Machine tool processing strategy planning method, device, equipment and storage medium

Abstract

The present application discloses a machine tool processing strategy planning method, device, equipment and storage medium, which relates to the technical field of CNC machine tools. The machine tool processing strategy planning method includes: obtaining historical processing data, establishing a deep neural network model based on the historical processing data, wherein the deep neural network model is used to automatically generate a machine tool processing strategy according to three-dimensional model data; obtaining three-dimensional model data, inputting the three-dimensional model data into the deep neural network model, and generating a machine tool processing strategy; executing the machine tool processing process according to the machine tool operation strategy, and obtaining the machine tool feedback data during the machine tool processing process; adjusting the machine tool processing strategy according to the machine tool feedback data, and determining the adjusted target processing strategy. The present application can improve the flexibility and adaptability of CNC machine tool automation.

Description

Technical Field

[0001] The present application relates to the technical field of numerically controlled machine tools, and in particular to a method, device, equipment and storage medium for planning a machining strategy for a machine tool. Background Art

[0002] In the process of automation development of CNC machine tool technology, computer-aided manufacturing software automates complex manufacturing process programming through design parameters and tool path planning provided by users. This process greatly simplifies the conversion steps from design drawings to physical parts, and improves production efficiency and processing accuracy.

[0003] However, traditional CNC machine tools optimize cutting parameters and path planning by learning historical data. These existing technologies require pre-definition of models and parameters during application, which means that the learning framework and rules must be set in advance before the CNC machine tools are operated, which severely limits the flexibility and adaptability of CNC machine tools when dealing with new situations, new materials or changes in processing technology.

[0004] Therefore, CNC machine tool automation is highly dependent on predefined models and parameter settings, resulting in poor adaptability and flexibility of machine tool automation, which has become a problem that needs to be solved urgently.

[0005] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0006] The main purpose of this application is to provide a machine tool processing strategy planning method, device, equipment and storage medium, aiming to solve the technical problem that CNC machine tool automation is highly dependent on predefined models and parameter settings, resulting in poor adaptability and flexibility of machine tool automation.

[0007] To achieve the above objectives, the present application proposes a machine tool processing strategy planning method, the machine tool processing strategy planning method comprising:

[0008] Acquire historical processing data, and establish a deep neural network model based on the historical processing data, wherein the deep neural network model is used to automatically generate a machine tool processing strategy according to the three-dimensional model data;

[0009] Acquire three-dimensional model data, input the three-dimensional model data into the deep neural network model, and generate a machine tool processing strategy, wherein the machine tool processing strategy at least includes a tool path, a rotation angle, a tool speed, and a feed rate;

[0010] Executing a machine tool processing process according to the machine tool operation strategy, and acquiring machine tool feedback data during the machine tool processing process, wherein the machine tool feedback data includes a real-time processing state and a processing result;

[0011] The machining strategy of the machine tool is adjusted according to the feedback data of the machine tool, and the adjusted target machining strategy is determined.

[0012] In one embodiment, the historical processing data includes historical three-dimensional model data and historical machine tool processing strategies, and the step of establishing a deep neural network model based on the historical processing data includes:

[0013] Constructing a self-supervised learning framework according to the historical three-dimensional model data and the historical machine tool processing strategy, wherein the self-supervised learning framework is used to reconstruct some parameters of the historical machine tool processing strategy;

[0014] The self-supervised learning framework is trained using the historical three-dimensional model data and the historical machine tool processing strategy to determine a deep neural network model after training.

[0015] In one embodiment, the step of constructing a self-supervised learning framework based on the historical three-dimensional model data and the historical machine tool processing strategy includes:

[0016] Designing a self-supervised learning task according to the historical three-dimensional model data and the historical machine tool processing strategy, wherein the self-supervised learning task includes predicting parameters of the machine tool processing strategy according to the historical three-dimensional model data, or determining some parameters of the historical machine tool processing strategy as first parameters, and predicting other parameters of the machine tool processing strategy except the first parameters according to the first parameters;

[0017] An initial model is created, the self-supervised learning task is used as a learning objective of the initial model, and a self-supervised learning framework is determined.

[0018] In one embodiment, after the step of training the self-supervised learning framework using the historical three-dimensional model data and the historical machine tool processing strategy to determine the deep neural network model after training, the step further includes:

[0019] Acquire historical feedback data collected by the machine tool during the execution of the historical machine tool processing strategy, wherein the historical feedback data includes cutting force, vibration frequency, temperature change, and tool wear condition;

[0020] The historical feedback data is input into the deep neural network model, the deep neural network model is optimized, and based on the optimized deep neural network model, the steps of obtaining three-dimensional model data and inputting the three-dimensional model data into the deep neural network model are performed.

[0021] In one embodiment, before the step of executing the machine tool processing according to the machine tool operation strategy and obtaining the machine tool feedback data during the machine tool processing, the step further includes:

[0022] Performing simulation test on the three-dimensional model data based on the machine tool operation strategy, determining simulation test results, and judging whether the machine tool operation strategy meets preset verification conditions according to the simulation test results, wherein the preset verification conditions include efficiency verification conditions and safety verification conditions;

[0023] If it is in compliance, the steps are executed: executing the machine tool processing process according to the machine tool operation strategy;

[0024] If it does not meet the requirements, the machine tool operation strategy is adjusted to determine the adjusted first operation strategy, and the first operation strategy is used as the machine tool operation strategy, and the execution step is returned to: the three-dimensional model data is simulated and tested based on the machine tool operation strategy until the machine tool operation strategy matches the preset verification condition.

[0025] In one embodiment, the step of adjusting the machine tool processing strategy according to the machine tool feedback data and determining the adjusted target processing strategy includes:

[0026] extracting actual machining behavior from the machine tool feedback data;

[0027] Matching the actual processing behavior with a preset normal processing mode to detect whether there is an abnormal behavior that does not match the preset normal processing mode;

[0028] If the abnormal behavior exists, the machine tool processing strategy is switched to an alternative processing strategy or the working path in the machine tool processing strategy is adjusted.

[0029] In addition, to achieve the above purpose, the present application also proposes a machine tool processing strategy planning device, the machine tool processing strategy planning device comprising:

[0030] A model generation module, used to obtain historical processing data and establish a deep neural network model based on the historical processing data, wherein the deep neural network model is used to automatically generate a machine tool processing strategy according to the three-dimensional model data;

[0031] A strategy generation module, used to obtain three-dimensional model data, input the three-dimensional model data into the deep neural network model, and generate a machine tool processing strategy, wherein the machine tool processing strategy at least includes a tool path, a rotation angle, a tool speed, and a feed rate;

[0032] A strategy execution module, used to execute a machine tool processing process according to the machine tool operation strategy, and obtain machine tool feedback data during the machine tool processing process, wherein the machine tool feedback data includes a real-time processing state and a processing result;

[0033] The strategy optimization module is used to adjust the machining strategy of the machine tool according to the feedback data of the machine tool and determine the adjusted target machining strategy.

[0034] In addition, to achieve the above-mentioned purpose, the present application also proposes a machine tool processing strategy planning device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the machine tool processing strategy planning method as described above.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the machine tool processing strategy planning method described above are implemented.

[0036] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the machine tool processing strategy planning method as described above.

[0037] In the present application, historical processing data is acquired and a deep neural network model is established based on the historical processing data, wherein the deep neural network model is used to automatically generate a machine tool processing strategy based on the three-dimensional model data; three-dimensional model data is acquired and the three-dimensional model data is input into the deep neural network model to generate a machine tool processing strategy, wherein the machine tool processing strategy includes at least a tool path, a rotation angle, a tool speed and a feed rate; a machine tool processing process is executed according to the machine tool operation strategy, and machine tool feedback data during the machine tool processing process is acquired, wherein the machine tool feedback data includes a real-time processing status and processing results; the machine tool processing strategy is adjusted according to the machine tool feedback data to determine the adjusted target processing strategy. This embodiment directly converts the three-dimensional model data into an available machine tool processing strategy through input into the model, automatically generates CNC programming code and operation path, reduces manual input and intervention, and improves efficiency from design to production. At the same time, in the subsequent process, based on the collected machine tool feedback data, the actual performance of the processing strategy is analyzed, and the model is adjusted or the processing parameters are directly modified to form a better target processing strategy, forming a closed-loop feedback system, so that the processing system can better adapt to changes in different materials, workpiece geometries and processing environments, improve the overall processing quality and production efficiency, and improve the adaptability and flexibility of machine tool automation. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0040] Figure 1 A flow chart of the first embodiment of the method for planning a machine tool processing strategy of the present application;

[0041] Figure 2 A flow chart of the second embodiment of the method for planning a machine tool processing strategy of the present application;

[0042] Figure 3 A brief flowchart of a machine tool processing strategy planning method provided in Example 2 of the present application;

[0043] Figure 4 This is a schematic diagram of the module structure of the machine tool processing strategy planning device according to an embodiment of the present application;

[0044] Figure 5 Schematic diagram of the equipment structure of the hardware operating environment involved in the machine tool processing strategy planning method in the embodiment of the present application.

[0045] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0046] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0047] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0048] The present application embodiment provides a method for planning a machine tool processing strategy, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the machine tool processing strategy planning method of the present application.

[0049] In this embodiment, the machine tool processing strategy planning method includes steps S10 to S40:

[0050] Step S10, acquiring historical processing data, and establishing a deep neural network model based on the historical processing data, wherein the deep neural network model is used to automatically generate a machine tool processing strategy according to the three-dimensional model data;

[0051] It should be noted that historical processing data is the basis for building a deep neural network model, including historical 3D model data, historical machine tool processing strategies and historical machine tool feedback data. The design of the deep neural network model needs to consider the mapping relationship between 3D model features (such as volume, surface area, feature recognition, etc.) and the expected output processing strategy.

[0052] Step S20, acquiring three-dimensional model data, inputting the three-dimensional model data into the deep neural network model, and generating a machine tool processing strategy, wherein the machine tool processing strategy at least includes a tool path, a rotation angle, a tool speed, and a feed rate;

[0053] It should be noted that after the aforementioned training, a deep neural network model is obtained, which learns the law of mapping from 3D model features to optimal processing parameters. Before inputting into the deep neural network model, the 3D model data may need to undergo some preprocessing, such as normalizing the size, extracting features, etc., so that the network can better understand and process it.

[0054] Machine tool processing strategies can include the following: Tool path: The deep neural network model calculates the optimal movement trajectory of the tool based on the geometric characteristics, complexity and required accuracy of the model to ensure an efficient and collision-free processing process. Rotation angle: refers to the rotation control of the tool or workpiece during the processing process, which is used to adapt to the processing requirements of different surfaces and improve surface quality. The deep neural network model can automatically determine the optimal rotation strategy based on the model characteristics. Tool speed: Based on the hardness of the model material, tool durability and processing requirements, the deep neural network model calculates the most suitable cutting speed to balance processing efficiency and tool life. Feed rate: The feed rate determines the speed at which the tool moves along the path, affecting the processing quality and efficiency. The deep neural network model will set the appropriate feed rate based on the model data to reduce cutting force and vibration and ensure processing quality.

[0055] In a feasible implementation manner, before step S30, steps A10 to A30 are also included:

[0056] Step A10, performing simulation test on the three-dimensional model data based on the machine tool operation strategy, determining the simulation test result, and judging whether the machine tool operation strategy meets the preset verification conditions according to the simulation test result, wherein the preset verification conditions include efficiency verification conditions and safety verification conditions;

[0057] It should be noted that professional computer-aided manufacturing software or simulation software, such as Siemens NX, VERICUT, DELMIA, etc., can simulate the tool's motion trajectory, material removal process, machine tool dynamics, etc. according to the input processing strategy and 3D model. The simulation test not only simulates the processing process, but also evaluates various parameters in the processing process, such as processing time, tool wear, material removal, machine tool load, etc., to fully understand the processing effect. Efficiency verification includes: analyzing the simulation test results to determine whether the processing strategy meets the preset efficiency verification conditions. This includes evaluating whether the processing time is within a reasonable range, whether the processing cost is economical, and whether the processing efficiency is maximized. Safety verification includes: checking whether the simulation results meet safety standards, such as whether there is a risk of collision between the tool and the workpiece or fixture, whether the machine tool is overloaded, and whether the tool is at risk of breakage due to overheating or excessive wear.

[0058] Based on the data obtained from the simulation test, the machine tool operation strategy is comprehensively evaluated to determine whether it has met the preset verification conditions for efficiency and safety. If the strategy passes the verification, it can proceed to the next step and prepare for actual processing; if it fails the verification, it is necessary to return to the strategy formulation stage for adjustment and optimization.

[0059] Step A20, if it is in compliance, then executing the step: executing the machine tool processing process according to the machine tool operation strategy;

[0060] Step A30: If it does not meet the requirements, adjust the machine tool operation strategy, determine the adjusted first operation strategy, use the first operation strategy as the machine tool operation strategy, and return to the execution step: perform simulation test on the three-dimensional model data based on the machine tool operation strategy until the machine tool operation strategy matches the preset verification condition.

[0061] In this embodiment, before actual processing, the processing process based on the three-dimensional model data and the preset machine tool operation strategy is simulated through software simulation to predict the processing efficiency and safety. When the simulation test results show that the machine tool operation strategy meets the preset efficiency and safety verification conditions, it means that the strategy is feasible and actual processing can be carried out. If the simulation test shows that the current machine tool operation strategy fails to meet the preset verification conditions, the strategy needs to be adjusted to solve problems such as inefficiency and safety hazards. This embodiment constitutes a closed-loop verification and optimization process to ensure that before actual processing, the machine tool operation strategy has been fully simulated and adjusted to meet the established efficiency and safety standards.

[0062] Step S30, executing a machine tool processing process according to the machine tool operation strategy, and acquiring machine tool feedback data during the machine tool processing process, wherein the machine tool feedback data includes a real-time processing state and a processing result;

[0063] It should be noted that the machining strategy generated in S20, including tool path, rotation angle, tool speed and feed rate, etc., is input into the CNC machine tool control system. The CNC machine tool control system instructs the machine tool to move according to these strategies, accurately controls the motion trajectory, speed and direction of the tool, and other necessary machining parameters.

[0064] During the machining process, the machine tool's built-in sensors and control systems continuously monitor and record various parameters, such as tool wear, spindle load, temperature, vibration, etc. These data reflect the real-time status of the machining process and are essential for monitoring the health and efficiency of the machining process. After the machining is completed, the size, shape error, surface roughness and other data of the machined parts are collected through measuring tools or built-in detection systems, and compared with the design requirements to evaluate the machining quality.

[0065] The machine tool feedback data provides a basis for subsequent process optimization. By analyzing the data, deficiencies in the processing process can be identified, such as extended processing time caused by unreasonable tool paths, rapid tool wear or reduced processing quality caused by inappropriate cutting parameters. In some advanced manufacturing systems, machine tool feedback data can be fed back to the control system in real time to achieve closed-loop control, adjust processing parameters in real time, and ensure that the processing process is always maintained in the optimal state.

[0066] Step S40, adjusting the machine tool processing strategy according to the machine tool feedback data, and determining the adjusted target processing strategy.

[0067] First, a comprehensive analysis of the machine tool feedback data collected from step S30 is required. This includes statistics and evaluation of data on real-time machining status (such as tool wear, spindle load, temperature fluctuations, vibration levels, etc.) and machining results (dimensional accuracy, surface finish, geometric tolerances, etc.). Based on data analysis, identify deficiencies in machining strategies, such as unreasonable machining parameter settings (such as excessive feed rates leading to accelerated tool wear, too low cutting speeds affecting efficiency, etc.), poor tool path selection leading to long machining time or material waste, etc. Identify specific aspects that need to be adjusted in order to solve identified problems, while considering multiple goals such as improving machining efficiency, reducing costs, and improving product quality.

[0068] Based on the identified problems, the machining parameters are carefully adjusted, such as feed rate, speed, cooling strategy, etc., to reduce tool wear, optimize the load distribution during machining, and keep the machine running in the best condition. If the machining path is inefficient or causes unnecessary machining residues, it may be necessary to re-plan the tool path to reduce machining time, improve material utilization, and reduce energy consumption. The above adjustments are integrated into a new set of machining strategies, namely the adjusted target machining strategy, which should take into account all optimization goals to ensure that the machining process is more efficient, accurate, and economical.

[0069] In a feasible implementation manner, step S40 may further include steps S41 to S43:

[0070] Step S41, extracting actual processing behavior from the machine tool feedback data;

[0071] Step S42, matching the actual processing behavior with a preset normal processing mode, and detecting whether there is an abnormal behavior that does not match the preset normal processing mode;

[0072] Step S43: if the abnormal behavior exists, switching the machine tool processing strategy to an alternative processing strategy or adjusting the working path in the machine tool processing strategy.

[0073] In this embodiment, useful information is extracted from the data collected by various sensors built into the CNC machine tool, which reflects the actual performance of the machine tool in the process of performing the processing task. These data may include but are not limited to the degree of tool wear, motor load, vibration frequency, temperature change, feed rate, etc. Through the data analysis algorithm, these raw data are converted into understandable actual processing behavior models, such as cutting efficiency, surface finish evaluation, etc., so as to provide a basis for subsequent analysis and decision-making. The system compares the actual processing behavior extracted from S41 with a set of normal processing modes set in advance. These preset modes are based on historical data and expert knowledge and define the performance characteristics of the processing process under ideal conditions. Through comparative analysis, the system can identify any behavior that deviates from the normal mode, which may indicate an abnormality in the processing process, such as tool breakage, unstable workpiece clamping, improper processing parameter settings, etc. This matching and detection mechanism is implemented based on a machine learning algorithm, which can learn and continuously optimize the ability to identify abnormal behavior. Once an abnormal behavior that does not match the preset normal processing mode is detected, the system will immediately take countermeasures. This may include two aspects: First, the machine tool's processing strategy may be switched to a pre-set alternative processing strategy, which is usually designed to handle specific types of exceptions, such as using a more conservative feed rate to reduce vibration, or using an alternative tool path to avoid known defective areas. Secondly, if the exception is related to a specific work path, the system will adjust the current work path, such as fine-tuning the tool trajectory to avoid the detected problem area, or adjusting the cutting parameters to reduce the burden on the machine tool. Such dynamic adjustments help to correct problems in a timely manner, prevent degradation of processing quality or damage to equipment, and maintain processing efficiency as much as possible.

[0074] In this embodiment, historical processing data is obtained, and a deep neural network model is established based on the historical processing data, wherein the deep neural network model is used to automatically generate a machine tool processing strategy according to the three-dimensional model data; three-dimensional model data is obtained, and the three-dimensional model data is input into the deep neural network model to generate a machine tool processing strategy, wherein the machine tool processing strategy includes at least a tool path, a rotation angle, a tool speed, and a feed rate; a machine tool processing process is executed according to the machine tool operation strategy, and machine tool feedback data during the machine tool processing process is obtained, wherein the machine tool feedback data includes a real-time processing status and processing results; the machine tool processing strategy is adjusted according to the machine tool feedback data, and an adjusted target processing strategy is determined. This embodiment directly converts the three-dimensional model data into an available machine tool processing strategy through input into the model, automatically generates CNC programming code and operation path, reduces manual input and intervention, and improves efficiency from design to production. At the same time, in the subsequent process, based on the collected machine tool feedback data, the actual performance of the processing strategy is analyzed, and the model is adjusted or the processing parameters are directly modified to form a better target processing strategy, forming a closed-loop feedback system, so that the processing system can better adapt to changes in different materials, workpiece geometries and processing environments, improve the overall processing quality and production efficiency, and improve the adaptability and flexibility of machine tool automation.

[0075] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 The historical processing data includes historical three-dimensional model data and historical machine tool processing strategies. Step S10 may include steps S11 to S12:

[0076] Step S11, constructing a self-supervised learning framework according to the historical three-dimensional model data and the historical machine tool processing strategy, wherein the self-supervised learning framework is used to reconstruct some parameters of the historical machine tool processing strategy;

[0077] It should be noted that the self-supervised task design task allows the model to predict or infer some parameters in the machining strategy based on the three-dimensional model features. The machining strategy parameters can be divided into two parts, one as the input of the model and the other as the target output. The task of the model is to predict the missing output parameters based on the input parameters. For example, the model accepts three-dimensional model features and cutting speed as input, and the goal is to predict the optimal feed rate. Alternatively, the model may predict the optimization solution of the machining path through the geometric features of the model. Select or design a deep learning model suitable for processing three-dimensional data, such as 3D convolutional neural network (3D CNN), graph neural network (GNN) or combine other advanced architectures to capture the complex relationship between the complex geometric structure of the part and the machining strategy.

[0078] It can be understood that through historical data, especially 3D models and previous machining strategies, a self-supervised learning framework is constructed, which can automatically learn how to predict or "reconstruct" the parameters used in the machining process based on the geometric characteristics of the part. "Reconstruction" here means that the model needs to use self-supervised tasks to extract useful information from the input data to infer certain parameters of the machining strategy without direct human annotation.

[0079] The significance of building such a self-supervised learning framework is that it can automatically extract the underlying rules of the processing strategy using existing processing experience and data, so that when faced with new processing tasks, the model can quickly and accurately recommend processing parameters, reduce trial and error costs, and improve processing efficiency and quality. In addition, since the self-supervised learning framework does not rely on a large amount of manually labeled data, it is more flexible and cost-effective in practical applications.

[0080] In a feasible implementation, step S11 may include steps S111 to S112:

[0081] Step S111, designing a self-supervised learning task based on the historical three-dimensional model data and the historical machine tool processing strategy, wherein the self-supervised learning task includes predicting parameters of the machine tool processing strategy based on the historical three-dimensional model data, or determining some parameters of the historical machine tool processing strategy as first parameters, and predicting other parameters in the machine tool processing strategy except the first parameters based on the first parameters;

[0082] It should be noted that the historical 3D model data contains the 3D geometric information of various parts, such as shape, size, surface characteristics, etc.; the historical machine tool processing strategy covers a series of processing parameters in successful processing cases, such as tool selection, cutting speed, feed rate, etc. These parameters directly determine the processing efficiency and part quality. The set self-supervised learning tasks include Task 1: Prediction of 3D model to processing strategy parameters: The design task allows the model to learn directly from the 3D model data and predict the corresponding processing strategy parameters. The model is required to identify and learn the complex relationship between model features and processing parameters. Task 2: Mutual prediction between parameters: Select one or more from the processing strategy parameters as the first parameter. The first parameter may be a parameter that is considered to have a greater impact on the processing process based on experience, or a relatively stable parameter in the data. When the first parameter is known, the design task allows the model to predict other parameters in the processing strategy except the first parameter, helping the model learn the dependency and potential rules between parameters and improving the generalization ability of the model.

[0083] By predicting machining parameters directly from 3D model features, the model can learn deeper and more abstract feature representations, which is crucial for accurate prediction of machining strategies. By predicting each other, the model can learn the intrinsic connections and mutual influences between machining parameters, which helps the model make reasonable predictions when facing new parts, even if some parameters are unknown.

[0084] It can be understood that by using historical 3D model data and historical machine tool processing strategies, through self-supervised learning, the design model can predict the processing strategy parameters according to the 3D geometric features of the part, or predict the remaining parameters when some parameters are known, thereby optimizing the processing process and improving production efficiency and processing quality.

[0085] Step S112, creating an initial model, taking the self-supervised learning task as the learning target of the initial model, and determining a self-supervised learning framework.

[0086] It should be noted that the design and implementation of a deep learning model capable of performing self-supervised learning tasks is usually an untrained or randomly initialized neural network model, and its architecture and scale depend on the complexity of the self-supervised task and the characteristics of the data. Ensure that the self-supervised learning task is clearly converted into the training goal of the model. For example, if the task is to predict machining parameters based on a three-dimensional model, the goal of the model is to learn a mapping function that maps the input model features to the expected machining strategy parameters. At the same time, select or design an appropriate loss function (such as mean square error, cross entropy loss, etc.) to quantify the gap between the model prediction and the true value, and guide the optimization of the model parameters.

[0087] By creating a model architecture that matches the task, clarifying the learning objectives, and establishing a comprehensive learning and optimization framework, a platform is provided for the model to learn from scratch and gradually optimize its performance. This process is not only about technical implementation, but also involves a deep understanding and reasonable application of task characteristics. The ultimate goal is to train a deep learning model that can effectively use self-supervised tasks to improve prediction or decision-making capabilities.

[0088] In this embodiment, through the designed self-supervised learning tasks and model architecture, the model can learn feature representations that are useful for predicting machining strategy parameters from historical data in an unsupervised environment, providing a clear direction for subsequent training and optimization.

[0089] Step S12: training the self-supervised learning framework using the historical three-dimensional model data and the historical machine tool processing strategy to determine a deep neural network model after training.

[0090] It should be noted that the training process includes: data preprocessing: first, the 3D model data is preprocessed as necessary, including standardization, normalization, feature extraction, etc., to facilitate model processing. The processing strategy data must also be organized into a form suitable for model input; model input design: combining the 3D model features and processing strategy parameters, designing the input structure of the model, including taking the model features and some processing strategy parameters as input to predict the remaining processing strategy parameters; self-supervised task implementation: during the training process, the model learns by solving self-supervised tasks; the model must predict certain parameters of the processing strategy from the 3D model data, or sort, classify, reconstruct the processing strategy parameters, etc.; loss function and optimization: define a loss function to measure the difference between the model prediction and the actual processing strategy parameters. Use back propagation and optimization algorithms to continuously adjust model parameters to minimize the loss function; training iteration: the model learns from historical data through multiple iteration cycles, and each iteration is updated based on randomly sampled small batches of data to gradually optimize model performance; performance monitoring and adjustment: during the training process, monitor the performance of the model on the validation set, which may include indicators such as accuracy and loss value, and adjust the learning rate, regularization parameters, etc. according to the verification results to avoid overfitting or underfitting.

[0091] It is understandable that through the effective use of historical data, a deep neural network model that can understand the complex relationship between the three-dimensional model and the processing strategy can be trained, thereby providing intelligent strategy recommendations for machine tool processing, optimizing the processing process, and improving production efficiency and product quality.

[0092] In a feasible implementation manner, after step S12, steps S13 and S14 may also be included:

[0093] Step S13, obtaining historical feedback data collected by the machine tool during the execution of the historical machine tool processing strategy, wherein the historical feedback data includes cutting force, vibration frequency, temperature change, and tool wear condition;

[0094] It should be noted that the cutting force reflects the force generated by the contact between the tool and the workpiece during the machining process, and is an important indicator for evaluating the stability of the machining process and the tool load. High cutting force may indicate that the machining conditions are too harsh, which may cause tool damage or workpiece deformation. The vibration frequency indicates the vibration frequency generated by the machine tool and the workpiece during machining, which can indirectly reflect the stability of the machining process. High-frequency vibration may be related to tool chatter, imbalance or improper machining parameters, affecting machining accuracy and surface quality. Temperature change refers to the temperature rise of the tool, workpiece and machine tool components during the machining process. Excessive temperature can cause problems such as accelerated tool wear and thermal deformation of the workpiece. Monitoring temperature changes helps optimize cooling strategies and machining parameters and extend tool life. Tool wear status indirectly evaluates tool wear status by monitoring changes in parameters such as cutting force and vibration. Accurately grasping the degree of tool wear is crucial for timely tool replacement and maintaining machining accuracy and quality.

[0095] By inputting these historical feedback data into the deep neural network model, the model's predictive ability can be verified, such as whether the predicted processing parameters lead to the expected processing effect (low vibration, appropriate temperature change, etc.), and the model parameters can be optimized accordingly to improve the prediction accuracy. By analyzing historical feedback data, problem areas in the processing process (such as excessive vibration periods and rapid tool wear stages) can be found, and the processing strategy can be adjusted accordingly, such as changing the cutting speed, feed rate or cooling strategy to achieve higher processing efficiency and quality. Long-term monitoring and analysis of tool wear and machine tool status can provide early warning of the tool's impending service life or possible mechanical problems with the machine tool, promoting preventive maintenance of equipment.

[0096] Step S14, inputting the historical feedback data into the deep neural network model, optimizing the deep neural network model, and executing the steps based on the optimized deep neural network model: obtaining three-dimensional model data, and inputting the three-dimensional model data into the deep neural network model.

[0097] It should be noted that the historical feedback data such as cutting force, vibration frequency, temperature change and tool wear condition collected in step S13 are integrated as the input of the deep neural network model. These data reflect the physical phenomena and processing conditions in the actual processing process and are an important basis for model learning and optimization. By inputting these actual operation data into the pre-trained deep neural network model, the model can adjust its internal parameters according to the actual feedback and optimize the prediction performance. The main goal of the optimization is to improve the model's prediction accuracy and generalization ability for the processing process, and ensure that the model can also give reliable and efficient processing strategy recommendations when facing unseen processing conditions. Through the feedback of historical data, the model can learn more about the complex relationship between cutting parameters and processing effects, so as to be more accurate in predicting processing strategies for new scenarios.

[0098] By integrating historical feedback data to optimize the deep neural network model, the model's predictive ability and practical application value were further improved. Subsequently, the optimized model was used to predict the processing strategy for new 3D model data, realizing a closed loop from historical data learning to new task prediction, improving the intelligence and adaptability of CNC machining.

[0099] In this implementation, the practicality and dynamic adaptability of the self-supervised learning framework are enhanced by shifting from historical data analysis to continuous optimization and practical application of the model. Through model optimization and verification, not only does the model's understanding and prediction of actual processing conditions become stronger, but it also provides a closed-loop feedback mechanism for the application of the model, ensuring that the model can continue to improve over time and with the accumulation of processing experience. Through this process, the model can more accurately predict processing parameters, optimize processing strategies, reduce resource waste, and improve processing efficiency and product quality.

[0100] In this embodiment, a self-supervised learning framework is constructed based on the historical three-dimensional model data and the historical machine tool processing strategy, wherein the self-supervised learning framework is used to reconstruct some parameters of the historical machine tool processing strategy, and the design model learns the task of predicting some or all machine tool processing strategy parameters from the three-dimensional model features and other parameters of the known processing strategy. This reconstruction task forces the model to learn the complex relationship between model features and processing strategies, thereby extracting features that have a deep understanding of the processing process; the self-supervised learning framework is trained through the historical three-dimensional model data and the historical machine tool processing strategy, and the deep neural network model after training is determined. The obtained deep neural network model not only learns to infer the processing strategy parameters from the three-dimensional model features, but also potentially captures the implicit knowledge in the processing process, providing a strong foundation for subsequent prediction, optimization or decision support tasks.

[0101] For example, in order to help understand the implementation process of the machine tool processing strategy planning method obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Figure 3 , Figure 3 A brief flow chart of a machine tool processing strategy planning method is provided, which is specifically divided into three processes: sensor 3D data acquisition, self-supervised learning mining machine and adaptive strategy update. In the sensor 3D data acquisition, the 3D model of the CNC five-axis machine tool is collected, the 3D model is parsed, and data preprocessing is performed; in the self-supervised learning framework, the preprocessed data is input into the deep learning framework DNN for feature extraction and learning, thereby generating operating parameters, optimizing parameters, simulating processing and adjusting the operating parameters; after obtaining the actual processing instructions, the processing process is monitored, feedback generated during the process is collected and adjusted in a timely manner, and the generated product is output.

[0102] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the machine tool processing strategy planning method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0103] This application also provides a machine tool processing strategy planning device, please refer to Figure 4 , the machine tool processing strategy planning device comprises:

[0104] A model generation module 10, used to obtain historical processing data and establish a deep neural network model based on the historical processing data, wherein the deep neural network model is used to automatically generate a machine tool processing strategy according to the three-dimensional model data;

[0105] A strategy generation module 20, for acquiring three-dimensional model data, inputting the three-dimensional model data into the deep neural network model, and generating a machine tool processing strategy, wherein the machine tool processing strategy at least includes a tool path, a rotation angle, a tool speed, and a feed rate;

[0106] A strategy execution module 30, used to execute a machine tool processing process according to the machine tool operation strategy, and obtain machine tool feedback data during the machine tool processing process, wherein the machine tool feedback data includes a real-time processing state and a processing result;

[0107] The strategy optimization module 40 is used to adjust the machining strategy of the machine tool according to the feedback data of the machine tool and determine the adjusted target machining strategy.

[0108] The machine tool processing strategy planning device provided by the present application adopts the machine tool processing strategy planning method in the above-mentioned embodiment, which can solve the technical problem that the automation of CNC machine tools is highly dependent on predefined models and parameter settings, resulting in poor adaptability and flexibility of machine tool automation. Compared with the prior art, the beneficial effects of the machine tool processing strategy planning device provided by the present application are the same as the beneficial effects of the machine tool processing strategy planning method provided by the above-mentioned embodiment, and the other technical features in the machine tool processing strategy planning device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0109] The present application provides a machine tool processing strategy planning device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the machine tool processing strategy planning method in the above-mentioned embodiment one.

[0110] Reference below Figure 5, which shows a schematic diagram of the structure of a machine tool processing strategy planning device suitable for implementing the embodiment of the present application. The machine tool processing strategy planning device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The machine tool processing strategy planning device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0111] like Figure 5 As shown, the machine tool processing strategy planning device may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the xxx device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the machine tool processing strategy planning device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a machine tool processing strategy planning device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.

[0112] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0113] The machine tool processing strategy planning device provided by the present application adopts the machine tool processing strategy planning method in the above embodiment, which can solve the technical problem that the automation of CNC machine tools is highly dependent on predefined models and parameter settings, resulting in poor adaptability and flexibility of machine tool automation. Compared with the prior art, the beneficial effects of the machine tool processing strategy planning device provided by the present application are the same as the beneficial effects of the machine tool processing strategy planning method provided by the above embodiment, and the other technical features in the machine tool processing strategy planning device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0114] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0115] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0116] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the machine tool processing strategy planning method in the above-mentioned embodiment.

[0117] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0118] The above-mentioned computer-readable storage medium may be included in the machine tool processing strategy planning device; or it may exist independently without being assembled into the machine tool processing strategy planning device.

[0119] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the machine tool processing strategy planning device, the machine tool processing strategy planning device: obtains historical processing data, and establishes a deep neural network model based on the historical processing data, wherein the deep neural network model is used to automatically generate a machine tool processing strategy according to the three-dimensional model data; obtains three-dimensional model data, inputs the three-dimensional model data into the deep neural network model, and generates a machine tool processing strategy, wherein the machine tool processing strategy includes at least a tool path, a rotation angle, a tool speed and a feed rate; executes a machine tool processing process according to the machine tool operation strategy, and obtains machine tool feedback data during the machine tool processing process, wherein the machine tool feedback data includes real-time processing status and processing results; adjusts the machine tool processing strategy according to the machine tool feedback data, and determines the adjusted target processing strategy.

[0120] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0121] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0122] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0123] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned machine tool processing strategy planning method, and can solve the technical problem that the automation of CNC machine tools is highly dependent on predefined models and parameter settings, resulting in poor adaptability and flexibility of machine tool automation. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the machine tool processing strategy planning method provided by the above-mentioned embodiment, and will not be repeated here.

[0124] The present application also provides a computer program product, including a computer program, which implements the steps of the machine tool processing strategy planning method as described above when the computer program is executed by a processor.

[0125] The computer program product provided by the present application can solve the technical problem that the automation of CNC machine tools is highly dependent on predefined models and parameter settings, resulting in poor adaptability and flexibility of machine tool automation. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the machine tool processing strategy planning method provided by the above embodiment, and will not be elaborated here.

[0126] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A machine tool processing strategy planning method, characterized in that: The machine tool processing strategy planning method comprises: Acquire historical processing data, and establish a deep neural network model based on the historical processing data, wherein the historical processing data includes historical three-dimensional model data, historical machine tool processing strategies and historical machine tool feedback data, and the deep neural network model is used to automatically generate machine tool processing strategies according to the three-dimensional model data; Acquire three-dimensional model data, input the three-dimensional model data into the deep neural network model, and generate a machine tool processing strategy, wherein the machine tool processing strategy at least includes a tool path, a rotation angle, a tool speed, and a feed rate; Execute a machine tool processing process according to the machine tool processing strategy, and obtain machine tool feedback data during the machine tool processing process, wherein the machine tool feedback data includes real-time processing status and processing results, wherein the real-time processing status includes tool wear status, spindle load, temperature fluctuation, and vibration level, and the processing results include dimensional accuracy, surface finish, and geometric tolerances; Adjust the machining strategy of the machine tool according to the feedback data of the machine tool, and determine the adjusted target machining strategy; Wherein, the step of establishing a deep neural network model based on the historical processing data includes: Constructing a self-supervised learning framework according to the historical three-dimensional model data and the historical machine tool processing strategy, wherein the self-supervised learning framework is used to reconstruct some parameters of the historical machine tool processing strategy; The self-supervised learning framework is trained by using the historical three-dimensional model data and the historical machine tool processing strategy to determine a deep neural network model after training; Wherein, after the step of training the self-supervised learning framework by using the historical three-dimensional model data and the historical machine tool processing strategy to determine the deep neural network model after the training is completed, it also includes: Acquire historical feedback data collected by the machine tool during the execution of the historical machine tool processing strategy, wherein the historical feedback data includes cutting force, vibration frequency, temperature change, and tool wear condition; The historical feedback data is input into the deep neural network model, the deep neural network model is optimized, and based on the optimized deep neural network model, the steps of obtaining three-dimensional model data and inputting the three-dimensional model data into the deep neural network model are performed.

2. The machine tool processing strategy planning method according to claim 1, characterized in that: The step of constructing a self-supervised learning framework based on the historical three-dimensional model data and the historical machine tool processing strategy includes: Designing a self-supervised learning task according to the historical three-dimensional model data and the historical machine tool processing strategy, wherein the self-supervised learning task includes predicting parameters of the machine tool processing strategy according to the historical three-dimensional model data, or determining some parameters of the historical machine tool processing strategy as first parameters, and predicting other parameters of the machine tool processing strategy except the first parameters according to the first parameters; An initial model is created, the self-supervised learning task is used as a learning objective of the initial model, and a self-supervised learning framework is determined.

3. The machine tool processing strategy planning method according to claim 1, characterized in that: Before the step of executing the machine tool processing according to the machine tool processing strategy and obtaining the machine tool feedback data during the machine tool processing, the step further includes: Performing simulation test on the three-dimensional model data based on the machine tool processing strategy, determining simulation test results, and judging whether the machine tool processing strategy meets preset verification conditions according to the simulation test results, wherein the preset verification conditions include efficiency verification conditions and safety verification conditions; If it is in compliance, the steps are executed: executing the machine tool processing process according to the machine tool processing strategy; If it does not meet the requirements, the machine tool processing strategy is adjusted to determine the adjusted first operation strategy, and the first operation strategy is used as the machine tool processing strategy, and the execution step is returned to: the three-dimensional model data is simulated and tested based on the machine tool processing strategy until the machine tool processing strategy matches the preset verification condition.

4. The machine tool processing strategy planning method according to claim 1, characterized in that: The step of adjusting the machine tool processing strategy according to the machine tool feedback data and determining the adjusted target processing strategy comprises: extracting actual machining behavior from the machine tool feedback data; Matching the actual processing behavior with a preset normal processing mode to detect whether there is an abnormal behavior that does not match the preset normal processing mode; If the abnormal behavior exists, the machine tool processing strategy is switched to an alternative processing strategy or the working path in the machine tool processing strategy is adjusted.

5. A machine tool processing strategy planning device, characterized in that: The machine tool processing strategy planning device comprises: A model generation module, used to obtain historical processing data, and establish a deep neural network model based on the historical processing data, wherein the historical processing data includes historical three-dimensional model data, historical machine tool processing strategies and historical machine tool feedback data, and the deep neural network model is used to automatically generate machine tool processing strategies according to the three-dimensional model data; A strategy generation module, used to obtain three-dimensional model data, input the three-dimensional model data into the deep neural network model, and generate a machine tool processing strategy, wherein the machine tool processing strategy at least includes a tool path, a rotation angle, a tool speed, and a feed rate; A strategy execution module, used for executing a machine tool processing process according to the machine tool processing strategy, and obtaining machine tool feedback data during the machine tool processing process, wherein the machine tool feedback data includes real-time processing status and processing results, wherein the real-time processing status includes tool wear status, spindle load, temperature fluctuation, and vibration level, and the processing results include dimensional accuracy, surface finish, and geometric tolerances; A strategy optimization module, used for adjusting the machining strategy of the machine tool according to the feedback data of the machine tool, and determining the adjusted target machining strategy; Wherein, the model generation module is specifically used for: Constructing a self-supervised learning framework according to the historical three-dimensional model data and the historical machine tool processing strategy, wherein the self-supervised learning framework is used to reconstruct some parameters of the historical machine tool processing strategy; The self-supervised learning framework is trained by using the historical three-dimensional model data and the historical machine tool processing strategy to determine a deep neural network model after training; Acquire historical feedback data collected by the machine tool during the execution of the historical machine tool processing strategy, wherein the historical feedback data includes cutting force, vibration frequency, temperature change, and tool wear condition; The historical feedback data is input into the deep neural network model, the deep neural network model is optimized, and based on the optimized deep neural network model, the steps of obtaining three-dimensional model data and inputting the three-dimensional model data into the deep neural network model are performed.

6. A machine tool processing strategy planning device, characterized in that: The machine tool processing strategy planning device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the machine tool processing strategy planning method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the machine tool machining strategy planning method according to any one of claims 1 to 4 are implemented.

8. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the machine tool processing strategy planning method according to any one of claims 1 to 4 are implemented.

Images