Method, System, Equipment and Medium for Reducing the Probability of Tool Sticking in CNC Machining

Abstract

The present application relates to the technical field of machine tool processing, and in particular to a method, a system, a device and a medium for reducing the probability of tool sticking in numerical control machine tool processing. The present application first obtains the overall processing parameter information, divides the processing area according to the workpiece geometric information and sets the partition parameters according to the overall processing parameter information; then triggers the corresponding processing instruction according to the current processing area; then monitors the processing status in real time and calculates the tool sticking risk index; finally, when the risk index exceeds the safety threshold, automatically adjusts the partition processing parameters; not only considers the overall characteristics of the workpiece, but also can meet the processing requirements of local areas, realizing flexible control of the processing process of complex workpieces; significantly improving the processing accuracy and efficiency, prolonging the tool life, and at the same time greatly reducing the probability of tool sticking.

Description

Technical Field

[0001] This application relates to the technical field of machine tool processing, and in particular to methods, systems, devices and media for reducing the probability of tool sticking in numerical control machine tool processing. Background Art

[0002] Numerical control machine tool processing is an important part of modern manufacturing, and its efficiency and accuracy directly affect product quality and production costs. When processing high-strength and low-thermal conductivity materials such as certain special alloys, tool sticking and built-up edge phenomena often occur. These problems not only affect machining accuracy and surface quality, but also significantly shorten tool life and increase production costs.

[0003] Existing processing systems often regard workpieces as homogeneous bodies, ignoring the possible differences in material properties and geometric shape changes in different regions of the workpiece, making it difficult to make flexible adjustments. Especially when dealing with workpieces with complex shapes or uneven heat treatment, the probability of tool sticking increases, and this situation needs to be further improved. Summary of the Invention

[0004] In order to solve the problem that existing processing systems are difficult to make flexible adjustments, resulting in an increase in the probability of tool sticking, this application provides a method, system, device and medium for reducing the probability of tool sticking in numerical control machine tool processing, and adopts the following technical solutions:

[0005] In a first aspect, this application provides a method for reducing the probability of tool sticking in numerical control machine tool processing, including the following steps:

[0006] Obtain processing selection information, and according to the processing selection information, obtain overall processing parameter information, where the overall processing parameter information includes initial cutting speed, initial feed speed, initial cutting depth and coolant flow rate;

[0007] Obtain workpiece geometric information, and according to the workpiece geometric information and the overall processing parameter information, obtain partitioned processing parameters. The workpiece is divided into several processing regions, and the partitioned processing parameters include local cutting speed, local feed speed, local cutting depth and local coolant flow rate for each region;

[0008] Trigger a processing instruction according to the partitioned processing parameters and the current processing region;

[0009] Obtain partitioned processing state detection information, calculate the tool sticking risk index, and compare the tool sticking risk index with a preset safety threshold;

[0010] If the tool sticking risk index exceeds the preset safety threshold, trigger a partitioned processing parameter adjustment instruction.

[0011] By adopting the above technical solution, traditional processing methods often regard workpieces as homogeneous bodies and are difficult to cope with the material property differences and geometric shape changes in different regions of complex workpieces such as titanium alloys used in aerospace; for example, when machining titanium alloy turbine blades with thin-walled structures and thick parts, due to uneven heat accumulation and cutting force distribution, over-deformation in the thin-walled area or serious tool sticking in the thick part often occurs; this application first obtains overall processing parameter information, divides the processing area according to the workpiece geometric information, and sets partition parameters according to the overall processing parameter information; then triggers corresponding processing instructions according to the current processing area; then monitors the processing state in real time and calculates the tool sticking risk index; finally, when the risk index exceeds the safety threshold, automatically adjusts the partition processing parameters; not only considers the overall characteristics of the workpiece, but also can meet the processing requirements of local areas, realizing flexible control of the processing process of complex workpieces; significantly improving the processing accuracy and efficiency, prolonging the tool life, and at the same time greatly reducing the probability of tool sticking.

[0012] Optionally, obtain processing selection information, and according to the processing selection information, obtain overall processing parameter information, specifically including the following steps:

[0013] Extract the processing material type, processing time, and processing accuracy requirements from the processing selection information;

[0014] According to the processing material type, obtain the recommended initial cutting speed and initial feed speed from the preset material database;

[0015] Determine the initial cutting depth according to the processing time and the processing accuracy requirements;

[0016] Determine the coolant flow rate based on the processing material type and the processing accuracy requirements;

[0017] Associate the initial cutting speed, the initial feed speed, the initial cutting depth, and the coolant flow rate to obtain the overall processing parameter information.

[0018] By adopting the above technical solution, traditional methods usually set initial parameters by using empirical values or rough estimates and are difficult to adapt to the diversity of different materials and processing requirements; this application establishes an adaptive parameter selection system; first extracts key factors from the processing selection information and recommends the initial cutting and feed speeds based on the material database; then determines the cutting depth according to the time and accuracy requirements; then considers the material characteristics and accuracy requirements to set the coolant flow rate; finally integrates to form the overall processing parameter information; not only considers the inherent characteristics of the material, but also incorporates the processing time and accuracy requirements into the parameter optimization process, realizing the intelligence and personalization of the initial parameter setting, greatly improving the processing efficiency and quality, and at the same time reducing the parameter debugging time and material waste.

[0019] Optionally, obtain the workpiece geometric information, and based on the workpiece geometric information and the overall machining parameter information, obtain the partitioned machining parameters, specifically including:

[0020] Divide the workpiece into several machining areas according to the workpiece geometric information;

[0021] For each machining area, calculate the local machining difficulty coefficient according to the corresponding geometric features and relative positions;

[0022] According to the local machining difficulty coefficient and the overall machining parameter information, calculate the local cutting speed, local feed rate, local cutting depth and the corresponding local coolant flow rate for each area, and form the partitioned machining parameters.

[0023] By adopting the above technical solution, when machining an aero-engine blade with thin walls, deep cavities and complex curved surfaces, using the same set of parameters may lead to over-cutting in some areas or low machining efficiency; the present application first performs intelligent partitioning based on the workpiece geometric information, and then calculates the local machining difficulty coefficient of each area; finally, according to the difficulty coefficient and the overall parameter information, calculates the local machining parameters of each area, can identify and cope with the geometric complexity of local areas, and realizes the adaptive optimization of machining parameters.

[0024] Optionally, obtain the partitioned machining state detection information and calculate the tool sticking risk index, specifically including the following steps:

[0025] Real-time collect the cutting force, temperature and vibration data of the current machining area;

[0026] Input the collected cutting force, temperature and vibration data into a preset tool sticking risk model to obtain the basic tool sticking risk value;

[0027] Combine the local cutting speed, local feed rate, local cutting depth and local coolant flow rate of the current machining area to correct the basic tool sticking risk value, and obtain the final tool sticking risk index.

[0028] By adopting the above technical solution, when machining superalloys, relying solely on cutting force monitoring may ignore the influence of temperature changes on material properties, resulting in inaccurate tool sticking risk assessment; the present application first real-time collects cutting force, temperature and vibration data, then inputs these data into a preset tool sticking risk model to calculate the basic risk value, and finally dynamically corrects the risk value in combination with the current machining parameters; realizes the intelligence of tool sticking risk prediction, can provide a more accurate and timely tool sticking risk assessment, effectively prevent the tool sticking phenomenon during machining, and improve the machining quality and efficiency.

[0029] Optionally, the basic tool adhesion risk value is corrected by combining the local cutting speed, local feed rate, local cutting depth, and local coolant flow rate of the current machining area to obtain the final tool adhesion risk index. The specific steps are as follows:

[0030] Obtain the local cutting speed, local feed rate, local cutting depth, and local coolant flow rate of the current machining area;

[0031] According to the preset parameter influence model, calculate the influence factors of the local cutting speed, local feed rate, local cutting depth, and local coolant flow rate on the tool adhesion risk respectively, and comprehensively obtain the overall parameter influence coefficient;

[0032] According to the basic tool adhesion risk value and the overall parameter influence coefficient, obtain the final tool adhesion risk index.

[0033] By adopting the above technical solution, traditional methods often simply consider machining parameters as fixed factors, making it difficult to accurately reflect the interaction between different parameters and their comprehensive influence on tool adhesion risk; for example, when machining high-strength titanium alloys, only considering the influence of cutting speed while ignoring its coupling effect with the feed rate, resulting in a large deviation between the risk assessment result and the actual situation; this application first obtains the local machining parameters of the current machining area, then based on the preset parameter influence model, calculates the influence factors of each parameter on the tool adhesion risk and comprehensively obtains the overall parameter influence coefficient, and finally combines the basic tool adhesion risk value and the overall parameter influence coefficient to calculate the final tool adhesion risk index; it can be flexibly adjusted according to different machining conditions and material properties.

[0034] Optionally, if the tool adhesion risk index exceeds the preset safety threshold, trigger a partition machining parameter adjustment instruction. The specific steps are as follows:

[0035] Determine the risk level according to the current tool adhesion risk index, and based on the risk level, obtain the initial adjustment information of the corresponding partition machining parameters;

[0036] Within the preset maximum number of adjustments, gradually adjust the machining parameters according to the initial adjustment information and recalculate the tool adhesion risk index until it drops below the preset warning threshold or reaches the maximum number of adjustments;

[0037] If the tool adhesion risk index drops below the preset warning threshold during the adjustment process, immediately trigger the instruction to execute the current adjusted parameters and end the adjustment process;

[0038] If the maximum number of adjustments is reached, perform the following operations according to the final tool adhesion risk index:

[0039] In the case where the final tool sticking risk index is higher than the warning threshold but lower than the preset mild risk threshold, trigger the instruction to execute the final adjustment parameters and increase the monitoring frequency;

[0040] In the case where the final tool sticking risk index is higher than the mild risk threshold, trigger a warning signal and require manual intervention.

[0041] By adopting the above technical solution, when machining superalloys, the system may over-adjust the parameters when detecting minor risks, affecting the machining efficiency; or may not respond in time when facing serious risks, resulting in tool damage. This application first determines the initial adjustment strategy based on the risk level, performs progressive parameter adjustment and risk re-evaluation within a preset range; then decides whether to end the process in advance according to the adjustment effect; adopts differentiated measures for different final risk levels, can adopt corresponding adjustment strategies according to the risk degree, not only ensures machining safety, but also avoids efficiency losses caused by excessive intervention. At the same time, when the system cannot handle high-risk situations independently, it promptly initiates manual judgment, further improving the reliability of risk management.

[0042] In a second aspect, this application provides a system for reducing the probability of tool sticking in numerical control machine tool machining, including:

[0043] An overall machining parameter information acquisition module, configured to acquire machining selection information, and according to the machining selection information, acquire overall machining parameter information, where the overall machining parameter information includes the initial cutting speed, the initial feed rate, the initial cutting depth, and the coolant flow rate;

[0044] A partition machining parameter acquisition module, configured to acquire workpiece geometry information, and according to the workpiece geometry information and the overall machining parameter information, acquire partition machining parameters, where the workpiece is divided into several machining regions, and the partition machining parameters include the local cutting speed, the local feed rate, the local cutting depth, and the local coolant flow rate for each region;

[0045] A machining instruction trigger module, configured to trigger a machining instruction according to the partition machining parameters and the current machining region;

[0046] A tool sticking risk index calculation module, configured to acquire partition machining state detection information, calculate a tool sticking risk index, and compare the tool sticking risk index with a preset safety threshold;

[0047] A parameter adjustment instruction trigger module, configured to trigger a partition machining parameter adjustment instruction if the tool sticking risk index exceeds the preset safety threshold.

[0048] In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of the method for reducing the probability of tool sticking in the above-mentioned numerical control machine tool machining are implemented.

[0049] In a fourth aspect, the present application 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 method for reducing the probability of tool sticking in the above-mentioned numerical control machine tool machining are implemented.

[0050] In summary, the present application includes at least one of the following beneficial technical effects:

[0051] 1. The present application first obtains the overall machining parameter information, divides the machining area according to the workpiece geometric information, and sets the partition parameters according to the overall machining parameter information; then triggers the corresponding machining instructions according to the current machining area; then monitors the machining status in real time and calculates the tool sticking risk index; finally, when the risk index exceeds the safety threshold, automatically adjusts the partition machining parameters; not only considers the overall characteristics of the workpiece, but also can meet the machining requirements of local areas, realizing flexible control of the machining process of complex workpieces; significantly improving the machining accuracy and efficiency, prolonging the tool life, and at the same time greatly reducing the probability of tool sticking;

[0052] 2. When machining an aero-engine blade with thin walls, deep cavities, and complex curved surfaces, using the same set of parameters may lead to over-cutting or low machining efficiency in some areas; the present application first performs intelligent partitioning based on the workpiece geometric information, then calculates the local machining difficulty coefficient of each area; finally, according to the difficulty coefficient and the overall parameter information, calculates the local machining parameters of each area, can identify and cope with the geometric complexity of local areas, and realizes the adaptive optimization of machining parameters;

[0053] 3. When machining superalloys, the system may over-adjust the parameters when detecting slight risks, affecting the machining efficiency; or may not respond in time when facing serious risks, resulting in tool damage; the present application first determines the initial adjustment strategy based on the risk level, performs progressive parameter adjustment and risk re-evaluation within a preset range; then decides whether to end the process in advance according to the adjustment effect; takes different measures for different final risk levels, can adopt corresponding adjustment strategies according to the risk degree, ensuring machining safety and avoiding efficiency losses caused by excessive intervention. At the same time, when the system cannot handle high-risk situations autonomously, it promptly starts manual judgment, further improving the reliability of risk management. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is a schematic flowchart of a method for reducing the probability of tool sticking in numerical control machine tool machining according to an embodiment of the present application;

[0055] Figure 2 It is a schematic flow chart of step S10 in a method for reducing the probability of tool sticking in numerical control machine tool processing according to an embodiment of the present application;

[0056] Figure 3 It is a schematic flow chart of step S20 in a method for reducing the probability of tool sticking in numerical control machine tool processing according to an embodiment of the present application;

[0057] Figure 4 It is a schematic flow chart of step S40 in a method for reducing the probability of tool sticking in numerical control machine tool processing according to an embodiment of the present application;

[0058] Figure 5 It is a schematic flow chart of step S43 in a method for reducing the probability of tool sticking in numerical control machine tool processing according to an embodiment of the present application;

[0059] Figure 6 It is a schematic flow chart of step S50 in a method for reducing the probability of tool sticking in numerical control machine tool processing according to an embodiment of the present application;

[0060] Figure 7 It is a schematic module diagram of a system for reducing the probability of tool sticking in numerical control machine tool processing according to an embodiment of the present application;

[0061] Figure 8 It is an internal structure diagram of an electronic device according to an embodiment of the present application. Detailed implementation manners

[0062] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. As used in the specification and claims of the present application, the singular forms "a", "an", "the", "above-mentioned", "said", and "this" are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in the present application refers to any and all possible combinations including one or more of the listed items.

[0063] Hereinafter, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as implying or suggesting relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0064] The following further describes the embodiments of the present application in detail with reference to the accompanying drawings of the specification.

[0065] In a first aspect, the present application provides a method for reducing the probability of tool sticking in numerical control machine tool processing. Referring to Figure 1 , the method includes the following steps:

[0066] S10. Obtain machining selection information, and based on the machining selection information, obtain overall machining parameter information.

[0067] Among them, the machining selection information refers to the information related to the machining task input by the operator or the automation system, including but not limited to the type of machining material, machining time, and machining accuracy requirements, etc. The overall machining parameter information refers to the initial set of machining parameters generated based on the machining selection information, including the initial cutting speed, initial feed rate, initial cutting depth, and coolant flow rate.

[0068] Specifically, the system can obtain the overall machining parameter information through a preset material database and machining experience model. For example, for a high-strength titanium alloy workpiece, the system may set the initial cutting speed to 50 m / min according to the material properties, etc.

[0069] S20. Obtain workpiece geometric information, and based on the workpiece geometric information and the overall machining parameter information, obtain zoned machining parameters.

[0070] In this embodiment, the workpiece geometric information refers to the three-dimensional shape data of the workpiece, including but not limited to the external dimensions, internal structure, and surface features of the workpiece, etc. The zoned machining parameters refer to the machining parameters set separately for each region after dividing the workpiece into multiple machining regions, including the local cutting speed, local feed rate, local cutting depth, and local coolant flow rate.

[0071] Specifically, the system obtains the workpiece geometric information through 3D scanning or CAD model import, and then uses an intelligent zoning algorithm to divide the workpiece into multiple machining regions. For example, for a complex turbine blade, the system may divide it into three main regions: the blade root, the blade body, and the blade tip. Subsequently, the system will calculate the local machining parameters for each region according to the geometric features and relative positions of each region, combined with the overall machining parameter information. For example, due to the relatively thin structure of the blade tip region, the local cutting speed and cutting depth will be reduced, while the coolant flow rate will be increased.

[0072] S30. Trigger a machining instruction according to the zoned machining parameters and the current machining region.

[0073] Among them, the current machining region refers to the region of the workpiece that the numerical control machine tool is currently machining. The machining instruction refers to a series of commands for controlling the numerical control machine tool to perform specific machining operations, including tool paths, cutting parameter settings, etc.

[0074] Specifically, the system determines the current machining area according to the machining sequence, and then extracts the local parameters of this area from the partition machining parameters. For example, when the machining reaches the blade body area of the turbine blade, the system will read the local cutting speed, feed rate, cutting depth, and coolant flow rate of the blade body area, and convert these parameters into the instruction format recognizable by the corresponding machine tool.

[0075] S40. Obtain the partition machining status detection information, calculate the tool sticking risk index, and compare the tool sticking risk index with a preset safety threshold.

[0076] In this embodiment, the partition machining status detection information refers to various process parameters and sensor data collected in real time during machining.

[0077] Specifically, the system obtains the partition machining status detection information through various sensors installed on the machine tool, such as cutting force sensors, temperature sensors, and vibration sensors, etc., and inputs it into a pre-trained tool sticking risk prediction model. The tool sticking risk index output by the model may be a value from 0 to 100, where 0 indicates no risk and 100 indicates extremely high risk.

[0078] S50. If the tool sticking risk index exceeds the preset safety threshold, trigger the partition machining parameter adjustment instruction.

[0079] Specifically, when the tool sticking risk index exceeds the safety threshold, the system will start an adaptive adjustment algorithm and select different adjustment strategies according to the current risk level. For example, if the risk index is slightly higher than the threshold, the system will slightly reduce the cutting speed or increase the coolant flow rate. If the risk index is significantly higher than the threshold, the system may adjust multiple parameters simultaneously, such as reducing the cutting speed and feed rate, decreasing the cutting depth, and significantly increasing the coolant flow rate.

[0080] In one embodiment, referring to Figure 2 , in step S10, obtain the machining selection information, and according to the machining selection information, obtain the overall machining parameter information, which specifically includes the following steps:

[0081] S11. Extract the machining material type, machining time, and machining accuracy requirements from the machining selection information.

[0082] Specifically, the system can obtain this information through the user interface or data interface. The system will parse and store this information in a standardized format for subsequent steps. For an automated production line, this information may be automatically transmitted from an upstream system, such as an enterprise resource planning system or a manufacturing execution system.

[0083] S12. According to the machining material type, obtain the recommended initial cutting speed and initial feed rate from the preset material database.

[0084] In this embodiment, the preset material database is a data set containing various common engineering materials and their recommended processing parameters. The initial cutting speed refers to the linear speed of the tool relative to the workpiece, and the initial feed rate refers to the displacement of the tool in the feed direction per revolution.

[0085] Specifically, the system will query the material database to match the input processing material type. These recommended values are based on a large amount of experimental data and engineering experience and can usually achieve a good balance between processing efficiency and tool life.

[0086] S13. Determine the initial cutting depth according to the processing time and processing accuracy requirements.

[0087] Among them, the initial cutting depth refers to the depth at which the tool cuts into the workpiece each time. Determining the initial cutting depth requires a trade-off between processing efficiency and processing quality. The shorter the processing time, the larger the cutting depth is required to improve processing efficiency; the higher the processing accuracy requirement, the smaller the cutting depth is required to ensure the surface quality.

[0088] S14. Determine the coolant flow rate based on the processing material type and processing accuracy requirements.

[0089] In this embodiment, the coolant flow rate refers to the volume of coolant flowing through the processing area per unit time. The main functions of the coolant are to reduce the cutting temperature, lubricate the contact surface between the tool and the workpiece, and remove chips. The coolant flow rate is determined by considering the thermal conductivity of the material, the processing accuracy requirements, and combining environmental factors.

[0090] S15. Correlate the initial cutting speed, initial feed rate, initial cutting depth, and coolant flow rate to obtain the overall processing parameter information.

[0091] In one embodiment, referring to Figure 3 , in step S20, obtain the workpiece geometric information, and according to the workpiece geometric information and the overall processing parameter information, obtain the partitioned processing parameters, specifically including:

[0092] S21. Divide the workpiece into several processing areas according to the workpiece geometric information.

[0093] S22. For each processing area, calculate the local processing difficulty coefficient according to the corresponding geometric features and relative positions.

[0094] In this embodiment, the local processing difficulty coefficient is a numerical index reflecting the complexity of processing in a specific area.

[0095] Specifically, the system uses a multi-factor scoring model to calculate the local machining difficulty coefficient, taking into account multiple factors such as surface complexity, material thickness variation, relative position, etc. Taking a turbine blade as an example, for the tip region, due to its thin thickness and large curvature, it may be assigned a higher difficulty coefficient.

[0096] S23. According to the local machining difficulty coefficient and the overall machining parameter information, calculate the local cutting speed, local feed rate, local cutting depth, and the corresponding local coolant flow rate for each region to form the zoned machining parameters.

[0097] Among them, the zoned machining parameters refer to a set of machining parameters optimized separately for each machining region, which are adjusted according to the local machining difficulty coefficient based on the overall machining parameter information.

[0098] Specifically, the system uses a series of weighted functions to calculate the zoned machining parameters. Taking the tip region of a turbine blade (assuming the difficulty coefficient is 0.9) as an example, the local cutting speed = initial cutting speed * (1 - difficulty coefficient * 0.5), etc.

[0099] In one embodiment, referring to Figure 4 , in step S40, obtain the zoned machining state detection information and calculate the tool sticking risk index, which specifically includes the following steps:

[0100] S41. Real-time collect the cutting force, temperature, and vibration data of the current machining region.

[0101] Among them, the cutting force refers to the resistance received by the tool during the machining process, usually divided into three components: tangential force, radial force, and axial force. The temperature refers to the temperature of the tool-workpiece contact region, which has an important impact on the plastic deformation of the material and tool wear. The vibration data reflects the dynamic stability of the system during the machining process, including amplitude and frequency information.

[0102] S42. Input the collected cutting force, temperature, and vibration data into a preset tool sticking risk model to obtain the basic tool sticking risk value.

[0103] In this embodiment, the tool sticking risk model is a pre-trained machine learning model used to evaluate the possibility of tool sticking in the current machining state. The basic tool sticking risk value is the preliminary risk assessment result output by the model, which is a numerical value between 0 and 1, where 0 indicates no risk and 1 indicates extremely high risk.

[0104] Specifically, the system uses a neural network model based on deep learning as the tool sticking risk model, which includes multiple convolutional layers and fully connected layers, and can effectively process time series data and extract features therefrom. The model inputs a data matrix containing multiple time steps, and each time step includes three components of cutting force, temperature value, and amplitude and frequency of vibration. By analyzing the time series features and mutual relationships of these data, a basic tool sticking risk value is output. The model is trained with a large amount of historical data, including normal machining data and known tool sticking event data, so as to learn the typical patterns before tool sticking occurs.

[0105] S43. Combine the local cutting speed, local feed rate, local cutting depth, and local coolant flow rate in the current machining area to correct the basic tool sticking risk value and obtain the final tool sticking risk index.

[0106] Among them, the final tool sticking risk index is a more accurate risk assessment result obtained by comprehensively considering the current real-time machining state and local machining parameters.

[0107] Specifically, the system uses a weighted correction function to adjust the basic tool sticking risk value, which includes multiple influencing factors, and each factor corresponds to a local machining parameter.

[0108] In one embodiment, referring to Figure 5 , in step S43, combine the local cutting speed, local feed rate, local cutting depth, and local coolant flow rate in the current machining area to correct the basic tool sticking risk value and obtain the final tool sticking risk index, which specifically includes the following steps:

[0109] S431. Obtain the local cutting speed, local feed rate, local cutting depth, and local coolant flow rate in the current machining area.

[0110] S432. According to the preset parameter influence model, calculate the influence factors of the local cutting speed, local feed rate, local cutting depth, and local coolant flow rate on the tool sticking risk respectively, and comprehensively obtain the overall parameter influence coefficient.

[0111] S433. Obtain the final tool sticking risk index according to the basic tool sticking risk value and the overall parameter influence coefficient.

[0112] In one embodiment, referring to Figure 6 , in step S50, if the tool sticking risk index exceeds the preset safety threshold, trigger a partition machining parameter adjustment instruction, which specifically includes the following steps:

[0113] S51. Determine the risk level according to the current tool sticking risk index, and obtain the corresponding initial adjustment information of the partition machining parameters based on the risk level.

[0114] S52. Within the preset maximum number of adjustments, gradually adjust the machining parameters according to the initial adjustment information and recalculate the tool sticking risk index until it drops below the preset warning threshold or the maximum number of adjustments is reached.

[0115] S53. Determine whether the tool sticking risk index drops below the preset warning threshold during the adjustment process.

[0116] If the tool sticking risk index drops below the preset warning threshold during the adjustment process, execute step S54.

[0117] S54. Immediately trigger the instruction to execute the current adjustment parameters and end the adjustment process.

[0118] If the maximum number of adjustments is reached, perform the following operations according to the final tool sticking risk index:

[0119] S55. Determine whether the final tool sticking risk index is higher than the preset mild risk threshold.

[0120] In the case where the final tool sticking risk index is higher than the warning threshold but lower than the preset mild risk threshold, execute step S56.

[0121] S56. Trigger the instruction to execute the final adjustment parameters and increase the monitoring frequency.

[0122] In the case where the final tool sticking risk index is higher than the mild risk threshold, execute step S57.

[0123] S57. Trigger a warning signal and request manual intervention.

[0124] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0125] In a second aspect, the present application provides a system for reducing the probability of tool sticking in numerical control machine tool machining. Below, in combination with the above method for reducing the probability of tool sticking in numerical control machine tool machining, the system for reducing the probability of tool sticking in numerical control machine tool machining of the present application will be described.

[0126] Referring to Figure 7 , a system for reducing the probability of tool sticking in numerical control machine tool machining includes:

[0127] An overall machining parameter information acquisition module, configured to acquire machining selection information, and according to the machining selection information, acquire overall machining parameter information, where the overall machining parameter information includes an initial cutting speed, an initial feed speed, an initial cutting depth, and a coolant flow rate;

[0128] The partitioned machining parameter acquisition module is used to acquire the geometric information of the workpiece, and based on the geometric information of the workpiece and the overall machining parameter information, acquire the partitioned machining parameters. Among them, the workpiece is divided into several machining areas, and the partitioned machining parameters include the local cutting speed, local feed rate, local cutting depth, and local coolant flow rate of each area;

[0129] The machining instruction trigger module is used to trigger machining instructions according to the partitioned machining parameters and the current machining area;

[0130] The tool sticking risk index calculation module is used to acquire the partitioned machining state detection information, calculate the tool sticking risk index, and compare the tool sticking risk index with a preset safety threshold;

[0131] The parameter adjustment instruction trigger module is used to trigger the partitioned machining parameter adjustment instruction if the tool sticking risk index exceeds the preset safety threshold.

[0132] In one embodiment, the overall machining parameter information acquisition module includes:

[0133] The machining information extraction unit is used to extract the machining material type, machining time, and machining accuracy requirements from the machining selection information;

[0134] The initial parameter acquisition unit is used to acquire the recommended initial cutting speed and initial feed rate from a preset material database according to the machining material type;

[0135] The cutting depth determination unit is used to determine the initial cutting depth according to the machining time and machining accuracy requirements;

[0136] The coolant flow rate determination unit is used to determine the coolant flow rate based on the machining material type and machining accuracy requirements;

[0137] The parameter association unit is used to associate the initial cutting speed, initial feed rate, initial cutting depth, and coolant flow rate to obtain the overall machining parameter information.

[0138] In one embodiment, the partitioned machining parameter acquisition module includes:

[0139] The area division unit is used to divide the workpiece into several machining areas according to the geometric information of the workpiece;

[0140] The difficulty coefficient calculation unit is used to calculate the local machining difficulty coefficient for each machining area according to the corresponding geometric features and relative positions;

[0141] The local parameter calculation unit is used to calculate the local cutting speed, local feed rate, local cutting depth, and corresponding local coolant flow rate of each area according to the local machining difficulty coefficient and the overall machining parameter information, and form the partitioned machining parameters.

[0142] In one embodiment, the sticking tool risk index calculation module includes:

[0143] a data acquisition unit configured to acquire in real time the cutting force, temperature, and vibration data of the current machining area;

[0144] a basic risk calculation unit configured to input the acquired cutting force, temperature, and vibration data into a preset sticking tool risk model to obtain a basic sticking tool risk value;

[0145] a risk correction unit configured to correct the basic sticking tool risk value in combination with the local cutting speed, local feed rate, local cutting depth, and local coolant flow rate of the current machining area, and obtain the final sticking tool risk index.

[0146] In one embodiment, the risk correction unit includes:

[0147] a local parameter acquisition sub-unit configured to acquire the local cutting speed, local feed rate, local cutting depth, and local coolant flow rate of the current machining area;

[0148] an influence factor calculation sub-unit configured to calculate, according to a preset parameter influence model, the influence factors of the local cutting speed, local feed rate, local cutting depth, and local coolant flow rate on the sticking tool risk respectively, and comprehensively obtain an overall parameter influence coefficient;

[0149] a final risk calculation sub-unit configured to obtain the final sticking tool risk index according to the basic sticking tool risk value and the overall parameter influence coefficient.

[0150] In one embodiment, the parameter adjustment instruction trigger module includes:

[0151] a risk level determination unit configured to determine the risk level according to the current sticking tool risk index, and obtain the initial adjustment information of the corresponding zoned machining parameters based on the risk level;

[0152] a parameter adjustment unit configured to gradually adjust the machining parameters according to the initial adjustment information within a preset maximum number of adjustments and recalculate the sticking tool risk index until it drops below a preset warning threshold or the maximum number of adjustments is reached;

[0153] an execution trigger unit configured to, if the sticking tool risk index drops below the preset warning threshold during the adjustment process, immediately trigger the instruction to execute the current adjusted parameters and end the adjustment process;

[0154] a risk response unit configured to, if the maximum number of adjustments is reached, perform the following operations according to the final sticking tool risk index:

[0155] In the case where the final tool sticking risk index is higher than the warning threshold but lower than the preset mild risk threshold, trigger an instruction to execute the final adjustment parameter and increase the monitoring frequency;

[0156] In the case where the final tool sticking risk index is higher than the mild risk threshold, trigger a warning signal and require manual intervention.

[0157] In one embodiment, the present application provides an electronic device, which may be a server, and its internal structure diagram may be as Figure 8 shown. The electronic device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the electronic device is used to store data. The network interface of the electronic device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it realizes a method for reducing the probability of tool sticking in numerical control machine tool processing.

[0158] Those skilled in the art can understand that Figure 8 the structure shown in

[0159] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the electronic device to which the solution of the present application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0160] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The above computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above various methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0161] The above are all preferred embodiments of the present application. The protection scope of the present application is not limited thereby. Therefore, all equivalent changes made according to the structure, shape, and principle of the present application should be covered within the protection scope of the present application.

Claims

1. A method for reducing the probability of tool sticking in CNC machine tool machining, characterized in that, The steps include: Acquiring processing selection information, and acquiring overall processing parameter information based on the processing selection information, wherein the overall processing parameter information includes an initial cutting speed, an initial feed speed, an initial cutting depth, and a coolant flow rate; Acquire workpiece geometric information, and acquire partitioned machining parameters based on the workpiece geometric information and the overall machining parameter information, wherein the workpiece is divided into a plurality of machining areas, and the partitioned machining parameters include a local cutting speed, a local feed speed, a local cutting depth, and a local coolant flow rate for each area; the step of acquiring the partitioned machining parameters comprises: dividing the workpiece into a plurality of machining areas based on the workpiece geometric information; calculating a local machining difficulty coefficient for each machining area based on corresponding geometric features and relative positions, the geometric features including surface complexity and material thickness variation; calculating a local cutting speed, a local feed speed, a local cutting depth, and a corresponding local coolant flow rate for each area based on the local machining difficulty coefficient and the overall machining parameter information, to form the partitioned machining parameters; triggering a processing instruction according to the partition processing parameters and the current processing area; Obtaining zoned machining state detection information, calculating a tool sticking risk index, and comparing the tool sticking risk index with a preset safety threshold; wherein the steps of obtaining zoned machining state detection information and calculating the tool sticking risk index include: collecting cutting force, temperature, and vibration data of the current machining area in real time; inputting the collected cutting force, temperature, and vibration data into a preset tool sticking risk model to obtain a basic tool sticking risk value; and correcting the basic tool sticking risk value based on the local cutting speed, local feed rate, local cutting depth, and local coolant flow rate of the current machining area to obtain a final tool sticking risk index; If the knife sticking risk index exceeds a preset safety threshold, a partition processing parameter adjustment instruction is triggered; wherein, the step of triggering the partition processing parameter adjustment instruction includes: determining a risk level according to the current knife sticking risk index, and obtaining corresponding initial adjustment information of the partition processing parameters based on the risk level; within a preset maximum adjustment number, gradually adjusting the processing parameters according to the initial adjustment information and recalculating the knife sticking risk index until it drops below a preset warning threshold or the maximum adjustment number is reached; if the knife sticking risk index drops below the preset warning threshold during the adjustment process, immediately triggering an instruction to execute the current adjustment parameter and ending the adjustment process; if the maximum adjustment number is reached, performing the following operations according to the final knife sticking risk index: if the final knife sticking risk index is higher than the warning threshold but lower than the preset mild risk threshold, triggering an instruction to execute the final adjustment parameter and increasing the monitoring frequency; if the final knife sticking risk index is higher than the mild risk threshold, triggering a warning signal and requiring manual intervention.

2. The method for reducing the probability of tool sticking in the machining of numerical control machine tools according to claim 1, wherein, Obtaining processing selection information, and obtaining overall processing parameter information based on the processing selection information, specifically includes the following steps: extracting the processing material type, processing time, and processing accuracy requirements from the processing selection information; According to the type of the processed material, a recommended initial cutting speed and an initial feed speed are obtained from a preset material database; Determine the initial cutting depth according to the machining time and the machining accuracy requirement; Determining a coolant flow rate based on the type of the processed material and the processing accuracy requirements; The initial cutting speed, the initial feed speed, the initial cutting depth and the coolant flow rate are correlated to obtain the overall processing parameter information.

3. The method for reducing the probability of tool sticking in CNC machine tool processing according to claim 1, characterized in that: The basic tool sticking risk value is corrected based on the local cutting speed, local feed speed, local cutting depth, and local coolant flow rate of the current machining area to obtain a final tool sticking risk index, which specifically includes the following steps: Obtain the local cutting speed, local feed rate, local cutting depth and local coolant flow rate of the current processing area; According to the preset parameter influence model, the influence factors of local cutting speed, local feed rate, local cutting depth and local coolant flow on the risk of tool sticking are calculated respectively, and the overall parameter influence coefficient is obtained comprehensively; A final knife sticking risk index is obtained according to the basic knife sticking risk value and the overall parameter influence coefficient.

4. A system for reducing the probability of tool sticking in CNC machine tool processing, characterized in that: include: an overall processing parameter information acquisition module, configured to acquire processing selection information, and acquire overall processing parameter information based on the processing selection information, wherein the overall processing parameter information includes an initial cutting speed, an initial feed speed, an initial cutting depth, and a coolant flow rate; A partition processing parameter acquisition module is used to acquire workpiece geometric information, and acquire partition processing parameters based on the workpiece geometric information and the overall processing parameter information, wherein the workpiece is divided into a plurality of processing areas, and the partition processing parameters include a local cutting speed, a local feed speed, a local cutting depth, and a local coolant flow rate of each area; the step of acquiring the partition processing parameters comprises: dividing the workpiece into a plurality of processing areas based on the workpiece geometric information; calculating a local processing difficulty coefficient for each processing area based on corresponding geometric features and relative positions; and calculating a local cutting speed, a local feed speed, a local cutting depth, and a corresponding local coolant flow rate of each area based on the local processing difficulty coefficient and the overall processing parameter information to form the partition processing parameters; A processing instruction triggering module, used for triggering a processing instruction according to the partition processing parameters and the current processing area; A tool sticking risk index calculation module is configured to obtain zoned machining state detection information, calculate a tool sticking risk index, and compare the tool sticking risk index with a preset safety threshold. The steps of obtaining zoned machining state detection information and calculating the tool sticking risk index include: collecting cutting force, temperature, and vibration data of the current machining area in real time; inputting the collected cutting force, temperature, and vibration data into a preset tool sticking risk model to obtain a basic tool sticking risk value; and modifying the basic tool sticking risk value based on the local cutting speed, local feed rate, local cutting depth, and local coolant flow rate of the current machining area to obtain a final tool sticking risk index. A parameter adjustment instruction trigger module, which is used to trigger a partitioned machining parameter adjustment instruction if the tool sticking risk index exceeds a preset safety threshold; wherein, the step of triggering the partitioned machining parameter adjustment instruction includes: determining a risk level according to the current tool sticking risk index, and based on the risk level, obtaining corresponding initial adjustment information of the partitioned machining parameters; within a preset maximum number of adjustments, gradually adjust the machining parameters according to the initial adjustment information and recalculate the tool sticking risk index until it drops below a preset warning threshold or reaches the maximum number of adjustments; if the tool sticking risk index drops below the preset warning threshold during the adjustment process, immediately trigger an instruction to execute the current adjusted parameters and end the adjustment process; if the maximum number of adjustments is reached, perform the following operations according to the final tool sticking risk index: in the case where the final tool sticking risk index is higher than the warning threshold but lower than a preset mild risk threshold, trigger an instruction to execute the final adjusted parameters and increase the monitoring frequency; in the case where the final tool sticking risk index is higher than the mild risk threshold, trigger a warning signal and request manual intervention.

5. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the method for reducing the probability of tool sticking in numerical control machine tool machining according to any one of claims 1-3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for reducing the probability of tool sticking in numerical control machine tool machining according to any one of claims 1-3.

Images