Metal material high-precision numerical control machining system and method based on intelligent adaptive control

Abstract

The application discloses a metal material high-precision numerical control machining system and method based on intelligent adaptive control, relates to the technical field of metal material processing, and collects historical metal material cutting process data, constructs a metal chip diffusion model, obtains metal chip diffusion conditions, evaluates the aging degree of a moving part, simultaneously evaluates the adhesion and wear effect of metal chip diffusion on the moving part, evaluates the damage risk of metal chip on the moving part based on the aging degree of the moving part and the adhesion and wear effect of metal chip diffusion on the moving part, dynamically adjusts the negative pressure parameter of a recovery air bellow based on the damage risk evaluation result of metal chip on the moving part and the chip diffusion condition, predicts the chip diffusion condition under different cutting conditions, combines the damage of diffused chips on moving parts with different aging degrees, obtains accurate recovery risk adjustment parameters, and realizes accurate control of negative pressure adjustment.

Description

Technical Field

[0001] This invention relates to the field of metal material processing technology, and in particular to a high-precision CNC machining system and method for metal materials based on intelligent adaptive control. Background Technology

[0002] In the current industrial field, the management of chips and protection of machine tools generated during metal cutting processes mostly adopt a fixed negative pressure strategy or simply adjust based on chip concentration. This makes it difficult to capture the chip diffusion pattern under complex cutting conditions, resulting in a large deviation between the predicted and actual chip distribution. This fails to provide an accurate basis for negative pressure adjustment. Furthermore, fixed negative pressure or linear adjustment based solely on chip concentration does not take into account the spatial distribution characteristics of component damage risks, which can easily lead to insufficient protection in high-risk areas or energy waste in low-risk areas.

[0003] To address the aforementioned problems, this invention provides a high-precision CNC machining system and method for metal materials based on intelligent adaptive control. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a high-precision CNC machining system and method for metal materials based on intelligent adaptive control. This invention predicts the chip diffusion under different cutting conditions, and then, combined with the damage of the diffused chips to moving parts with different aging degrees, obtains accurate risk adjustment parameters for recycling, thereby achieving precise control of negative pressure regulation.

[0005] To achieve the above objectives, this invention provides a high-precision CNC machining method for metallic materials based on intelligent adaptive control, comprising the following specific steps:

[0006] Step 1: Collect historical data on metal material cutting processes, including cutting data, metal chip data, and diffusion data, and construct a metal chip diffusion model;

[0007] Step 2: Monitor metal material cutting data in real time and obtain metal debris diffusion information based on the metal debris diffusion model;

[0008] Step 3: Collect monitoring data of moving parts of CNC machine tools, assess the aging degree of moving parts, and at the same time assess the adhesion and wear effect of metal debris diffusion on moving parts;

[0009] Step 4: Assess the risk of damage to moving parts from metal debris based on the aging degree of the moving parts, the adhesion of metal debris to the moving parts, and the wear effect;

[0010] Step 5: Based on the damage risk assessment results of metal debris to moving parts and the debris diffusion situation, dynamically adjust the negative pressure parameters of the recovery bellows.

[0011] Preferably, step one includes the following specific steps:

[0012] Step 11: Use a high-speed camera to aim at the cutting area and capture the initial diffusion trajectory and shape of the metal chips. Place a numbered metal chip collection tray at the bottom of each grid in the metal processing area and collect historical metal material cutting process data. The historical metal material cutting process data includes cutting data, metal chip data, and diffusion data. The cutting data includes cutting speed, feed rate, depth of cut, coolant pressure, and coolant flow rate. The metal chip data includes chip temperature, equivalent chip diameter, chip hardness, and chip shape factor. The diffusion data includes initial chip velocity and spatial distribution density.

[0013] Step 12: Divide the historical metal material cutting process dataset into an 80% training set and a 20% test set. The training set is used to learn the mapping function T from M to N, and the test set is used to evaluate the ability of the metal debris diffusion model to predict metal debris diffusion data after training. The cutting data is used as the input vector M. Where sp is the cutting speed, fr is the feed rate, dp is the depth of cut, pr is the coolant pressure, tr is the coolant flow rate, and T is the transpose sign. The metal processing area is divided into i×j grids, and the output vector N is obtained based on the chip density D of each grid. The random forest model consists of multiple independent decision trees. Composition, define the number U of decision trees, for each tree U distinct subsets are created from the training set by sampling with replacement. A complete decision tree is trained on each subset to learn the mapping. Each node randomly selects some features during splitting, and the final prediction result is the average of all tree prediction results. For a set of splitting data... Its predicted output The goal of the training process is to adjust the structure of each tree to minimize the loss function on the training set. The mean square error is used for evaluation. The test set is input into the trained metal debris diffusion model to obtain the predicted output. The root mean square error is used to quantify the difference between the predicted output and the actual value. The root mean square error represents the average error between the debris density predicted by the metal debris diffusion model and the actual density of each grid.

[0014] Preferably, step two includes the following specific steps:

[0015] Step 21: Monitor the metal material cutting data in real time, and input the metal material cutting data as the input vector into the metal debris diffusion model. Each tree in the metal debris diffusion model outputs the corresponding prediction vector, and the final prediction result is the average of the prediction results of all trees.

[0016] Step 22: Reshape the prediction vectors according to the metal processing area grid, and map each prediction vector to the metal processing area grid to obtain a two-dimensional matrix. This two-dimensional matrix is ​​a visualization of the metal debris diffusion prediction map. Each value in the map represents the predicted debris density at the corresponding spatial location.

[0017] Preferably, step three includes the following specific steps:

[0018] Step 31: Collect monitoring data of moving parts of CNC machine tool, including vibration acceleration, operating temperature, operating noise and cumulative running time;

[0019] Step 32: Obtain abnormal vibration acceleration values ​​based on the ratio of vibration acceleration to standard vibration acceleration; obtain abnormal operating temperature values ​​based on the ratio of operating temperature to standard operating temperature; obtain abnormal noise values ​​based on the ratio of operating noise to standard operating noise; obtain abnormal operating time values ​​based on the ratio of cumulative operating time to standard usage time; and obtain the aging assessment value of moving parts by weighted summation of abnormal vibration acceleration values, abnormal operating temperature values, abnormal noise values, and abnormal operating time values.

[0020] Step 33: Obtain the influence value of debris temperature based on the ratio of debris temperature to the standard melting point of moving part material; obtain the adhesion risk coefficient of metal debris diffusion to moving part by weighted summation of debris temperature influence value and debris shape coefficient.

[0021] Step 34: Obtain the influence value of chip hardness based on the ratio of chip hardness to moving part surface hardness; obtain the influence value of chip diameter based on the ratio of chip equivalent diameter to critical wear size; obtain the influence value of chip velocity based on the ratio of chip initial velocity to critical wear velocity; and obtain the wear risk coefficient of metal chip diffusion on moving parts by weighted summation of chip hardness influence value, chip diameter influence value and chip velocity influence value.

[0022] Preferably, step four includes the following specific steps:

[0023] Step 41: Obtain the influence coefficient of metal debris diffusion on moving parts by weighted summation of adhesion risk coefficient and wear risk coefficient; obtain the debris threat assessment value based on the debris threat assessment value calculation formula, which is: ,in, This is the debris threat assessment value. Let be the debris density at coordinates (x, y). This is the coefficient representing the influence of metal debris diffusion on moving parts. The set of spatial coordinates occupied by the moving parts;

[0024] Step 42: Obtain the damage risk value of metal debris to moving parts based on the product of the debris threat assessment value and the moving part aging assessment value.

[0025] Preferably, step five includes the following specific steps:

[0026] Step 51: Calculate the debris density risk assessment value based on the debris density risk assessment value calculation formula, wherein the debris density risk assessment value calculation formula is: ,in, Let be the debris density risk assessment value for the i-th air intake. Let be the debris density in the upwind direction of the i-th air intake. For risk sensitivity coefficient, The damage risk value of the moving parts to the metal debris corresponding to the i-th air intake is denoted as .

[0027] Step 52: Calculate the negative pressure distribution value of each air intake of the recovery air box based on the negative pressure distribution calculation formula, wherein the negative pressure distribution calculation formula is: ,in, Let be the negative pressure distribution value for the i-th air intake. To recover the base negative pressure of the bellows, that is, the baseline suction force when there is no risk. The average of the debris density risk assessment values ​​for all air intakes. To assign sensitivity coefficients.

[0028] This invention also provides a high-precision CNC machining system for metal materials based on intelligent adaptive control, comprising:

[0029] The diffusion model construction module is used to collect historical data on metal material cutting processes, including cutting data, metal debris data, and diffusion data, and to construct a metal debris diffusion model.

[0030] The chip diffusion prediction module is used to monitor metal material cutting data in real time and obtain the metal chip diffusion situation based on the metal chip diffusion model.

[0031] The moving parts evaluation module is used to collect monitoring data of moving parts of CNC machine tools, evaluate the aging degree of moving parts, and evaluate the adhesion and wear effect of metal debris diffusion on moving parts.

[0032] The damage risk assessment module is used to assess the damage risk of metal debris to moving parts based on the aging degree of moving parts, the adhesion of metal debris to moving parts, and the wear effect.

[0033] The negative pressure parameter adjustment module is used to dynamically adjust the negative pressure parameter of the recovery air box based on the damage risk assessment results of metal debris to moving parts and the debris diffusion situation.

[0034] The present invention also provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes the above-described high-precision CNC machining method for metal materials based on intelligent adaptive control by calling the computer program stored in the memory.

[0035] The present invention also provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the above-described method for high-precision CNC machining of metal materials based on intelligent adaptive control.

[0036] Compared with the prior art, the beneficial effects of the present invention are:

[0037] This invention collects historical data on metal material cutting processes, including cutting data, metal chip data, and diffusion data, constructs a metal chip diffusion model, monitors metal material cutting data in real time, obtains metal chip diffusion information based on the metal chip diffusion model, collects monitoring data of CNC machine tool moving parts, assesses the aging degree of moving parts, and evaluates the adhesion and wear effects of metal chip diffusion on moving parts. Based on the aging degree of moving parts and the adhesion and wear effects of metal chip diffusion, the damage risk of metal chips to moving parts is assessed. Based on the damage risk assessment results of metal chips to moving parts and the chip diffusion situation, the negative pressure parameters of the recovery bellows are dynamically adjusted. This invention predicts the chip diffusion situation under different cutting conditions, and then, combined with the damage of diffused chips to moving parts with different aging degrees, obtains accurate recovery risk adjustment parameters, achieving precise control of negative pressure regulation. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is a schematic diagram of the high-precision CNC machining method for metal materials based on intelligent adaptive control according to the present invention;

[0040] Figure 2 This is a schematic diagram of the calculation process for step three of the high-precision CNC machining method for metal materials based on intelligent adaptive control according to the present invention;

[0041] Figure 3 This is a schematic diagram of the framework of the high-precision CNC machining system for metal materials based on intelligent adaptive control according to the present invention;

[0042] Figure 4This is a schematic diagram of an electronic device frame according to the present invention. Detailed Implementation

[0043] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention are within the scope of protection of the present invention.

[0044] Example 1

[0045] Please see Figure 1 This invention provides a high-precision CNC machining method for metal materials based on intelligent adaptive control, comprising the following specific steps:

[0046] Step 1: Collect historical data on metal material cutting processes, including cutting data, metal chip data, and diffusion data, and construct a metal chip diffusion model;

[0047] In this embodiment, step one includes the following specific steps:

[0048] Step 11: Use a high-speed camera to target the cutting area and capture the initial diffusion trajectory and morphology of metal chips. Place a numbered metal chip collection tray at the bottom of each grid in the metal processing area to collect historical metal material cutting process data. This data includes cutting data, metal chip data, and diffusion data. Cutting data includes cutting speed, feed rate, depth of cut, coolant pressure, and coolant flow rate. The cutting speed, feed rate, and depth of cut are read in real time by the CNC system. A pressure sensor is installed on the coolant line to measure the real-time pressure, and a flow meter is connected in series in the coolant line to measure the real-time flow rate. Metal chip data includes chip temperature, equivalent chip diameter, chip hardness, and chip shape factor. A high-speed infrared thermal imager is used to target the cutting area and capture the temperature of the chips at the moment of ejection as the chip temperature. The chip temperature and equivalent diameter of the chips are measured by the projected area of ​​each chip using image analysis software, which is equivalent to the diameter of a circle. The average value is then taken. The chip hardness is tested on the cross-section of the chips using a microhardness tester. The average chip hardness of each grid is calculated. The chip shape coefficient is classified into categories such as ribbon, C-shape, and spherical using image analysis. Values ​​are assigned according to the shape complexity: ribbon can be 1.0, C-shape can be 0.7, and spherical can be 0.5. The weighted average value of each grid is then calculated to obtain the chip shape coefficient of the metal chips in each grid. The diffusion data includes the initial velocity and spatial distribution density of the chips. After the metal processing area is completed, the chip mass of each metal chip collection plate is measured to obtain the density value of each grid. The trajectory of the chips is captured by a high-speed camera, and the initial velocity of the chips is calculated using particle image velocimetry technology.

[0049] Step 12: Divide the historical metal material cutting process dataset into an 80% training set and a 20% test set. The training set is used to learn the mapping function T from M to N, and the test set is used to evaluate the ability of the metal debris diffusion model to predict metal debris diffusion data after training. The cutting data is used as the input vector M. Where sp is the cutting speed, fr is the feed rate, dp is the depth of cut, pr is the coolant pressure, tr is the coolant flow rate, and T is the transpose sign. The metal processing area is divided into i×j grids, and the output vector N is obtained based on the chip density D of each grid. The random forest model consists of multiple independent decision trees. Composition, define the number U of decision trees, for each tree U distinct subsets are created from the training set by sampling with replacement. A complete decision tree is trained on each subset to learn the mapping. Each node randomly selects some features during splitting, and the final prediction result is the average of all tree prediction results. For a set of splitting data... Its predicted output The goal of the training process is to adjust the structure of each tree to minimize the loss function on the training set. The mean square error is used for evaluation. The test set is input into the trained metal debris diffusion model to obtain the predicted output. The root mean square error is used to quantify the difference between the predicted output and the actual value. The root mean square error represents the average error between the debris density predicted by the metal debris diffusion model and the actual density. The smaller the root mean square error, the higher the prediction accuracy of the metal debris diffusion model.

[0050] Step 2: Monitor metal material cutting data in real time and obtain metal debris diffusion information based on the metal debris diffusion model;

[0051] In this embodiment, step two includes the following specific steps:

[0052] Step 21: Monitor the metal material cutting data in real time, and input the metal material cutting data as the input vector into the metal debris diffusion model. Each tree in the metal debris diffusion model outputs the corresponding prediction vector, and the final prediction result is the average of the prediction results of all trees.

[0053] Step 22: Reshape the prediction vectors according to the metal processing area grid, and map each prediction vector to the metal processing area grid to obtain a two-dimensional matrix. This two-dimensional matrix is ​​a visualization of the metal debris diffusion prediction map. Each value in the map represents the predicted debris density at the corresponding spatial location.

[0054] Step 3: Collect monitoring data of moving parts of CNC machine tools, assess the aging degree of moving parts, and at the same time assess the adhesion and wear effect of metal debris diffusion on moving parts;

[0055] Please see Figure 2 In this embodiment, step three includes the following specific steps:

[0056] Step 31: Collect monitoring data of moving parts of CNC machine tool. The monitoring data of moving parts of CNC machine tool includes vibration acceleration, operating temperature, operating noise and cumulative running time. Vibration acceleration is obtained through accelerometer, operating temperature is obtained through infrared thermal imager, operating noise is obtained through high-sensitivity microphone, and cumulative running time is obtained through CNC system internal timer.

[0057] Step 32: Obtain abnormal vibration acceleration values ​​based on the ratio of vibration acceleration to standard vibration acceleration; obtain abnormal operating temperature values ​​based on the ratio of operating temperature to standard operating temperature; obtain abnormal noise values ​​based on the ratio of operating noise to standard operating noise; obtain abnormal operating time values ​​based on the ratio of cumulative operating time to standard usage time; and obtain the aging assessment value of moving parts by weighted summation of abnormal vibration acceleration values, abnormal operating temperature values, abnormal noise values, and abnormal operating time values. Among these, standard vibration acceleration, standard operating temperature, standard operating noise, and standard usage time are obtained through design documents or industry standards, and standard usage time is the design service life.

[0058] Step 33: Obtain the influence value of debris temperature based on the ratio of debris temperature to the standard melting point of moving part material; obtain the adhesion risk coefficient of metal debris diffusion to moving part by weighted summation of debris temperature influence value and debris shape coefficient.

[0059] Step 34: Obtain the influence value of debris hardness based on the ratio of debris hardness to the surface hardness of the moving part; obtain the influence value of debris diameter based on the ratio of equivalent debris diameter to critical wear size; obtain the influence value of debris velocity based on the ratio of initial debris velocity to critical wear velocity; and obtain the wear risk coefficient of metal debris diffusion on the moving part by weighted summing of the influence values ​​of debris hardness, debris diameter, and debris velocity. This embodiment analyzes the damage to the moving part within the diffusion area of ​​metal debris after diffusion in each grid. The critical wear size is obtained through wear experiments. Using debris samples of the same size, the impact on the surface of the moving part is simulated. Under the same conditions (impact speed and number of impacts), the wear on the surface of the part is measured, and a correlation curve between debris size and wear is plotted. The inflection point at which the wear increases significantly is obtained, and the debris size corresponding to this inflection point is the critical wear size. The critical wear speed is obtained through impact experiments: using debris of the same size, the surface of the part is impacted at different speeds, and the initial velocity of the debris is measured with a high-speed camera. A correlation curve between velocity and wear is plotted, and the inflection point at which the wear increases significantly is obtained. The velocity corresponding to this inflection point is the critical wear speed.

[0060] Step 4: Assess the risk of damage to moving parts from metal debris based on the aging degree of the moving parts, the adhesion of metal debris to the moving parts, and the wear effect;

[0061] In this embodiment, step four includes the following specific steps:

[0062] Step 41: Obtain the influence coefficient of metal debris diffusion on moving parts by weighted summation of adhesion risk coefficient and wear risk coefficient. Obtain the debris threat assessment value based on the debris threat assessment value calculation formula. The debris threat assessment value calculation formula is as follows: ,in, This is the debris threat assessment value. The value represents the debris density at coordinates (x, y). A higher debris density indicates a more concentrated debris concentration at that location, posing a greater threat to the component. This is the coefficient representing the influence of metal debris diffusion on moving parts. The set of spatial coordinates occupied by the moving parts;

[0063] Step 42: Obtain the damage risk value of metal debris to moving parts based on the product of the debris threat assessment value and the moving part aging assessment value.

[0064] In this embodiment, the weights are obtained using the coefficient of variation method: the mean and standard deviation of each indicator are calculated, and then the standard deviation of each indicator is divided by its mean to obtain the coefficient of variation of that indicator, which represents the degree of dispersion of the indicator data. Then, the coefficients of variation of each indicator are added together, and finally, the weight of each indicator is obtained by calculating the proportion of each coefficient of variation to the sum.

[0065] Step 5: Based on the damage risk assessment results of metal debris to moving parts and the debris diffusion situation, dynamically adjust the negative pressure parameters of the recovery bellows.

[0066] In this embodiment, step five includes the following specific steps:

[0067] Step 51: Calculate the debris density risk assessment value based on the debris density risk assessment value calculation formula. The debris density risk assessment value calculation formula is as follows: ,in, Let be the debris density risk assessment value for the i-th air intake. Let be the debris density in the upwind direction of the i-th air intake. The risk sensitivity coefficient is used to measure the damage risk control effect and energy consumption change corresponding to different risk sensitivity coefficients under the same operating conditions. The risk sensitivity coefficient corresponding to the highest damage risk reduction rate and reasonable energy consumption is obtained. For example, when the risk sensitivity coefficient is 0.5, the damage risk decreases by 40%, but energy consumption increases by 15%. The damage risk value of the moving parts to the metal debris corresponding to the i-th air intake is denoted as .

[0068] Step 52: Calculate the negative pressure distribution value for each air intake of the recovery air box based on the negative pressure distribution calculation formula. The negative pressure distribution calculation formula is as follows: ,in, Let be the negative pressure distribution value for the i-th air intake. To maintain basic cleanliness, the base negative pressure of the recovery bellows, i.e., the baseline suction power under no-risk conditions, is required. The average of the debris density risk assessment values ​​for all air intakes. To determine the sensitivity coefficient, the negative pressure adjustment effect corresponding to different sensitivity coefficients was measured to obtain the sensitivity coefficient corresponding to the highest debris removal rate and the lowest energy consumption. For example, when the sensitivity coefficient is 1.2, the removal rate is increased by 30% while the energy consumption only increases by 10%. Pressure distribution reduces the negative pressure in low-demand areas to reduce energy consumption, while increasing the negative pressure in high-demand areas to ensure cleaning effect.

[0069] Example 2

[0070] Please see Figure 3 This invention also provides a high-precision CNC machining system for metal materials based on intelligent adaptive control, comprising:

[0071] The diffusion model construction module is used to collect historical data on metal material cutting processes, including cutting data, metal debris data, and diffusion data, and to construct a metal debris diffusion model.

[0072] The chip diffusion prediction module is used to monitor metal material cutting data in real time and obtain the metal chip diffusion situation based on the metal chip diffusion model.

[0073] The moving parts evaluation module is used to collect monitoring data of moving parts of CNC machine tools, evaluate the aging degree of moving parts, and evaluate the adhesion and wear effect of metal debris diffusion on moving parts.

[0074] The damage risk assessment module is used to assess the damage risk of metal debris to moving parts based on the aging degree of moving parts, the adhesion of metal debris to moving parts, and the wear effect.

[0075] The negative pressure parameter adjustment module is used to dynamically adjust the negative pressure parameter of the recovery air box based on the damage risk assessment results of metal debris to moving parts and the debris diffusion situation.

[0076] Example 3

[0077] Please see Figure 4 The present invention also provides an electronic device, including a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes the above-described high-precision CNC machining method for metal materials based on intelligent adaptive control by calling the computer program stored in the memory.

[0078] The electronic device can vary considerably depending on its configuration or performance, and may include one or more processors (Central Processing Units, CPUs) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the high-precision CNC machining method for metal materials based on intelligent adaptive control provided in the above-described method embodiments.

[0079] In addition, the electronic device also includes a power supply, a communication interface, an input / output interface, and a communication bus; wherein, the power supply is used to provide operating voltage for the various hardware devices on the electronic device; the communication interface can create a data transmission channel between the electronic device and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this invention, and is not specifically limited here; the input / output interface is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0080] Example 4

[0081] This invention also provides a computer-readable storage medium storing instructions that, when a computer program is run on a computer device, cause the computer device to execute the above-described high-precision CNC machining method for metal materials based on intelligent adaptive control.

[0082] For example, computer-readable storage media can be read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage devices.

[0083] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A high-precision CNC machining method for metallic materials based on intelligent adaptive control, characterized in that, The specific steps include the following: Step 1: Collect historical data on metal material cutting processes, including cutting data, metal chip data, and diffusion data, and construct a metal chip diffusion model; Step 2: Monitor metal material cutting data in real time and obtain metal debris diffusion information based on the metal debris diffusion model; Step 3: Collect monitoring data of moving parts of CNC machine tools, assess the aging degree of moving parts, and at the same time assess the adhesion and wear effect of metal debris diffusion on moving parts; Step 4: Assess the risk of damage to moving parts from metal debris based on the aging degree of the moving parts, the adhesion of metal debris to the moving parts, and the wear effect; Step 5: Based on the damage risk assessment results of metal debris to moving parts and the debris diffusion situation, dynamically adjust the negative pressure parameters of the recovery bellows.

2. The high-precision CNC machining method for metal materials based on intelligent adaptive control according to claim 1, characterized in that, Step one includes the following specific steps: Step 11: Collect historical metal material cutting process data. The historical metal material cutting process data includes cutting data, metal chip data, and diffusion data. The cutting data includes cutting speed, feed rate, depth of cut, coolant pressure, and coolant flow rate. The metal chip data includes chip temperature, equivalent chip diameter, chip hardness, and chip shape factor. The diffusion data includes initial chip velocity and spatial distribution density. Step 12: Divide the historical metal material cutting process dataset into an 80% training set and a 20% test set. Use the cutting data as the input vector, divide the metal processing area into a grid of a set specification, obtain the output vector based on the chip density of each grid, set the number of decision trees, and for each tree, create a subset from the training set by sampling with replacement. Train a complete decision tree for each subset. The final prediction result is the average of the prediction results of all trees. Input the test set into the trained metal chip diffusion model to obtain the prediction output.

3. The high-precision CNC machining method for metal materials based on intelligent adaptive control according to claim 2, characterized in that, Step two includes the following specific steps: Step 21: Monitor the metal material cutting data in real time, and input the metal material cutting data as the input vector into the metal debris diffusion model. Each tree in the metal debris diffusion model outputs the corresponding prediction vector, and the final prediction result is the average of the prediction results of all trees. Step 22: Map the predicted vectors one-to-one with the metal processing area grid to obtain a two-dimensional matrix, which is a visualization of the predicted metal debris diffusion.

4. The high-precision CNC machining method for metal materials based on intelligent adaptive control according to claim 3, characterized in that, Step three includes the following specific steps: Step 31: Collect monitoring data of moving parts of CNC machine tool, including vibration acceleration, operating temperature, operating noise and cumulative running time; Step 32: Obtain abnormal vibration acceleration values ​​based on the ratio of vibration acceleration to standard vibration acceleration; obtain abnormal operating temperature values ​​based on the ratio of operating temperature to standard operating temperature; obtain abnormal noise values ​​based on the ratio of operating noise to standard operating noise; obtain abnormal operating time values ​​based on the ratio of cumulative operating time to standard usage time; and obtain the aging assessment value of moving parts by weighted summation of abnormal vibration acceleration values, abnormal operating temperature values, abnormal noise values, and abnormal operating time values. Step 33: Obtain the influence value of debris temperature based on the ratio of debris temperature to the standard melting point of moving part material; obtain the adhesion risk coefficient of metal debris diffusion to moving part by weighted summation of debris temperature influence value and debris shape coefficient. Step 34: Obtain the influence value of chip hardness based on the ratio of chip hardness to moving part surface hardness; obtain the influence value of chip diameter based on the ratio of chip equivalent diameter to critical wear size; obtain the influence value of chip velocity based on the ratio of chip initial velocity to critical wear velocity; and obtain the wear risk coefficient of metal chip diffusion on moving parts by weighted summation of chip hardness influence value, chip diameter influence value and chip velocity influence value.

5. The high-precision CNC machining method for metal materials based on intelligent adaptive control according to claim 4, characterized in that, Step four includes the following specific steps: Step 41: Obtain the influence coefficient of metal debris diffusion on moving parts by weighted summation of adhesion risk coefficient and wear risk coefficient; obtain the debris threat assessment value based on the debris threat assessment value calculation formula, which is: ,in, This is the debris threat assessment value. Let be the debris density at coordinates (x, y). This is the coefficient representing the influence of metal debris diffusion on moving parts. The set of spatial coordinates occupied by the moving parts; Step 42: Obtain the damage risk value of metal debris to moving parts based on the product of the debris threat assessment value and the moving part aging assessment value.

6. The high-precision CNC machining method for metal materials based on intelligent adaptive control according to claim 5, characterized in that, Step five includes the following specific steps: Step 51: Calculate the debris density risk assessment value based on the debris density risk assessment value calculation formula, wherein the debris density risk assessment value calculation formula is: ,in, Let be the debris density risk assessment value for the i-th air intake. Let be the debris density in the upwind direction of the i-th air intake. For risk sensitivity coefficient, The damage risk value of the moving parts to the metal debris corresponding to the i-th air intake is denoted as . Step 52: Calculate the negative pressure distribution value of each air intake of the recovery air box based on the negative pressure distribution calculation formula, wherein the negative pressure distribution calculation formula is: ,in, Let be the negative pressure distribution value for the i-th air intake. To recover the negative pressure in the foundation of the bellows, The average of the debris density risk assessment values ​​for all air intakes. To assign sensitivity coefficients.

7. A high-precision CNC machining system for metal materials based on intelligent adaptive control, used to implement the high-precision CNC machining method for metal materials based on intelligent adaptive control as described in any one of claims 1-6, characterized in that, include: The diffusion model construction module is used to collect historical data on metal material cutting processes, including cutting data, metal debris data, and diffusion data, and to construct a metal debris diffusion model. The chip diffusion prediction module is used to monitor metal material cutting data in real time and obtain the metal chip diffusion situation based on the metal chip diffusion model. The moving parts evaluation module is used to collect monitoring data of moving parts of CNC machine tools, evaluate the aging degree of moving parts, and evaluate the adhesion and wear effect of metal debris diffusion on moving parts. The damage risk assessment module is used to assess the damage risk of metal debris to moving parts based on the aging degree of moving parts, the adhesion of metal debris to moving parts, and the wear effect. The negative pressure parameter adjustment module is used to dynamically adjust the negative pressure parameter of the recovery air box based on the damage risk assessment results of metal debris to moving parts and the debris diffusion situation.

8. An electronic device, characterized in that, include: A memory and a processor, wherein the memory stores a computer program that can be called by the processor, and the processor executes the high-precision CNC machining method for metal materials based on intelligent adaptive control as described in any one of claims 1-6 by calling the computer program stored in the memory.

9. A computer-readable storage medium, characterized in that, The system stores instructions that, when executed on a computer, cause the computer to perform the high-precision CNC machining method for metal materials based on intelligent adaptive control as described in any one of claims 1-6.

Images