Cutting force prediction method based on physical guidance data driven network

By adopting a data-driven network method based on physical guidance in cutting force prediction, combining the data-driven module and the physical guidance module, the problems of insufficient accuracy and poor model interpretation in the existing technology are solved, and high-precision and strong adaptability are achieved. Force prediction reduces dependence on large amounts of data.

CN119066979AActive Publication Date: 2024-12-03HEFEI INSTITUTE OF PHYSICAL SCIENCE CHINESE ACADEMY OF SCIENCES

Patent Information

Application Number
CN202411241804.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-05
Publication Date
2024-12-03
Estimated Expiration
2044-09-05

AI Technical Summary

Technical Problem

The existing cutting force prediction methods have problems such as insufficient accuracy, limited scope of application, poor model interpretability and dependence on large amounts of data, resulting in low machining efficiency, dimensional errors and tool wear.

Method used

Using a data-driven network method based on physical guidance, the cutting force signal and processing information are collected through force sensors, combined with the data-driven module and the physical guidance module, the cutting force prediction model is constructed using the autoencoder and the extended Kalman filtering algorithm, and the physical term loss is introduced. Functions to improve model consistency and interpretability.

Benefits of technology

It realizes higher precision and wider application of cutting force prediction, reduces dependence on large amounts of data, improves the interpretability and adaptability of the model, and enhances the ability to capture complex nonlinear relationships.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066979A_ABST
    Figure CN119066979A_ABST
Patent Text Reader

Abstract

The invention discloses a cutting force prediction method based on a physical guidance data driven network, which is applied to various manufacturing and processing scenes, especially in a processing environment requiring high precision and high efficiency, and comprises the following steps: 1, collecting a model training data set; 2, constructing a physical boot data driven network; 3, constructing a loss function of the physical boot data driven network; 4, training and obtaining a cutting force prediction model meeting a specified threshold value; and 5, machining information in the machining process is input into the cutting force prediction model to obtain a predicted value, and visualization is achieved. According to the method, related limitations brought by a purely physical method and a data driving method are solved, and by combining the mechanism analysis of a physical model and the learning ability of a data driving model, the complex dynamic state in the cutting process can be more accurately captured, and the learning process is guided by utilizing a physical principle; therefore, the dependence on a large amount of data is reduced, and the prediction precision, generalization and interpretability of the cutting force are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of cutting force prediction, and in particular is a cutting force prediction method based on a physics-guided data-driven network. Background Art

[0002] Cutting force prediction in intelligent machining plays a vital role in improving production efficiency, reducing costs, ensuring machining quality, and improving the safety of equipment and operators. Too high a cutting force prediction may lead to the selection of smaller cutting parameters, thereby reducing machining efficiency. Inaccurate or uneven cutting force prediction may lead to dimensional errors and reduced surface quality during machining, affecting the accuracy and performance of the product. It may also increase tool wear and shorten the tool life.

[0003] The current methods for predicting cutting forces are mainly divided into physics-based methods and data-driven methods. Physics-based methods include simplified models based on empirical formulas, mechanical principle models that deeply analyze cutting mechanisms, and simulations using computer simulation technology. Data-driven methods include statistical learning methods through historical data mining, and complex nonlinear models constructed using machine learning and artificial intelligence technologies. These methods each have their own advantages and limitations. The empirical formula method is easy to apply but has a limited scope of application and cannot reflect the machining mechanism. The mechanical principle model has a wide range of applicability but is complex to model and is affected by many factors. Computer simulation provides detailed processes but consumes a lot of resources. Statistical learning models rely on a large amount of data and have limited generalization capabilities. Although machine learning methods have strong predictive capabilities, they require a large amount of training data and have poor model interpretability. Therefore, in order to overcome the relevant limitations of purely physics-based methods and data-driven methods and to give play to their complementary advantages, it is urgent to develop physics-guided data-driven methods to reduce computational costs and improve model transparency, interpretability, and analytical capabilities. Summary of the invention

[0004] The present invention aims to address the shortcomings of the above-mentioned physics-based methods and data-driven methods, and proposes a cutting force prediction method based on a physics-guided data-driven network, in order to combine the interpretability of the physical model and the generalization ability of the data-driven model, thereby achieving more accurate cutting force prediction.

[0005] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme:

[0006] The cutting force prediction method based on a physics-guided data-driven network of the present invention is characterized in that it is performed according to the following steps:

[0007] Step 1: Use the force sensor installed on the worktable of the CNC machine tool to collect the cutting force signal during the processing online and use it as the label value; collect the processing information of the CNC machine tool as the input of the model, including: processing parameters, material characteristics of the processed parts and cutting fluid conditions, and record the cutting time;

[0008] Step 2: construct a physical guidance data drive network, including: a data drive module and a physical guidance module;

[0009] Step 2.1, the data driven module includes a feature extraction block and a head decision block;

[0010] The feature extraction block is composed of M autoencoder blocks with the same structure and shared weights;

[0011] The head decision block is composed of an attention mechanism layer and a fully connected layer in series;

[0012] Step 2.1.1, input the collected processing information into the data driving module, and after being processed by the M autoencoders of the feature extraction block in turn, obtain a processing feature vector;

[0013] Step 2.1.2, the attention mechanism layer of the head decision block extracts features from the processing feature vector to obtain processing attention features, and then obtains data prediction cutting force after being processed by the fully connected layer;

[0014] Step 2.2, the physical guidance module includes an extended Kalman filter block and a mechanical model block;

[0015] Step 2.2.1, input the data predicted cutting force into the extended Kalman filter block, process it by the extended Kalman filter method, and obtain the specific force coefficient and initial cutting angle required by the mechanical model block;

[0016] Step 2.2.2, inputting the specific force coefficient, the initial intrusion angle and the processing parameters into the mechanical model block to obtain the physical predicted milling force;

[0017] Step 3: Use formula (1) to construct the loss function of the physical guided data driven network :

[0018] (1)

[0019] In formula (1), represents the data term loss function, represents the physical term loss function; represents the coefficient of scale variation;

[0020] Step 4: Train the physical guided data driven network by gradient descent method to obtain a trained milling force prediction model:

[0021] Step 4.1: Train the data-driven module and calculate the data item loss function To update the parameters of the data driver module, when When it drops to the specified threshold, the pre-trained data-driven module is obtained;

[0022] Step 4.2: Train the pre-trained data-driven module and physical guidance module, and calculate the loss function To update the parameters of the network, when When it drops to the specified threshold, the trained cutting force prediction model is obtained;

[0023] Step 5: Input the processing information of a section of the processing process into the trained cutting force prediction model, obtain the predicted value of the cutting force under the corresponding processing conditions and visualize it.

[0024] The cutting force prediction method based on a physics-guided data-driven network described in the present invention is also characterized in that step 2.2.1 includes:

[0025] Step a: Use the specific force coefficient and the initial intrusion angle as the estimated variables of the extended Kalman filter algorithm, use the data predicted cutting force as the observed variable in the extended Kalman filter, and use formula (2) to obtain the state estimation variable of the i+1 stage: :

[0026] (2)

[0027] In formula (2), is the state transfer matrix of stage i, is the predicted cutting force at stage i, is the nonlinear function of stage i, is the process noise of stage i, is the measurement noise of stage i; is the state estimation variable of stage i, and ,in, They represent the tangential cutting force coefficient of stage i, the radial cutting force coefficient of stage i, the tangential edge force coefficient of stage i, and the radial edge force coefficient of stage i, respectively. are the lateral and longitudinal jumping forces in stage i, They are Derivative, is the initial angle of stage i;

[0028] Step b: Use equations (3) and (4) to obtain the prior estimates of the state estimation variables of stage i: and the posterior estimate ;

[0029] (3)

[0030] (4)

[0031] In formula (3) and formula (4), is the Kalman filter gain of stage i.

[0032] 3. According to the cutting force prediction method based on physical guided data driven network in claim 1, it is characterized in that in step 2.2.2, the physical predicted milling force of stage i is obtained by using formula (5): :

[0033] (5)

[0034] In formula (5), is the rotation matrix of stage i, is the specific force coefficient matrix of stage i, for The uncut thickness of the jth cutting edge on the tool at is the time of stage i, for The tool cutting depth at is the number of blades, is the upper limit of the height of the cutting part of the jth cutting edge on the tool during processing, It is the lower limit of the height of the cutting part of the jth cutting edge on the tool during processing.

[0035] Furthermore, the step 3 comprises:

[0036] Step 3.1: Use formula (6) to construct the data loss function :

[0037] (6)

[0038] In formula (6), is the milling force predicted by the data of stage i, is the real milling force at stage i, and n represents the total number of stages;

[0039] Step 3.2: Use formula (7) to construct the physical term loss function :

[0040] (7)

[0041] In formula (7), represents the physical consistency function, and , is a nonlinear function operator, representing the mechanical model process, represents the extended Kalman filter process, represents the processing parameters of stage i;

[0042] Step 3.3: Calculate the scale difference coefficient using formula (8) ;

[0043] (8)

[0044] In formula (8), epoch is the number of times all training data sets are used for training. Represents the activation function.

[0045] The electronic device of the present invention includes a memory and a processor, wherein the memory is used to store a program that supports the processor to execute the cutting force prediction method, and the processor is configured to execute the program stored in the memory.

[0046] The present invention provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and the computer program executes the steps of the cutting force prediction method when the computer program is executed by a processor.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. The present invention can learn the implicit patterns from a large amount of data through a data-driven module, so that the prediction model is not only applicable to specific cutting conditions, but also can adapt to different materials, tools and processing parameters.

[0049] 2. The present invention embeds the prior knowledge of the cutting force mechanical model into the data-driven model by introducing the physical term loss function, and uses the physical model labels and real labels to jointly train the network, thereby reducing the dependence on large amounts of data, improving physical consistency, and enhancing the interpretability of traditional data-driven models.

[0050] 3. By combining the mechanism analysis of the physical model and the generalization ability of the data-driven model, the present invention can more accurately capture the complex nonlinear relationship in the cutting process, thereby improving the accuracy of cutting force prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a flow chart of a cutting force prediction method based on a physics-guided data-driven network according to an embodiment of the present invention;

[0052] Figure 2 It is a structural diagram of a feature extraction block according to an embodiment of the present invention;

[0053] Figure 3 A comparison diagram of the predicted value and the actual value of the cutting force in the x-direction of an embodiment of the present invention;

[0054] Figure 4 1 is a comparison diagram between the predicted value and the actual value of the cutting force in the y direction of an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The present invention will be further described in detail below in conjunction with the accompanying drawings in the embodiments of the present invention. The embodiments are only examples and are not intended to limit the present invention.

[0056] In this embodiment, a cutting force prediction method based on a physics-guided data-driven network achieves high-precision and high-generalization cutting force prediction by combining a physical model with a data-driven model. Figure 1 This is a flow chart of a cutting force prediction method based on a physics-guided data-driven network according to an embodiment of the present invention. The specific steps are as follows:

[0057] Step 1: Use the force sensor installed on the workbench of the CNC machine tool to collect the cutting force signal during the processing online and use it as the label value; collect the processing information of the CNC machine tool as the input of the model, including: processing parameters, material properties of the processed parts and cutting fluid conditions, and record the cutting time. In this embodiment, the CNC machine tool adopts the JDGR50A10H vertical milling machining center, which contains multiple wiring ports and sensor fixing brackets. The force sensor adopts Kistler9265B with a sampling frequency of 24 kHz and is installed on the sensor fixing bracket. During the processing, a double-edged milling cutter is used to perform transverse cutting on the AISI4340 workpiece, during which the processing information of the CNC machine tool is collected and the cutting force signal is collected synchronously. The collected processing information and cutting force signal are simultaneously cleaned, and the processing information data is normalized. Data cleaning includes removing redundant data, processing missing data and processing abnormal values.

[0058] Step 2: construct a physical guidance data drive network, including: a data drive module and a physical guidance module;

[0059] Step 2.1, the data driven module includes a feature extraction block and a head decision block;

[0060] The feature extraction block consists of M autoencoder blocks with the same structure and shared weights;

[0061] The head decision block is composed of an attention mechanism layer and a fully connected layer in series;

[0062] Step 2.1.1: Input the collected processing information into the data driving module, and then process it through the M autoencoders of the feature extraction block to obtain the processing feature vector. Figure 2 As shown, in this example, M is 3. is the input i-stage processing information vector, is the output feature vector of stage i processing.

[0063] Step 2.1.2: The attention mechanism layer of the head decision block extracts features from the processing feature vector to obtain the processing attention features, which are then processed by the fully connected layer to obtain the data predicted cutting force.

[0064] Step 2.2, the physical guidance module includes an extended Kalman filter block and a mechanical model block;

[0065] Step 2.2.1, input the data predicted cutting force into the extended Kalman filter block, process it through the extended Kalman filter method, and obtain the specific force coefficient and initial cutting angle required by the mechanical model block;

[0066] Step a: Use the specific force coefficient and the initial intrusion angle as the estimated variables of the extended Kalman filter algorithm, use the data predicted cutting force as the observed variable in the extended Kalman filter, and use formula (1) to obtain the state estimation variable of the i+1 stage: :

[0067] (1)

[0068] In formula (1), is the state transfer matrix of stage i, is the predicted cutting force at stage i, is the nonlinear function of stage i, is the process noise of stage i, is the measurement noise of stage i; is the state estimation variable of stage i, and ,in, They represent the tangential cutting force coefficient of stage i, the radial cutting force coefficient of stage i, the tangential edge force coefficient of stage i, and the radial edge force coefficient of stage i, respectively. are the lateral and longitudinal jumping forces in stage i, They are Derivative, is the initial angle of stage i.

[0069] When the sampling frequency is high, the nonlinear function can be linearized, so the state space can be expressed as shown in formula (2):

[0070] (2)

[0071] In formula (2), is the Jacobian matrix of stage i;

[0072] Step b: Use equations (3) and (4) to obtain the prior estimates of the state estimation variables of stage i: and the posterior estimate ;

[0073] (3)

[0074] (4)

[0075] In formula (3) and formula (4), is the Kalman filter gain of stage i, which is updated according to formula (5);

[0076] (5)

[0077] In formula (5), is the prior estimate of the covariance matrix of stage i, is the posterior estimate of the covariance matrix of stage i, is the covariance matrix of process noise, is the covariance matrix of the measurement noise.

[0078] Step 2.2.2, input the specific force coefficient, initial intrusion angle and machining parameters into the mechanical model block to obtain the physical predicted milling force;

[0079] Use formula (6) to obtain the physical prediction milling force at stage i: :

[0080] (6)

[0081] In formula (6), is the rotation matrix of stage i, is the specific force coefficient matrix of stage i, for The uncut thickness of the jth cutting edge on the tool at is the time of stage i, for The tool cutting depth at is the number of blades, is the upper limit of the height of the cutting part of the jth cutting edge on the tool during processing, It is the lower limit of the height of the cutting part of the jth cutting edge on the tool during processing.

[0082] Step 3: Use formula (7) to construct the loss function of the physical guided data driven network :

[0083] (7)

[0084] In formula (7), represents the data term loss function, represents the physical term loss function; represents the coefficient of scale variation;

[0085] Step 3.1: Use formula (8) to construct the data loss function :

[0086] (8)

[0087] In formula (8), is the milling force predicted by the data of stage i, is the real milling force at stage i, and n represents the total number of stages.

[0088] Step 3.2: Use formula (9) to construct the physical term loss function :

[0089] (9)

[0090] In formula (9), represents the physical consistency function, and , is a nonlinear function operator, representing the mechanical model process, represents the extended Kalman filter process, Indicates the processing parameters of stage i.

[0091] Step 3.3: Calculate the scale difference coefficient using formula (10) ;

[0092] (10)

[0093] In formula (10), epoch is the number of times all training data sets are used for training. Represents the activation function.

[0094] Step 4: Train the physical guided data driven network by gradient descent method. In this case, the gradient descent algorithm can be Adam, SGD, MSprop or Adadelta to obtain the trained milling force prediction model:

[0095] Step 4.1: Train the data-driven module and calculate the data item loss function To update the parameters of the data driver module, when When it drops to the specified threshold, the pre-trained data-driven module is obtained;

[0096] Step 4.2: Train the pre-trained data-driven module and physical guidance module, and calculate the loss function To update the parameters of the network, when When it drops to the specified threshold, the trained cutting force prediction model is obtained;

[0097] Step 5: Input the processing information of a section of the processing process into the trained cutting force prediction model, obtain the predicted value of the cutting force under the corresponding processing conditions and realize visualization. The visualization result of the comparison between the cutting force prediction and the actual value in this embodiment is as follows: Figure 3 and Figure 4 As shown, Figure 3 It is a visual diagram of the cutting force comparison in the x direction. Figure 4 It is a visualization diagram of the cutting force comparison in the y direction.

[0098] In this embodiment, an electronic device includes a memory and a processor, wherein the memory is used to store a program that supports the processor to execute the above method, and the processor is configured to execute the program stored in the memory.

[0099] In this embodiment, a computer-readable storage medium stores a computer program on the computer-readable storage medium, and the computer program executes the steps of the above method when executed by a processor.

[0100] In summary, the present invention combines the mechanism analysis of the physical model and the generalization ability of the data-driven model, and can more accurately predict the cutting force, solving the problem that the traditional cutting force prediction method may be too dependent on empirical formulas or a single data-driven model and have insufficient accuracy; the present invention enhances the adaptability of the model to different cutting conditions by introducing physical principles, solving the problem that a single data-driven model may have insufficient generalization ability when facing new or unknown cutting conditions; the present invention combines the physical model to improve the interpretability of the model, making the prediction results easier to understand and accept, solving the problem that the pure data-driven model is regarded as a "black box" and its prediction results are difficult to explain; the present invention reduces the dependence on a large amount of data through a physically guided method, guides the training and prediction of the model through physical principles, and solves the problem that some data-driven models require a large amount of labeled data for training. This method has the advantages of high prediction accuracy, strong adaptability, good interpretability, and reduced dependence on a large amount of data.

Claims

1. A cutting force prediction method based on a physics-guided data-driven network, characterized in that: Follow these steps: Step 1: Use the force sensor installed on the worktable of the CNC machine tool to collect the cutting force signal during the processing online and use it as the label value; collect the processing information of the CNC machine tool as the input of the model, including: processing parameters, material characteristics of the processed parts and cutting fluid conditions, and record the cutting time; Step 2: construct a physical guidance data drive network, including: a data drive module and a physical guidance module; Step 2.1, the data driven module includes a feature extraction block and a head decision block; The feature extraction block is composed of M autoencoder blocks with the same structure and shared weights; The head decision block is composed of an attention mechanism layer and a fully connected layer in series; Step 2.1.1, input the collected processing information into the data driving module, and after being processed by the M autoencoders of the feature extraction block in turn, obtain a processing feature vector; Step 2.1.2, the attention mechanism layer of the head decision block extracts features from the processing feature vector to obtain processing attention features, and then obtains data prediction cutting force after being processed by the fully connected layer; Step 2.2, the physical guidance module includes an extended Kalman filter block and a mechanical model block; Step 2.2.1, input the data predicted cutting force into the extended Kalman filter block, process it by the extended Kalman filter method, and obtain the specific force coefficient and initial cutting angle required by the mechanical model block; Step 2.2.2, inputting the specific force coefficient, the initial intrusion angle and the processing parameters into the mechanical model block to obtain the physical predicted milling force; Step 3: Use formula (1) to construct the loss function of the physical guided data driven network : (1) In formula (1), represents the data term loss function, represents the physical term loss function; represents the coefficient of scale variation; Step 4: Train the physical guided data driven network by gradient descent method to obtain a trained milling force prediction model: Step 4.1: Train the data-driven module and calculate the data item loss function To update the parameters of the data-driven module, when When it drops to the specified threshold, the pre-trained data-driven module is obtained; Step 4.2: Train the pre-trained data-driven module and physical guidance module, and calculate the loss function To update the parameters of the network, when When it drops to the specified threshold, the trained cutting force prediction model is obtained; Step 5: Input the processing information of a section of the processing process into the trained cutting force prediction model, obtain the predicted value of the cutting force under the corresponding processing conditions and visualize it.

2. The cutting force prediction method based on a physics-guided data-driven network according to claim 1, characterized in that: Step 2.2.1 includes: Step a: Use the specific force coefficient and the initial intrusion angle as the estimated variables of the extended Kalman filter algorithm, use the data predicted cutting force as the observed variable in the extended Kalman filter, and use formula (2) to obtain the state estimation variable of the i+1 stage: : (2) In formula (2), is the state transfer matrix of stage i, is the predicted cutting force at stage i, is the nonlinear function of stage i, is the process noise of stage i, is the measurement noise of stage i; is the state estimation variable of stage i, and ,in, They represent the tangential cutting force coefficient of stage i, the radial cutting force coefficient of stage i, the tangential edge force coefficient of stage i, and the radial edge force coefficient of stage i, respectively. are the lateral and longitudinal jumping forces in stage i, They are Derivative, is the initial angle of stage i; Step b: Use equations (3) and (4) to obtain the prior estimates of the state estimation variables of stage i: and the posterior estimate ; (3) (4) In formula (3) and formula (4), is the Kalman filter gain of stage i.

3. The cutting force prediction method based on a physics-guided data-driven network according to claim 1, characterized in that: In step 2.2.2, equation (5) is used to obtain the physical prediction milling force at stage i: : (5) In formula (5), is the rotation matrix of stage i, is the specific force coefficient matrix of stage i, for The uncut thickness of the jth cutting edge on the tool at is the time of stage i, for The tool cutting depth at is the number of blades, is the upper limit of the height of the cutting part of the jth cutting edge on the tool during processing, It is the lower limit of the height of the cutting part of the jth cutting edge on the tool during processing.

4. The cutting force prediction method based on a physics-guided data-driven network according to claim 1, characterized in that: The step 3 comprises: Step 3.1: Use formula (6) to construct the data loss function : (6) In formula (6), is the milling force predicted by the data of stage i, is the real milling force at stage i, and n represents the total number of stages; Step 3.2: Use formula (7) to construct the physical term loss function : (7) In formula (7), represents the physical consistency function, and , is a nonlinear function operator, representing the mechanical model process, represents the extended Kalman filter process, represents the processing parameters of stage i; Step 3.3: Calculate the scale difference coefficient using formula (8) ; (8) In formula (8), epoch is the number of times all training data sets are used for training. Represents the activation function.

5. An electronic device, comprising a memory and a processor, characterized in that: The memory is used to store a program that supports the processor to execute the cutting force prediction method described in any one of claims 1 to 3, and the processor is configured to execute the program stored in the memory.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the cutting force prediction method according to any one of claims 1 to 3 are executed.

Citation Information

Patent Citations

  • Cutter wear state monitoring method of deep learning network based on physical guidance and application

    CN115446663A

  • Cutter wear state monitoring method based on multi-scale space-time fusion network model

    CN115828754A

  • Cutting machining real-time simulation visualization method based on unreal engine

    CN116796464A

  • Fluid-structure interaction system prediction method for recursive physical information deep learning

    CN116822337A

  • Machining parameter recommendations using in-process machining data aggregation

    US20240069525A1

Cited By

  • Three-dimensional stratum model construction method and system, electronic equipment and storage medium

    CN120182513A