Low-Temperature Machining Methods Based on Material Removal Mechanism Control and Intelligent Machine Tools

Abstract

This invention discloses a low-temperature machining method and intelligent machine tool based on material removal mechanism control, relating to the field of machine tool processing. The method includes: acquiring cutting force and vibration signals during the cutting process; preprocessing the cutting force and vibration signals to obtain key feature values; acquiring a preset plastic-brittle transition critical model and extracting the corresponding critical feature thresholds for the material; comparing the key feature values ​​with the critical feature thresholds, calculating the plasticity membership degree of each key feature value, and weighted calculating the comprehensive plasticity membership degree to identify the material removal mechanism; and adaptively adjusting the cutting strategy based on the state indicators output by the material removal mechanism. This invention can identify the material removal mechanism during the cutting process online and adaptively adjust the cutting parameters and liquid nitrogen cooling parameters to ensure that the machining process remains stable within the range dominated by plastic material removal, thereby achieving high-efficiency and high-quality machining of difficult-to-machine materials.

Description

Technical Field

[0001] This invention relates to the field of machine tool processing, and in particular to a low-temperature cutting process based on material removal mechanism control and an intelligent machine tool. Background Technology

[0002] With the development of aerospace, precision instruments, and other fields, the application of difficult-to-machine materials such as titanium alloys, high-temperature alloys, and engineering ceramics is increasing. These materials typically have characteristics such as high strength, high hardness, and low thermal conductivity, which can easily lead to tool wear and reduced machining efficiency in traditional cutting processes. Cryogenic cutting technology is an effective means of machining difficult-to-machine materials, which can significantly reduce cutting temperature and increase cutting speed. However, excessive low-temperature cooling can reduce the plasticity of the workpiece material, making it more prone to brittle fracture and hindering the achievement of a smooth surface.

[0003] Existing machine tools for cryogenic cutting typically include a machine body, CNC system, cryogenic cooling system, and basic signal detection elements. The liquid nitrogen injection rate is usually a pre-set fixed value and cannot be dynamically optimized according to the real-time status during the cutting process, easily leading to insufficient or excessive cooling. Some cryogenic cutting machine tools correlate cutting parameters with cooling parameters during the control process, but this is based solely on feedback from surface physical quantities such as cutting temperature and tool wear, without addressing the material removal mechanism. Therefore, they cannot achieve adaptive parameter matching and still cannot avoid problems such as insufficient or excessive cooling and unstable machining quality. Summary of the Invention

[0004] To address the shortcomings of existing technologies, the purpose of this invention is to provide a cryogenic machining method and intelligent machine tool based on material removal mechanism control. This method can identify the material removal mechanism during the cutting process online and adaptively adjust the cutting parameters and liquid nitrogen cooling parameters to ensure that the machining process remains stable within the range dominated by plastic material removal, thereby achieving high-efficiency and high-quality machining of difficult-to-machine materials.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solution:

[0006] In a first aspect, embodiments of the present invention provide a low-temperature cutting method based on material removal mechanism control, comprising:

[0007] Acquire cutting force and vibration signals during the cutting process; preprocess the cutting force and vibration signals to obtain key feature values;

[0008] Obtain the preset plastic-brittle transition critical model and extract the critical feature thresholds of the corresponding materials; compare the key feature values ​​with the critical feature thresholds, calculate the plastic membership degree of each key feature value, and calculate the weighted comprehensive plastic membership degree to determine the material removal mechanism;

[0009] Based on the state indicators output by the material removal mechanism, the cutting process strategy is adaptively adjusted.

[0010] As a further implementation, the key characteristic values ​​include the mean cutting force, the peak vibration acceleration, and the coefficient of variation of the cutting force.

[0011] As a further implementation, the pre-defined critical model for the plastic-brittle transition is constructed in advance through the following steps:

[0012] A multi-factor orthogonal experiment was designed with cutting speed, feed rate, and liquid nitrogen injection rate as variables.

[0013] Cutting force and vibration signals were collected from different test groups, and labels were added for each test group corresponding to the plasticity removal, brittleness removal, and critical states of plastic-brittle transition.

[0014] Using cutting parameters and cooling parameters as input variables, and the critical signal characteristics of the plastic-brittle transition as output variables, a critical model for the plastic-brittle transition is established through data fitting.

[0015] As a further implementation, the data fitting includes:

[0016] For large sample data, a backpropagation neural network is used for fitting, while for small sample data, a support vector machine algorithm is used for data fitting.

[0017] As a further implementation, plasticity retention is used as a state index. When the state index is less than a first threshold, it indicates a state of brittle removal; when the state index is greater than the first threshold, it indicates a state of plastic removal; when the state index is greater than or equal to a second threshold, it indicates an ideal state of plastic removal; when the state index is between the first and second thresholds, it indicates a state of plastic removal but with slight deviation.

[0018] Wherein, the first threshold is less than the second threshold.

[0019] As a further implementation, the control strategy for the brittle removal state includes:

[0020] When the status index is less than the first threshold, reduce the liquid nitrogen injection volume, reduce the feed rate, or increase the cutting speed within the allowable range of tool wear; until the status index rises above the first threshold and remains stable for a preset time.

[0021] As a further implementation, the strategy for controlling the plastic removal state includes:

[0022] When the status indicator is greater than or equal to the set safety threshold, the feed rate is increased first; if the feed rate reaches a set multiple of the initial feed rate, the cutting rate is increased.

[0023] As a further implementation, when the status index is greater than or equal to the second threshold and the tool wear is within the set allowable range, it is determined that there is room for efficiency optimization.

[0024] As a further implementation, the control constraint condition for the plastic removal state is as follows:

[0025] The adjusted status indicator remains greater than or equal to the set value; the set value is less than the second threshold and greater than the first threshold.

[0026] Secondly, embodiments of the present invention also provide a low-temperature cutting intelligent machine tool based on material removal mechanism control, including a machine tool body, wherein the machine tool body is equipped with a signal detection module and an intelligent control unit, and the intelligent control unit includes a signal preprocessing module, a material cutting database, a material removal mechanism discrimination module and an adaptive control decision module;

[0027] The signal detection module is used to collect cutting force signals and vibration signals during the cutting process; the signal preprocessing module is used to preprocess the cutting force signals and vibration signals to obtain key feature values.

[0028] The material cutting database is used to obtain a preset plastic-brittle transition critical model and extract the critical feature thresholds of the corresponding materials; the material removal mechanism discrimination module is used to compare the key feature values ​​with the critical feature thresholds, calculate the plastic membership degree of each key feature value, and calculate the weighted comprehensive plastic membership degree to discriminate the material removal mechanism.

[0029] The adaptive control decision module is used to adaptively adjust the cutting strategy based on the state indicators output by the material removal mechanism.

[0030] The beneficial effects of this invention are as follows:

[0031] (1) This invention collects cutting force signals and vibration signals during the cutting process in real time, extracts key feature values, obtains a preset critical model for plastic-brittle transition, extracts the critical feature threshold of the corresponding material, and calculates the comprehensive plasticity membership degree by weighting, determines the material removal mechanism, and outputs state indicators; based on the state indicators, it adaptively adjusts the cutting parameters and liquid nitrogen injection amount; forms a closed loop of "perception-discrimination-decision-execution" to maintain the plasticity removal state.

[0032] (2) The present invention uses plasticity retention as a state index. The control strategy for brittle removal state is as follows: when the state index is less than the first threshold, reduce the amount of liquid nitrogen injection, reduce the feed rate or moderately increase the cutting rate within the allowable range of tool wear; until the state index is raised to above the first threshold and remains stable within a preset time; the control strategy for plastic removal state is as follows: prioritize increasing the feed rate; if the feed rate reaches a set multiple of the initial feed rate, then increase the cutting rate, and the control constraint condition for plastic removal state is: the adjusted state index remains greater than or equal to the set value; thereby achieving automatic optimization of cutting parameters and improvement of material removal rate under the premise of ensuring plastic removal. Attached Figure Description

[0033] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0034] Figure 1 This is a flowchart of a low-temperature cutting process according to one or more embodiments of the present invention;

[0035] Figure 2 This is a flowchart illustrating the specific steps of a low-temperature cutting process according to one or more embodiments of the present invention;

[0036] Figure 3 This is a schematic diagram of the intelligent machine tool structure according to one or more embodiments of the present invention;

[0037] Figure 4 This is a block diagram of the intelligent control unit structure according to one or more embodiments of the present invention.

[0038] The components include: 1. Bed, 2. Three-jaw chuck, 3. Spindle, 4. Turret, 5. Tank, 6. Conveying pipe, 7. Nozzle, 8. Flow control valve, 9. Flow meter, 10. Pressure gauge, 11. Force gauge, 12. Accelerometer, and 13. CNC system. Detailed Implementation

[0039] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0040] Example 1:

[0041] Existing technologies rely on surface physical quantity feedback such as cutting temperature and tool wear, without delving into the core logic of material removal mechanisms, resulting in a lack of targeted coordination. Furthermore, there is a strong nonlinear coupling relationship between the plastic-brittle transition of difficult-to-machine materials and cutting and cooling parameters. This embodiment provides a low-temperature machining method based on material removal mechanism control, achieving adaptive parameter matching by establishing a dynamic correlation model. Figure 1 As shown, it includes:

[0042] Acquire cutting force and vibration signals during the cutting process; preprocess the cutting force and vibration signals to obtain key feature values;

[0043] Obtain the preset plastic-brittle transition critical model and extract the critical feature thresholds of the corresponding materials; compare the key feature values ​​with the critical feature thresholds, calculate the plastic membership degree of each key feature value, and calculate the weighted comprehensive plastic membership degree to determine the material removal mechanism;

[0044] Based on the state indicators output by the material removal mechanism, the cutting process strategy is adaptively adjusted.

[0045] Specifically, such as Figure 2 As shown, the low-temperature cutting method in this embodiment includes the following steps:

[0046] S1: Start processing, system initialization, call the material's critical model for plastic-brittle transition.

[0047] S2: Real-time acquisition of cutting force and vibration signals.

[0048] S3: Process the signal, extract features, and determine the material removal mechanism.

[0049] The cutting force and vibration signals are filtered and noise-reduced, and key feature values ​​are extracted, including the mean cutting force, peak vibration acceleration, and coefficient of variation of cutting force. This is because the mean cutting force reflects the cutting load and the plasticity of the material, the peak vibration acceleration reflects the impact degree and the risk of surface damage, and the coefficient of variation of cutting force reflects the processing stability and mechanism fluctuation. These key features can reflect the processing state from different dimensions and provide a basis for the discrimination of plastic-brittle removal mechanism.

[0050] In this embodiment, the extraction process of the mean cutting force is as follows: From the denoised cutting force time-domain signal, a continuous data segment of the stable cutting stage is selected, and the mean cutting force of the data segment is calculated using the arithmetic mean method. The extraction process of the peak vibration acceleration is as follows: The denoised vibration time-domain signal is divided into multiple data segments according to a fixed time window. For each data segment, the absolute acceleration values ​​of all sampling points are traversed, and the maximum absolute value of each segment is selected, which is the peak vibration acceleration of that segment. The extraction process of the coefficient of variation of cutting force is as follows: Based on the cutting force data of the stable segment obtained during the extraction of the mean cutting force, the standard deviation of the cutting force of the data segment is first calculated. The coefficient of variation of cutting force is the ratio of the standard deviation to the mean.

[0051] Furthermore, the pre-defined critical model for the plastic-brittle transition is constructed in advance through the following steps:

[0052] S301: Collect test data: Select the target difficult-to-machine material (such as titanium alloy, high temperature alloy, etc.), design a multi-factor orthogonal experiment, where the variables include cutting speed, feed rate, liquid nitrogen injection rate, and other parameters are fixed.

[0053] S302: Data preprocessing: Collect cutting force signals and vibration signals from different test groups, and simultaneously use metallographic analysis to observe the degree of plastic deformation on the machined surface and whether there are microcracks. Label each test group with labels for plastic removal, brittle removal, and critical state of plastic-brittle transition.

[0054] S303: Model Fitting: Using cutting parameters and cooling parameters as input variables, and the critical signal characteristics of the plastic-brittle transition (such as the average cutting force threshold and the peak vibration acceleration) as output variables, a BP neural network algorithm is used for data fitting for large sample data and small sample data, and a support vector machine algorithm is used for data fitting for small sample data to establish a multivariate nonlinear mapping model, namely the critical model of plastic-brittle transition.

[0055] Since cutting parameters and cooling parameters are key parameters that can be actively adjusted during low-temperature cutting, directly determining the material removal mode (plastic / brittle), this embodiment selects them as input variables. The critical signal characteristics of the plastic-brittle transition are a direct quantitative manifestation of the processing state, which can objectively and in real time reflect the change in the material removal mechanism, and has a clear causal relationship with the input variables.

[0056] It should be noted that the specific amount of data included in large sample data and small sample data is determined according to actual requirements.

[0057] S304: Verification and Optimization: For parameter combinations not covered by orthogonal experiments, verify the model accuracy through additional validation experiments. If the deviation between the predicted results and the actual processing conditions exceeds 5%, supplementary experimental data are used to retrain the model until the deviation is ≤3%. Simultaneously, the model parameters are corrected using the material physics model. The optimized models are stored according to material grades.

[0058] Furthermore, the process for determining the material removal mechanism includes:

[0059] S311: Based on the workpiece material grade, call the corresponding plastic-brittle transition critical model to extract the critical characteristic threshold of the material.

[0060] In this embodiment, the workpiece material grade is first input, and the intelligent control unit parses the input information. The parsed core grade is then transmitted to the index module. The index module searches for the corresponding model storage path in the "Material Grade-Model Path" index table based on the grade, and simultaneously obtains the basic information of the model. The database loads the corresponding plastic-brittle transition critical model based on the matched path.

[0061] Since the critical feature threshold changes with the cutting parameters, it is necessary to dynamically extract the threshold based on the current actual cutting parameters: First, obtain the current cutting parameters, input the current cutting parameters into the loaded plastic-brittle transition critical model, and calculate the plastic-brittle transition critical feature threshold under this parameter combination through internal algorithms (such as forward propagation of BP neural network and decision function of support vector machine).

[0062] S312: Using a fuzzy logic algorithm, the real-time extracted feature values ​​are compared with the critical threshold to calculate the plastic membership degree of each feature. The plastic membership degree ranges from 0 to 1, with the closer to 1 indicating that it is more consistent with the plastic removal feature.

[0063] S313: Calculate the weighted comprehensive plasticity membership degree and determine the material removal mechanism based on the comprehensive plasticity membership degree.

[0064] S4: Determine if it is plastic removal;

[0065] If so, proceed to S5: determine if there is room for parameter optimization; if so, fine-tune the parameters; otherwise, maintain the parameters.

[0066] If not, proceed to S6: Adjust the cutting speed, feed rate, and liquid nitrogen injection amount in a coordinated manner based on the degree of brittleness.

[0067] Return to S2 to form a closed loop.

[0068] In this embodiment, the state index characterizes the degree of deviation between the current state and the ideal plastic state. The plasticity retention degree S is used as the state index, and its value ranges from 0 to 100.

[0069] S = Comprehensive plasticity membership degree × 100, where a state index less than the first threshold indicates brittle removal; a state index greater than the first threshold indicates plastic removal; a state index greater than or equal to the second threshold indicates ideal plastic removal; a state index between the first and second thresholds indicates plastic removal but with slight deviation; and the first threshold is less than the second threshold.

[0070] In this embodiment, the first threshold is 60 and the second threshold is 85. That is, S≥85 represents the ideal plastic removal state; 60≤S<85 represents the plastic removal state with slight deviation; and S<60 represents the brittle removal state.

[0071] Further strategies for regulating the brittle removal state include:

[0072] Priority 1: Reduce the amount of liquid nitrogen injected (the smaller the value of S, the greater the adjustment range), with the goal of increasing the local temperature of the workpiece and restoring the plasticity of the material.

[0073] Priority 2: Reduce feed rate or increase cutting speed to avoid excessive cutting force or strain rate leading to brittle fracture.

[0074] The status indicator S is collected every 0.5 seconds. If the adjustment improves S by less than 10%, the above adjustment is repeated. If S improves to 60 or above, the adjustment is paused and the current parameter is maintained for 3 seconds before entering dynamic optimization.

[0075] This embodiment, by controlling the brittle removal state, can quickly shift the material removal mechanism to plastic dominance, reduce the generation of microcracks on the processed surface, lower surface roughness, and improve surface quality.

[0076] Furthermore, strategies for controlling the plastic removal state include:

[0077] Optimization judgment criteria: If S≥85 and the tool wear is within the allowable range, it is determined that there is room for efficiency optimization.

[0078] Parameter adjustment: Prioritize increasing the feed rate; if the feed rate reaches a set multiple of the initial feed rate, then increase the cutting speed. In this embodiment, when the feed rate reaches twice the initial feed rate, the cutting speed is increased.

[0079] Constraints: After adjustment, S must be kept at ≥80. If S < 80, immediately revert to the previous parameter combination.

[0080] This embodiment improves the material removal rate and optimizes processing efficiency by controlling the plastic removal state while ensuring surface integrity (no brittle damage).

[0081] This embodiment achieves online material removal mechanism discrimination through real-time detection and feature extraction of cutting force and vibration signals; and uses algorithms such as fuzzy logic, support vector machine or deep learning neural network to output material removal mechanism status indicators in real time based on the built-in material cutting database; according to the status indicators, cutting parameters (cutting speed, feed rate) and cooling parameters (liquid nitrogen injection rate) are adjusted in a coordinated manner to maintain the plastic removal state, forming an intelligent closed loop of "perception-discrimination-decision-execution" to ensure a stable processing process.

[0082] This embodiment actively maintains the machining process within the plastic removal zone through real-time sensing and closed-loop control, fundamentally avoiding surface microcracks and subsurface damage caused by brittle removal, thus improving the surface integrity and service performance of the machined parts; and automatically optimizes cutting parameters while ensuring plastic removal; and intelligently adjusts the amount of liquid nitrogen according to the real-time needs of the machining state, avoiding waste caused by blind spraying.

[0083] Example 2:

[0084] This embodiment provides a low-temperature cutting intelligent machine tool based on material removal mechanism control, such as... Figure 3 and Figure 4 As shown, the system includes a machine tool body, a signal detection module, and an intelligent control unit. The machine tool body includes a bed 1 and a three-jaw chuck 2, a spindle 3, a tool turret 4, a CNC system 13, etc., mounted on the bed 1. A cryogenic cooling system is installed on one side of the bed 1. The cryogenic cooling system includes a tank 5, which is connected to a nozzle 7 via a delivery pipe 6. The nozzle 7 is positioned corresponding to the tool turret 4. The delivery pipe 6 is equipped with a flow control valve 8, a flow meter 9, a pressure gauge 10, and other components for spraying liquid nitrogen into the contact area between the tool and the workpiece.

[0085] The signal detection module includes a force gauge 11 and an accelerometer 12. The force gauge 11 is mounted on the underside of the fixture or turret 4 and is used to measure the three-dimensional cutting force. F x , F y , F z Accelerometer 12 is mounted on turret 4 or spindle box to measure vibration signals.

[0086] The intelligent control unit is used to receive the detection data from the signal detection module and output control commands to the CNC system 13 and flow control valve 8 of the machine tool to realize the adjustment of liquid nitrogen injection volume.

[0087] The intelligent control unit includes a memory and a processor. The memory stores computer program instructions, and the processor is responsible for executing the computer program instructions to implement the steps of the cryogenic cutting process based on material removal mechanism control in Example 1.

[0088] In this embodiment, the intelligent control unit includes a signal preprocessing module, a material cutting database, a material removal mechanism discrimination module, and an adaptive control decision module. The signal preprocessing module filters and reduces noise in the cutting force and vibration signals, and extracts key features. The material cutting database stores critical models of the plastic-brittle transition for various difficult-to-machine materials under different cutting parameters and cooling conditions. These models are constructed by fitting extensive preliminary process test data or by calculation based on material physics models.

[0089] The material removal mechanism discrimination module is used to determine the material removal mechanism in real time based on the extracted signal features, call the database model, and output status indicators. The adaptive control decision module is used to adaptively adjust the cutting strategy based on the status indicators output by the material removal mechanism. The intelligent control unit also includes a control signal output module, which is used to send control commands to the CNC system 13 and the flow control valve 8.

[0090] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A low-temperature cutting method based on material removal mechanism control, characterized by, The method comprises the following steps: Collecting cutting force signals and vibration signals during the cutting process; Preprocessing the cutting force signals and vibration signals to obtain key feature values; Obtaining a preset plastic-brittle transition critical model and extracting critical feature thresholds corresponding to the material; Comparing the key feature values with the critical feature thresholds, calculating the plastic membership degrees of each key feature value, and weightedly calculating the comprehensive plastic membership degree to determine the material removal mechanism; The preset plastic-brittle transition critical model is constructed by the following steps: Designing a multi-factor orthogonal test with cutting speed, feed rate, and liquid nitrogen injection amount as variables; Collecting cutting force signals and vibration signals of different test groups, and labeling the plastic removal, brittle removal, and plastic-brittle transition critical state labels corresponding to each test group; Taking the cutting parameters and cooling parameters as input variables and the critical signal features of plastic-brittle transition as output variables, a plastic-brittle transition critical model is established by data fitting, wherein the critical signal features are the critical feature thresholds corresponding to the material; the data fitting includes: for large sample data, BP neural network is used for fitting, and for small sample data, support vector machine algorithm is used for data fitting; Adaptive control of the cutting processing strategy based on the state indicators output by the material removal mechanism; Taking the plastic retention degree as the state indicator, when the state indicator is less than the first threshold, it indicates the brittle removal state; when the state indicator is greater than the first threshold, it indicates the plastic removal state; The control strategy of the brittle removal state includes: when the state indicator is less than the first threshold, reducing the liquid nitrogen injection amount, reducing the feed speed or increasing the cutting speed within the allowable range of tool wear; until the state indicator is improved to above the first threshold and remains stable within a preset time; The control strategy of the plastic removal state includes: when the state indicator is greater than or equal to the set safety threshold, the feed speed is preferentially increased; if the feed speed reaches the set multiple of the initial feed speed, the cutting speed is increased.

2. The material-removal-mechanism-based low-temperature cutting process of claim 1, wherein, The key feature values include cutting force mean value, vibration acceleration peak value, and cutting force variation coefficient.

3. The material removal mechanism-based low-temperature cutting process of claim 1, wherein Further comprising: taking the plastic retention degree as the state indicator, when the state indicator is greater than or equal to the second threshold, it indicates the ideal plastic removal state; When the state indicator is between the first threshold and the second threshold, it indicates that the plastic removal exists a slight deviation state; Wherein, the first threshold is less than the second threshold.

4. The material-removal-mechanism-based low-temperature cutting process of claim 1, wherein, When the state indicator is greater than or equal to the second threshold and the tool wear amount is within the set allowable range, it is determined that there is an efficiency optimization space.

5. The material-removal-mechanism-based low-temperature cutting process of claim 4, wherein, The control constraint condition of the plastic removal state is: The adjusted state indicator remains greater than or equal to the set value; the set value is less than the second threshold and greater than the first threshold.

6. An intelligent machine tool for low-temperature cutting machining based on material removal mechanism control for implementing the method of low-temperature cutting machining based on material removal mechanism control according to any one of claims 1 to 5, characterized in that, The machine tool body is provided with a signal detection module, an intelligent control unit, the intelligent control unit includes a signal preprocessing module, a material cutting database, a material removal mechanism determination module, and an adaptive control decision module; The signal detection module is used to collect cutting force signals and vibration signals during the cutting process; the signal preprocessing module is used to preprocess the cutting force signals and vibration signals to obtain key feature values; The material cutting database is used to obtain a preset plastic-brittle transition critical model, and critical characteristic thresholds of a corresponding material are extracted; The material removal mechanism discrimination module is used to compare the key characteristic values with the critical characteristic thresholds, calculate plastic membership degrees of the key characteristic values, and calculate a comprehensive plastic membership degree by weighting, so as to discriminate the material removal mechanism; the preset plastic-brittle transition critical model is constructed by the following steps: Taking a cutting speed, a feed rate and a liquid nitrogen spraying amount as variables, a multi-factor orthogonal test is designed; Cutting force signals and vibration signals of different test groups are collected, and plastic removal, brittle removal and plastic-brittle transition critical state labels corresponding to each test group are labeled; Taking cutting parameters and cooling parameters as input variables and taking critical signal characteristics of plastic-brittle transition as output variables, a plastic-brittle transition critical model is established by data fitting, and the critical signal characteristics are critical characteristic thresholds of a corresponding material; the data fitting includes: for large sample data, BP neural network is used for fitting, and for small sample data, a support vector machine algorithm is used for data fitting; The adaptive regulation and decision module is used to adaptively adjust a cutting processing strategy based on a state index output by the material removal mechanism.

Images