A cutting temperature control system and control method for machine tool heated cutting

Abstract

The application discloses a cutting temperature control system and control method for machine tool heating cutting, and the control system comprises a temperature detection module, a temperature control module comprising a cooling control submodule and a heating control submodule, a temperature prediction module for predicting the temperature of a cutting area, a temperature control scheme generation module for generating a temperature control scheme in a machine tool heating cutting process according to the result of the temperature prediction module, and a central control module for controlling the temperature control module according to the temperature control scheme generated by the temperature prediction module in the machine tool heating cutting process, so that the temperature of the cutting area is controlled in a preset target control temperature range T b of the cutting area. The temperature control scheme of the application has better synchronism, can avoid the lag of the actual temperature relative to the target temperature in the feedback control scheme, and can guarantee a longer tool service life and better cutting effect.

Description

Technical Field

[0001] This invention relates to the field of machine tool processing, and in particular to a cutting temperature control system and method for machine tool heating and cutting. Background Technology

[0002] High cutting temperatures are a major cause of tool wear, but higher cutting temperatures are beneficial for improving the toughness of carbide tool materials. In heated cutting, if cutting is performed near the temperature where the hardness difference between the tool material and the workpiece material is at its maximum, the cutting tool will have an optimal cutting temperature range when machining various materials. Within this optimal temperature range, not only do the workpiece material properties meet the requirements, but the tool life is also relatively high. For example, the optimal cutting temperature for high-speed steel tools cutting titanium alloys is approximately 480℃~540℃, while for carbide tools it is approximately 650℃~750℃.

[0003] During machining, controlling the tool temperature to near the optimal cutting temperature can extend tool life and ensure cutting performance. However, current tool temperature control often employs a feedback mechanism: first, the temperature of the cutting zone (the average temperature of the tool, workpiece, and chips) is measured, and then temperature control is applied. This method suffers from significant lag and often has a slow response (i.e., slow temperature regulation), resulting in poor control of the cutting zone temperature. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to provide a cutting temperature control system and control method for machine tool heating cutting, which addresses the shortcomings of the prior art.

[0005] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is: a cutting temperature control system for machine tool heating and cutting, comprising:

[0006] A temperature detection module, used to detect the temperature of the cutting zone in a non-contact manner;

[0007] The temperature control module includes a cooling control submodule and a heating control submodule. The cooling control submodule is used to cool the cutting zone, and the heating control submodule is used to heat the workpiece being processed by conductive heating.

[0008] Temperature prediction module, which is used to predict the temperature of the cutting zone;

[0009] The temperature control scheme generation module is used to generate a temperature control scheme for the machine tool heating and cutting process based on the results of the temperature prediction module.

[0010] And a central control module, which is used to control the temperature control module according to the temperature control scheme generated by the temperature prediction module during the machine tool heating and cutting process, so as to keep the temperature of the cutting zone within the preset target control temperature range T of the cutting zone. b Inside.

[0011] Preferably, the cooling control submodule includes a cooling air host for providing cold air, a cold air duct connected to the cooling air host, and a cold air nozzle connected to the end of the cold air duct. The cold air nozzle is used to spray cold air onto the cutting area for cooling.

[0012] Preferably, the heating control submodule includes a heating host for supplying current to the workpiece being processed and a heating controller for controlling the heating host.

[0013] Preferably, the temperature detection module includes multiple infrared temperature sensors, which detect the temperature of the cutting area from several angles, and output the average value of the temperature detected by the multiple infrared temperature sensors as the detection result.

[0014] The temperature control scheme generation module is communicatively connected to the temperature detection module, temperature control module, temperature prediction module, and central control module.

[0015] Preferably, the temperature prediction module is trained based on a NARX neural network, and it is based on the cutting process characteristic value E of the heated cutting tool. g E, the material characteristic value of the workpiece being processed c Environmental factor characteristic value E h The predicted cutting zone temperature trend curve I(t) is obtained. g T g );

[0016] The cutting process characteristic value E g = Cutting speed Vc × Feed rate f × Depth of cut αp, where the unit of cutting speed Vc is m / min, the unit of feed rate f is mm / r, and the unit of depth of cut αp is mm;

[0017] The material characteristic value E of the workpiece being processed c = Tool hardness - Workpiece hardness;

[0018] The characteristic value of the environmental factor E h The ambient temperature during the heating and cutting process is expressed in °C.

[0019] Preferably, the temperature prediction module is constructed using the following method:

[0020] 1) Construct the training dataset Q1:

[0021] 1-1) Without cooling or heating measures, use cutting tools to machine workpieces with different hardnesses, and record the characteristic value E of each cutting process. g E, the material characteristic value of the workpiece being processed c Environmental factor characteristic value E h Below, different processing times t g Temperature T in the cutting zone at that time g The cutting process characteristic value E g E, the material characteristic value of the workpiece being processed c Environmental factor characteristic value E h Processing time t g Temperature T g Combined to form a training data set q1;

[0022] 1-2) Through several experiments, the training data q1 obtained are combined to construct the training dataset Q1;

[0023] 2) Using the training dataset Q1, with cutting process feature values ​​E g E, the material characteristic value of the workpiece being processed c Environmental factor characteristic value E h As input, representing different processing times t g Temperature T in the cutting zone at that time g The temperature trend curve of the cutting zone I(t) g T g The NARX neural network is trained using the output , and the NARX prediction model is obtained after training.

[0024] During the cutting process, friction between the cutting tool and the workpiece generates heat, causing the tool temperature to rise sharply. This temperature rise is influenced by various factors, which can be mainly summarized into the following three aspects:

[0025] (1) Cutting process, including cutting speed Vc, feed rate f, depth of cut αp, etc. In this invention, the cutting process characteristic value E is used. g Characterizing this influencing factor, specifically, the cutting process characteristic value E g = Cutting speed Vc × Feed rate f × Depth of cut αp, where the unit of cutting speed Vc is m / min, the unit of feed rate f is mm / r, and the unit of depth of cut αp is mm. The above process parameters in the cutting process are obtained in advance based on the specific processing requirements of the workpiece and are known quantities; for example, for a certain workpiece to be processed into a product of a certain shape and size, its cutting process will be designed and confirmed in advance, and in this invention, the cutting process can be directly retrieved.

[0026] (2) The characteristics of the workpiece material can be mainly attributed to the hardness difference between the workpiece and the cutting tool. In this invention, the characteristic value E of the workpiece material is used. c Characterization is performed to obtain the material characteristic value E of the machined workpiece. c = Tool hardness - Workpiece hardness; Hardness can be characterized by Rockwell hardness, Vickers hardness, etc., as long as they are consistent.

[0027] (3) Environmental influence of cutting process: In this invention, the ambient temperature during the cutting process is mainly used to characterize it, denoted as the environmental factor characteristic value E. h (Unit: °C)

[0028] Therefore, the tool temperature at various moments during the cutting process can be predicted based on the above factors. Specifically, this invention uses a temperature prediction module based on a NARX neural network. The NARX (Nonlinear Autoregressive Exogenous Neural Network) model is a time series modeling technique used to predict future values ​​based on past values. In this invention, the NARX model is used as the basic network model, and it is trained using the constructed training dataset Q1. This enables accurate prediction of the tool temperature at various moments during the cutting process, which can then be used to construct temperature control schemes.

[0029] Preferably, the temperature control scheme generation module is trained based on a generative adversarial network (GAN), and it generates the temperature trend curve I(t) of the cutting zone obtained by the temperature prediction module. g T g And the preset target control temperature range T of the cutting zone. b Generate a temperature control solution;

[0030] The temperature control scheme includes cooling control parameters of the cooling control submodule and heating control parameters of the heating control submodule at different times;

[0031] The cooling control parameters include the temperature T of the cold air ejected from the cold air nozzle. k and traffic Q k The heating control parameters include heating current I. k and heating voltage U k ;

[0032] Temperature T k The unit is ℃, and the flow rate is Q. k The unit is L / min, heating current I k The unit is A, and the heating voltage is U. k The unit is V.

[0033] Preferably, the temperature control scheme generation module is constructed using the following method:

[0034] S1. Construct the training dataset Q2:

[0035] S1-1. Conduct the experiment according to the following method:

[0036] S1-1-1, under different cooling control parameters, heating control parameters, and target control temperature range T b Temperature trend curve of cutting zone I(t) g T g Under these conditions, different processing times t are obtained manually. g Control value C of the cooling process parameters g This forms the temperature control strategy function fr(t) g C g );

[0037] S1-1-2, In heated cutting processes, the temperature control strategy function fr(t) is followed. g C g The cooling control submodule and the heating control submodule are controlled to ensure that the temperature of the cutting zone is always kept within the target control temperature range T. b Continue until the cutting process is completed;

[0038] Cooling control parameters, heating control parameters, and target control temperature range T b Temperature trend curve of cutting zone I(t) g T g ) are combined to form a training data set q2;

[0039] S1-2. Conduct several experiments and combine all the training data q2 obtained to construct the training dataset Q2;

[0040] S2. Using the training dataset Q2, the target control temperature range T is... b Temperature trend curve of cutting zone I(t) g T g ) is the input, and the temperature control strategy function is fr(t). g C g The output is used to train the Generative Adversarial Network (GAN), and the temperature control scheme generation module is obtained after training.

[0041] High cutting temperatures are a major cause of tool wear, but higher cutting temperatures are beneficial for improving the toughness of carbide tool materials. In heated cutting, there is usually an optimal temperature range in the cutting zone. Within this optimal temperature range, not only do the workpiece material properties meet the requirements, but the tool life is also relatively high.

[0042] In this invention, a heated cutting machining scheme is employed. Based on the specific materials of the cutting tool and the workpiece, the suitable cutting temperature range, i.e., the target control temperature range T, can be determined in advance. b The temperature of the cutting zone is controlled by the cooling control submodule and the heating control submodule, so that the temperature of the cutting zone is kept within the range, thereby ensuring a longer tool life and better cutting effect.

[0043] The optimal cutting temperature for different workpieces can be obtained through relevant experiments. For example, Ye Bangyan, Xu Lanying, Liu Jianping, et al. (Control of conductive heating cutting current based on the law of conservation of optimal cutting temperature [C] / / 13th Annual Academic Conference of the National Association for Manufacturing Automation of Higher Education Institutions. 2008) used tool durability tests to determine the optimal cutting temperature as the cutting temperature at which the tool wear is minimized.

[0044] Conventional tool temperature control schemes are generally based on feedback mechanisms. This means that the actual temperature is detected first, and then cooling / heating measures are provided based on the detected temperature value to bring the temperature closer to the target temperature. This method has a large lag and poor temperature control accuracy, resulting in poor temperature control performance.

[0045] In this invention, the cutting temperature trend curve I(t) relating the cutting zone temperature to the machining time is first predicted. g T g Then, control the temperature range T according to the set target range. b By generating a temperature control scheme through a temperature control scheme generation module based on machine learning algorithms, and then controlling the temperature control module, the actual temperature of the cutting zone at various times can be made closer to the target control temperature range T. b It has better synchronization and can avoid the lag between the actual temperature and the target temperature in the feedback control scheme.

[0046] The present invention also provides a cutting temperature control method for machine tool heating and cutting, which uses the control system described above to control the temperature of the cutting zone during the machine tool heating and cutting process.

[0047] Preferably, the cutting temperature control method for machine tool heating and cutting includes the following steps:

[0048] Step 1: Before heating and cutting, first set the cutting process characteristic value E of the tool to be heated and cut. g E, the material characteristic value of the workpiece being processed c Environmental factor characteristic value E h The temperature prediction module is input to obtain the cutting zone temperature trend curve I(t) of the cutting zone. g T g );

[0049] Step 2: The temperature control scheme generation module obtains the temperature trend curve I(t) of the cutting zone. g T g And the preset target control temperature range T of the cutting zone. b Then, a temperature control scheme is generated for the current heating and cutting operation;

[0050] Step 3: The machine tool is started to perform heated cutting processing. At the same time, the central control module controls the temperature control module according to the temperature control scheme obtained in Step 2.

[0051] Throughout the heated cutting process, the actual temperature T of the cutting zone is monitored by a temperature detection module. s Monitoring is conducted when T s Exceeding the target control temperature range T b The duration exceeds the preset threshold ε t1 At that time, the central control module issues an alarm message, and the temperature control module is manually controlled until T... s Return to the target control temperature range T b And the duration exceeds the preset threshold ε t2 This method allows for manual adjustments to the temperature control scheme, further ensuring the reliability of temperature control in the cutting zone during heated cutting processes.

[0052] The beneficial effects of this invention are:

[0053] This invention provides a cutting temperature control system and method for machine tool heated cutting. In this invention, a heated cutting machining scheme is employed, and the suitable cutting temperature range, i.e., the target control temperature range T, can be determined in advance based on the specific materials of the cutting tool and the workpiece. b The temperature of the cutting zone is controlled by the cooling control submodule and the heating control submodule, so that the temperature of the cutting zone is kept within the range, thereby ensuring a longer tool life and better cutting effect.

[0054] In this invention, the cutting temperature trend curve I(t) relating the cutting zone temperature to the machining time is first predicted. g T g Then, control the temperature range T according to the set target range. b By generating a temperature control scheme through a temperature control scheme generation module based on machine learning algorithms, and then controlling the temperature control module, the actual temperature of the cutting zone at various times can be made closer to the target control temperature range T. b It has better synchronization and can avoid the lag between the actual temperature and the target temperature in the feedback control scheme. Attached Figure Description

[0055] Figure 1 This is a schematic diagram of the cutting temperature control system for machine tool heating and cutting in Example 1;

[0056] Figure 2 This is a schematic diagram of some components of the cutting temperature control system for machine tool heating and cutting in Example 1;

[0057] Figure 3 This is a schematic diagram illustrating the construction process of the temperature prediction module in Example 1;

[0058] Figure 4 This is a schematic diagram of the construction process of the temperature control scheme generation module in Example 1;

[0059] Figure 5 This is a flowchart of the cutting temperature control method for machine tool heating and cutting in Example 2;

[0060] Figure 6 The results show the accuracy comparison of the temperature trend curves in the cutting zone;

[0061] Figure 7 These are the results of wear performance tests.

[0062] Explanation of reference numerals in the attached figures:

[0063] 1—Workpiece to be processed; 2—Cutting tool; 3—Cooling air main unit; 4—Cooling air duct; 5—Cooling air nozzle; 6—Heating main unit; 7—Heating controller; 8—Infrared temperature sensor. Detailed Implementation

[0064] The present invention will be further described in detail below with reference to embodiments, so that those skilled in the art can implement it based on the description.

[0065] It should be understood that terms such as “having,” “comprising,” and “including” as used herein do not exclude the presence or addition of one or more other elements or combinations thereof.

[0066] Example 1

[0067] Reference Figure 1 and Figure 2 This embodiment provides a cutting temperature control system for machine tool heating and cutting, including:

[0068] A temperature detection module, used to detect the temperature of the cutting zone in a non-contact manner;

[0069] The temperature control module includes a cooling control submodule and a heating control submodule. The cooling control submodule is used to cool the cutting area, and the heating control submodule is used to heat the workpiece 1 being processed by conductive heating.

[0070] Temperature prediction module, which is used to predict the temperature of the cutting zone;

[0071] The temperature control scheme generation module is used to generate a temperature control scheme for the machine tool heating and cutting process based on the results of the temperature prediction module.

[0072] And a central control module, which is used to control the temperature control module according to the temperature control scheme generated by the temperature prediction module during the machine tool heating and cutting process, so as to keep the temperature of the cutting zone within the preset target control temperature range T of the cutting zone. b Inside.

[0073] In this invention, the cutting zone refers to the area where the cutting tool 2 contacts the workpiece 1 being processed.

[0074] The cooling control submodule includes a cooling air host 3 for providing cold air, a cooling air duct 4 connected to the cooling air host 3, and a cooling air nozzle 5 connected to the end of the cooling air duct 4. The cooling air nozzle 5 is used to spray cold air onto the cutting area for cooling.

[0075] The heating control submodule includes a heating host 6 for supplying current to the workpiece 1 being processed, and a heating controller 7 for controlling the heating host 6.

[0076] The temperature detection module includes multiple infrared temperature sensors 8, which detect the temperature of the cutting area from several angles and output the average value of the temperatures detected by the multiple infrared temperature sensors 8 as the detection result. In this embodiment, four infrared temperature sensors 8 are spatially spaced on the outer periphery of the cutting area. By setting multiple infrared temperature sensors 8 for detection and taking the average value, the detection accuracy can be improved.

[0077] The temperature control scheme generation module is communicatively connected to the temperature detection module, temperature control module, temperature prediction module, and central control module.

[0078] In this embodiment, the temperature prediction module is trained based on a NARX neural network, and it is based on the cutting process characteristic value E of the heated cutting tool 2. g Material characteristic value E of workpiece 1 c Environmental factor characteristic value E h The predicted cutting zone temperature trend curve I(t) is obtained. g T g );

[0079] Cutting process characteristic value E g = Cutting speed Vc × Feed rate f × Depth of cut αp, where the unit of cutting speed Vc is m / min, the unit of feed rate f is mm / r, and the unit of depth of cut αp is mm;

[0080] Material characteristic value E of workpiece 1 c = Hardness of tool 2 - Hardness of workpiece 1;

[0081] Environmental factor characteristic value E h The ambient temperature during the heating and cutting process is expressed in °C.

[0082] In this embodiment, refer to Figure 3 The temperature prediction module is constructed using the following method:

[0083] 1) Construct the training dataset Q1:

[0084] 1-1) Without cooling or heating measures, the workpiece 1 with different hardness is machined using tool 2, and the characteristic value E of each cutting process is recorded. g Material characteristic value E of workpiece 1 c Environmental factor characteristic value E h Below, different processing times t g Temperature T in the cutting zone at that time g The cutting process characteristic value E g Material characteristic value E of workpiece 1 c Environmental factor characteristic value E h Processing time t g Temperature T g Combined to form a training data set q1;

[0085] 1-2) Through several experiments, the training data q1 obtained are combined to construct the training dataset Q1;

[0086] 2) Using the training dataset Q1, with cutting process feature values ​​E g Material characteristic value E of workpiece 1 c Environmental factor characteristic value E h As input, representing different processing times t g Temperature T in the cutting zone at that time g The temperature trend curve of the cutting zone I(t) g T g The NARX neural network is trained using the output , and the trained NARX prediction model is obtained.

[0087] In this embodiment, the temperature control scheme generation module is trained based on a generative adversarial network (GAN), and it generates the cutting zone temperature trend curve I(t) obtained by the temperature prediction module. g T g And the preset target control temperature range T of the cutting zone. b Generate a temperature control solution;

[0088] The temperature control scheme includes cooling control parameters for the cooling control submodule and heating control parameters for the heating control submodule at different times;

[0089] Cooling control parameters include the temperature T of the cold air ejected from the cold air nozzle 5. k and traffic Q k Heating control parameters include heating current I k and heating voltage U k ;

[0090] Temperature T k The unit is ℃, and the flow rate is Q. k The unit is L / min, heating current I k The unit is A, and the heating voltage is U. k The unit is V.

[0091] In this embodiment, refer to Figure 4 The temperature control solution generation module is constructed using the following method:

[0092] S1. Construct the training dataset Q2:

[0093] S1-1. Conduct the experiment according to the following method:

[0094] S1-1-1, under different cooling control parameters, heating control parameters, and target control temperature range T b Temperature trend curve of cutting zone I(t) g T g Under these conditions, different processing times t are obtained manually. g Control value C of the cooling process parameters g This forms the temperature control strategy function fr(t) g C g );

[0095] S1-1-2, In heated cutting processes, the temperature control strategy function fr(t) is followed. g C g The cooling control submodule and the heating control submodule are controlled to ensure that the temperature in the cutting zone is always kept within the target control temperature range T. b Continue until the cutting process is completed;

[0096] Cooling control parameters, heating control parameters, and target control temperature range T b Temperature trend curve of cutting zone I(t) g T g ) are combined to form a training data set q2;

[0097] S1-2. Conduct several experiments and combine all the training data q2 obtained to construct the training dataset Q2;

[0098] S2. Using the training dataset Q2, the target control temperature range T is... b Temperature trend curve of cutting zone I(t) g T g ) is the input, and the temperature control strategy function is fr(t). g C g The output is used to train the Generative Adversarial Network (GAN), and the temperature control scheme generation module is obtained after training.

[0099] Example 2

[0100] Reference Figure 5 This embodiment provides a cutting temperature control method for machine tool heating and cutting. It uses the control system of Embodiment 1 to control the temperature of the cutting zone during the machine tool heating and cutting process. The method specifically includes the following steps:

[0101] Step 1: Before heating and cutting, first set the cutting process characteristic value E of the tool 2 to be heated and cut. g Material characteristic value E of workpiece 1 c Environmental factor characteristic value E h In the input temperature prediction module, the cutting zone temperature trend curve I(t) of the cutting zone is obtained. g T g );

[0102] Step 2: The temperature control scheme generation module obtains the cutting zone temperature trend curve I(t). g T g And the preset target control temperature range T of the cutting zone. b Then, a temperature control scheme is generated for the current heating and cutting operation;

[0103] Step 3: The machine tool is started to perform heated cutting processing. At the same time, the central control module controls the temperature control module according to the temperature control scheme obtained in Step 2.

[0104] Throughout the heated cutting process, the actual temperature T of the cutting zone is monitored by a temperature detection module. s Monitoring is conducted when T s Exceeding the target control temperature range T b The duration exceeds the preset threshold ε t1 At that time, the central control module issues an alarm message, and the temperature control module is manually controlled until T... s Return to the target control temperature range T b And the duration exceeds the preset threshold ε t2 In this embodiment, ε t1 =1s, ε t2 =1.5s

[0105] Test case

[0106] In this test example, the system of Example 2 is used to control the cutting temperature of machine tool heating cutting. The main parameters are as follows:

[0107] The material being processed is 38CrMoAl steel (after quenching and tempering), with a hardness of 61.4HRC, a cuboid shape, and geometric dimensions of 200mm×120mm×60mm.

[0108] The system uses a VMC850 three-axis vertical CNC milling machine with a maximum speed of 8000 r / min and a maximum power of 22 kW. Cooling gas is air, and the temperature is 20℃.

[0109] The cutting tool uses SG4 ceramic, with a hardness of 95.2 HRC, a bending strength of 1.05 GPa, and an impact toughness ≥14.6 kJ / m. 2 Tool 2 geometric parameters: rake angle g0 = -6°, clearance angle a0 = 6°, principal cutting edge angle kr = 45°, cutting edge inclination angle ls = -6°;

[0110] Target control temperature range T b =720℃.

[0111] (1) Comparison of the accuracy of temperature trend curves in the cutting zone:

[0112] Reference Figure 6 This is the cutting zone temperature trend curve I(t) predicted by the temperature prediction module in this example. g T g ) and the actual cutting zone temperature trend curve I'(t) obtained under the same conditions. g T g The actual cutting zone temperature trend curve was plotted by monitoring the temperature at various processing times using the temperature detection module, under the same conditions as above, without applying temperature control measures (i.e., the temperature control module is not working). The results in the figure show that the predicted cutting zone temperature trend curve I' has a high degree of consistency with the actual cutting zone temperature trend curve I', indicating that the temperature prediction module of this invention can accurately predict the temperature.

[0113] (2) Wear performance test:

[0114] The wear morphology of tool 2 was observed using a JSM-6380LA scanning electron microscope; the wear amount on the flank face of tool 2 was measured using a tool microscope with an accuracy of 0.01 mm. After each cutting stroke, the wear morphology of the flank face was observed and the wear amount on the flank face was measured; the cutting time of tool 2 was calculated according to the cutting path, and the flank face wear amount under different cutting times was calculated and statistically analyzed, and wear curves were plotted (test example).

[0115] As a comparison, a conventional feedback temperature control scheme is used, which monitors the real-time temperature of tool 2 against the target control temperature range T. b The difference was used to adjust the cooling and heating control parameters, and the wear curve was plotted using the same method as described above (comparative example).

[0116] Reference Figure 7 The figures show the wear curves for the test case and the control case. It can be seen that, compared with the control case, the temperature control of the cutting zone using the test case method can significantly reduce the wear of tool 2, thereby extending its service life. This is attributed to the higher accuracy and synchronization of the temperature control method in the test case.

[0117] Although the embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the specification and embodiments. They can be applied to various fields suitable for the present invention. For those skilled in the art, other modifications can be easily made. Therefore, without departing from the general concept defined by the claims and their equivalents, the present invention is not limited to the specific details.

Claims

1. A cutting temperature control system for machine tool heating and cutting, characterized in that, include: A temperature detection module, used to detect the temperature of the cutting zone in a non-contact manner; The temperature control module includes a cooling control submodule and a heating control submodule. The cooling control submodule is used to cool the cutting zone, and the heating control submodule is used to heat the workpiece being processed by conductive heating. Temperature prediction module, which is used to predict the temperature of the cutting zone; The temperature control scheme generation module is used to generate a temperature control scheme for the machine tool heating and cutting process based on the results of the temperature prediction module. And a central control module, which is used to control the temperature control module according to the temperature control scheme generated by the temperature prediction module during the machine tool heating and cutting process, so as to keep the temperature of the cutting zone within the preset target control temperature range T of the cutting zone. b Inside; The temperature prediction module is trained based on a NARX neural network, and it is based on the cutting process characteristic value E of the heated cutting tool. g E, the material characteristic value of the workpiece being processed c Environmental factor characteristic value E h The predicted cutting zone temperature trend curve I(t) is obtained. g T g ), t g It is the processing time, T g It is the temperature of the cutting zone; The cutting process characteristic value E g = Cutting speed Vc × Feed rate f × Depth of cut αp, where the unit of cutting speed Vc is m / min, the unit of feed rate f is mm / r, and the unit of depth of cut αp is mm; The material characteristic value E of the workpiece being processed c = Tool hardness - Workpiece hardness; The characteristic value of the environmental factor E h The ambient temperature during the heating and cutting process is expressed in °C. The temperature control scheme generation module is trained based on a generative adversarial network (GAN), and it generates the cutting zone temperature trend curve I(t) obtained by the temperature prediction module. g T g And the preset target control temperature range T of the cutting zone. b Generate a temperature control solution; The temperature control scheme generation module is constructed using the following method: S1. Construct the training dataset Q2: S1-1. Conduct the experiment according to the following method: S1-1-1, under different cooling control parameters, heating control parameters, and target control temperature range T b Temperature trend curve I (t) in the cutting zone g T g Under these conditions, different processing times t are obtained manually. g Control value C of the cooling process parameters g Forming a temperature control strategy function fr (t) g C g ); S1-1-2, In heated cutting processes, the temperature control strategy function is followed. fr (t) g C g The cooling control submodule and the heating control submodule are controlled to ensure that the temperature of the cutting zone is always kept within the target control temperature range T. b Continue until the cutting process is completed; Cooling control parameters, heating control parameters, and target control temperature range T b Temperature trend curve I (t) in the cutting zone g T g The data are combined to form a training data set q2; S1-2. Conduct several experiments and combine all the training data q2 obtained to construct the training dataset Q2; S2. Using the training dataset Q2, the target control temperature range T is... b Temperature trend curve I (t) in the cutting zone g T g ( ) is the input, and the temperature control strategy function is... fr (t) g C g The output is used to train the Generative Adversarial Network (GAN), and the temperature control scheme generation module is obtained after training.

2. The cutting temperature control system for machine tool heating and cutting according to claim 1, characterized in that, The cooling control submodule includes a cooling air host for providing cold air, a cold air duct connected to the cooling air host, and a cold air nozzle connected to the end of the cold air duct. The cold air nozzle is used to spray cold air onto the cutting area for cooling.

3. The cutting temperature control system for machine tool heating and cutting according to claim 2, characterized in that, The heating control submodule includes a heating host for supplying current to the workpiece being processed and a heating controller for controlling the heating host.

4. The cutting temperature control system for machine tool heating and cutting according to claim 3, characterized in that, The temperature detection module includes multiple infrared temperature sensors, which detect the temperature of the cutting area from several angles and output the average value of the temperature detected by the multiple infrared temperature sensors as the detection result. The temperature control scheme generation module is communicatively connected to the temperature detection module, temperature control module, temperature prediction module, and central control module.

5. The cutting temperature control system for machine tool heating and cutting according to claim 4, characterized in that, The temperature prediction module is constructed using the following method: 1) Construct the training dataset Q1: 1-1) Without cooling or heating measures, use cutting tools to machine workpieces with different hardnesses, and record the characteristic value E of each cutting process. g E, the material characteristic value of the workpiece being processed c Environmental factor characteristic value E h Below, different processing times t g Temperature T in the cutting zone at that time g The cutting process characteristic value E g E, the material characteristic value of the workpiece being processed c Environmental factor characteristic value E h Processing time t g Temperature T g Combined to form a training data set q1; 1-2) Through several experiments, the training data q1 obtained are combined to construct the training dataset Q1; 2) Using the training dataset Q1, with cutting process feature values ​​E g E, the material characteristic value of the workpiece being processed c Environmental factor characteristic value E h As input, representing different processing times t g Temperature T in the cutting zone at that time g The temperature trend curve of the cutting zone I (t) g T g The NARX neural network is trained using the output , and the trained NARX prediction model is obtained.

6. The cutting temperature control system for machine tool heating and cutting according to claim 4, characterized in that, The temperature control scheme includes cooling control parameters of the cooling control submodule and heating control parameters of the heating control submodule at different times; The cooling control parameters include the temperature T of the cold air ejected from the cold air nozzle. k and traffic Q k The heating control parameters include heating current I. k and heating voltage U k ; Temperature T k The unit is ℃, and the flow rate is Q. k The unit is L / min, heating current I k The unit is A, and the heating voltage is U. k The unit is V.

7. A method for controlling the cutting temperature in machine tool heating cutting, characterized in that, It employs a control system as described in any one of claims 1-6 to control the temperature of the cutting zone during the machine tool heating and cutting process.

8. The cutting temperature control method for machine tool heating cutting according to claim 7, characterized in that, Includes the following steps: Step 1: Before heating and cutting, first set the cutting process characteristic value E of the tool to be heated and cut. g E, the material characteristic value of the workpiece being processed c Environmental factor characteristic value E h The temperature prediction module is input to obtain the cutting zone temperature trend curve I(t) of the cutting zone. g T g ); Step 2: The temperature control scheme generation module obtains the cutting zone temperature trend curve I(t). g T g And the preset target control temperature range T of the cutting zone. b Then, a temperature control scheme is generated for the current heating and cutting operation; Step 3: The machine tool is started to perform heated cutting processing. At the same time, the central control module controls the temperature control module according to the temperature control scheme obtained in Step 2. Throughout the heated cutting process, the actual temperature T of the cutting zone is monitored by a temperature detection module. s Monitoring is conducted when T s Exceeding the target control temperature range T b The duration exceeds the preset threshold ε t1 At that time, the central control module issues an alarm message, and the temperature control module is manually controlled until T... s Return to the target control temperature range T b And the duration exceeds the preset threshold ε t2 .

Images