Numerical control machine tool intelligent control method and equipment combined with error analysis and storage medium

Abstract

The invention provides a numerical control machine tool intelligent control method and device combined with error analysis and a storage medium, and relates to the technical field of numerical control machine tool intelligent control. Setting U error hiding mode starting points and V error hiding mode ending points; performing propagation simulation according to error state transition, and simulating an error hidden cumulative map; configuring U error hiding mode starting points by using equipment basic data, performing propagation path simulation in an error hiding cumulative map, and obtaining M error simulation propagation paths; identifying a key error source sequence with the influence on the machining precision from large to small; setting an error compensation strategy and sending the error compensation strategy to the numerical control machine tool terminal for compensation control. The technical problems that in the prior art, deep analysis on an error propagation path is lacked, and the control precision of a numerical control machine tool is low are solved, and the technical effect that the control precision is improved by combining error analysis and a corresponding compensation strategy is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control of numerically controlled machine tools, and in particular to an intelligent control method, device and storage medium for numerically controlled machine tools combined with error analysis. Background Art

[0002] CNC machine tools are core equipment in modern manufacturing, and their machining accuracy directly determines product quality. However, during the machining process, errors inevitably arise and accumulate due to the complexity of equipment states (such as power-on and power-off frequency and idle time) and operating conditions (such as spindle speed and load). Traditional CNC machine tool control systems typically rely on fixed parameter configurations for machining process control. These controls lack in-depth analysis of error propagation paths and effective dynamic adjustment mechanisms. As a result, they struggle to meet the increasingly demanding machining accuracy standards for complex machining tasks. Summary of the Invention

[0003] This application aims to solve the technical problems in the prior art of lacking in-depth analysis of error propagation paths and low control accuracy of CNC machine tools by providing an intelligent control method, device and storage medium for CNC machine tools combined with error analysis.

[0004] The first aspect disclosed in the present application provides an intelligent control method for a CNC machine tool combined with error analysis, the method comprising: Connect to the CNC machine tool terminal to obtain basic equipment data, including the power-on time, power-off time, and standby time corresponding to the equipment status data, and the feed rate, spindle speed, spindle rate, and spindle load corresponding to the equipment operation data; Connecting to the machine tool control database, establishing an error hiding pattern analysis model, and setting U error hiding pattern starting points and V error hiding pattern end points, where U and V are integers greater than or equal to 1; Based on the U error concealment mode starting points and the V error concealment mode end points, propagation simulation is performed against the error state transition to simulate an error concealment accumulation graph; The U error concealment mode starting points are configured using the device basic data, and propagation path simulation is performed on the error concealment cumulative map to obtain M error simulation propagation paths, where M is an integer greater than or equal to 1; Based on the M error simulation propagation paths, the error hidden pattern analysis model is used to calculate the cumulative effect of errors at different processing stages, and a sequence of key error sources with decreasing impact on processing accuracy is identified; Based on the M error simulation propagation paths and key error source sequences, an error compensation strategy is set and sent to the CNC machine tool terminal for compensation control.

[0005] In a second aspect of the present disclosure, an electronic device is provided, comprising a memory and a processor, wherein the memory stores executable instructions, and the processor executes the executable instructions stored in the memory to implement any step of the first aspect of the present disclosure.

[0006] In a third aspect of the present disclosure, a computer readable storage medium is provided, which stores a computer program for executing any step of the first aspect of the present disclosure.

[0007] The one or more technical solutions provided in the present application have at least the following technical effects or advantages: Connect the numerical control machine tool terminal, obtain the equipment basic data, the equipment basic data includes the boot time, the shutdown time, the standby time length corresponding to the equipment state data and the feed rate, the spindle speed, the spindle rate, the spindle load corresponding to the equipment running data; connect the machine tool control database, establish an error hidden mode analysis model, and set U error hidden mode starting points and V error hidden mode ending points, U and V are integers greater than or equal to 1; based on the U error hidden mode starting points and the V error hidden mode ending points, the error state transition is compared and propagated simulation is performed, and an error hidden cumulative atlas is generated; the U error hidden mode starting points are configured based on the equipment basic data, the propagation path simulation is performed in the error hidden cumulative atlas, M error simulation propagation paths are obtained, and M is an integer greater than or equal to 1; based on the M error simulation propagation paths, the error hidden mode analysis model is used to calculate the cumulative effect of the error in different machining stages, and a key error source sequence from large to small affecting the machining precision is identified; based on the M error simulation propagation paths and the key error source sequence, an error compensation strategy is set and sent to the numerical control machine tool terminal for compensation control. The technical effects of improving the control precision of the numerical control machine tool, reducing the cumulative effect of the error, and improving the machining quality are achieved.

[0008] The above description is only a summary of the technical solutions of the present application. In order to more clearly understand the technical means of the present application, the present application can be implemented according to the content of the specification, and in order to make the above and other purposes, characteristics and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0009] Figure 1 The intelligent control method flow chart of the numerical control machine tool combined with error analysis provided by the embodiments of the present application; Figure 2 The internal structure diagram of the electronic device provided by the embodiments of the present application; Explanation of reference numerals: bus 300, receiver 301, processor 302, transmitter 303, memory 304, bus interface 305. DETAILED DESCRIPTION

[0010] The embodiments of the present application solve the technical problems in the prior art of lacking in-depth analysis of error propagation paths and low control accuracy of CNC machine tools by providing an intelligent control method for CNC machine tools combined with error analysis.

[0011] After introducing the basic principles of this application, various non-limiting embodiments of this application will be specifically described below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described here are only used to explain this application and are not used to limit this application.

[0012] Example 1, as Figure 1 As shown, an embodiment of the present application provides an intelligent control method for CNC machine tools combined with error analysis, the method comprising: Step S100: Connecting to a CNC machine tool terminal to obtain basic equipment data, including the startup time, shutdown time, and standby time corresponding to equipment status data, and the feed rate, spindle speed, spindle override, and spindle load corresponding to equipment operation data; In one embodiment, the CNC machine tool terminal refers to a device terminal used to operate and control the CNC machine tool, and may include a machine control panel, an operating system, or a connected external computer. The basic equipment data refers to core parameter information generated during the operation of the CNC machine tool, including equipment status data and equipment operation data, which is used to reflect the working status and operating conditions of the machine tool.

[0013] Device status data describes information related to device operating time, such as power-on time, power-off time, and standby time. Device operation data describes machine tool operating parameters during machining, including feedrate (the ratio of machining feedrate to nominal speed), spindle speed (spindle revolutions per minute), spindle override (the ratio of actual spindle speed to rated speed), and spindle load (the ratio of the current spindle machining load to the rated load).

[0014] Preferably, basic equipment data is obtained by connecting to the CNC machine tool terminal. This data contains the CNC machine tool's operating status and processing operation information, providing basic support for subsequent analysis. First, by extracting equipment status data such as power-on time, power-off time, and standby time, the frequency and efficiency of equipment usage can be understood. Then, by collecting operating data such as feed rate, spindle speed, spindle ratio, and spindle load, the actual operating parameters of the equipment during processing can be understood. This achieves the technical effect of providing reliable initial data input for subsequent error analysis.

[0015] Step S200: Connecting to the machine tool control database, establishing an error hiding pattern analysis model, and setting U error hiding pattern starting points and V error hiding pattern end points, where U and V are integers greater than or equal to 1; In one embodiment, the machine tool control database refers to a database that stores historical data and control parameters related to the operation of CNC machine tools, typically including information such as basic equipment data, processing process data, and historical error data. The error hiding pattern analysis model refers to a mathematical model used to analyze the laws of error generation, propagation, and accumulation, revealing the existence and impact of error hiding patterns through data extraction and processing. The U error hiding pattern starting points refer to the starting points of error propagation, which are usually related to changes in processing conditions or specific machine tool states. The V error hiding pattern end points refer to the end points of error propagation, which are usually the locations where error accumulation is most obvious.

[0016] Determine the storage location and access rights of the machine tool control database and establish a connection to the machine tool control database through a data interface (such as an API or database driver) to ensure real-time or batch access rights. Verify the integrity and accuracy of key data stored in the database (including equipment operating data and historical error data) to lay the data foundation for subsequent analysis.

[0017] Extract relevant data from the database, including equipment status data, operating parameters, and historical error data. Clean and format the extracted data to remove noise and redundant information, such as deleting incomplete records or abnormal data points. Normalize the data to ensure the consistency of the model input data. Analyze the underlying patterns and cumulative characteristics of error propagation using statistical analysis, machine learning, or deep learning methods. Based on the extracted data, define the basic framework of the error hidden pattern analysis model, including the model's input parameters, characteristic variables, and output targets. The model must be able to map the error propagation path from the starting point to the end point and quantify the cumulative effect of errors at each link.

[0018] Preferably, multiple historical error paths and multiple historical cumulative errors are extracted from the machine tool control database, wherein each historical error path includes an error starting point and an error end point. The historical cumulative error is the machining offset from the standard machining data exposed at the error end point in the error propagation path from the error starting point to the error end point. Using the multiple historical error paths and the multiple historical cumulative errors as training data, a framework constructed based on a convolutional neural network is subjected to supervised training to learn the one-to-one mapping relationship between error paths and cumulative errors until training converges, thereby obtaining the trained error hidden pattern analysis model.

[0019] Optionally, the error starting points with the highest U occurrence frequencies from the multiple historical error paths are extracted as the U error hiding pattern starting points, and the error ending points with the highest V occurrence frequencies from the multiple historical error paths are extracted as the V error hiding pattern ending points. By establishing an error hiding pattern analysis model, a basic framework can be provided for simulating error propagation paths and identifying key error sources, enabling in-depth analysis of error generation, accumulation, and propagation. This achieves the technical effect of improving the machining accuracy and efficiency of CNC machine tools and laying the foundation for the subsequent development of error compensation strategies.

[0020] Step S300: Based on the U error concealment mode starting points and the V error concealment mode end points, a propagation simulation is performed against the error state transition to generate an error concealment accumulation graph; In a possible embodiment, the error hiding cumulative graph is used to display the error propagation path and cumulative effect from multiple starting points to multiple end points in the form of a graph, intuitively reflecting the key nodes of error transmission and their impact.

[0021] Preferably, an error propagation simulation is performed based on the U error concealment pattern starting points and V error concealment pattern endpoints, connected to the basic data of the CNC machine tool terminal. The U error concealment pattern starting points are used as the initial state set, and their probability distribution is defined. Based on the basic equipment data, U occurrence frequencies of the U error concealment pattern starting points are determined, and the U occurrence frequencies are divided by the sum of the U occurrence frequencies to obtain the probability distribution of the initial state set. The V error concealment pattern endpoints are selected as the target state set for terminating the propagation simulation.

[0022] The number of times any error concealment mode starting point in the initial state set transitions to any error concealment mode endpoint in the target state set is traversed and counted, and the number of times the error concealment mode starting point transitions to all error concealment mode endpoints in the target state set is divided by the total number of times the error concealment mode starting point transitions to all error concealment mode endpoints in the target state set to obtain the state transition probability from an error concealment mode starting point to an error concealment mode endpoint. Based on the above state transition probability calculation principle, a state transition probability matrix is ​​constructed. The state transition probability matrix reflects the probability distribution of error propagation.

[0023] Based on historical control data from the machine tool control database, multiple error propagation paths from the initial state set to the target state set are obtained. The state transition probability matrix is ​​then used to perform cumulative error analysis. Nodes are used to represent the starting points or endpoints of different error hiding modes, while edges represent transition paths between states. Transition probabilities and cumulative error values ​​are annotated, with paths with the greatest cumulative error effects or highest transition probabilities highlighted. Key error propagation paths and their characteristics are highlighted. A graph is generated using graphical tools, including a cumulative error hiding graph, to intuitively present the patterns and cumulative effects of error propagation.

[0024] Step S400: configuring the U error concealment mode starting points using the device basic data, performing propagation path simulation on the error concealment cumulative graph, and obtaining M error simulation propagation paths, where M is an integer greater than or equal to 1; In one embodiment, the M error simulation propagation paths are obtained through simulation deduction of the error hiding cumulative map, and are specific paths where errors may propagate in accordance with the basic data of the device. M is an integer greater than or equal to 1, representing the number of paths.

[0025] First, the U starting points of the error hiding patterns are configured using basic equipment data. This step analyzes the equipment's operating status and processing conditions to associate the initial error source with the starting point, ensuring the accuracy of the error propagation simulation. Next, within the error hiding accumulation map, propagation path simulation is performed based on the error state transition patterns. During the simulation, based on input data such as the processing environment, equipment parameters, and error characteristics, the error propagation path and cumulative effect from the starting point to the end point are gradually derived, generating the M simulated error propagation paths.

[0026] From the perspective of error propagation, we identify the potential error transmission paths and their impact on the machining process. Through detailed simulation of these propagation paths, we can identify the key links in error propagation within complex machining environments, providing data support for subsequent error compensation strategies. This step also helps optimize machining processes and improve the accuracy and efficiency of CNC machine tools by analyzing the characteristics of multiple propagation paths.

[0027] Step S500: Based on the M error simulation propagation paths, the error hidden pattern analysis model is used to calculate the cumulative effect of errors at different processing stages, and a sequence of key error sources having a decreasing impact on processing accuracy is identified; In one possible embodiment, the M simulated error propagation paths are input into the error hidden pattern analysis model for analysis to determine M accumulated errors. The M accumulated errors are arranged in descending order, and the error sources in the corresponding propagation paths are arranged to obtain a sequence of key error sources that have a decreasing impact on machining accuracy.

[0028] The key error source sequence intuitively demonstrates the priority error sources to be compensated during machining, providing a clear target for developing error compensation strategies. By identifying the error sources that most impact machining accuracy, this provides a basis for decision-making to optimize machining accuracy, effectively concentrating resources for targeted processing, thereby avoiding generalized control and improving compensation efficiency and overall machining performance.

[0029] Step S600: Based on the M error simulation propagation paths and key error source sequences, an error compensation strategy is set and sent to the CNC machine tool terminal for compensation control.

[0030] In one embodiment, an error compensation strategy is designed based on M error simulation propagation paths and a sequence of key error sources. First, the characteristics of each key error source and the degree of its impact on machining accuracy are analyzed. Combined with the cumulative trend of errors in the propagation path, a specific compensation scheme is set. For example, for spindle speed errors, the speed deviation can be corrected by adjusting the control algorithm; for load anomalies, balanced control can be performed by dynamically distributing the machining load. Next, the designed compensation strategy is converted into an executable instruction or parameter configuration file for the CNC machine tool and sent to the machine tool terminal through the communication interface. The machine tool terminal adjusts the operating status according to the instruction and dynamically implements compensation control, such as adjusting the feed rate, optimizing the tool path, or correcting the machining posture in real time.

[0031] Through precise compensation control, the cumulative effects of errors generated during the machining process can be promptly eliminated or mitigated, significantly improving machining accuracy and product quality. At the same time, the application of targeted compensation strategies can optimize resource utilization and avoid efficiency losses caused by global adjustments, achieving the technical effects of efficient error control and machining process optimization.

[0032] Furthermore, based on the U error concealment mode starting points and the V error concealment mode end points, propagation simulation is performed against the error state transition to generate an error concealment accumulation graph. In this embodiment of the application, step S300 further includes: Obtaining basic data of similar equipment of the CNC machine tool terminal; Performing incremental learning based on the basic data of the similar device to set a propagation path check point, wherein the propagation path check point is located on a line connecting a starting point of an error concealment mode and an end point of the error concealment mode; The error concealment accumulation map is verified and adjusted according to the propagation path verification point.

[0033] In one possible embodiment, the basic data of similar equipment refers to the operating data of equipment that is similar to the current CNC machine tool terminal in terms of model, purpose or operating characteristics, including equipment status data (such as power on / off time, standby time) and processing parameter data (such as spindle speed, feed rate, etc.). Incremental learning is a method of gradually optimizing a model based on existing data and new input data. By gradually absorbing new data, the adaptability and accuracy of the error analysis model are improved. The propagation path checkpoint is a key point used to detect and verify the accuracy of the error transfer results during the simulation of the error propagation path. The verification adjustment is to correct and optimize the structure or data of the error hidden accumulation map based on the verification results of the propagation path checkpoint to make it more consistent with the actual processing situation.

[0034] Preferably, the path checkpoints are key points in the error propagation path. Similar devices with similar CNC machine tool terminal models, processing tasks, and operating conditions are selected from the database and their basic data is extracted. Duplicate, incomplete, or abnormal records are removed to ensure data accuracy and consistency. Newly collected data is converted to a standard format compatible with the existing model to ensure smooth incremental learning.

[0035] Based on the basic data of similar devices, similar error propagation paths are extracted to obtain a set of similar error propagation paths. Key nodes or states in the set of similar error propagation paths are selected as checkpoints, typically including: intermediate nodes: key stages of error propagation (such as device state switching or process conversion). The propagation path checkpoints are located on the line connecting the starting point and the end point of the error concealment mode.

[0036] Compare the propagation path checkpoints with the simulation results in the error hiding accumulation map, and record any deviations. Based on the deviations from the checkpoints, modify the model's transition probabilities, error accumulation values, or path weights. Verify the effectiveness of the optimized model and checkpoints through simulation experiments or actual processing to ensure the accuracy of the error hiding accumulation map. Use the verification feedback as input for the next round of incremental learning to further improve the model's adaptability and the rationality of the checkpoints.

[0037] Through incremental learning, the error propagation model can be gradually optimized using basic data from similar equipment. The setting of propagation path checkpoints ensures the accuracy of model adjustments. This improves the model's adaptability to complex machining scenarios and provides more reliable theoretical and data support for subsequent error compensation.

[0038] Furthermore, according to the propagation path check point, the error concealment cumulative map is checked and adjusted. In the embodiment of the present application, step S300 further includes: Based on the propagation path check point, setting a check adjustment model, the check adjustment model including a servo control layer and a feedback control layer; Performing performance verification and adjustment using a servo control layer of the verification and adjustment model, the servo control layer including a predicted performance indicator; Error compensation adjustment is performed using a feedback control layer of the verification adjustment model, wherein the feedback control layer includes a prediction accuracy indicator.

[0039] In one possible embodiment, a verification and adjustment model is established, divided into two layers: a servo control layer, which monitors the performance deviation of the error propagation path in real time and performs verification and adjustment based on predicted performance indicators. A feedback control layer, which uses predicted accuracy indicators to compensate for the deviation between the actual error in the processing result and the expected value. Key parameters (such as weights and threshold ranges) of the servo and feedback control layers are initialized based on historical data from verification points along the propagation path.

[0040] By collecting real-time operating parameters from each stage of the machining process and combining them with predicted performance indicators (such as error accumulation rate and state transition probability deviation), the deviation of the actual error propagation path is calculated. Based on the calculated results, the parameters of the error hiding accumulation graph are adjusted. When the actual error propagation path deviates from the predicted performance indicators, the node weights or transition probabilities in the graph are adjusted to correct the performance deviation of the propagation path. For example, the error weight of the critical path is increased, and the path distribution of abnormal transition probabilities is corrected.

[0041] Optionally, the processing results are monitored in real time, and the deviation between the actual error and the predicted value is determined based on the prediction accuracy indicator combined with the real-time monitoring results. Based on the deviation analysis results of the feedback control layer, the error compensation strategy is dynamically adjusted. For example, compensation efforts can be increased for paths with rapidly increasing cumulative errors. For error-sensitive processing stages, the compensation strategy parameter configuration can be optimized.

[0042] A closed-loop control system is established from the servo control layer to the feedback control layer, feeding the servo control adjustment results back into the error hiding accumulation map to further optimize the accuracy of the calibration and adjustment model. By combining the real-time error propagation path and machining results, the servo and feedback control parameter configurations are continuously optimized to adapt the model to different machining environments.

[0043] By utilizing the servo and feedback control layers to precisely verify and adjust the propagation path, the error hiding accumulation map is made more relevant to actual machining scenarios. The servo control layer focuses on performance calibration of the error propagation path, while the feedback control layer optimizes compensation based on the machining results. Together, these two layers enhance the map's dynamic adjustment capabilities and the practicality of the compensation strategy.

[0044] Furthermore, error compensation adjustment is performed using the feedback control layer of the verification adjustment model, wherein the feedback control layer includes a prediction accuracy index. In the embodiment of the present application, step S300 further includes: Integrating a feedback mechanism into the calibration and adjustment model allows dynamic adjustment of error compensation parameters based on changes in the actual machining process; Historical data is introduced to analyze the error data accumulated during the processing and dynamically adjust the error compensation strategy.

[0045] Furthermore, historical data is introduced to analyze the error data accumulated during the processing and dynamically adjust the error compensation strategy. In this embodiment of the application, step S300 further includes: Set periodic evaluation criteria and add processing quality indicators; Based on the processing quality indicators, extract short-term abnormal fluctuations and long-term error trends; Long-term and short-term adaptive error compensation is performed based on the short-term abnormal fluctuations and long-term error trends.

[0046] In one possible implementation, a feedback mechanism is integrated into the calibration and adjustment model to monitor error data generated during the actual machining process in real time. When machining parameters or error characteristics change, the feedback mechanism dynamically adjusts error compensation parameters (such as compensation intensity and frequency) to adapt to the new machining conditions. Furthermore, historical data is incorporated to analyze trends in the accumulated error information, identifying long-term patterns in the machining process and supporting subsequent strategy optimization.

[0047] Preferably, periodic evaluation criteria are set and machining quality indicators are added. The effectiveness of the current compensation strategy is determined by regularly evaluating the deviation of machining results (such as dimensional tolerances and surface roughness) from the set standards. When analyzing the evaluation results, the machining quality in the historical data is analyzed using the machining quality indicators, and the fluctuation variance of the analysis results is calculated to obtain short-term abnormal fluctuations. Furthermore, the fluctuation variance of the fluctuation data within a preset long-term window (a time period predefined by skilled artisans) is extracted to obtain the long-term error trend. Combining a short-term response mechanism (rapidly responding to fluctuations) with a long-term optimization mechanism (adjusting machining parameters), a long-term and short-term adaptive error compensation strategy is developed to achieve comprehensive optimization of machining accuracy.

[0048] Through feedback control and dynamic analysis of historical data, the flexibility and accuracy of error compensation are improved. The short-term response mechanism quickly addresses sudden errors during machining, while the long-term optimization mechanism gradually improves machining accuracy, significantly enhancing the machining performance and quality of CNC machine tools.

[0049] Furthermore, by using the short-term abnormal fluctuation and the long-term error trend, long-term and short-term adaptive error compensation is performed. In the embodiment of the present application, step S300 further includes: Filtering error precursor features based on the short-term abnormal fluctuations and long-term error trends; Based on the error precursor characteristics, a short-term response mechanism and a long-term optimization mechanism are set up; An adaptive multi-layer control strategy is configured through the short-term response mechanism and long-term optimization mechanism.

[0050] Furthermore, by configuring the adaptive multi-layer control strategy through the short-term response mechanism and the long-term optimization mechanism, step S300 in the embodiment of the present application further includes: Setting up an error compensation decision engine through the short-term response mechanism and long-term optimization mechanism; Time series prediction is performed based on the error compensation decision engine and outputted synchronously on a visual interface.

[0051] In a possible embodiment, the error precursor feature is early warning information extracted from data before an error occurs, such as a sudden change, increased fluctuation, or abnormal trend of a specific parameter, which is used to predict an impending error.

[0052] By analyzing short-term abnormal fluctuations and long-term error trends, we extract error precursor features. This is achieved by comparing and analyzing real-time and historical data to identify key parameter changes that could trigger errors, such as sudden increases in spindle load or abnormal fluctuations in cutting force. Based on these precursor features, we then establish short-term response mechanisms and long-term optimization mechanisms.

[0053] The short-term response mechanism makes immediate adjustments to short-term abnormal fluctuations, such as optimizing the cutting path, reducing the spindle speed, or dynamically correcting the tool position to suppress error propagation. The long-term optimization mechanism combines historical data to analyze the trend of error accumulation and gradually reduce the error source through process improvements (such as optimizing feed strategies) or equipment adjustments (such as reconfiguring control parameters).

[0054] Furthermore, by integrating short-term response mechanisms with long-term optimization mechanisms, an adaptive multi-layer control strategy is formed. This strategy dynamically adjusts compensation measures at different time scales to achieve comprehensive error suppression. Furthermore, an error compensation decision engine is configured. Based on error data, precursor characteristics, and time series prediction results, the decision engine intelligently selects and implements the optimal compensation strategy. Simultaneously, error analysis, prediction results, and compensation execution status are displayed through a visual interface, enabling operators to understand the optimization status of machining accuracy in real time and intervene quickly.

[0055] By accurately extracting error precursor features and providing intelligent decision support, error compensation is elevated to a multi-level, adaptive dynamic control level. The combination of short-term response and long-term optimization significantly improves the machining accuracy and stability of CNC machine tools, while the error compensation decision engine and visual output further enhance the system's operability and user experience.

[0056] By verifying and adjusting the error hiding accumulation map, the clarity and controllability of the error propagation path are significantly improved, and the technical effect of effectively reducing the delay of error analysis and compensation is achieved.

[0057] In summary, the intelligent control method for CNC machine tools combined with error analysis provided in the embodiments of the present application has the following technical effects: This application introduces an error hiding pattern analysis model, combines basic equipment data with data from similar equipment, and conducts in-depth analysis of error propagation paths and cumulative effects, generating a dynamically calibrated error hiding cumulative map. Through a feedback mechanism, error compensation parameters are adjusted in real time. By combining short-term abnormal fluctuations with long-term error trends, an adaptive multi-layer control strategy combining short-term response with long-term optimization is constructed, significantly improving machining accuracy and compensation efficiency. The combination of an error compensation decision engine and time series prediction enables dynamic error management during machining, achieving the technical effect of improving the control accuracy of CNC machine tools.

[0058] Example 2, as Figure 2 As shown, it is a schematic diagram of the structure of an exemplary electronic device of the present application. Figure 2 In the present invention, the bus architecture is represented by bus 300, which can include any number of interconnected buses and bridges. Bus 300 connects various circuits, including one or more processors represented by processor 302 and memory represented by memory 304. Bus 300 can also connect various other circuits, such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are not described further herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 can be the same component, namely a transceiver, which provides a unit for communicating with various other devices over a transmission medium.

[0059] The memory 304, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as the program instructions / modules corresponding to the CNC machine tool intelligent control method combined with error analysis in the embodiment of the present application. The processor 302 executes various functional applications and data processing of the computer device by running the software programs, instructions and modules stored in the memory 304, that is, realizes the above-mentioned CNC machine tool intelligent control method combined with error analysis. The various technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0060] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent control method for CNC machine tools combined with error analysis is characterized in that: The method comprises: Connect to the CNC machine tool terminal to obtain basic equipment data, including the power-on time, power-off time, and standby time corresponding to the equipment status data, and the feed rate, spindle speed, spindle rate, and spindle load corresponding to the equipment operation data; Connecting to the machine tool control database, establishing an error hiding pattern analysis model, and setting U error hiding pattern starting points and V error hiding pattern end points, where U and V are integers greater than or equal to 1; Based on the U error concealment mode starting points and the V error concealment mode end points, propagation simulation is performed against the error state transition to simulate an error concealment accumulation graph; The U error concealment mode starting points are configured using the device basic data, and propagation path simulation is performed on the error concealment cumulative map to obtain M error simulation propagation paths, where M is an integer greater than or equal to 1; Based on the M error simulation propagation paths, the error hidden pattern analysis model is used to calculate the cumulative effect of errors at different processing stages, and a sequence of key error sources with decreasing impact on processing accuracy is identified; Based on the M error simulation propagation paths and key error source sequences, an error compensation strategy is set and sent to the CNC machine tool terminal for compensation control.

2. The intelligent control method for CNC machine tools combined with error analysis according to claim 1, characterized in that: Based on the U error concealment mode starting points and the V error concealment mode end points, propagation simulation is performed against error state transition to generate an error concealment accumulation graph, the method comprising: Obtaining basic data of similar equipment of the CNC machine tool terminal; Performing incremental learning based on the basic data of the similar device to set a propagation path check point, wherein the propagation path check point is located on a line connecting a starting point of an error concealment mode and an end point of the error concealment mode; The error concealment accumulation map is verified and adjusted according to the propagation path verification point.

3. The intelligent control method for CNC machine tools combined with error analysis according to claim 2, characterized in that: According to the propagation path check point, the error concealment accumulation map is checked and adjusted, and the method includes: Based on the propagation path check point, setting a check adjustment model, the check adjustment model including a servo control layer and a feedback control layer; Performing performance verification and adjustment using a servo control layer of the verification and adjustment model, the servo control layer including a predicted performance indicator; Error compensation adjustment is performed using a feedback control layer of the verification adjustment model, wherein the feedback control layer includes a prediction accuracy indicator.

4. The intelligent control method for CNC machine tools combined with error analysis according to claim 3, characterized in that: Using the feedback control layer of the verification adjustment model to perform error compensation adjustment, the feedback control layer includes a prediction accuracy indicator, and the method includes: Integrating a feedback mechanism into the calibration and adjustment model allows dynamic adjustment of error compensation parameters based on changes in the actual machining process; Historical data is introduced to analyze the error data accumulated during the processing and dynamically adjust the error compensation strategy.

5. The intelligent control method for CNC machine tools combined with error analysis according to claim 4, characterized in that: Introducing historical data, analyzing error data accumulated during the machining process, and dynamically adjusting the error compensation strategy, the method includes: Set periodic evaluation criteria and add processing quality indicators; Based on the processing quality indicators, extract short-term abnormal fluctuations and long-term error trends; Long-term and short-term adaptive error compensation is performed based on the short-term abnormal fluctuations and long-term error trends.

6. The intelligent control method for CNC machine tools combined with error analysis according to claim 5, characterized in that: By using the short-term abnormal fluctuation and the long-term error trend, long-term and short-term adaptive error compensation is performed, and the method includes: Filtering error precursor features based on the short-term abnormal fluctuations and long-term error trends; Based on the error precursor characteristics, a short-term response mechanism and a long-term optimization mechanism are set up; An adaptive multi-layer control strategy is configured through the short-term response mechanism and long-term optimization mechanism.

7. The intelligent control method for CNC machine tools combined with error analysis according to claim 6, characterized in that: By configuring the short-term response mechanism and the long-term optimization mechanism, an adaptive multi-layer control strategy is configured, and the method includes: Setting up an error compensation decision engine through the short-term response mechanism and long-term optimization mechanism; Time series prediction is performed based on the error compensation decision engine and outputted synchronously on a visual interface.

8. An electronic device, characterized in that: The electronic device comprises: a memory for storing executable instructions; The processor is configured to implement the intelligent control method for a CNC machine tool combined with error analysis according to any one of claims 1 to 7 when executing the executable instructions stored in the memory.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the intelligent control method for a CNC machine tool combined with error analysis as described in any one of claims 1 to 7 is implemented.

Images