Physical information embedded instantaneous cutting force prediction method and system

Abstract

The invention belongs to the technical field of cutting force prediction, and discloses a physical information embedded instantaneous cutting force prediction method and system. The method comprises the steps of inputting machining time sequence data into a feature extraction network of a trained instantaneous cutting force prediction model to obtain features of the machining time sequence data; the static machining parameters are input into the theoretical mechanical cutting force model, and corresponding theoretical cutting force is obtained through calculation; the theoretical cutting force and the static machining parameters are spliced to obtain a mechanism feature vector, and the mechanism feature vector is input into a full connection layer of the instantaneous cutting force prediction model; and in the full connection layer, splicing and regression are carried out on the mechanism feature vector and the obtained machining time sequence data features, and an instantaneous cutting force prediction result is obtained. According to the method, the accuracy of cutting force prediction can be improved, the generalization ability of the model and the real-time performance of prediction can be improved, and the interpretability of the model is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of cutting force prediction, and more specifically, relates to a physical information embedded instantaneous cutting force prediction method and system. Background Art

[0002] Boring is a common method for making deep grooves or deep cuts, which involves the axial movement of the tool into the workpiece, using a rotating tool to remove material. The technique is known for axial feed, which reduces cutting forces, improves chip removal and extends tool life. In boring operations, accurate prediction of cutting forces is important for optimizing machining parameters, designing robust machining processes and preventing tool failure.

[0003] In the complex boring process, it is very difficult to directly measure and collect cutting force, and the cost of intelligent toolholders that can detect cutting force is very high. Therefore, the cutting force of boring processing is generally predicted by relevant data during the processing. With the rise of deep learning, cutting force prediction methods based on deep neural networks have occupied an increasingly critical position.

[0004] Existing deep learning-based cutting force prediction mainly uses a single data detection method, such as cutting force prediction based on current signals or vibration signals during machining, which results in insufficient prediction accuracy and limited generalization. At the same time, the existing prediction models also have the problem of poor interpretability. In addition, many prediction models are limited by the large amount of calculation and usually use cloud computing for real-time diagnosis, which increases dependence on the network. When the network is disconnected, they cannot work normally, which has a serious impact on production efficiency. Summary of the invention

[0005] In view of the above defects or improvement needs of the prior art, the present invention provides a physical information embedded instantaneous cutting force prediction method and system, which aims to improve the accuracy of cutting force prediction, improve the generalization ability of the model, and the real-time performance of the prediction.

[0006] To achieve the above object, according to a first aspect of the present invention, a method for predicting instantaneous cutting force with physical information embedded is provided, comprising:

[0007] Inputting the processing time series data into the feature extraction network of the trained instantaneous cutting force prediction model to obtain the features of the processing time series data; wherein the processing time series data includes a tool vibration signal and a machine tool motor current signal;

[0008] The static machining parameters are input into the theoretical mechanical cutting force model to calculate the corresponding theoretical cutting force; the theoretical cutting force is concatenated with the static machining parameters to obtain a mechanism characteristic vector, and the mechanism characteristic vector is input into the fully connected layer of the instantaneous cutting force prediction model; wherein the static machining parameters include the rotation speed, feed rate and cutting depth of the tool;

[0009] In the fully connected layer, the mechanism feature vector is concatenated and regressed with the acquired processing timing data features to obtain the instantaneous cutting force prediction result.

[0010] Further, the features of the processing time series data include global time series features and local time series features;

[0011] The feature extraction network includes:

[0012] An embedding layer, used for converting the processed time series data into a high-dimensional time series vector;

[0013] A position encoding layer, used for position encoding the high-dimensional time series vector to obtain encoded processed time series data;

[0014] An attention layer, used for calculating the weights of the features of different scales of the encoded processed time series data by using the attention mechanism, and performing weighted summation on the features of different scales by using the corresponding weights to obtain a fused global time series feature;

[0015] A feed-forward layer, used for performing nonlinear mapping on the global temporal features;

[0016] Normalization layer, used to normalize the global temporal features after nonlinear mapping;

[0017] The convolution module is used to extract local features from the normalized global time series features to obtain finer-grained local time series features;

[0018] Correspondingly, the fully connected layer is used to concatenate and regress the normalized global time series features, the local time series features and the mechanism feature vector to obtain an instantaneous cutting force prediction result.

[0019] Furthermore, the theoretical mechanical cutting force model is:

[0020]

[0021] Among them, F c is the theoretical cutting force, A is the yield strength, B is the strain hardening coefficient, C is the strain rate sensitivity coefficient, n is the strain hardening index, m is the thermal softening index, ∈ is the shear plastic strain; v is the relative speed between the tool and the workpiece material, which is determined based on the rotation speed of the tool; h is the undeformed chip thickness, T is the temperature of the workpiece material, Troom is room temperature, T melt is the melting point of the workpiece material; φ c is the shear angle, β n is the friction angle, α n is the rake angle of the tool, a p is the cutting depth and f is the feed rate.

[0022] Furthermore, the theoretical mechanical cutting force model is constructed as follows:

[0023] Theoretical cutting force F is established based on Merchant's cutting theory c Relationship with shear force on shear plane:

[0024]

[0025] In the formula, τ s is the shear yield strength of the processed material, A s is the shear area;

[0026] The shear yield strength τ is replaced by the flow stress σ determined based on the simplified Johnson-Cook constitutive model. s ; Wherein, the flow stress σ is:

[0027]

[0028] The shear area A s The cutting depth a p And the feed rate f is determined by:

[0029] A s =a p fsinφ c

[0030] The shear yield strength τ s and the shear area A s Substitute the calculation formula of the theoretical cutting force F into c The theoretical mechanical cutting force model is obtained from the relationship between the shear force on the shear surface.

[0031] Furthermore, the attention mechanism is a multi-scale attention mechanism.

[0032] According to a second aspect of the present invention, a physical information embedded instantaneous cutting force prediction system is provided, comprising: a trained instantaneous cutting force prediction model and a mechanism feature vector acquisition module; the instantaneous cutting force prediction model comprises a feature extraction network and a fully connected layer;

[0033] The feature extraction network is used to extract features of processing time series data; wherein the processing time series data includes tool vibration signals and machine tool motor current signals;

[0034] The mechanism characteristic vector acquisition module is used to input the static machining parameters into the theoretical mechanical cutting force model to calculate the corresponding theoretical cutting force; and to obtain the mechanism characteristic vector after splicing the theoretical cutting force with the static machining parameters; wherein the static machining parameters include the tool rotation speed, feed rate and cutting depth;

[0035] The fully connected layer is used to concatenate and regress the mechanism feature vector with the acquired processing time series data features to obtain an instantaneous cutting force prediction result.

[0036] Further, the features of the processing time series data include global time series features and local time series features;

[0037] The feature extraction network includes:

[0038] An embedding layer, used for converting the processed time series data into a high-dimensional time series vector;

[0039] A position encoding layer, used for position encoding the high-dimensional time series vector to obtain encoded processed time series data;

[0040] An attention layer, used for calculating the weights of the features of different scales of the encoded processed time series data by using the attention mechanism, and performing weighted summation on the features of different scales by using the corresponding weights to obtain a fused global time series feature;

[0041] A feed-forward layer, used for performing nonlinear mapping on the global temporal features;

[0042] Normalization layer, used to normalize the global temporal features after nonlinear mapping;

[0043] The convolution module is used to extract local features from the normalized global time series features to obtain finer-grained local time series features;

[0044] Correspondingly, the fully connected layer is used to concatenate and regress the normalized global time series features, the local time series features and the mechanism feature vector to obtain an instantaneous cutting force prediction result.

[0045] According to a third aspect of the present invention, there is provided an electronic device comprising a computer-readable storage medium and a processor;

[0046] The computer-readable storage medium is used to store executable instructions;

[0047] The processor is used to read the executable instructions stored in the computer-readable storage medium to execute the instantaneous cutting force prediction method embedded with physical information as described in any one of the first aspects.

[0048] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the method for predicting instantaneous cutting force by embedding physical information as described in any one of the first aspects is implemented.

[0049] According to a fifth aspect of the present invention, there is provided a computer program product, comprising a computer program, which, when executed on a computer, enables the computer to execute the instantaneous cutting force prediction method embedded with physical information as described in any one of the first aspects.

[0050] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects:

[0051] (1) The instantaneous cutting force prediction method provided by the present invention is to input the processing time series data in the process of workpiece material processing into the instantaneous cutting force prediction model to extract the time series features, input the static processing parameters into the theoretical mechanical cutting force model, calculate the corresponding theoretical cutting force, and splice the theoretical cutting force with the static processing parameters to obtain the mechanism feature vector. The mechanism feature vector is embedded in the instantaneous cutting force prediction model as physical information, and the mechanism feature vector and the time series features are spliced ​​in the fully connected layer of the model to predict the instantaneous cutting force. The static processing parameters reflect the different processing conditions in the process of workpiece material processing. The static processing parameters and their corresponding theoretical cutting forces constitute the mechanism feature vector and are input into the model. Together with the time series features, they participate in the instantaneous cutting force prediction, which can enhance the generalization ability of the model under different working conditions and speed up the calculation speed of the model to improve the real-time performance of the prediction. In addition, by using processing timing data including tool vibration signals and machine tool motor current signals and static processing parameters including tool rotation speed, feed rate and cutting depth to simultaneously predict cutting force, the present invention takes into account both direct process fluctuations (characteristics of timing data) and long-term force trends (characteristics of theoretical cutting force numerical values) in the cutting process, thereby improving the accuracy of prediction.

[0052] (2) Furthermore, the feature extraction network designed by the present invention positions the convolution module after the attention layer, and establishes a hierarchical feature representation structure. When the attention layer captures global features, the convolution refines these features into more fine-grained local features. Specifically, based on the global features captured by the attention layer, the time series features are processed by convolution to capture local dependencies and patterns, which is crucial for accurately predicting high-frequency non-stationary time series. This hierarchical feature representation structure significantly enhances the recognition and classification capabilities of the model.

[0053] (3) As a preferred method, the attention layer uses a multi-scale attention mechanism to extract time series representation information at different scales. Through the use of the multi-scale attention mechanism and the convolution module, the multi-scale features of the time series signal are fully extracted, and the global features and local features are effectively integrated, which significantly improves the representation learning ability of the model, realizes deep feature extraction from the spatial scale to the temporal dimension, and improves the cutting force prediction accuracy.

[0054] (4) The present invention provides a specific method for calculating theoretical cutting force, which integrates Merchant's cutting theory and the simplified Johnson-Cook constitutive model to construct a theoretical mechanical cutting force model to calculate the cutting force value. Specifically, Merchant's cutting theory is based on the balance of forces in the cutting process, and establishes the relationship between the theoretical cutting force and the shear force on the shear surface; during the cutting process, the shear yield strength τ s The flow stress σ calculated by the simplified Johnson-Cook model without thermal softening terms is used to express it, which provides a theoretical basis for the prediction of cutting force during machining. The theoretical cutting force calculation method provided comprehensively covers the machining geometry information and static machining parameters involved in the theoretical mechanical cutting force model, which can reduce the number of model training iterations, significantly reduce the model training time and convergence speed, and enhance the interpretability of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 Schematic diagram of the instantaneous cutting force prediction method embedded with physical information in an embodiment of the present invention.

[0056] Figure 2 Schematic diagram of the instantaneous cutting force prediction model structure in an embodiment of the present invention.

[0057] Figure 3 This is a verification diagram of the training prediction results based on the boring processing data set in an embodiment of the present invention.

[0058] Figure 4 This is a schematic diagram of a timing signal acquisition module provided in an embodiment of the present invention.

[0059] Figure 5 The figure is a schematic diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0061] Example 1

[0062] like Figure 1 As shown, an embodiment of the present invention provides a physical information embedded instantaneous cutting force prediction method, which mainly includes:

[0063] During the workpiece material processing, multi-channel processing timing data and static processing parameters are collected; in the embodiment of the present invention, the processing timing data includes the tool vibration signal and the machine tool motor current signal, and the static processing parameters include the tool speed, feed rate f and cutting depth a p ;

[0064] Inputting the processing time series data into the feature extraction network of the trained instantaneous cutting force prediction model to obtain the features of the processing time series data;

[0065] The static machining parameters are input into the theoretical mechanical cutting force model to calculate the corresponding theoretical cutting force; the theoretical cutting force and the static machining parameters are concatenated to obtain the mechanism feature vector, and the mechanism feature vector is input into the fully connected layer of the trained instantaneous cutting force prediction model;

[0066] In the fully connected layer, the acquired processing timing data features and mechanism feature vectors are concatenated and regressed to obtain the instantaneous cutting force prediction results.

[0067] As a preferred implementation, the features of the processing time series data include global time series features and local time series features. Correspondingly, Figure 2 As shown, the instantaneous cutting force prediction model mentioned above includes a feature extraction network and a fully connected layer; wherein the feature extraction network includes an embedding layer, a position encoding layer, an attention layer, a feedforward layer, a normalization layer and a convolution module connected in sequence.

[0068] The embedding layer is used to convert the processed time series data (low-dimensional dense data) into high-dimensional time series vectors to facilitate subsequent processing of the model.

[0069] The position encoding layer is used to perform position encoding on the high-dimensional time series vector to obtain the encoded processed time series data, so that the attention mechanism can learn the position information, which is used to reflect the time series order in the time series data. In the embodiment of the present invention, the classic sin and cos encoding method in the transformer is used, and the formula is as follows:

[0070]

[0071] Among them, PE represents position encoding, pos represents the position of the input vector to be requested (i.e., token, output of the embedding layer) in the entire input vector (the converted high-dimensional vector), the position encoding is a vector (embedding), i represents the index of each element in the vector, and dmodel The dimension of the vector representing the positional encoding.

[0072] The attention layer is used to calculate the weights of the features of different scales of the encoded processed time series data using the attention mechanism, and use the corresponding weights to perform weighted summation on the features of different scales to obtain the fused global time series features. In the embodiment of the present invention, the attention weight allocation of the Value is achieved by converging the attention of the Query and the Key, and the final output result is generated. 1 As an example, the attention mechanism between a vector and other vectors, 1 The q vector of the input vector is multiplied by the k vector of other input vectors and passed through the softmax layer to obtain a 1 The matching value of other input vectors is multiplied by the weighted v vector of each input vector to obtain the output vector. This process can be described by the formula:

[0073]

[0074] Among them, Q, K, V are the matrix representations of q, k, and v of the above-mentioned input vectors (encoded processing time series data), d k It is a scaling factor, which makes the dot product result fall in the area with larger softmax function gradient, thereby accelerating the training process of the model.

[0075] Preferably, the attention layer uses a multi-scale attention mechanism to extract time series representation information at different scales.

[0076] The feedforward layer is used to perform nonlinear mapping on the fused global time series features, and after normalization by the normalization layer, obtain the normalized global time series features. In the embodiment of the present invention, the feedforward layer includes a linear layer and a nonlinear activation function, which are used to enhance the model's ability to learn nonlinear mapping relationships; the normalization layer uses layer normalization technology to improve the convergence speed and stability of the model during training.

[0077] The convolution module is used to extract local features of the normalized global time series features to obtain finer-grained local time series features; in an embodiment of the present invention, the convolution module includes a convolution layer, a batch normalization layer, an activation function and a fully connected layer connected in sequence.

[0078] The fully connected layer of the instantaneous cutting force prediction model is used to concatenate and regress the normalized global timing features, local timing features and mechanism feature vectors to obtain the instantaneous cutting force prediction results.

[0079] As a preferred implementation, the theoretical mechanical cutting force model in the embodiment of the present invention calculates the theoretical cutting force value by integrating Merchant cutting theory, oblique cutting theory and a simplified Johnson-Cook constitutive model.

[0080] Merchant's cutting theory starts from the balance of forces during cutting and establishes the relationship between cutting force and shear force on the shear surface:

[0081]

[0082] In the formula, F c is the tangential cutting force, also known as the theoretical cutting force, φ c is the shear angle, β n is the friction angle, α n is the rake angle of the tool, τ s is the shear yield strength of the processed material, A s is the shear area.

[0083] The oblique cutting theory is used to calculate the shear angle φ in the formula c , friction angle β n and the rake angle α of the tool n .

[0084] Determination of shear yield strength τ based on the simplified Johnson-Cook constitutive model s A simplified Johnson-Cook constitutive model is provided in an embodiment of the present invention, which describes the relationship between material flow stress and strain, strain rate and temperature:

[0085]

[0086] Where σ is the flow stress, ∈ is the shear plastic strain; v is the relative speed between the tool and the workpiece material, which is determined based on the tool speed; h is the undeformed chip thickness, T is the temperature of the workpiece material, and T room is room temperature, T melt is the melting point of the workpiece material, A is the yield strength (MPa), B is the strain hardening coefficient (MPa), C is the strain rate sensitivity coefficient, n is the strain hardening exponent, and m is the thermal softening exponent.

[0087] Use flow stress σ instead of shear yield strength τ s , shear area A s The cutting depth a p and the feed rate f is determined by:

[0088] A s =a p fsinφ c

[0089] The theoretical cutting force calculation formula is obtained:

[0090]

[0091] As a preferred implementation method, in an embodiment of the present invention, a data set is used to train an instantaneous cutting force prediction model to obtain the above-mentioned trained instantaneous cutting force prediction model; wherein the samples in the data set include multi-channel processing timing data and static processing parameters, and the labels are the cutting force timing data during the processing, that is, the cutting force corresponding to the processing timing data and static processing parameters at different times.

[0092] The static machining parameters are input into the theoretical mechanical cutting force model to obtain the corresponding theoretical cutting force values, which are then combined with the static machining parameters to form a mechanism characteristic vector.

[0093] The machining timing data and mechanism characteristic vector are input into the instantaneous cutting force prediction model to obtain the corresponding cutting force prediction results.

[0094] The instantaneous cutting force prediction model is trained by minimizing the difference loss between the cutting force prediction results and the corresponding labels.

[0095] In an optional embodiment, data collection is performed in a vertical boring process, the tool used is a triangular boring tool, and the workpiece used is a titanium alloy test piece. Vibration and current signals are collected by sensors, and then through the AD conversion module, high-quality timing data and static parameters of boring processing are finally obtained. All signals are collected at a frequency of 10kHz for 50s. The data set is randomly divided into a training set, a validation set, and a test set, accounting for 80%, 10%, and 10% of the data set, respectively. The model is initialized with random weights using the xavier initialization technique, and the model is optimized using the Adam optimizer.

[0096] After the training is completed, the performance of the model is evaluated using MAE, MSE, R2 and other evaluation indicators. The MAE, RMSE and R2 evaluation indicators of the flank wear bandwidth detection model reached 0.0052, 0.0126 and 0.9578 respectively, which means that the prediction accuracy of the method of the present invention is relatively high. Figure 3 As shown, the predicted value is basically consistent with the true value, which also shows that the prediction accuracy of the method of the present invention is high.

[0097] The instantaneous cutting force prediction method provided by the present invention is to input the processing time series data in the process of workpiece material processing into the instantaneous cutting force prediction model to extract the time series features, input the static processing parameters into the theoretical mechanical cutting force model, calculate the corresponding theoretical cutting force, and obtain the mechanism feature vector after splicing the theoretical cutting force with the static processing parameters. The mechanism feature vector is embedded in the instantaneous cutting force prediction model as physical information, and the mechanism feature vector and the time series features are spliced ​​in the fully connected layer of the model to predict the instantaneous cutting force. The static processing parameters reflect the different processing conditions in the process of workpiece material processing. The static processing parameters and their corresponding theoretical cutting forces constitute the mechanism feature vector and are input into the model. Together with the time series features, they participate in the instantaneous cutting force prediction, which can enhance the generalization ability of the model under different working conditions and accelerate the calculation speed of the model to improve the real-time performance of the prediction. In addition, the processing time series data including the tool vibration signal and the machine tool motor current signal and the tool speed, feed rate f and cutting depth a are used. p By simultaneously predicting the cutting force with the static machining parameters including the cutting force, the present invention takes into account both the direct process fluctuations (characteristics of time series data) and the long-term force trends (characteristics of theoretical cutting force numerical values) in the cutting process, thereby improving the accuracy of the prediction.

[0098] Furthermore, the feature extraction network designed by the present invention positions the convolution module after the attention layer, and establishes a hierarchical feature representation structure. When the attention layer captures global features, the convolution refines these features into more fine-grained local features. Specifically, based on the global features captured by the attention layer, the convolution processes the time series features to capture local dependencies and patterns, which is crucial for accurately predicting high-frequency non-stationary time series. This hierarchical feature representation structure significantly enhances the recognition and classification capabilities of the model.

[0099] The attention layer uses a multi-scale attention mechanism to extract time series representation information at different scales. Through the use of the multi-scale attention mechanism and the convolution module, the multi-scale features of the time series signal are fully extracted, and the global features and local features are effectively integrated, which significantly improves the representation learning ability of the model, realizes deep feature extraction from the spatial scale to the temporal dimension, and improves the cutting force prediction accuracy.

[0100] Furthermore, considering that current deep learning has the black box nature, the calculation process is difficult to understand and has no significant physical meaning, the present invention embeds features that reflect the physical information of the cutting process (static processing parameters and theoretical cutting forces) into the deep learning model, bringing a certain degree of interpretability to the model.

[0101] The present invention provides a specific theoretical cutting force calculation method. By integrating Merchant cutting theory, oblique cutting theory and simplified Johnson-Cook constitutive model to calculate the cutting force value, compared with the prior art, the oblique cutting theoretical cutting force calculation method based on Merchant theory has the advantages of solid theoretical basis, clear physical meaning, high calculation efficiency, good versatility, strong engineering practicality, etc. In the cutting process, the shear yield strength τ s The flow stress σ calculated by the simplified Johnson-Cook model without thermal softening terms is used to express it, which provides a theoretical basis for the prediction of cutting force during machining. The theoretical cutting force calculation method provided comprehensively covers the machining geometry information and static machining parameters involved in the theoretical mechanical cutting force model, which can reduce the number of model training iterations, significantly reduce the model training time and convergence speed, and enhance the interpretability of the model.

[0102] Example 2

[0103] An embodiment of the present invention provides a physical information embedded instantaneous cutting force prediction system, comprising:

[0104] Trained instantaneous cutting force prediction model and mechanism feature vector acquisition module; the instantaneous cutting force prediction model includes a feature extraction network and a fully connected layer;

[0105] The feature extraction network is used to extract features of processing time series data; wherein the processing time series data includes tool vibration signals and machine tool motor current signals;

[0106] The mechanism characteristic vector acquisition module is used to input the static machining parameters into the theoretical mechanical cutting force model to calculate the corresponding theoretical cutting force; and to obtain the mechanism characteristic vector after splicing the theoretical cutting force with the static machining parameters; wherein the static machining parameters include the tool speed, feed rate and cutting depth;

[0107] The fully connected layer is used to concatenate and regress the mechanism feature vector with the acquired machining timing data features to obtain the instantaneous cutting force prediction result.

[0108] For the related technical solutions, please refer to the description in Example 1 and will not be repeated here.

[0109] Furthermore, it also includes a data acquisition module for collecting processing time sequence data and processing static parameters during the processing; wherein the processing time sequence data includes: tool vibration signal and machine tool motor current signal, and the processing static parameters include tool speed, feed rate f and cutting depth a p .

[0110] Specifically, Figure 4As shown, the timing signal acquisition module includes: sensors, main control module, analog-to-digital converter; the sensors include: acceleration sensor and current sensor; the acceleration sensor is installed on the tool handle to collect vibration signals; the current sensor is installed on the machine tool motor to collect current signals. The main control module is used to send start / end signals to each sensor to ensure the synchronization of the collected data; the analog-to-digital converter is used to convert the analog signal sent back by the sensor into a digital signal, which is convenient for the computer to read and save.

[0111] Example 3

[0112] An embodiment of the present invention provides an electronic device, which includes a computer-readable storage medium and a processor; the computer-readable storage medium is used to store executable instructions; the processor is used to read the executable instructions stored in the computer-readable storage medium to execute the instantaneous cutting force prediction method embedded with physical information in Example 1 to obtain an instantaneous cutting force prediction result.

[0113] The electronic device may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The memory may be used to store computer programs and / or modules, and the processor may perform various functions of the electronic device by running or executing computer programs and / or modules stored in the memory, and calling data stored in the memory.

[0114] For the related technical solutions, please refer to the description in Example 1 and will not be repeated here.

[0115] Specifically, Figure 5 As shown, as a specific implementation method, the collected processing timing data and processing static parameters are input into a computer, and the processor in the computer reads the executable instructions stored in the computer-readable storage medium to execute the instantaneous cutting force prediction method embedded with physical information in Example 1 to obtain the instantaneous cutting force prediction result.

[0116] Example 4

[0117] An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method in the above-mentioned embodiment 1 are implemented.

[0118] Specifically, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, an internal memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0119] The relevant technical solutions are the same as above and will not be described again here.

[0120] Example 5

[0121] The embodiment of the present invention provides a computer program product, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps of the method of the above embodiment 1.

[0122] The relevant technical solutions are the same as above and will not be described again here.

[0123] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A physical information embedded instantaneous cutting force prediction method, characterized in that: include: Inputting the processing time series data into the feature extraction network of the trained instantaneous cutting force prediction model to obtain the features of the processing time series data; wherein the processing time series data includes a tool vibration signal and a machine tool motor current signal; The static machining parameters are input into the theoretical mechanical cutting force model to calculate the corresponding theoretical cutting force; the theoretical cutting force is concatenated with the static machining parameters to obtain a mechanism characteristic vector, and the mechanism characteristic vector is input into the fully connected layer of the instantaneous cutting force prediction model; wherein the static machining parameters include the rotation speed, feed rate and cutting depth of the tool; In the fully connected layer, the mechanism feature vector is concatenated and regressed with the acquired processing timing data features to obtain the instantaneous cutting force prediction result.

2. The instantaneous cutting force prediction method based on physical information embedding according to claim 1 is characterized in that: The features of the processing time series data include global time series features and local time series features; The feature extraction network includes: An embedding layer, used for converting the processed time series data into a high-dimensional time series vector; A position encoding layer, used for position encoding the high-dimensional time series vector to obtain encoded processed time series data; An attention layer, used for calculating the weights of the features of different scales of the encoded processed time series data by using the attention mechanism, and performing weighted summation on the features of different scales by using the corresponding weights to obtain a fused global time series feature; A feed-forward layer, used for performing nonlinear mapping on the global temporal features; Normalization layer, used to normalize the global temporal features after nonlinear mapping; The convolution module is used to extract local features from the normalized global time series features to obtain finer-grained local time series features; Correspondingly, the fully connected layer is used to concatenate and regress the normalized global time series features, the local time series features and the mechanism feature vector to obtain an instantaneous cutting force prediction result.

3. The instantaneous cutting force prediction method based on physical information embedding according to claim 1 or 2, characterized in that: The theoretical mechanical cutting force model is: Among them, F c is the theoretical cutting force, A is the yield strength, B is the strain hardening coefficient, C is the strain rate sensitivity coefficient, n is the strain hardening index, m is the thermal softening index, ∈ is the shear plastic strain; v is the relative speed between the tool and the workpiece material, which is determined based on the rotation speed of the tool; h is the undeformed chip thickness, T is the temperature of the workpiece material, T room is room temperature, T melt is the melting point of the workpiece material; φ c is the shear angle, β n is the friction angle, α n is the rake angle of the tool, a p is the cutting depth and f is the feed rate.

4. The instantaneous cutting force prediction method based on physical information embedding according to claim 3 is characterized in that: The theoretical mechanical cutting force model is constructed as follows: Theoretical cutting force F is established based on Merchant's cutting theory c Relationship with shear force on shear plane: In the formula, τ s is the shear yield strength of the processed material, A s is the shear area; The shear yield strength τ is replaced by the flow stress σ determined based on the simplified Johnson-Cook constitutive model. s ; Wherein, the flow stress σ is: The shear area A s The cutting depth a p And the feed rate f is determined by: A s =a p fsinφ c The shear yield strength τ s and the shear area A s Substitute the calculation formula of the theoretical cutting force F into c The theoretical mechanical cutting force model is obtained from the relationship between the shear force on the shear surface.

5. The instantaneous cutting force prediction method based on physical information embedding according to claim 2 is characterized in that: The attention mechanism is a multi-scale attention mechanism.

6. A physical information embedded instantaneous cutting force prediction system, characterized in that: include: A trained instantaneous cutting force prediction model and a mechanism feature vector acquisition module; the instantaneous cutting force prediction model includes a feature extraction network and a fully connected layer; The feature extraction network is used to extract features of processing time series data; wherein the processing time series data includes tool vibration signals and machine tool motor current signals; The mechanism characteristic vector acquisition module is used to input the static machining parameters into the theoretical mechanical cutting force model to calculate the corresponding theoretical cutting force; and to obtain the mechanism characteristic vector after splicing the theoretical cutting force with the static machining parameters; wherein the static machining parameters include the tool rotation speed, feed rate and cutting depth; The fully connected layer is used to concatenate and regress the mechanism feature vector with the acquired processing time series data features to obtain an instantaneous cutting force prediction result.

7. The instantaneous cutting force prediction system with physical information embedding according to claim 6 is characterized in that: The features of the processing time series data include global time series features and local time series features; The feature extraction network includes: An embedding layer, used for converting the processed time series data into a high-dimensional time series vector; A position encoding layer, used for position encoding the high-dimensional time series vector to obtain encoded processed time series data; An attention layer, used for calculating the weights of the features of different scales of the encoded processed time series data by using the attention mechanism, and performing weighted summation on the features of different scales by using the corresponding weights to obtain a fused global time series feature; A feed-forward layer, used for performing nonlinear mapping on the global temporal features; Normalization layer, used to normalize the global temporal features after nonlinear mapping; The convolution module is used to extract local features from the normalized global time series features to obtain finer-grained local time series features; Correspondingly, the fully connected layer is used to concatenate and regress the normalized global time series features, the local time series features and the mechanism feature vector to obtain an instantaneous cutting force prediction result.

8. An electronic device, characterized in that: comprising a computer readable storage medium and a processor; The computer-readable storage medium is used to store executable instructions; The processor is used to read the executable instructions stored in the computer-readable storage medium to execute the instantaneous cutting force prediction method embedded with physical information as described in any one of claims 1-5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the instantaneous cutting force prediction method embedded with physical information as described in any one of claims 1 to 5 is implemented.

10. A computer program product, characterized in that It comprises a computer program, which, when running on a computer, enables the computer to execute the instantaneous cutting force prediction method embedded with physical information as claimed in any one of claims 1 to 5.

Images