined monitoring items when the first tool and the second tool process the target workpiece under the target milling machine control scheme, and the processing monitoring record includes a first record and a second record.

[0023] Specifically, the process of obtaining machining monitoring records, which are monitoring data of specific tools (first tool and second tool) when machining the target workpiece under the target milling machine control scheme, collects and analyzes key data in the machining process in order to evaluate and optimize the machining quality and efficiency.

[0024] Specifically, first, determine the predetermined items that need to be monitored, which may include key indicators such as processing time, cutting force, temperature, tool wear, etc. Then, under the target milling machine control scheme, use the first tool and the second tool to process the target workpiece, and record the data of the above predetermined monitoring items. Next, these data are divided into two parts: the first record and the second record, which correspond to the processing conditions of the first tool and the second tool, respectively. In addition, these records may also include additional information such as the vibration of the tool and the roughness of the workpiece surface. Finally, the collected processing monitoring records will be used to analyze and evaluate the processing process in order to further optimize the tool and milling machine control scheme.

[0025] In summary, by acquiring and analyzing the machining monitoring records of the first tool and the second tool under the target milling machine control scheme, fine monitoring and evaluation of the machining process can be achieved.

[0026] Step 4: extracting the first monitoring item from the predetermined monitoring items, and performing parameter matching in the first record and the second record in turn to obtain first item parameters and second item parameters respectively.

[0027] Specifically, first, a specific first monitoring item is extracted from the predetermined monitoring items, and parameter matching is performed in the first record and the second record to obtain the first item parameter and the second item parameter. Through parameter matching, specific monitoring items of two different tools during the machining process are compared and analyzed to better understand the performance and machining effect of each tool.

[0028] Specifically, first, identify and extract the first monitoring item from the predetermined monitoring items, which may be a key performance indicator, such as cutting force, processing temperature, etc. Then, in the first record, that is, the processing monitoring record for the first tool, find the parameter data related to the first monitoring item. Next, in the second record, that is, the processing monitoring record for the second tool, perform the same parameter matching operation. In this way, the first item parameters and the second item parameters are obtained respectively, representing the performance of the two tools under the same monitoring item. In addition, this process may also include further analysis of the parameter data, such as calculating the mean value, standard deviation, etc., in order to have a deeper understanding of the differences in tool performance.

[0029] In summary, by extracting the first monitoring item from the predetermined monitoring items and matching the parameters in the first record and the second record, the technical solution can achieve the performance comparison of two different tools under specific monitoring items. This helps to evaluate and optimize the selection and use of tools, thereby improving the overall performance and efficiency of the machining process.

[0030] Step 5: Building a target comparison deviation set based on the first project comparison deviation obtained by comparing the first project parameter and the second project parameter.

[0031] Specifically, firstly, a target comparison deviation set is constructed by comparing the parameters of the first project with those of the second project, and the differences are identified by comparing the performance parameters of the two tools under the same monitoring items, and these differences are integrated into a comparison deviation set for further analysis and optimization of the machining process.

[0032] Specifically, first, a detailed comparative analysis is performed on the first project parameters and the second project parameters. This may include calculating the difference, standard deviation or other statistics between the two parameter sets. Then, based on the results of these comparative analyses, significant deviations between the two parameters are identified. Next, these deviation data are integrated into a target comparative deviation set. This set will contain all the significant deviations identified, providing basic data for subsequent analysis. In addition, the establishment of the target comparative deviation set may also include the classification and sorting of deviation data in order to better understand the degree of influence of different deviations on the machining process.

[0033] In summary, by comparing the first item parameters with the second item parameters and constructing a target comparison deviation set, this technical solution can achieve quantitative analysis of the performance difference between the two tools.

[0034] Step 6: Analyze the target comparison deviation set through a processing synchronization prediction model to obtain a predicted synchronization index. The processing synchronization prediction model is an intelligent model trained based on a neural network model.

[0035] Specifically, first, the target comparison deviation set is analyzed using the machining synchronization prediction model to obtain the predicted synchronization index. An intelligent model based on neural network training is used to evaluate and predict the synchronization of the two tools during the machining process, thereby providing a basis for optimizing machining parameters and improving machining quality.

[0036] Specifically, first, the target contrast deviation set is provided as input data to the machining synchronization prediction model. This model is based on neural network training and can process and analyze complex parameter relationships. Then, the model will analyze the input deviation data, including identifying deviation patterns, evaluating the impact of deviations on machining synchronization, etc. Next, based on these analysis results, the model will output a predicted synchronization index, which reflects the degree of synchronization between the two tools during the machining process. In addition, the training process of the neural network model may also include a large amount of historical machining data and synchronization evaluation results to ensure the prediction accuracy of the model. The target contrast deviation set is analyzed by the machining synchronization prediction model, and the predicted synchronization index is obtained to realize the intelligent prediction of the machining synchronization of the two tools.

[0037] Step seven: When the predicted synchronization index is not within the synchronization index limit, a dynamic adjustment instruction is issued, and the target milling machine control scheme is dynamically adjusted and optimized based on the dynamic adjustment instruction.

[0038] Specifically, when the predicted synchronization index does not reach the synchronization index limit, a dynamic adjustment instruction is issued, and the target milling machine control scheme is dynamically adjusted and optimized based on the instruction. The stability and efficiency of the machining process are ensured by real-time monitoring and evaluation of machining synchronization, so that the milling machine control scheme can be dynamically adjusted when necessary.

[0039] Specifically, first, a synchronization index limit is set, which is the ideal synchronization index range predetermined based on the machining quality and efficiency requirements. Then, the predicted synchronization index is compared with this limit. If the predicted synchronization index is lower or higher than the limit range, it indicates that there is a problem with the machining synchronization. Next, a dynamic adjustment instruction is issued, which contains adjustment suggestions for the milling machine control scheme, such as changing the cutting speed, feed rate or tool path. In addition, the generation of dynamic adjustment instructions may also include a comprehensive analysis of the current machining status to ensure the effectiveness of the adjustment measures. Finally, according to the dynamic adjustment instructions, the target milling machine control scheme is adjusted and optimized in real time to restore and maintain the ideal machining synchronization.

[0040] In summary, by monitoring and predicting the synchronization index and issuing dynamic adjustment instructions when it does not reach the synchronization index limit, the control scheme of the target milling machine can be optimized in real time. This helps to ensure the stability and efficiency of the machining process and reduce machining errors and tool wear caused by synchronization problems.

[0041] Furthermore, the present application includes: the target workpiece characteristic parameters include workpiece material type, workpiece heat treatment state, machining surface quality requirements, machining accuracy requirements and machining allowance.

[0042] Specifically, first, determine the material type of the workpiece, which is the basis for selecting tools and processing parameters. Different material types have different requirements for the processing process. For example, some materials may require special cutting speeds and feed rates. Then, consider the heat treatment state of the workpiece, which affects the hardness and processing performance of the material. Next, clarify the processing surface quality requirements, which include indicators such as surface roughness and finish. These requirements will affect the selection of tools and the setting of processing parameters. In addition, the processing accuracy requirement is also one of the key parameters, which determines the maximum error that can be tolerated during the processing. Finally, the processing allowance also needs to be considered, which refers to the amount of material that needs to be retained during the processing process to ensure the accuracy of the final workpiece size.

[0043] In summary, by defining the characteristic parameters of the target workpiece in detail, including workpiece material type, heat treatment status, machining surface quality requirements, machining accuracy requirements and machining allowance, comprehensive information support can be provided for selecting appropriate machining strategies and tools.

[0044] Furthermore, the present application includes: extracting the first fine machining data from the fine machining database, the first fine machining data including the first fine machining workpiece characteristic parameters and the first fine machining milling machine control scheme; reading the parameter labeling scheme, and based on the parameter labeling scheme, sequentially labeling the target workpiece characteristic parameters and the first fine machining workpiece characteristic parameters to obtain a target label vector and a first label vector, respectively; comparing the target label vector and the first label vector to obtain a first consistency ratio; when the first consistency ratio reaches the consistency ratio limit, recording the first fine machining milling machine control scheme as the target milling machine control scheme.

[0045] Specifically, first, the first fine processing data is extracted from the fine processing database, and the target workpiece characteristic parameters and the first fine processing workpiece characteristic parameters are labeled based on the parameter labeling scheme, and the first fine processing milling machine control scheme is determined by comparing the consistency ratio. Through labeling and consistency ratio comparison, the most suitable milling machine control scheme is automatically selected to improve the automation and intelligence level of the processing process.

[0046] Specifically, first, the first fine machining data is extracted from the fine machining database, which includes the first fine machining workpiece feature parameters and the corresponding milling machine control scheme. Then, the parameter labeling scheme is read, which defines how to convert the workpiece feature parameters into label vectors. Next, based on this scheme, the target workpiece feature parameters and the first fine machining workpiece feature parameters are labeled to obtain the target label vector and the first label vector, respectively. These label vectors are quantitative representations of the workpiece feature parameters, which facilitate subsequent comparative analysis. In addition, by comparing the target label vector and the first label vector, the first consistency ratio is calculated, which reflects the degree of similarity between the two workpiece feature parameter sets. Finally, when the first consistency ratio reaches the preset consistency ratio limit, it indicates that the two workpiece feature parameter sets are highly similar, so the first fine machining milling machine control scheme is used as the target milling machine control scheme.

[0047] In summary, by extracting data from the fine machining database, labeling the workpiece feature parameters, and calculating the consistency ratio, it is possible to achieve intelligent selection of the target milling machine control scheme, which helps to improve the automation level of the machining process and reduce manual intervention. At the same time, it ensures that the selected milling machine control scheme can meet the machining requirements of the target workpiece, thereby improving machining efficiency and accuracy.

[0048] Further, the present application includes: the target milling machine control scheme includes a target spindle speed, a target feed speed and a target cutting depth.

[0049] Specifically, the target milling machine control scheme consists of the target spindle speed, target feed rate and target cutting depth. By accurately setting the spindle speed, feed rate and cutting depth of the milling machine, the machining process can be optimized to meet the machining requirements of the target workpiece.

[0050] Specifically, first, determine the target spindle speed, which refers to the speed at which the milling machine spindle rotates, which directly affects the cutting efficiency and the quality of the workpiece surface. Then, set the target feed rate, which is the speed at which the tool moves during the machining process, which affects the machining time and workpiece accuracy. Next, determine the target cutting depth, which refers to the maximum depth that the tool cuts into the workpiece, which determines the amount of material removed per cut and the number of machining operations. The setting of these three parameters requires comprehensive consideration of factors such as the material properties of the workpiece, machining accuracy requirements, and tool performance. In addition, the determination of the target milling machine control scheme may also include the optimization of other parameters, such as cutting paths, coolant flow, etc.

[0051] In summary, by accurately setting the spindle speed, feed rate and cutting depth in the target milling machine control scheme, the optimal control of the machining process can be achieved.

[0052] Furthermore, the present application includes: the predetermined monitoring items include tool wear rate, cutting heat value and cutting vibration amplitude.

[0053] Specifically, the scheduled monitoring items include tool wear rate, cutting heat value and cutting vibration amplitude. By monitoring these key indicators, the tool status and processing performance during the processing are evaluated, thus providing a basis for optimizing processing parameters and improving processing quality.

[0054] Specifically, first, the tool wear rate is monitored, which refers to the degree of tool wear during the machining process, reflecting the tool's durability and machining efficiency. Then, the cutting heat value, that is, the heat generated during the machining process, is measured, which affects the heat treatment state of the workpiece and the life of the tool. Next, the cutting vibration amplitude is recorded, which refers to the vibration of the tool during the machining process, which is related to the machining accuracy and workpiece surface quality. The data collection and analysis of these monitoring items help to promptly discover problems in the machining process, such as excessive tool wear, excessive cutting temperature or excessive vibration, so as to adjust the machining strategy in a timely manner.

[0055] In summary, by monitoring the predetermined monitoring items such as tool wear rate, cutting heat value and cutting vibration amplitude, this technical solution can achieve fine monitoring of the machining process.

[0056] Further, the present application includes: generating a first parameter time series of the first monitoring project based on the first project parameter; generating a second parameter time series of the first monitoring project based on the second project parameter; obtaining a scheduled time; performing a trend prediction analysis on the first parameter time series in combination with the scheduled time to obtain a first prediction project parameter; performing a trend prediction analysis on the second parameter time series in combination with the scheduled time to obtain a second prediction project parameter; and recording the parameter difference between the first prediction project parameter and the second prediction project parameter as the first project comparison deviation.

[0057] Specifically, a parameter time series is generated based on the first project parameter and the second project parameter, and a trend forecast analysis is performed in combination with a predetermined time to obtain the first forecast project parameter and the second forecast project parameter, and then the first project comparison deviation is calculated. By analyzing the trend of the parameter time series, the parameter value at a predetermined time point in the future is predicted, and by comparing the predicted values ​​of the two parameters, the difference between the two projects is evaluated.

[0058] Specifically, first, a first parameter time series of the first monitoring project is generated based on the first project parameter, which reflects the changing trend of the first project parameter over time. Then, a second parameter time series is generated based on the second project parameter, which also reflects the changing trend of the second project parameter over time. Next, a predetermined time point is determined, which is the time base for trend forecasting analysis. After the predetermined time is determined, a trend forecasting analysis is performed on the first parameter time series to obtain the first forecast project parameter, which is the predicted value of the first project parameter at the predetermined time point. Similarly, a trend forecasting analysis is performed on the second parameter time series to obtain the second forecast project parameter. Finally, the parameter difference between the first forecast project parameter and the second forecast project parameter is calculated. This difference is the first project comparison deviation, which reflects the performance difference between the two projects at the predetermined time point.

[0059] In summary, by generating a parameter time series, performing trend forecast analysis in combination with a predetermined time, and calculating the first item comparison deviation, it is possible to predict and evaluate the performance difference between the two items.

[0060] Further, the present application includes: obtaining a first time; matching the first parameter at the first time in the first parameter time series and matching the second parameter at the first time in the second parameter time series in sequence; obtaining a first synchronization index at the first time through a predetermined measuring device, and combining the first parameter and the second parameter to form a first training data group; performing supervised learning on the first training data group to obtain the processing synchronization prediction model.

[0061] Specifically, the parameter values ​​in the first parameter time series and the second parameter time series are matched at a first time, and a first synchronization index is obtained through a predetermined measuring device, and then these data are used to form a first training data group, and finally a processing synchronization prediction model is obtained through supervised learning. By analyzing the parameter values ​​and synchronization indexes of the two parameter time series at the first time point, an intelligent model capable of predicting processing synchronization is trained.

[0062] Specifically, first, determine the first time point, which is the time base for parameter matching and synchronization index measurement. Then, find the first parameter value corresponding to the first time point in the first parameter time series, and find the second parameter value corresponding to the first time point in the second parameter time series. Next, obtain the first synchronization index of the first time point through a predetermined measuring device, which is a quantitative assessment of the synchronization of the two parameters at the first time point. Then, the first parameter, the second parameter and the first synchronization index at the first time point are combined into a first training data group. In addition, in order to improve the predictive ability of the model, it may be necessary to collect training data groups at multiple different time points. Finally, supervised learning is performed on the first training data group, which is a machine learning method that trains the model with known input and output data to obtain a processing synchronization prediction model.

[0063] In summary, by matching the parameter values ​​in the parameter time series at the first time point, obtaining the synchronization index, and forming a training data group, an intelligent model for predicting processing synchronization can be trained, which helps to monitor and predict processing synchronization in real time during the actual processing process, so as to adjust the processing parameters in time to ensure processing quality and efficiency.

[0064] Furthermore, the present application includes: reading a predetermined dynamic adjustment optimization strategy based on the dynamic adjustment instruction; forming a candidate factor set based on the predetermined dynamic adjustment optimization strategy, and performing a correlation analysis on the candidate factor set and the predicted synchronization index to obtain a correlation analysis result; screening the candidate factor set based on the correlation analysis result to obtain a target factor set; and dynamically adjusting and optimizing the target milling machine control scheme by adjusting the target factor set.

[0065] Specifically, the dynamic adjustment optimization strategy is read based on the dynamic adjustment instruction, and the target factor set is screened out by forming a candidate factor set and performing correlation analysis. Finally, the target milling machine control scheme is dynamically optimized by adjusting the target factor set. By analyzing the correlation between the predicted synchronization index and the candidate factor set, the factor with the greatest impact on the machining synchronization is determined, and the milling machine control scheme is adjusted accordingly to improve the synchronization and efficiency of the machining process.

[0066] Specifically, first, a predetermined dynamic adjustment optimization strategy is read based on the dynamic adjustment instruction, which refers to the rules and methods for adjusting the control parameters of the milling machine during the machining process. Then, a candidate factor set is formed, which includes various parameters that may affect the machining synchronization, such as spindle speed, feed rate, cutting depth, etc. Next, a correlation analysis is performed on the candidate factor set and the predicted synchronization index to determine which factors are most relevant to synchronization. In addition, the correlation analysis results will guide the screening of the candidate factor set to obtain the target factor set, which are the factors that have the greatest impact on machining synchronization. Finally, by adjusting the parameters in the target factor set, the target milling machine control scheme is dynamically adjusted and optimized to improve machining synchronization.

[0067] In summary, by reading the dynamic adjustment optimization strategy, forming and screening the target factor set, the intelligent optimization of the target milling machine control scheme is achieved.

[0068] Furthermore, the present application includes: the candidate factor set includes the target workpiece feature parameters, the target milling machine control scheme and the processing monitoring record.

[0069] Specifically, the candidate factor set consists of target workpiece characteristic parameters, target milling machine control scheme and processing monitoring records. By analyzing the correlation between these candidate factors and the predicted synchronization index, the key factors affecting processing synchronization are determined, thus providing a basis for dynamically adjusting and optimizing the milling machine control scheme.

[0070] Specifically, first, the candidate factor set includes the target workpiece characteristic parameters, which describe the material type, heat treatment status, machining surface quality requirements, etc. of the workpiece, and have a direct impact on the machining process and synchronization. Then, the candidate factor set also includes the target milling machine control scheme, which refers to the specific parameter settings used to machine the workpiece, such as spindle speed, feed speed, etc. The settings of these parameters directly affect the machining efficiency and synchronization. Next, the machining monitoring records are also part of the candidate factor set. These records contain key data in the actual machining process, such as tool wear rate, cutting heat value, etc., reflecting the actual status and performance of the machining process. Through the correlation analysis of these candidate factors, it is possible to determine which factors have the greatest impact on machining synchronization, thereby providing guidance for dynamically adjusting and optimizing the milling machine control scheme.

[0071] In summary, by incorporating the target workpiece characteristic parameters, the target milling machine control scheme, and the processing monitoring records into the candidate factor set, various factors affecting the processing synchronization can be comprehensively considered, which helps to determine the key factors through correlation analysis and provide a scientific basis for dynamically adjusting and optimizing the milling machine control scheme, thereby improving the synchronization and efficiency of the processing process.

[0072] In summary, the fine processing method of a double-sided CNC milling machine provided by the present application has the following technical effects: By acquiring a target CNC machining tool, the target CNC machining tool includes a first tool for a first CNC surface and a second tool for a second CNC surface of a target double-sided CNC milling machine; traversing and matching the target workpiece feature parameters obtained by multi-dimensional feature collection of the target workpiece in a fine machining database to obtain a target milling machine control scheme; acquiring a machining monitoring record, the machining monitoring record refers to a record of a predetermined monitoring item when the first tool and the second tool process the target workpiece under the target milling machine control scheme, the machining monitoring record includes a first record and a second record; extracting a first monitoring item from the predetermined monitoring items, and matching parameters in the first record and the second record in turn to obtain a first item parameter and a second item parameter respectively; forming a target comparison deviation set based on a first item comparison deviation obtained by comparing the first item parameter and the second item parameter; analyzing the target comparison deviation set through a machining synchronization prediction model to obtain a predicted synchronization index, the machining synchronization prediction model is an intelligent model trained based on a neural network model; when the predicted synchronization index is not at the synchronization index limit, issuing a dynamic adjustment instruction, and dynamically adjusting and optimizing the target milling machine control scheme based on the dynamic adjustment instruction. In other words, by integrating advanced monitoring technology, data analysis, intelligent models and automated control technology, the technical goals of intelligent, automated and data-based double-sided CNC machining processes have been achieved, and the problem of double-sided machining asynchrony has been discovered in a timely manner, and timely and targeted adjustments have been made, ultimately improving the technical effect of machining accuracy.

[0073] Embodiment 2: Based on the same inventive concept as the fine processing method of a double-sided CNC milling machine in the above embodiment, the present application also provides a fine processing device for a double-sided CNC milling machine, please refer to the attached Figure 2 , the fine processing device of the double-sided CNC milling machine comprises: The tool acquisition module 11 is used to acquire a target CNC machining tool, wherein the target CNC machining tool comprises a first tool on a first CNC surface and a second tool on a second CNC surface of a target double-sided CNC milling machine.

[0074] The solution obtaining module 12 is used to traverse and match the target workpiece feature parameters obtained by multi-dimensional feature collection of the target workpiece in the fine processing database to obtain the target milling machine control solution.

[0075] The monitoring and recording module 13 is used to obtain processing monitoring records, which refer to the records of predetermined monitoring items when the first tool and the second tool process the target workpiece under the target milling machine control scheme, and the processing monitoring records include the first record and the second record.

[0076] The parameter matching module 14 is used to extract the first monitoring item from the predetermined monitoring items, and perform parameter matching in the first record and the second record in sequence to obtain the first item parameter and the second item parameter respectively.

[0077] The comparison and analysis module 15 is used to form a target comparison deviation set based on a first project comparison deviation obtained by comparing the first project parameter and the second project parameter.

[0078] The synchronization index prediction module 16 is used to analyze the target comparison deviation set through a processing synchronization prediction model to obtain a predicted synchronization index. The processing synchronization prediction model is an intelligent model trained based on a neural network model.

[0079] The dynamic adjustment module 17 is used to issue a dynamic adjustment instruction when the predicted synchronization index is not within the synchronization index limit, and dynamically adjust and optimize the target milling machine control scheme based on the dynamic adjustment instruction.

[0080] Furthermore, the scheme obtaining module 12 in the fine processing device of the double-sided CNC milling machine is also used for: the target workpiece characteristic parameters include workpiece material type, workpiece heat treatment state, processing surface quality requirements, processing accuracy requirements and processing allowance.

[0081] Furthermore, the scheme obtaining module 12 in the fine machining device of the double-sided CNC milling machine is also used to: extract the first fine machining data in the fine machining database, the first fine machining data including the first fine machining workpiece characteristic parameters and the first fine machining milling machine control scheme; read the parameter labeling scheme, and based on the parameter labeling scheme, sequentially label the target workpiece characteristic parameters and the first fine machining workpiece characteristic parameters to obtain a target label vector and a first label vector, respectively; compare the target label vector and the first label vector to obtain a first consistency ratio; when the first consistency ratio reaches the consistency ratio limit, record the first fine machining milling machine control scheme as the target milling machine control scheme.

[0082] Furthermore, the scheme obtaining module 12 in the fine processing device of the double-sided CNC milling machine is also used for: the target milling machine control scheme includes a target spindle speed, a target feed speed and a target cutting depth.

[0083] Furthermore, the monitoring and recording module 13 in the fine processing device of the double-sided CNC milling machine is also used for: the predetermined monitoring items include tool wear rate, cutting heat value and cutting vibration amplitude.

[0084] Furthermore, the comparison and analysis module 15 in the fine processing device of the double-sided CNC milling machine is also used to: generate a first parameter time series of the first monitoring project based on the first project parameters; generate a second parameter time series of the first monitoring project based on the second project parameters; obtain a predetermined time; perform a trend prediction analysis on the first parameter time series in combination with the predetermined time to obtain a first prediction project parameter; perform a trend prediction analysis on the second parameter time series in combination with the predetermined time to obtain a second prediction project parameter; and record the parameter difference between the first prediction project parameter and the second prediction project parameter as the first project comparison deviation.

[0085] Furthermore, the synchronization index prediction module 16 in the fine processing device of the double-sided CNC milling machine is also used to: obtain a first time; match the first parameter at the first time in the first parameter time series and the second parameter at the first time in the second parameter time series in sequence; obtain the first synchronization index at the first time through a predetermined measuring device, and combine the first parameter and the second parameter to form a first training data group; perform supervised learning on the first training data group to obtain the processing synchronization prediction model.

[0086] Furthermore, the fine processing device of a double-sided CNC milling machine also includes an adjustment decision module, which is used to: read a predetermined dynamic adjustment optimization strategy based on the dynamic adjustment instruction; form a candidate factor set based on the predetermined dynamic adjustment optimization strategy, and perform correlation analysis on the candidate factor set and the predicted synchronization index to obtain a correlation analysis result; screen the candidate factor set based on the correlation analysis result to obtain a target factor set; and dynamically adjust and optimize the target milling machine control scheme by adjusting the target factor set.

[0087] Furthermore, the adjustment decision module in the fine processing device of the double-sided CNC milling machine is also used for: the candidate factor set includes the target workpiece characteristic parameters, the target milling machine control scheme and the processing monitoring record.

[0088] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The fine processing method and specific examples of a double-sided CNC milling machine in the first embodiment are also applicable to the fine processing device of a double-sided CNC milling machine in the present embodiment. Through the above detailed description of the fine processing method of a double-sided CNC milling machine, those skilled in the art can clearly know the fine processing device of a double-sided CNC milling machine in the present embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0089] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in their embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0090] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A fine processing method for a double-sided CNC milling machine, characterized in that: include: Acquire a target CNC machining tool, wherein the target CNC machining tool comprises a first tool on a first CNC surface and a second tool on a second CNC surface of a target double-sided CNC milling machine; The target workpiece feature parameters obtained by multi-dimensional feature collection of the target workpiece are traversed and matched in the fine processing database to obtain the target milling machine control solution; Acquire a processing monitoring record, wherein the processing monitoring record refers to a record of predetermined monitoring items when the first tool and the second tool process the target workpiece under the target milling machine control scheme, and the processing monitoring record includes a first record and a second record; Extracting a first monitoring item from the predetermined monitoring items, and matching parameters in the first record and the second record in sequence to obtain first item parameters and second item parameters respectively; forming a target contrast deviation set based on a first item contrast deviation obtained by comparing the first item parameter with the second item parameter; The target contrast deviation set is analyzed by a processing synchronization prediction model to obtain a prediction synchronization index, wherein the processing synchronization prediction model is an intelligent model trained based on a neural network model; When the predicted synchronization index is not within the synchronization index limit, a dynamic adjustment instruction is issued, and the target milling machine control scheme is dynamically adjusted and optimized based on the dynamic adjustment instruction.

2. The fine processing method of a double-sided CNC milling machine according to claim 1, characterized in that: The target workpiece characteristic parameters include workpiece material type, workpiece heat treatment state, machining surface quality requirements, machining accuracy requirements and machining allowance.

3. The fine processing method of a double-sided CNC milling machine according to claim 1, characterized in that: include: Extracting first fine machining data from the fine machining database, wherein the first fine machining data includes first fine machining workpiece characteristic parameters and a first fine machining milling machine control scheme; Reading a parameter labeling scheme, and sequentially labeling the target workpiece feature parameters and the first fine-machining workpiece feature parameters based on the parameter labeling scheme to obtain a target label vector and a first label vector respectively; Comparing the target label vector and the first label vector to obtain a first consistency ratio; When the first consistency ratio reaches the consistency ratio limit, the first fine machining milling machine control scheme is recorded as the target milling machine control scheme.

4. The fine processing method of a double-sided CNC milling machine according to claim 1, characterized in that: The target milling machine control scheme includes a target spindle speed, a target feed speed and a target cutting depth.

5. The fine processing method of a double-sided CNC milling machine according to claim 1, characterized in that: The predetermined monitoring items include tool wear rate, cutting heat value and cutting vibration amplitude.

6. The fine processing method of a double-sided CNC milling machine according to claim 1, characterized in that: include: generating a first parameter time series of the first monitoring item based on the first item parameter; generating a second parameter time series of the first monitoring item based on the second item parameter; Get the scheduled time; Performing trend forecast analysis on the first parameter time series in combination with the predetermined time to obtain a first forecast item parameter; Performing trend forecast analysis on the second parameter time series in combination with the predetermined time to obtain a second forecast item parameter; The parameter difference between the first prediction item parameter and the second prediction item parameter is recorded as the first item comparison deviation.

7. The fine processing method of a double-sided CNC milling machine according to claim 6, characterized in that: include: Get the first time; sequentially matching the first parameter at the first time in the first parameter sequence and matching the second parameter at the first time in the second parameter sequence; Acquire a first synchronization index at the first time by using a predetermined measuring device, and combine the first parameter with the second parameter to form a first training data group; The processing synchronization prediction model is obtained by performing supervised learning on the first training data set.

8. The fine processing method of a double-sided CNC milling machine according to claim 1, characterized in that: Also includes: Reading a predetermined dynamic adjustment optimization strategy based on the dynamic adjustment instruction; Based on the predetermined dynamic adjustment optimization strategy, a candidate factor set is formed, and a correlation analysis is performed between the candidate factor set and the predicted synchronization index to obtain a correlation analysis result; Screening the candidate factor set based on the correlation analysis result to obtain a target factor set; The target milling machine control scheme is dynamically adjusted and optimized by adjusting the target factor set.

9. The fine processing method of a double-sided CNC milling machine according to claim 8, characterized in that: The candidate factor set includes the target workpiece feature parameters, the target milling machine control scheme and the processing monitoring record.

10. A fine processing device for a double-sided CNC milling machine, characterized in that: The steps for implementing the fine processing method of a double-sided CNC milling machine as described in any one of claims 1 to 9 include: A tool acquisition module, the tool acquisition module is used to acquire a target CNC machining tool, the target CNC machining tool includes a first tool on a first CNC surface and a second tool on a second CNC surface of a target double-sided CNC milling machine; A scheme obtaining module, wherein the scheme obtaining module is used to traverse and match the target workpiece feature parameters obtained by multi-dimensional feature collection of the target workpiece in the fine processing database to obtain a target milling machine control scheme; A monitoring and recording module, wherein the monitoring and recording module is used to obtain a processing monitoring record, wherein the processing monitoring record refers to a record of predetermined monitoring items when the first tool and the second tool process the target workpiece under the target milling machine control scheme, and the processing monitoring record includes a first record and a second record; A parameter matching module, the parameter matching module is used to extract the first monitoring item from the predetermined monitoring items, and perform parameter matching in the first record and the second record in sequence to obtain first item parameters and second item parameters respectively; A comparison and analysis module, the comparison and analysis module is used to form a target comparison deviation set based on a first project comparison deviation obtained by comparing the first project parameter and the second project parameter; A synchronization index prediction module, wherein the synchronization index prediction module is used to analyze the target comparison deviation set through a processing synchronization prediction model to obtain a predicted synchronization index, wherein the processing synchronization prediction model is an intelligent model trained based on a neural network model; A dynamic adjustment module is used to issue a dynamic adjustment instruction when the predicted synchronization index is not within the synchronization index limit, and dynamically adjust and optimize the target milling machine control scheme based on the dynamic adjustment instruction.

Images