Cutter stringing control method, device and equipment for CNC (computer numerical control) machine tool and medium

Abstract

The invention relates to the field of numerical control machine tool control, in particular to a CNC numerical control machine tool tool stringing control method, device and equipment and a medium. The method comprises the following steps: acquiring a numerical control machine tool monitoring image and a processing demand log; marking a plurality of to-be-processed workpieces based on the numerical control machine tool monitoring image; performing section-by-section process demand dependency analysis on the processing demand log based on the plurality of to-be-processed workpieces so as to generate a process demand logic dependency graph; acquiring a real-time state of a numerical control machine tool cutter based on multiple sensors; marking a plurality of machine tool cutter nodes based on the numerical control machine tool monitoring image; performing cutter dynamic operation state evaluation on the real-time state of the numerical control machine tool cutter according to the plurality of machine tool cutter nodes so as to generate cutter dynamic operation state characteristics; and carrying out position positioning calculation on the plurality of machine tool cutter nodes and the plurality of workpieces to be machined, and constructing a real-time twinning model of the numerical control machine tool. According to the invention, efficient and accurate tool stringing control is realized, so that the working operation efficiency of the CNC numerical control machine tool is greatly improved.

Description

Technical Field

[0001] The invention relates to the field of numerical control machine tool control, and in particular to a CNC numerical control machine tool string tool control method, device, equipment and medium. Background Art

[0002] With the rapid development of intelligent manufacturing technology, CNC machine tools play an increasingly important role in modern industrial production. As key processing equipment, the tool stringing control of CNC machine tools directly affects the processing quality and production efficiency. In the CNC processing process, tool stringing is a crucial operation. The purpose of tool stringing is to quickly adjust the new tool to the position and posture that is completely consistent with the previous tool when changing the tool to ensure the continuity and accuracy of the processing. However, during long-term continuous work, the tools on the CNC machine tools will have various abnormal states, such as tool wear, deformation, etc. These factors will have an adverse effect on the tool stringing accuracy and even cause serious processing quality problems.

[0003] However, traditional CNC tool stringing control methods often rely on manual experience, and have problems such as inaccurate analysis and slow response, which leads to a decrease in the operating efficiency of CNC machine tools and makes it difficult to meet increasingly complex processing needs. Once an abnormal situation occurs, it is difficult to detect and respond effectively in time, and it is impossible to ensure the continuous stability of processing quality. Therefore, an intelligent CNC machine tool tool stringing control method is urgently needed to improve the autonomy and robustness of the tool stringing process. Summary of the invention

[0004] In order to solve the above technical problems, the present invention proposes a CNC machine tool string tool control method, device, equipment and medium to solve at least one of the above technical problems.

[0005] To achieve the above object, the present invention provides a CNC machine tool string tool control method, comprising the following steps: Step S1: Acquire a CNC machine tool monitoring image and a processing requirement log; mark a plurality of workpieces to be processed based on the CNC machine tool monitoring image; perform a process requirement dependency analysis on the processing requirement log section by section based on the plurality of workpieces to be processed, thereby generating a process requirement logical dependency graph; Step S2: acquiring the real-time status of the CNC machine tool tool based on multiple sensors; marking multiple machine tool tool nodes based on the CNC machine tool monitoring image; performing a tool dynamic operation status evaluation on the real-time status of the CNC machine tool tool according to the multiple machine tool tool nodes to generate a tool dynamic operation status feature; Step S3: performing position positioning calculations on multiple machine tool tool nodes and multiple workpieces to be processed, and performing three-dimensional point cloud modeling to construct a real-time twin model of the CNC machine tool; Step S4: Predicting the stage process tool wear based on the tool dynamic operation state characteristics based on the process requirement logic dependency graph, and optimizing the tool operation parameters, thereby obtaining a stage tool operation parameter sequence; Step S5: Dynamically plan machining paths for multiple workpieces to be machined, and adjust the sequence of tool stringing to construct an optimized tool stringing machining path; Step S6: Based on the stage tool operation parameter sequence and the optimized path of tool stringing processing, the real-time twin model of the CNC machine tool is iteratively simulated, and then the tool stringing control parameters are fine-tuned to construct an intelligent tool stringing control strategy for the CNC machine tool.

[0006] The present invention also provides a CNC machine tool string tool control device, comprising: The process requirement dependency module obtains the CNC machine tool monitoring image and processing requirement log; marks multiple workpieces to be processed based on the CNC machine tool monitoring image; performs process requirement dependency analysis on the processing requirement log section by section based on multiple workpieces to be processed, thereby generating a process requirement logical dependency graph; The tool operation status module obtains the real-time status of CNC machine tool tools based on multiple sensors; marks multiple machine tool tool nodes based on the CNC machine tool monitoring image; and evaluates the dynamic operation status of the CNC machine tool tools based on the real-time status of the multiple machine tool tool nodes to generate the dynamic operation status characteristics of the tools; The twin model module calculates the position of multiple machine tool nodes and multiple workpieces to be processed, performs three-dimensional point cloud modeling, and constructs a real-time twin model of the CNC machine tool; The tool operation optimization module predicts the stage process tool wear based on the tool dynamic operation state characteristics based on the process requirement logic dependency graph, and optimizes the tool operation parameters to obtain the stage tool operation parameter sequence; The processing path planning module dynamically plans the processing paths for multiple workpieces to be processed and adjusts the sequence of tool stringing to construct an optimized path for tool stringing processing; The parameter fine-tuning module performs iterative processing simulation on the real-time twin model of the CNC machine tool based on the stage tool operation parameter sequence and the optimized path of the tool string processing, and then fine-tunes the tool string control parameters to build an intelligent tool string control strategy for the CNC machine tool.

[0007] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the CNC machine tool string tool control method described in any one of the above items are implemented.

[0008] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned CNC machine tool string tool control methods are implemented.

[0009] The beneficial effects of the present invention are specifically as follows: by marking the workpieces to be processed, the identification and positioning of multiple workpieces in the machine tool monitoring image are realized, the process requirement dependency is analyzed section by section, and a process requirement logical dependency graph is generated, which is helpful to clarify the processing flow and optimize the process design, and the real-time status of the tool is obtained through multiple sensors to ensure that the tool is in the best operating state, the dynamic operating state of the tool is evaluated, and the dynamic operating state characteristics of the tool are generated to improve the processing accuracy and efficiency, and a real-time twin model of a CNC machine tool is constructed through position positioning calculation and three-dimensional point cloud modeling to provide an accurate real-time model for subsequent processing, and a real-time twin model of a CNC machine tool is constructed to provide an accurate real-time simulation environment for subsequent processing, and processing accuracy and stability are improved through three-dimensional point cloud modeling and position positioning calculation, and tool wear prediction and operation parameter optimization of the stage process are used to extend the tool life and reduce production costs, and a sequence of stage tool operation parameters is obtained to improve processing efficiency and product quality, and through iterative processing simulation and string tool control parameter fine-tuning, the processing process is optimized to improve production efficiency and product quality, and an intelligent string tool control strategy for CNC machine tools is constructed to improve processing stability and automation level. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic diagram of the steps of a CNC machine tool stringing control method of the present invention; Figure 2 Detailed implementation flow chart of step S1; Figure 3 Detailed implementation flow chart of step S2; Figure 4 Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0011] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0012] The present application example provides a CNC machine tool stringing control method, device, equipment and medium. The execution subjects of the CNC machine tool stringing control method, device, equipment and medium include but are not limited to the following: mechanical equipment, data processing platform, cloud server node, network upload equipment, etc. equipped with the system can be regarded as the general computing node of the present application, and the data processing platform includes but is not limited to: at least one of an audio image management system, an information management system, and a cloud data management system.

[0013] See also Figures 1 to 4 The present invention provides a CNC machine tool stringing control method, the CNC machine tool stringing control method comprising the following steps: Step S1: Acquire a CNC machine tool monitoring image and a processing requirement log; mark a plurality of workpieces to be processed based on the CNC machine tool monitoring image; perform a process requirement dependency analysis on the processing requirement log section by section based on the plurality of workpieces to be processed, thereby generating a process requirement logical dependency graph; Step S2: acquiring the real-time status of the CNC machine tool tool based on multiple sensors; marking multiple machine tool tool nodes based on the CNC machine tool monitoring image; performing a tool dynamic operation status evaluation on the real-time status of the CNC machine tool tool according to the multiple machine tool tool nodes to generate a tool dynamic operation status feature; Step S3: performing position positioning calculations on multiple machine tool tool nodes and multiple workpieces to be processed, and performing three-dimensional point cloud modeling to construct a real-time twin model of the CNC machine tool; Step S4: Predicting the stage process tool wear based on the tool dynamic operation state characteristics based on the process requirement logic dependency graph, and optimizing the tool operation parameters, thereby obtaining a stage tool operation parameter sequence; Step S5: Dynamically plan machining paths for multiple workpieces to be machined, and adjust the sequence of tool stringing to construct an optimized tool stringing machining path; Step S6: Based on the stage tool operation parameter sequence and the optimized path of tool stringing processing, the real-time twin model of the CNC machine tool is iteratively simulated, and then the tool stringing control parameters are fine-tuned to construct an intelligent tool stringing control strategy for the CNC machine tool.

[0014] By marking the workpieces to be processed, the identification and positioning of multiple workpieces in the machine tool monitoring image can be achieved, the process requirement dependency can be analyzed section by section, and a process requirement logical dependency diagram can be generated, which is helpful to clarify the processing flow and optimize the process design. The real-time status of the tool can be obtained through multiple sensors to ensure that the tool is in the best operating state. The dynamic operating state of the tool is evaluated, and the dynamic operating state characteristics of the tool are generated to improve the processing accuracy and efficiency. Through position positioning calculation and three-dimensional point cloud modeling, a real-time twin model of the CNC machine tool is constructed to provide an accurate real-time model for subsequent processing. A real-time twin model of the CNC machine tool is constructed to provide an accurate real-time simulation environment for subsequent processing. Through three-dimensional point cloud modeling and position positioning calculation, the processing accuracy and stability are improved. Through stage process tool wear prediction and operation parameter optimization, the tool life is extended and the production cost is reduced. The stage tool operation parameter sequence is obtained to improve the processing efficiency and product quality. Through iterative processing simulation and string tool control parameter fine-tuning, the processing process is optimized to improve production efficiency and product quality. An intelligent string tool control strategy for CNC machine tools is constructed to improve processing stability and automation level.

[0015] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of a CNC machine tool stringing control method of the present invention. In this example, the steps of the CNC machine tool stringing control method include: Step S1: Acquire a CNC machine tool monitoring image and a processing requirement log; mark a plurality of workpieces to be processed based on the CNC machine tool monitoring image; perform a process requirement dependency analysis on the processing requirement log section by section based on the plurality of workpieces to be processed, thereby generating a process requirement logical dependency graph; In this embodiment, a high-resolution camera or video monitoring equipment is installed to ensure that the image in the working area of ​​the machine tool can be clearly captured, and the shooting frequency of the camera is set, for example, one frame of image is taken per second, so as to obtain real-time monitoring, and the monitoring system is started to automatically collect monitoring images of the CNC machine tool to ensure that the image contains the full picture of all workpieces to be processed to avoid information loss due to angle problems. The collected images are stored in a local database or cloud storage to form a data table called "monitoring image data" for subsequent processing. The processing requirement log is accessed through the control system of the CNC machine tool to ensure that all relevant processing task information can be obtained. The log should contain the processing sequence of the workpiece, the required process parameters (such as cutting speed, feed rate), etc., extract the relevant information in the processing requirement log, and record it. The processing requirements of each workpiece are formed into a data table called "processing requirement log". Use image annotation tools (such as LabelImg or VGGImageAnnotator) to mark the workpieces, manually or automatically mark the position of the workpiece to be processed on the monitoring image, record the bounding box and category of each workpiece, ensure that the marking is accurate and can reflect the actual shape and position of the workpiece, and analyze the process requirements of each workpiece according to the marked workpieces to be processed and the processing requirement log, determine their dependencies, identify the sequence and mutual dependencies between different processes, adopt the dependency construction method in graph theory, and use algorithms (such as topological sorting) to parse the process requirements. For example, compare the processing requirements of workpiece 1 with those of workpiece 2 to generate dependencies.

[0016] Step S2: acquiring the real-time status of the CNC machine tool tool based on multiple sensors; marking multiple machine tool tool nodes based on the CNC machine tool monitoring image; and evaluating the dynamic operation status of the CNC machine tool tool based on the multiple machine tool tool nodes to generate a dynamic operation status feature of the tool; In this embodiment, a variety of sensors are installed on the CNC machine tool tool, such as vibration sensors, temperature sensors, cutting force sensors and accelerometers. These sensors can monitor the operating status of the tool in real time. Configure a data acquisition system (such as NIDAQ or Arduino) to ensure that data from each sensor can be obtained in real time. Start the data acquisition system to collect the status data of the tool in real time, including vibration frequency, temperature, cutting force and acceleration. Set the data acquisition frequency (such as 10 times per second). Use a high-definition camera installed on the machine tool to capture a real-time image of the tool to ensure that the image quality and angle are suitable for subsequent analysis. Select a suitable image processing tool (such as OpenCV, TensorFlow) for the identification and marking of tool nodes. Use a deep learning algorithm (such as YOLO or SSD) to identify the tool in the image, generate bounding boxes of multiple tool nodes, and record their position coordinates. Save the marking result as structured data in a format such as: {"Tool number":"Tool 1","Coordinate":{"x_min":100,"y_min":150,"x_max":300,"y_max":400}}. Establish a tool dynamic operation state evaluation model, combining sensor data and tool node information. The model uses machine learning algorithms (such as random forests and support vector machines) to evaluate tool status. Integrate the tool real-time status data obtained in step 1 with the tool node data marked in step 2 to generate a feature vector containing all tool states. Input the evaluation model based on the integrated data to calculate the dynamic operation state characteristics of each tool (such as cutting state, wear degree, thermal state, etc.). Record the evaluation results as tool dynamic operation state characteristics, in the format of {"Tool number":"Tool 1","State characteristics":{"Cutting state":"Normal","Wear degree":"Mild"}}.

[0017] Step S3: performing position positioning calculations on multiple machine tool tool nodes and multiple workpieces to be processed, and performing three-dimensional point cloud modeling to construct a real-time twin model of the CNC machine tool; In this embodiment, a laser rangefinder, a depth camera or a stereo vision camera is installed on the machine tool to ensure all-round monitoring of the tool and the workpiece, ensure that the sensor's field of view covers all key components of the machine tool, start the sensor to collect real-time data of the machine tool tool and the workpiece, record the two-dimensional or three-dimensional coordinates of each node, use the corresponding algorithm (such as a stereo vision algorithm) to calculate the point cloud data, convert it into three-dimensional coordinates, perform coordinate transformation on the collected data, use a three-dimensional coordinate system (such as a world coordinate system) for position positioning, determine the position coordinates of each tool node and the workpiece to be processed, and record them in a database to form a data table called "tool and workpiece position data", process the collected three-dimensional coordinate data, remove noise and redundant data, ensure the accuracy of the point cloud data, use a filtering algorithm (such as a statistical noise filter) to remove outliers, and use point cloud processing The processing software (such as PCL (PointCloudLibrary) or MeshLab) constructs the processed data into a three-dimensional point cloud model to ensure that the point cloud model can accurately represent the shape and relative position of the tool and workpiece, and optimizes the three-dimensional point cloud model, for example, by reconstructing the surface and simplifying the point cloud to improve the efficiency of subsequent processing, centralize and normalize the point cloud to make the model consistent in different environments, integrate the processed point cloud model with the real-time status data of the tool (such as speed, temperature, etc.) to form a complete real-time twin model, and use modeling software (such as Unity or Blender) for visualization to ensure that the model is intuitive and easy to understand, establish a dynamic update mechanism to ensure that the real-time twin model can be automatically updated according to new sensor data, and design a data flow mechanism so that changes in tool status can be reflected in the model in real time.

[0018] Step S4: Predicting the stage process tool wear based on the tool dynamic operation state characteristics based on the process requirement logic dependency graph, and optimizing the tool operation parameters, thereby obtaining a stage tool operation parameter sequence; In this embodiment, the process requirement logic dependency graph is analyzed, each process stage and its influencing factors on tool wear are identified, and the key parameters of each process stage, such as cutting speed, feed rate, cutting depth, etc., are determined. The dynamic operation state characteristic data of the tool (such as cutting force, temperature, vibration, etc.) are collected to provide basic data for wear prediction. The state characteristics are combined with the process parameters to form a data set containing wear influencing factors. A tool wear prediction model is established using a machine learning algorithm (such as linear regression, random forest or neural network). The model is trained using historical data so that it can predict the tool wear amount based on the dynamic state characteristics and process parameters. The trained model predicts the tool wear at each stage and records the expected wear amount at each stage. Based on the wear prediction data, the goal of optimizing the tool operating parameters is set, such as minimizing wear and maximizing cutting efficiency. The parameters that need to be optimized, such as cutting speed, feed rate, cutting depth, etc., are determined. A suitable optimization algorithm, such as genetic algorithm, particle swarm optimization (PSO) or simulated annealing algorithm, is selected to ensure that the best parameter combination can be effectively found. The wear prediction results are used as the input of the optimization algorithm to perform parameter optimization calculations. During the optimization process, the algorithm will continuously adjust the cutting parameters of the tool and evaluate the effect of each combination until the best parameters are found.

[0019] Step S5: Dynamically plan machining paths for multiple workpieces to be machined, and adjust the sequence of tool stringing to construct an optimized tool stringing machining path; In this embodiment, an appropriate path planning algorithm is selected, such as the A* algorithm, the Dijkstra algorithm, or the RRT (rapidly expanding random tree) algorithm, and the optimal path is determined according to the shape of the workpiece and the characteristics of the machine tool. The position information, geometric shape, size, processing requirements and other data of the workpiece to be processed are collected, and the dynamic operation state characteristics and wear prediction results of the tool are sorted out to optimize the path planning. The processing path of each workpiece is calculated by the algorithm. The path should consider the following factors: the range and limitation of the tool, the cutting parameters of the tool (such as speed and feed rate), avoid collision with other workpieces or machine tool parts, optimize the generated path, ensure the path is smooth, reduce the tool movement time and the number of tool changes, so that Use path smoothing algorithms (such as Bezier curves) for post-processing to ensure the feasibility of the path, analyze the generated processing paths, record the tool types and usage order required for each workpiece, identify the mutual influence between tools, such as tool wear and cutting conditions, and develop optimization strategies, considering the following factors: tool wear prediction results, give priority to tools with less wear, logical order of processing paths, reduce the time the tool moves between workpieces, minimize the frequency of tool changes, and improve processing efficiency. Apply algorithms (such as greedy algorithms or genetic algorithms) to adjust the tool stringing sequence to find the optimal tool stringing sequence. After each adjustment, re-evaluate the feasibility of the path and the efficiency of tool use.

[0020] Step S6: Based on the stage tool operation parameter sequence and the optimized path of tool stringing processing, the real-time twin model of the CNC machine tool is iteratively simulated, and then the tool stringing control parameters are fine-tuned to construct an intelligent tool stringing control strategy for the CNC machine tool.

[0021] In this embodiment, it is ensured that the real-time twin model has been correctly constructed, including all machine tool components, tools and their status data, the tool operation parameter sequence and the optimized path of string tool processing in the import stage are imported to ensure that the model can reflect the actual processing requirements, and the parameters of the simulation environment, such as cutting speed, feed rate, cutting depth, etc., are configured to ensure that they are consistent with the tool operation parameters, and the physical properties in the processing process, such as material properties, cutting force model, etc., are set to increase the realism of the simulation, start the iterative processing simulation, monitor the tool status, processing effect and machine tool response in real time, collect simulation result data, including tool wear, processing accuracy, processing time and other information, compare the simulation results with the preset goals, identify deviations and deficiencies in tool operation, analyze the impact of various parameters on the processing effect, determine the parameters that need to be fine-tuned, and formulate specific fine-tuning strategies based on the simulation results, such as: increase or decrease the cutting speed, adjust the feed rate, optimize the tool change frequency rate, use optimization algorithms (such as gradient descent or Newton's method) to fine-tune the control parameters, calculate the best parameter combination, perform multiple iterations, until the optimal string tool control parameters are found, and record the fine-tuned string tool control parameters in the database to form a data table called "string tool control parameter fine-tuning results". Based on the fine-tuned parameters, design an intelligent string tool control strategy to ensure the collaborative work of the tools during the machining process, the order of tool use, the dynamic adjustment of cutting parameters, and the tool wear monitoring and feedback mechanism. Develop an intelligent control system that integrates tool status monitoring, parameter adjustment, and control logic to ensure that the system can respond to changes in machining requirements in real time. Use programming languages ​​(such as Python or C++) to implement control logic to ensure the stability and efficiency of the system. Test the effectiveness of the control strategy in an actual machining environment to verify its performance in improving machining accuracy and efficiency. Make necessary adjustments and optimizations based on the test results.

[0022] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include: Step S11: Acquire CNC machine tool monitoring images and processing demand logs; Step S12: performing visual recognition of the target to be processed on the CNC machine tool monitoring image, and marking a plurality of workpieces to be processed; Step S13: extracting processing requirement instructions from the processing requirement log based on the multiple workpieces to be processed, thereby obtaining real-time processing requirement instruction data; Step S14: performing multi-stage process analysis on the real-time processing demand instruction data to obtain a multi-stage processing process sequence; Step S15: performing process requirement dependency analysis on the multi-stage processing sequence stage by stage, thereby generating a process requirement logic dependency graph; The process requirement dependency analysis of the multi-stage processing sequence is performed stage by stage to generate a process requirement logic dependency graph as follows: Extract all machining process stages based on multi-stage machining process sequence; Sequentially encode all the processing technology stages to obtain process stage codes; Calculate the cutting depth and force of all the processing technology stages to obtain the cutting requirement parameters of each processing technology stage; Conduct process timing logic analysis on multi-stage processing sequences to obtain process logic data; Perform process dependency fitting on process logic data based on process stage coding to construct a process logic dependency graph; According to the cutting requirement parameters of each processing stage, the process logic dependency graph is mined between stages to construct a process requirement logic dependency graph.

[0023] In this embodiment, a camera installed on a CNC machine tool is used to capture the working status of the machine tool in real time to obtain a monitoring image. At the same time, the processing requirement log is collected through the machine tool control system interface, including information such as workpiece type, processing parameters, and timestamps. The acquired image and log data are stored in a local database or cloud storage for subsequent processing. Image processing techniques (such as denoising and contrast enhancement) are used to improve image quality. A deep learning model (such as a convolutional neural network CNN) is used to perform target detection on the processed image to identify the workpiece to be processed. A marking tool is used to mark each identified workpiece in the image for subsequent analysis. The identified workpieces (such as "workpiece A" and "workpiece B") are matched with the processing requirement log and associated according to the timestamp. The instructions related to workpiece A are extracted to obtain the processing requirements (such as "tool type: T1" and "processing time: 15 minutes"). Workpiece A: Tool T1, cutting speed 120m / min, feed rate 0.2mm / rev, Workpiece B: Tool T2, cutting speed 100m / min, feed rate 0.15mm / rev, set a multi-stage process analysis model to analyze the processing order of the workpieces (such as workpiece A is processed first, then workpiece B). Use Python's Pandas library to load real-time instruction data and analyze the processing time and tool usage of each workpiece. Step 1: Workpiece A, tool T1, processing time 15 minutes, Step 2: Workpiece B, tool T2, processing time 20 minutes, set dependencies, for example, the processing of workpiece B depends on the completion of workpiece A. Analyze step by step to identify process dependencies (such as "workpiece B" must be carried out after the processing of "workpiece A" is completed). Use Graphviz to visualize the process requirement logical dependency graph, showing the dependency relationship between workpieces A and B, and mark the workpiece status in the graph (such as "to be processed", "in process", "completed").

[0024] The detailed implementation steps of performing process requirement dependency analysis on a multi-stage processing sequence stage by stage to generate a process requirement logic dependency graph are as follows: Use regular expressions or parsing algorithms to extract key information of each processing step from the process sequence (such as "roughing", "finishing", etc.). Record the name and parameters of each processing stage (such as processing time, tool type). Define unique coding rules for each processing stage (such as "P1", "P2"). Code the extracted processing technology stages in sequence to generate a coding list (such as "roughing" is coded as P1, "finishing" is coded as P2). Define calculation formulas for cutting depth and force (such as using cutting speed, feed rate and material properties). Obtain relevant parameters from the processing requirement instructions (such as cutting speed, feed rate, material hardness). Apply the calculation formula to each process stage to obtain the cutting depth and force: for example, the cutting depth of the roughing stage is 5mm and the force is 200N. Store the calculation results (cutting depth, force) in the database and associate them with the stage code. Design a process timing model to describe the time relationship between each process stage (such as the next stage can only start after the previous stage is completed). Use graph theory or state machine models to analyze the timing logic of the process stages and determine the dependencies. Identify the process logic data (e.g., "P1→P2" means that P2 starts after P1 is completed). Record the analysis results as process logic data to form a graph structure. Use graph algorithms (e.g., DAG) to fit the process logic data and construct a process logic dependency graph. Identify the dependencies between the various process stages. Use a graph library (e.g., Graphviz) to visualize the dependencies and display the logical structure of the process stages. Integrate the cutting depth and force of each process stage into the process logic dependency graph as node attributes. Analyze the demand relationship between the stages and identify which process stages have interdependent cutting requirements. For example, if the cutting depth of P1 affects the cutting force of P2, establish the corresponding dependency relationship. Generate a process demand logic dependency graph based on the dependency relationship to display the cutting requirements of each process stage and their mutual influence.

[0025] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include: Step S21: Acquire the real-time status of CNC machine tool tools based on multiple sensors; Step S22: performing multi-tool image recognition on the CNC machine tool monitoring image and marking multiple machine tool tool nodes; Step S23: performing tool region image segmentation based on multiple machine tool tool nodes to obtain a tool boundary box image; Step S24: Analyze the current cutting state of the CNC machine tool tool in real time to extract the current cutting state of the tool; Step S25: performing real-time posture recognition on the tool boundary frame image according to the current cutting state of the tool to obtain the real-time posture parameters of each tool; Step S26: Evaluate the dynamic operation state of the tool based on the real-time posture parameters of each tool in the current cutting state of the tool to generate a dynamic operation state feature of the tool.

[0026] In this embodiment, a variety of sensors are installed on the CNC machine tool, including vibration sensors, temperature sensors, and pressure sensors, to monitor the status of the tool in real time. The sensors collect real-time data of the tool, such as vibration frequency, temperature change, and cutting force. The data collection frequency is set (e.g., 10 times per second). The collected real-time status data is stored in a local or cloud database through a data acquisition system (e.g., NIDAQ) for subsequent analysis. A high-definition camera (e.g., 1080p) installed on the machine tool is used to capture a real-time image of the tool. The image is preprocessed (e.g., denoising, contrast enhancement) to improve the accuracy of tool recognition. A deep learning model (e.g., YOLO or SSD) is used to perform multi-tool recognition on the image, and tool nodes are marked. A confidence threshold (e.g., 0.75) is set, and only recognition results above the threshold are retained. A semantic segmentation algorithm (e.g., U-Net) is used to perform image segmentation on the tool area, and the feature area of ​​each tool is extracted. Based on the segmentation result, the bounding box of each tool is calculated, and its coordinate information (upper left corner and lower right corner coordinates) is recorded to generate the tool's The bounding box image highlights the position of each tool for subsequent analysis. The current cutting state of the tool is defined, including normal cutting, cutting wear, cutting overheating, etc. According to the real-time sensor data collected, the vibration, temperature and pressure data of the tool are analyzed to determine the current cutting state. A threshold is set (such as temperature exceeding 150°C is determined as overheating). The real-time data is judged and the analysis results are recorded as the current cutting state, such as "normal cutting" or "cutting wear". The bounding box image of the tool is analyzed using a posture recognition algorithm (such as OpenPose or a posture estimation network). Combined with the current cutting state, the real-time posture of each tool is identified and posture parameters (such as tool inclination angle and rotation angle) are extracted. The identification results are combined with the bounding box information of the tool to generate a list of real-time posture parameters of the tool. A dynamic evaluation model is constructed to evaluate the dynamic operation state of the tool by combining the posture parameters with the cutting state. The operation characteristics of the tool, such as cutting efficiency and tool wear rate, are calculated. A dynamic operation state characteristic report of the tool is generated, including the status evaluation results of each tool, for subsequent decision-making and maintenance.

[0027] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include: Step S31: performing position positioning calculation on multiple machine tool tool nodes to obtain the spatial position coordinates of each machine tool tool; Step S32: performing three-dimensional surface contour analysis on a plurality of workpieces to be processed, and extracting three-dimensional contour lines of the workpieces; Step S33: performing morphological structure recognition on the three-dimensional contour line of the workpiece to generate morphological structure data of the workpiece; Step S34: performing a machine tool area spatial distribution analysis on a plurality of workpieces to be processed, thereby obtaining distribution data within a plurality of workpiece areas; Step S35: performing three-dimensional point cloud modeling on the workpiece morphological structure data according to the distribution data in the multiple workpiece regions, and constructing a machine tool workpiece distribution model; Step S36: Based on the spatial position coordinates of each machine tool tool, the machine tool workpiece distribution model is rendered in real time to construct a real-time twin model of the CNC machine tool.

[0028] In this embodiment, according to the coordinate system of the machine tool, the image coordinates of the tool node are converted into actual spatial coordinates, and the spatial position coordinates (such as X, Y, Z) of each machine tool tool are calculated using perspective transformation or camera calibration method, and recorded in a list, and the calculated tool spatial position coordinates are saved in a database in the form of: {"tool number": "tool 1", "coordinates": (X1, Y1, Z1)}, and each workpiece to be processed is scanned using a 3D scanner to obtain its surface point cloud data, and the scanning accuracy is set, for example, the resolution is 0.1mm, and the scanned point cloud data is processed, including denoising and filling in missing points. The data is collected by the image processing unit, and the multiple scan data are merged using a registration algorithm (such as the ICP algorithm) to obtain a complete 3D model. The 3D contour of the workpiece is extracted using an edge detection algorithm, such as the Canny edge detection. The extracted contour is saved in a visual format (such as STL or OBJ). The extracted 3D contour is analyzed to identify the geometric features of the workpiece, such as edges, faces, corners, etc. The feature extraction algorithm (such as the Hough transform) is used to identify specific morphological features. Based on the identified features, the workpiece is classified into different morphological structures, such as "cylindrical", "cubic", etc. The parameters of each morphological structure (such as radius, side length) are analyzed. Line records are made. The workpieces are divided into different spatial areas according to the working area of ​​the machine tool, such as the left area, the right area and the central area. The number and distribution of the workpieces to be processed in each area are counted, and the coordinate information of each workpiece in the area is recorded. There are 3 workpieces in the left area and 5 workpieces in the right area. The density and distribution characteristics of the workpieces in each area are calculated using statistical analysis methods, and a regional distribution map is generated to intuitively display the spatial distribution of the workpieces. According to the regional distribution data, a corresponding three-dimensional point cloud model is created, and point cloud processing software (such as CloudCompare) is used to convert the workpiece data in each area into a three-dimensional point cloud. The generated point cloud model is optimized, including removing redundant points and filling holes to improve the integrity and accuracy of the model. A real-time rendering system is set up to integrate the tool position data with the workpiece distribution model. A suitable rendering engine (such as Unity or UnrealEngine) is selected for real-time visualization. The acquired tool space position coordinates (for example, the position of tool 1 is (150, 200, 300)) are applied to the rendering system to dynamically display the position of the tool on the workpiece, realize the real-time monitoring interface, update the status of the tool and workpiece in real time, display the processing process, and adjust the tool position and status through sensor feedback to ensure real-time performance.

[0029] In this embodiment, step S4 includes the following steps: Step S41: Decomposing the process requirement logic dependency graph into multi-stage task requirements and extracting task requirement parameters of multiple stages; Step S42: Calculate the stage processing accuracy on the process requirement logic dependency graph, and extract the processing accuracy correlation data of multiple stages; Step S43: performing a stage tool cutting parameter prediction calculation on the tool dynamic operation state characteristics based on the task requirement parameters of multiple stages and the processing accuracy associated data of multiple stages, and extracting the cutting parameter prediction data of each stage; Step S44: performing a stage process tool wear prediction on the tool dynamic operation state characteristics based on the cutting parameter prediction data of each stage, and obtaining tool wear prediction data of each stage; Step S45: Optimize the tool operation parameters of each stage according to the tool wear prediction data of each stage, so as to obtain a sequence of tool operation parameters of each stage.

[0030] In this embodiment, according to the process dependency, the tasks of each stage are decomposed into specific demand parameters (such as material requirements, time requirements, tool requirements), and the tasks of each stage are recorded in a tree structure or table form to ensure clarity and readability. The machining accuracy calculation formula is defined, and factors such as tool wear, material properties and machining technology (for example, cutting speed, feed rate) are considered. The relevant parameters of each stage (such as cutting depth, tool material, workpiece material) are collected and input into the accuracy calculation model, the machining accuracy of each stage is calculated, and the stage machining accuracy associated data is generated and recorded as the accuracy value of each stage (such as "P1 accuracy: ±0.01mm"). A cutting parameter prediction model is established. Combined with the task demand parameters and machining accuracy associated data of the stage, a machine learning algorithm (such as linear regression or random forest) is used to integrate the extracted task requirements and accuracy data as input features, and the prediction model is run to predict the cutting parameters (such as cutting speed, feed rate) of each stage to obtain the cutting parameter prediction data. The cutting parameter prediction results of each segment are used to form structured data (for example, "P1 cutting speed prediction: 120m / min"), and a tool wear prediction model is constructed. Based on the cutting parameter prediction data, wear factors (such as material properties and cutting conditions) are considered. The historical tool wear data is used for model training, and a relational model for tool wear prediction is established. According to the cutting parameter prediction of each stage, wear prediction calculations are performed to obtain wear prediction data for each stage (such as "P1 wear prediction: 0.02mm"). The tool operating parameters are optimized using an optimization algorithm (such as a genetic algorithm or a particle swarm optimization) to ensure that the tool service life is extended while maintaining machining accuracy. The optimal tool operating parameters (such as the optimal cutting speed and feed rate) are calculated based on the wear prediction data to generate the final tool operating parameter sequence. The tool operating parameters are optimized using an optimization algorithm (such as a genetic algorithm or a particle swarm optimization). The current cutting parameters and wear predictions are input to calculate the optimal tool operating parameters (such as cutting speed and feed rate).

[0031] In this embodiment, the specific steps of step S5 are: Step S51: positioning a plurality of workpieces to be processed by a machine tool to obtain position coordinates of the workpieces to be processed; Step S52: dynamically planning a machining path for the position coordinates of the workpiece to be machined based on the spatial position coordinates of each machine tool tool, thereby obtaining a plurality of workpiece machining paths; Step S53: performing multi-tool collaborative construction analysis based on tool dynamic operation state characteristics to obtain tool collaborative construction rules; Step S54: adjusting the cutter stringing sequence according to the cutter collaborative construction rule to generate a multi-cutter stringing adjustment parameter; Step S55: performing intelligent tool stringing optimization on multiple workpiece processing paths according to the multi-tool tool stringing adjustment parameters to construct a tool stringing optimization path.

[0032] In this embodiment, a laser rangefinder or a 3D scanner is used to scan the workpiece to be processed to obtain its position data. The acquired workpiece position data is converted into coordinates (X, Y, Z) in the machine tool coordinate system to ensure consistency with the working coordinate system of the machine tool. The spatial position coordinates of each workpiece to be processed are stored in the form of structured data (for example: {"workpiece number": "workpiece 1", "coordinates": (X1, Y1, Z1)}). Select a suitable path planning algorithm (such as A* algorithm or Dijkstra algorithm) to calculate the optimal path of the tool from the current position to the workpiece position. According to the spatial position coordinates of the tool and the position coordinates of the workpiece to be processed, the processing paths of multiple workpieces are dynamically calculated. Considerations include the range of motion of the tool, the speed limit and the processing order of the workpiece. The calculated processing path is stored in the form of coordinate points, for example: {"workpiece number": "workpiece 1", "path": [(X_start, Y_start, Z_start), (X_end, Y_end, Z_end)]}. The dynamic operation state characteristics of the tool are collected, including cutting speed, feed rate, tool wear state, etc. Construct a collaborative construction analysis model to analyze the working status of multiple tools in the same time period and their mutual influence. Extract the collaborative construction rules between tools through data analysis (such as cluster analysis or association rule mining), such as "the cutting speed of tool A and tool B should be maintained in the same range during rough machining". Use scheduling algorithms (such as priority scheduling or genetic algorithms) to optimize the tool stringing sequence to ensure that the conflicts and switching time between tools are minimized during the machining process. Record the adjusted tool stringing sequence and corresponding parameters, for example: {"stringing sequence": ["tool A", "tool B", "tool C"]}. Store the generated multi-tool stringing adjustment parameters for subsequent use. Design an intelligent stringing processing optimization model, combining the processing path generated in step S52 and the stringing adjustment parameters in step S54. Apply optimization algorithms (such as simulated annealing or particle swarm optimization) to optimize the processing paths of multiple workpieces to ensure processing efficiency and quality. Update the processing path according to the optimization results, generate the final stringing optimization path, and record the new path information of each workpiece. Save the optimized machining path in a structured format, for example: {"Workpiece number":"Workpiece 1","Optimized path":[(X_start, Y_start, Z_start), (X_end, Y_end, Z_end)]}.

[0033] In this embodiment, the specific steps of step S6 are: Step S61: performing iterative machining simulation on the real-time twin model of the CNC machine tool based on the stage tool operation parameter sequence and the tool string machining optimization path, and collecting the machine tool machining simulation response data; Step S62: performing workpiece machining path deviation identification on the machine tool machining simulation response data, and extracting machining path deviation data; Step S63: Calculate the stage processing accuracy error of the machine tool processing simulation response data based on the real-time processing demand instruction data, and extract the processing accuracy error of each stage; Step S64: fine-tuning the cutter control parameters based on the machining accuracy error and machining path deviation data of each stage to generate the optimal cutter control parameters; Step S65: Based on the optimal tool stringing control parameters, the CNC machine tool is collaboratively controlled and optimized to construct an intelligent tool stringing control strategy for the CNC machine tool.

[0034] In this embodiment, a real-time twin model is created using CNC machine tool simulation software (such as Mastercam and Fusion360), a sequence of stage tool operation parameters and a string tool processing optimization path are input, an iterative processing simulation is run, the tool is simulated to process on a given path, and the machine tool status (such as tool position, cutting force, temperature, etc.) during the simulation is recorded. During the processing simulation, the machine tool processing simulation response data is collected in real time to form a data set (such as "tool position change", "cutting force change"), a path deviation recognition algorithm is designed, the difference between the actual tool path and the expected processing path is compared, the actual tool position recorded in the simulation response data is compared with the optimized path, the path deviation (such as "actual position - expected position") is calculated, the processing path deviation data is extracted and recorded, and structured data (such as "workpiece number", "deviation value") is formed, and real-time processing demand instruction data is collected, including the target processing accuracy of each stage (such as "target size: 10mm"), and an accuracy error calculation model is established. The error calculation is based on the processing requirements and the actual processing results. Error (such as "actual size - target size"), calculate the error for each stage, extract the machining accuracy error of each stage (such as "P1 accuracy error: ±0.02mm"), design a fine-tuning model for string tool control parameters, consider the impact of machining accuracy error and machining path deviation on tool performance, calculate the string tool control parameters that need to be adjusted according to the deviation data (such as "cutting speed", "feed rate"), use optimization algorithms (such as gradient descent method), and generate optimal string tool control parameters based on the fine-tuning results, for example: {"cutting speed": 120m / min, "feed rate": 0.1mm / rev}, develop a collaborative control strategy based on the optimal string tool control parameters to ensure that multiple tools can collaborate efficiently, integrate the optimized control parameters into the control system of the CNC machine tool, use PLC or NC code to achieve automated control, monitor the tool status in real time during the machining process, and make dynamic adjustments when necessary to ensure machining accuracy and efficiency, record the optimized collaborative control strategy and implementation effect, and evaluate its impact on machining quality and efficiency.

[0035] In this embodiment, the present invention further provides a CNC machine tool string tool control device, comprising: The process requirement dependency module obtains the CNC machine tool monitoring image and processing requirement log; marks multiple workpieces to be processed based on the CNC machine tool monitoring image; performs process requirement dependency analysis on the processing requirement log section by section based on multiple workpieces to be processed, thereby generating a process requirement logical dependency graph; The tool operation status module obtains the real-time status of CNC machine tool tools based on multiple sensors; marks multiple machine tool tool nodes based on the CNC machine tool monitoring image; and evaluates the dynamic operation status of the CNC machine tool tools based on the real-time status of the multiple machine tool tool nodes to generate the dynamic operation status characteristics of the tools; The twin model module calculates the position of multiple machine tool nodes and multiple workpieces to be processed, performs three-dimensional point cloud modeling, and constructs a real-time twin model of the CNC machine tool; The tool operation optimization module predicts the stage process tool wear based on the tool dynamic operation state characteristics based on the process requirement logic dependency graph, and optimizes the tool operation parameters to obtain the stage tool operation parameter sequence; The processing path planning module dynamically plans the processing paths for multiple workpieces to be processed and adjusts the sequence of tool stringing to construct an optimized path for tool stringing processing; The parameter fine-tuning module performs iterative processing simulation on the real-time twin model of the CNC machine tool based on the stage tool operation parameter sequence and the optimized path of the tool string processing, and then fine-tunes the tool string control parameters to build an intelligent tool string control strategy for the CNC machine tool.

[0036] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, any of the above-mentioned CNC machine tool string tool control methods is implemented.

[0037] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the CNC machine tool string tool control method described in any one of the above items are implemented.

[0038] Those skilled in the art clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0039] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it is stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or partly or all or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media for storing program codes such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks or optical disks.

[0040] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0041] The above is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those 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 invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A CNC machine tool string tool control method, characterized in that: The following steps are involved: Step S1: Obtain CNC machine tool monitoring images and processing demand logs; Mark multiple workpieces to be processed based on the CNC machine tool monitoring image; perform process requirement dependency analysis on the processing requirement log section by section based on the multiple workpieces to be processed, thereby generating a process requirement logical dependency graph; Step S2: Acquire the real-time status of CNC machine tool tools based on multiple sensors; Mark multiple machine tool tool nodes based on the CNC machine tool monitoring image; evaluate the dynamic operation state of the CNC machine tool tool in real time based on the multiple machine tool tool nodes to generate the dynamic operation state characteristics of the tool; Step S3: performing position positioning calculations on multiple machine tool tool nodes and multiple workpieces to be processed, and performing three-dimensional point cloud modeling to construct a real-time twin model of the CNC machine tool; Step S4: Predicting the stage process tool wear based on the tool dynamic operation state characteristics based on the process requirement logic dependency graph, and optimizing the tool operation parameters, thereby obtaining a stage tool operation parameter sequence; Step S5: Dynamically plan machining paths for multiple workpieces to be machined, and adjust the sequence of tool stringing to construct an optimized tool stringing machining path; Step S6: Based on the stage tool operation parameter sequence and the optimized path of tool stringing processing, the real-time twin model of the CNC machine tool is iteratively simulated, and then the tool stringing control parameters are fine-tuned to construct an intelligent tool stringing control strategy for the CNC machine tool.

2. The CNC machine tool string control method according to claim 1, characterized in that: The specific steps of step S1 are: Step S11: Acquire CNC machine tool monitoring images and processing demand logs; Step S12: performing visual recognition of the target to be processed on the CNC machine tool monitoring image, and marking a plurality of workpieces to be processed; Step S13: extracting processing requirement instructions from the processing requirement log based on the multiple workpieces to be processed, thereby obtaining real-time processing requirement instruction data; Step S14: performing multi-stage process analysis on the real-time processing demand instruction data to obtain a multi-stage processing process sequence; Step S15: performing process requirement dependency analysis on the multi-stage processing sequence stage by stage, thereby generating a process requirement logic dependency graph; The process requirement dependency analysis of the multi-stage processing sequence is performed stage by stage to generate a process requirement logic dependency graph as follows: Extract all machining process stages based on multi-stage machining process sequence; Sequentially encode all the processing technology stages to obtain process stage codes; Calculate the cutting depth and force of all the processing technology stages to obtain the cutting requirement parameters of each processing technology stage; Conduct process timing logic analysis on multi-stage processing sequences to obtain process logic data; Perform process dependency fitting on process logic data based on process stage coding to construct a process logic dependency graph; According to the cutting requirement parameters of each processing stage, the process logic dependency graph is mined between stages to construct a process requirement logic dependency graph.

3. The CNC machine tool string control method according to claim 1, characterized in that: The specific steps of step S2 are: Step S21: Acquire the real-time status of CNC machine tool tools based on multiple sensors; Step S22: performing multi-tool image recognition on the CNC machine tool monitoring image and marking multiple machine tool tool nodes; Step S23: performing tool region image segmentation based on multiple machine tool tool nodes to obtain a tool boundary box image; Step S24: Analyze the current cutting state of the CNC machine tool tool in real time to extract the current cutting state of the tool; Step S25: performing real-time posture recognition on the tool boundary frame image according to the current cutting state of the tool to obtain the real-time posture parameters of each tool; Step S26: Evaluate the dynamic operation state of the tool based on the real-time posture parameters of each tool in the current cutting state of the tool to generate a dynamic operation state feature of the tool.

4. The CNC machine tool string tool control method according to claim 1, characterized in that: The specific steps of step S3 are: Step S31: performing position positioning calculation on multiple machine tool tool nodes to obtain the spatial position coordinates of each machine tool tool; Step S32: performing three-dimensional surface contour analysis on a plurality of workpieces to be processed, and extracting three-dimensional contour lines of the workpieces; Step S33: performing morphological structure recognition on the three-dimensional contour line of the workpiece to generate morphological structure data of the workpiece; Step S34: performing a machine tool area spatial distribution analysis on a plurality of workpieces to be processed, thereby obtaining distribution data within a plurality of workpiece areas; Step S35: performing three-dimensional point cloud modeling on the workpiece morphological structure data according to the distribution data in the multiple workpiece regions, and constructing a machine tool workpiece distribution model; Step S36: Based on the spatial position coordinates of each machine tool tool, the machine tool workpiece distribution model is rendered in real time to construct a real-time twin model of the CNC machine tool.

5. The CNC machine tool string control method according to claim 1, characterized in that: The specific steps of step S4 are: Step S41: Decomposing the process requirement logic dependency graph into multi-stage task requirements and extracting task requirement parameters of multiple stages; Step S42: Calculate the stage processing accuracy on the process requirement logic dependency graph, and extract the processing accuracy correlation data of multiple stages; Step S43: performing a stage tool cutting parameter prediction calculation on the tool dynamic operation state characteristics based on the task requirement parameters of multiple stages and the processing accuracy associated data of multiple stages, and extracting the cutting parameter prediction data of each stage; Step S44: performing a stage process tool wear prediction on the tool dynamic operation state characteristics based on the cutting parameter prediction data of each stage, and obtaining tool wear prediction data of each stage; Step S45: Optimize the tool operation parameters of each stage according to the tool wear prediction data of each stage, so as to obtain a sequence of tool operation parameters of each stage.

6. The CNC machine tool stringing control method according to claim 1, characterized in that: The specific steps of step S5 are: Step S51: positioning a plurality of workpieces to be processed by a machine tool to obtain position coordinates of the workpieces to be processed; Step S52: dynamically planning a machining path for the position coordinates of the workpiece to be machined based on the spatial position coordinates of each machine tool tool, thereby obtaining a plurality of workpiece machining paths; Step S53: performing multi-tool collaborative construction analysis based on tool dynamic operation state characteristics to obtain tool collaborative construction rules; Step S54: adjusting the cutter stringing sequence according to the cutter collaborative construction rule to generate a multi-cutter stringing adjustment parameter; Step S55: performing intelligent tool stringing optimization on multiple workpiece processing paths according to the multi-tool tool stringing adjustment parameters to construct a tool stringing optimization path.

7. The CNC machine tool string control method according to claim 1, characterized in that: The specific steps of step S6 are: Step S61: performing iterative machining simulation on the real-time twin model of the CNC machine tool based on the stage tool operation parameter sequence and the tool string machining optimization path, and collecting the machine tool machining simulation response data; Step S62: performing workpiece machining path deviation identification on the machine tool machining simulation response data, and extracting machining path deviation data; Step S63: Calculate the stage processing accuracy error of the machine tool processing simulation response data based on the real-time processing demand instruction data, and extract the processing accuracy error of each stage; Step S64: fine-tuning the cutter control parameters based on the machining accuracy error and machining path deviation data of each stage to generate the optimal cutter control parameters; Step S65: Based on the optimal tool stringing control parameters, the CNC machine tool is optimized for collaborative control, and an intelligent tool stringing control strategy for the CNC machine tool is constructed.

8. A CNC machine tool string tool control device, characterized in that: The method for controlling the cutting of a CNC machine tool according to claim 1 comprises: The process requirement dependency module obtains the CNC machine tool monitoring image and processing requirement log; marks multiple workpieces to be processed based on the CNC machine tool monitoring image; performs process requirement dependency analysis on the processing requirement log section by section based on multiple workpieces to be processed, thereby generating a process requirement logical dependency graph; The tool operation status module obtains the real-time status of CNC machine tool tools based on multiple sensors; marks multiple machine tool tool nodes based on the CNC machine tool monitoring image; and evaluates the dynamic operation status of the CNC machine tool tools based on the real-time status of the multiple machine tool tool nodes to generate the dynamic operation status characteristics of the tools; The twin model module calculates the position of multiple machine tool nodes and multiple workpieces to be processed, performs three-dimensional point cloud modeling, and constructs a real-time twin model of the CNC machine tool; The tool operation optimization module predicts the stage process tool wear based on the tool dynamic operation state characteristics based on the process requirement logic dependency graph, and optimizes the tool operation parameters to obtain the stage tool operation parameter sequence; The processing path planning module dynamically plans the processing paths for multiple workpieces to be processed and adjusts the sequence of tool stringing to construct an optimized path for tool stringing processing; The parameter fine-tuning module performs iterative processing simulation on the real-time twin model of the CNC machine tool based on the stage tool operation parameter sequence and the optimized path of the tool string processing, and then fine-tunes the tool string control parameters to build an intelligent tool string control strategy for the CNC machine tool.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the CNC machine tool string tool control method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the CNC machine tool string tool control method described in any one of claims 1 to 7 are implemented.

Images