Real-time material identification method for dual-metal milling process based on unit cutting force map

Abstract

The application provides a material real-time identification method for double-metal milling based on a unit cutting force map, which comprises the following steps: obtaining the driving load of a tool spindle and calculating the average driving load thereof; calculating the unit cutting force based on the average driving load; using the calculated unit cutting force for the training of a neural network in the monitoring of a milling process in a machine data protocol; predicting the real-time unit cutting force based on the trained neural network; establishing the unit cutting force map based on the predicted real-time unit cutting force; and identifying the material based on the unit cutting force map.

Description

Technical Field

[0001] This invention belongs to the field of real-time material identification technology, and particularly relates to a real-time material identification method for bimetallic milling processes based on unit cutting force maps. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] The demand for clean energy is one of the most significant challenges facing the automotive industry. Reducing vehicle weight decreases carbon emissions over the lifespan of transportation systems. Solid dissimilar bimetallic materials have garnered widespread attention in the automotive industry due to their advantages in lightweighting, sustainability, and low cost, showing promising application prospects. However, the difference in mechanical properties between the two metals leads to a "soft-hard" change in the workpiece material during machining compared to single-metal materials. This subjectes the cutting tool to unstable thermal load fields and prolonged exposure to harsh environments such as sudden stress field changes, inevitably resulting in severe wear and failure of the cutting edge. This leads to high tool costs and compromised workpiece surface quality.

[0004] With industrial development, the demand for intelligent manufacturing is increasing. Automation, networking, and the learning of technical information are currently key research areas in parts manufacturing. By using intelligent data processing methods, productivity and performance reserves can be improved.

[0005] For bimetallic machining, material identification is a fundamental prerequisite for achieving intelligent manufacturing. However, material identification remains a challenge in bimetallic machining with various parameters. Summary of the Invention

[0006] To overcome the shortcomings of the prior art, this invention provides a real-time material identification method for bimetallic milling processes based on unit cutting force maps, which can realize real-time identification of bimetallic materials during the machining process.

[0007] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions:

[0008] The first aspect discloses a real-time material identification method for bimetallic milling processes based on unit cutting force maps, including:

[0009] Obtain the drive load of the tool spindle and calculate its average drive load;

[0010] Calculate the unit cutting force based on the average driving load;

[0011] The calculated unit cutting force is used to train a neural network during a milling process monitored by a machine data protocol.

[0012] Real-time unit cutting force is predicted based on a trained neural network;

[0013] Based on the predicted real-time unit cutting force, a unit cutting force map is established;

[0014] Material identification based on unit cutting force map.

[0015] As a further technical solution, the specific formula for calculating the unit cutting force is as follows:

[0016]

[0017] Where, k c It is the unit cutting force, A is the chip cross-section, and F is the cutting force per unit area. c This is the cutting force.

[0018] As a further technical solution, the specific process for calculating the cutting force is as follows:

[0019]

[0020] Among them, F c Pc is the cutting force, Pc is the cutting power, and v is the cutting speed.

[0021] As a further technical solution, the formula for calculating the cutting power is:

[0022] P c =M c *ω=M c *2π*n

[0023] Wherein, the tool rotation speed n is equal to the spindle rotation speed, which can be obtained from the machining process, and the cutting torque M... c With spindle drive torque M X Proportional.

[0024] As a further technical solution, the cutting torque M c As shown in the following formula:

[0025] M c ~(M) X -M X0 );

[0026] The driving torque M X With the spindle drive load a i Proportional to the load a i It is the actual current I i With nominal current I n The percentage value is obtained as follows:

[0027] M c ~(M) X -M X0)~(a X -a X0 ).

[0028] As a further technical solution, the cutting speed calculation formula is as follows:

[0029] v c =r*ω=d*π*n (11)

[0030] As a further technical solution, the chip cross-section A is the number of milling cutter teeth Z involved in the cutting. E The product of the chip cross-sectional area Az of each tooth;

[0031] The number of milling cutter teeth Z involved in the cutting process E Determined by the milling cutter's cutting method:

[0032]

[0033] In the formula, the number of teeth Z is known, and the angle of approach is... and cut-out angle It can be calculated using the following formula:

[0034]

[0035]

[0036] Cross-sectional area A of each tooth's chip Z The chip width b and the average chip thickness h m The calculation yielded:

[0037] A Z =b*h m

[0038] chip width b and average chip thickness h m The following formula can be used to calculate:

[0039]

[0040]

[0041] In the formula, the cutting depth a p and the principal cutting edge angle k of the cutting tool r and feed per tooth f z All of these are known.

[0042] Secondly, a real-time material identification system for bimetallic milling processes based on unit cutting force maps is disclosed, including:

[0043] The unit cutting force calculation module is configured to: obtain the drive load of the tool spindle and calculate its average drive load; calculate the unit cutting force based on the average drive load;

[0044] The unit cutting force prediction module is configured to use the calculated unit cutting force for training the neural network during a milling process monitored by a machine data protocol.

[0045] Real-time unit cutting force is predicted based on a trained neural network;

[0046] The unit cutting force map generation module is configured to: generate a unit cutting force map based on the predicted real-time unit cutting force;

[0047] The material identification module is configured to identify materials based on the unit cutting force map.

[0048] The above one or more technical solutions have the following beneficial effects:

[0049] This embodiment's sub-technical solution starts with the unit cutting force coefficient ratio. Based on real-time measurement of instantaneous cutting force, it creates a unit cutting force coefficient ratio map for the milling process. Based on the significant difference in the unit cutting force coefficient ratio between cast iron and aluminum materials, it performs real-time identification of bimetallic materials during machining, providing a foundation for intelligent processing of bimetallic materials.

[0050] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0051] 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.

[0052] Figure 1 This is a schematic diagram of the artificial neural network prediction process for unit cutting force according to an embodiment of the present invention;

[0053] Figure 2 This is a schematic diagram showing the distribution of unit cutting force of bimetallic materials under different feed rates in an embodiment of the present invention;

[0054] Figure 3 This is a material identification spectrum using the Kc / Kr ratio in an embodiment of the present invention;

[0055] Figure 4 This is a flowchart illustrating the material identification process during the bimetallic material milling process according to an embodiment of the present invention.

[0056] Figure 5 This is a flowchart illustrating the overall material identification process in an embodiment of the present invention.

[0057] Figure 6 This is a more detailed flowchart illustrating the process of predicting unit cutting force according to an embodiment of the present invention. Detailed Implementation

[0058] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0059] It should be noted that the terminology used herein is for the purpose of describing particular implementations only and is not intended to limit the exemplary implementations of the present invention.

[0060] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0061] Example 1

[0062] Regarding the influence of material properties on cutting force:

[0063] Since plastic deformation occurs during the cutting of metal materials, consuming cutting energy, the cutting force can be estimated by calculating the cutting energy and the relationship between the cutting force and the cutting energy. This is also the approach given by the Merchant minimum cutting energy cutting model, which calculates the cutting force during the cutting process based on the principle of minimum energy.

[0064] Because actual cutting processes often involve spatial and temporal complexity, they cannot be replaced by simple right-angle cutting processes. However, in mechanism discussions and formula derivations, the complex oblique cutting process is often simplified to right-angle cutting. After establishing the relationship between physical parameters, it is then extended to the oblique cutting process through coordinate transformation or derivation.

[0065] For right-angle cutting, the energy during the cutting process mainly consists of shear energy and friction energy. Shear energy is calculated from parameters such as shear angle and shear stress, while friction energy is calculated from parameters such as friction angle. In the orthogonal cutting model, the shear angle, shear stress, and friction angle on the shear surface are functions of cutting speed, undeformed chip thickness, and rake angle, as shown in equation (1). However, during the cutting process, the shear angle, shear stress, and friction angle are different for different workpiece materials. For example, the shear angle, shear stress, and friction angle for hard material cast iron and soft material aluminum alloy are shown in equations (2) and (3), respectively. Therefore, different workpiece materials exhibit different cutting difficulties during the cutting process, especially materials with large differences in properties also exhibit significant differences in cutting force values. That is to say, due to the differences in material properties, different workpiece materials result in differences in shear angle, shear stress, and friction angle, which in turn require different cutting energies, leading to differences in the magnitude of the cutting force.

[0066]

[0067] For cast iron materials

[0068]

[0069] For aluminum alloy materials

[0070]

[0071] Since the cutting force value is closely related to the workpiece material type, and our experimental platform can measure the cutting force in real time during the cutting process, we can consider using the cutting force characteristic value to identify the transformation of bimetallic material regions during the cutting process.

[0072] In one or more implementation examples, a method for real-time material identification in bimetallic milling processes based on unit cutting force maps is disclosed, including:

[0073] Determination of cutting force characteristic values ​​for material identification:

[0074] Unlike simply using the gradient change of cutting force over time to identify materials, this example uses unit cutting force for material identification. During the cutting process, parameters such as shear angle, friction angle, and shear yield stress are difficult or impossible to measure. The combined effect of these parameters is included in the unit cutting force of the force model.

[0075] Calculation of unit cutting force:

[0076] Calculate the unit cutting force from the cutting power: unit cutting force k c It is an important parameter characterizing the cutting process. It describes the force required to process materials with specific process parameters, as shown in equation (4).

[0077]

[0078] A is the cross-section of the chip, and the cutting force F is... c Since it cannot be directly measured, it is related to the cutting power Pc, as shown in equation (5).

[0079]

[0080] The cutting power Pc is not a directly measurable parameter. It can be expressed as equation (6).

[0081] P c =M c *ω=M c *2π*n (6)

[0082] In equation (6), the tool rotational speed n is equal to the spindle rotational speed, which can be obtained from the machining process. Cutting torque M c With spindle drive torque M XProportional. This is because each drive has a certain base torque M. X0 This must be subtracted from the driving torque. Therefore, the cutting torque M... c As shown in equation (7).

[0083] M c ~(M) X -M X0 (7)

[0084] In addition, the driving torque M X With the spindle drive load a i It is directly proportional, as shown in equation (8). Ignoring effects such as friction, the driving load a i It is the actual current I i With nominal current I n The percentage value of (current obtained by measurement) is shown in Equation (9).

[0085] M i ~a i (8)

[0086]

[0087] Substituting equation (8) into equation (7) yields the following:

[0088] M c ~(M) X -M X0 )~(a X -a XO (10)

[0089] In the formula, a X and a X0 These are the driving load and the base load, respectively.

[0090] The formula for calculating the cutting speed is shown in equation (11).

[0091] v c =r*ω=d*π*n (11)

[0092] In the formula, d is the diameter of the cutter head;

[0093] The chip cross section A is the number of milling cutter teeth Z involved in the cutting. E The product of the chip cross-sectional area Az of each tooth is shown in Equation (12).

[0094] A = Z E *A Z (12)

[0095] The number of milling cutter teeth Z involved in the cutting process E It is determined by the milling cutter cutting method, as shown in equation (13).

[0096]

[0097] In the formula, the number of teeth Z is known. The angle of approach... and cut-out angle It can be calculated using equation (14-15):

[0098]

[0099]

[0100] In the formula, a e d is the cutting width, and d is the diameter of the cutter head.

[0101] Cross-sectional area A of each tooth's chip Z The chip width b and the average chip thickness h m The result is obtained as shown in equation (16).

[0102] A Z =b*h m (16)

[0103] chip width b and average chip thickness h m It can be calculated using equation (17-18).

[0104]

[0105]

[0106] In the formula, the cutting depth a p and the principal cutting edge angle k of the cutting tool r and feed per tooth f z All of these are known.

[0107] The above formula is based on the calculation of unit cutting force using kinematics.

[0108] for Figure 1 The average driving load for the milling operation shown can be calculated as shown in equation (19).

[0109]

[0110] In this embodiment, both the driving load and the base load are average loads and are calculated using the formula shown in equation (19).

[0111] After calculating the average driving load Then, the unit cutting force can be determined according to formulas (4) to (19). The unit cutting force values ​​under specific conditions are stored in a database so that they can be used in artificial neural networks.

[0112] Predicting cutting force using artificial neural networks:

[0113] The milling process is monitored via a machine data protocol, and the unit cutting force is calculated. The influencing parameters and values ​​of the unit cutting force are collected in a database. Based on this, a neural network is trained to predict the unit cutting force. If the prediction deviation is too large, the artificial neural network is retrained using expanded data; see [link to detailed process] for more information. Figure 1 .

[0114] For more details, please see the appendix. Figure 6 As shown, the process includes measuring the actual current of the driving load during the cutting process, calculating the driving load based on the current, then calculating the cutting torque, cutting power and cutting force, and then calculating the unit cutting force. The calculated data is used as training data to train an ANN neural network to obtain the tool diameter, number of tool teeth, principal cutting edge angle, rotational speed, feed per tooth, depth of cut, entry angle and exit angle. These are then input into the trained neural network to obtain the predicted value of the unit cutting force.

[0115] Establishment of the unit cutting force diagram:

[0116] Figure 2 The distribution of unit cutting force (including radial cutting force and axial unit cutting force Kr and Kc) for bimetallic materials under different feed per tooth conditions.

[0117] To reduce errors, the Kc / Kr ratio is used for material identification, such as... Figure 3 As shown.

[0118] Figure 3 This diagram illustrates material identification mapping using Kc / Kr during the milling of bimetallic materials. It's important to note that Kr in milling originates from the radial cutting force. Identifying regions as aluminum and cast iron using the minimum and maximum points on the mapping (without threshold overlap) is a simple approach. Nevertheless, this method can be improved using other more complex clustering methods. This clear distinction enhances material identification accuracy, representing a first step in self-adjusting cutting parameter techniques.

[0119] The implementation process of material identification technology:

[0120] See the attached flowchart for the overall material identification process. Figure 5 As shown, specifically, after obtaining the predicted value of the unit cutting force, the unit cutting force ratio is obtained, and then the material type is determined.

[0121] The actual milling process can be based on Figure 4 The procedure shown is used to identify bimetallic materials.

[0122] By establishing the relationship between physical and mechanical properties such as hardness, plasticity, toughness, elasticity, and coefficient of thermal expansion and the ratio of unit cutting force for different workpiece materials, the material identification method can be extended to more bimetallic materials.

[0123] Example 2

[0124] The purpose of this embodiment is to provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the above-described method.

[0125] Example 3

[0126] The purpose of this embodiment is to provide a computer-readable storage medium.

[0127] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the steps of the above method.

[0128] Example 4

[0129] The purpose of this embodiment is to provide a real-time material identification system for bimetallic milling processes based on a unit cutting force map, including:

[0130] The unit cutting force calculation module is configured to: obtain the drive load of the tool spindle and calculate its average drive load; calculate the unit cutting force based on the average drive load;

[0131] The unit cutting force prediction module is configured to use the calculated unit cutting force for training the neural network during a milling process monitored by a machine data protocol.

[0132] Real-time unit cutting force is predicted based on a trained neural network;

[0133] The unit cutting force map generation module is configured to: generate a unit cutting force map based on the predicted real-time unit cutting force;

[0134] The material identification module is configured to identify materials based on the unit cutting force map.

[0135] The steps and methods involved in the apparatuses of Embodiments 2, 3, and 4 above correspond to those in Embodiment 1. For specific implementation details, please refer to the relevant description section of Embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood as including any medium capable of storing, encoding, or carrying an instruction set for execution by a processor and enabling the processor to perform any of the methods in this invention.

[0136] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computer devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computer device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. The present invention is not limited to any particular combination of hardware and software.

[0137] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A real-time material identification method for bimetallic milling processes based on unit cutting force maps, characterized in that... include: Obtain the drive load of the tool spindle and calculate its average drive load; Calculate the unit cutting force based on the average driving load; The calculated unit cutting force is used to train a neural network during a milling process monitored by a machine data protocol. Real-time unit cutting force is predicted based on a trained neural network; The steps of neural network prediction of cutting force include measuring the actual current of the driving load during the cutting process, calculating the driving load based on the current, then calculating the cutting torque, cutting power and cutting force, and then calculating the unit cutting force. The calculated data is used as training data to train the ANN neural network to obtain the tool diameter, number of tool teeth, principal cutting edge angle, rotation speed, feed per tooth, depth of cut, entry angle and exit angle, which are then input into the trained neural network to obtain the predicted value of the unit cutting force. Based on the predicted real-time unit cutting force, a unit cutting force map is established; The steps for establishing the unit cutting force map include: establishing the corresponding radial cutting force and axial unit cutting force distributions Kr and Kc for bimetallic materials under different feed per tooth conditions; Material identification is performed based on a unit cutting force map, which includes material identification using the Kc / Kr ratio.

2. The real-time material identification method for bimetallic milling process based on unit cutting force spectrum as described in claim 1, characterized in that, The specific formula for calculating the unit cutting force is as follows: in, It is the unit cutting force, and A is the chip cross-section. This is the cutting force.

3. The real-time material identification method for bimetallic milling process based on unit cutting force spectrum as described in claim 2, characterized in that, The specific process for calculating cutting force is as follows: in, Pc is the cutting force, and Pc is the cutting power. This refers to the cutting speed.

4. The real-time material identification method for bimetallic milling process based on unit cutting force spectrum as described in claim 3, characterized in that, The formula for calculating the cutting power is: 2 Wherein, the tool rotation speed n is equal to the spindle rotation speed, which can be obtained from the machining process, and the cutting torque M... c With spindle drive torque M X Proportional.

5. The real-time material identification method for bimetallic milling process based on unit cutting force spectrum as described in claim 4, characterized in that, The cutting torque M c As shown in the following formula: ； The driving torque M X With the spindle drive load a i Proportional to the load a i It is the actual current I i With nominal current I n The percentage value is obtained as follows: ； In the formula, and These are the driving load and the base load, respectively. This is the initial driving torque.

6. The real-time material identification method for bimetallic milling process based on unit cutting force spectrum as described in claim 3, characterized in that, The formula for calculating the cutting speed is as follows: n（11） In the formula, d is the diameter of the cutter head, and n is the cutting speed.

7. The real-time material identification method for bimetallic milling process based on unit cutting force spectrum as described in claim 2, characterized in that, The chip cross-section A is the number of milling cutter teeth Z involved in the cutting. E The product of the chip cross-sectional area Az of each tooth; The number of milling cutter teeth Z involved in the cutting process E Determined by the milling cutter's cutting method: （13） In the formula, the number of teeth Z is known, and the angle of approach is... and cut-out angle It can be calculated using the following formula: In the formula, a e d is the cutting width, and d is the diameter of the cutter head; Cross-sectional area A of each tooth's chip Z The chip width b and the average chip thickness h m The calculation yielded: chip width b and average chip thickness h m Calculate using the following formula: In the formula, the cutting depth a p and the main cutting edge angle of the cutting tool k r and feed per tooth f z All of these are known.

8. A real-time material identification system for bimetallic milling processes based on unit cutting force maps, characterized in that, include: The unit cutting force calculation module is configured to: obtain the drive load of the tool spindle and calculate its average drive load; Calculate the unit cutting force based on the average driving load; The unit cutting force prediction module is configured to use the calculated unit cutting force for training the neural network during a milling process monitored by a machine data protocol. Real-time unit cutting force is predicted based on a trained neural network; The steps of neural network prediction of cutting force include measuring the actual current of the driving load during the cutting process, calculating the driving load based on the current, then calculating the cutting torque, cutting power and cutting force, and then calculating the unit cutting force. The calculated data is used as training data to train the ANN neural network to obtain the tool diameter, number of tool teeth, principal cutting edge angle, rotation speed, feed per tooth, depth of cut, entry angle and exit angle, which are then input into the trained neural network to obtain the predicted value of the unit cutting force. The unit cutting force map generation module is configured to: generate a unit cutting force map based on the predicted real-time unit cutting force; The steps for establishing the unit cutting force map include: establishing the corresponding radial cutting force and axial unit cutting force distributions Kr and Kc for bimetallic materials under different feed per tooth conditions; The material identification module is configured to identify materials based on a unit cutting force map, which includes material identification using the Kc / Kr ratio.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it performs the steps of the method described in any one of claims 1-7.

Images