A method and system for predicting machine tool milling stability based on hybrid drive

Abstract

The present invention discloses a method and system for predicting machine tool milling stability based on hybrid drive, belonging to the field of advanced manufacturing device prediction technology. The method uses simulation and test data sets to train a prediction network. The prediction network is then back-trained using a back-propagation algorithm with distribution difference loss to complete domain adaptation between the simulation and test domains, thereby obtaining a milling chatter stability prediction model. The obtained milling chatter stability prediction model is used to predict the milling stability of the milling machine based on the milling machine's processing parameters. This method can more effectively handle nonlinear and uncertainty issues, and can effectively address chatter stability domain deviations caused by spindle system nonlinearity and model parameter uncertainty. The local maximum mean difference indicator can extract the distribution differences between the simulation chatter data and the test chatter data, fully extracting the correlation information contained in the data.

Description

Technical Field

[0001] The present invention belongs to the technical field of advanced manufacturing device prediction, and in particular relates to a method and system for predicting machine tool milling stability based on hybrid drive. Background Art

[0002] With the rapid development of modern industry, the automotive, shipbuilding, aerospace, and aviation manufacturing sectors are placing increasingly stringent demands on the surface quality of parts. Part structures are also becoming increasingly complex, and the demands on the processing capabilities of CNC machine tools are also constantly increasing. The selection of cutting parameters during machining must, on the one hand, match the requirements of the part itself, and on the other hand, adapt to the cutting process. For example, in actual machining, overly conservative machining parameters are often selected, making it difficult to fully utilize the machine tool's operating efficiency and limiting cost reduction. Furthermore, blindly selecting high-efficiency machining parameters can easily lead to chatter during the cutting process, seriously affecting part quality, exacerbating tool wear, and increasing the risk of equipment failure. Self-excited chatter remains the primary factor limiting milling productivity in industrial environments, and growing demand has amplified the impact of this factor, becoming a bottleneck restricting my country's manufacturing industry from moving towards high-precision and advanced technology.

[0003] In advanced manufacturing, avoiding chatter is crucial. To achieve this, chatter stability prediction technology has emerged. Traditional chatter stability prediction relies on mechanism modeling. By constructing a machine tool dynamics model, a cutting mechanics model, and a milling dynamics model, this method predicts the milling stability region, defined by rotational speed and critical cutting depth. This effectively optimizes machining parameter selection, ensuring machining accuracy while improving efficiency and enabling high-performance machining using CNC machining equipment. However, with increasing manufacturing demands, this requirement is increasingly difficult to meet in real-world engineering applications. The primary problem is that the chatter stability region predicted by the mechanism model differs significantly from the stability region in actual machining, misleading cutting parameter selection and failing to effectively prevent chatter. The reasons for this difference are mainly from two aspects: (1) The factors inducing the chatter process are extremely complex. The chatter dynamics model itself contains many assumptions and it is difficult to cover all the chatter mechanisms and influencing factors. This leads to the inevitable essential difference between the chatter dynamics model and the actual chatter physical object process. This difference is particularly obvious in high-precision manufacturing processes. (2) The chatter dynamics model involves many input parameters, including the structural geometric parameters of the tool and the tool holder, the material parameters of the tool and the workpiece, the dynamic characteristic parameters including the natural frequency and damping ratio, and the cutting force coefficient, etc. On the one hand, these parameters are uncertain and difficult to accurately identify. On the other hand, the machine tool dynamic characteristic parameters and cutting force coefficient will change with the changes in the processing conditions. This change is more significant in high-demand processing scenarios. These two reasons limit the application of the chatter mechanism model in actual engineering.

[0004] With the rapid development of artificial intelligence (AI) technology in recent years, particularly thanks to the significant advantages of machine learning in handling nonlinear characteristics and identifying system changes, data-driven intelligent chatter stability analysis has garnered increasing attention. However, such methods typically require a large number of chatter samples from experiments or tests. To address this issue, mechanistic data fusion or hybrid-driven approaches have been proposed and are gaining increasing application. These hybrid-driven approaches fall into two main categories. One is probabilistic methods, exemplified by Bayesian reasoning. These methods attribute all uncertainty and variation to probabilistic uncertainty, resulting in a probabilistic chatter stability domain. However, this approach cannot effectively address the nonlinearities present in the chatter stability domain. The other is transfer learning methods, which extract information from mechanistic or simulation models to reduce the amount of experimental or test data required. By incorporating actual test data into the modeling process, these methods significantly address the shortcomings of traditional milling stability prediction methods.

[0005] The main bottleneck of current transfer learning-based intelligent stability prediction methods is efficiency issues caused by insufficient data. Specifically, they require extensive experiments or repeated calls to the mechanism model during each training session to generate sufficient data. Additionally, they require additional manual operations or feature engineering to address data sparsity. These operations, such as introducing sufficient randomness by assigning uncertain ranges to parameters and constructing subnetworks for ensemble learning, require extensive manual intervention. This significantly limits the method's practical application in engineering. Therefore, there is an urgent need for an intelligent milling stability prediction model capable of adaptive training to improve application efficiency. Summary of the Invention

[0006] The purpose of the present invention is to provide a method and system for predicting milling stability of machine tools based on hybrid drive, so as to overcome the problem of poor milling stability prediction accuracy in the prior art. The method of the present invention improves the prediction performance while maintaining a high implementation efficiency.

[0007] To achieve the above object, the technical solution adopted by the present invention is as follows:

[0008] A method for predicting milling stability of a machine tool based on hybrid drive includes the following steps:

[0009] S1, generating simulation data sets based on the milling stability prediction mechanism model and machining condition parameters;

[0010] S2, conducts chatter stability test on the milling process of the machine tool and obtains milling process signals, and constructs a test data set based on the milling process signals;

[0011] S3, using a deep subdomain adaptation network model to extract features from simulation and test datasets for classification and prediction of milling chatter stability states;

[0012] S4, calculating the distribution difference between the simulation data and the flutter test data based on the extracted features in the simulation data set and the test data set, and calculating the distribution difference loss based on the distribution difference;

[0013] S5, the prediction network is trained using the simulation data set and the test data set, and then the prediction network is reversely trained through the back propagation algorithm using the distribution difference loss to complete the domain adaptation of the simulation domain and the test domain, thereby obtaining the milling chatter stability prediction model. The obtained milling chatter stability prediction model is used to predict the milling stability of the milling machine according to the milling machine processing parameters.

[0014] Preferably, the milling stability prediction mechanism model includes a milling cutting mechanics model, a machine tool processing dynamics model and a chatter prediction model.

[0015] Preferably, the simulation data set is formed into a source domain, which is expressed as , which contains labeled simulation samples; input For cutting condition parameters, input parameter definition ,in 、 、 and Represents the spindle speed, axial cutting depth, radial cutting depth and the clamping length of the tool in the tool holder. All optional working conditions together constitute the feature space .

[0016] Preferably, a data acquisition system and a sensor system are used to collect signals during the milling process of the machine tool, and the collected signals are processed by signal processing technology to obtain a signal spectrum, so as to judge whether the stability state, that is, whether chatter occurs, and construct a test data set based on the judgment result.

[0017] Preferably, a local maximum mean distribution difference (LMMD) evaluation index is constructed to evaluate the distribution difference between simulation data and flutter test data.

[0018] Preferably, the distribution difference loss calculated based on the local maximum mean difference between the simulation and test samples of the vibration, and the classification loss of the model together constitute the total loss of the model training.

[0019] Preferably, the distribution difference loss is expressed as:

[0020]

[0021] Where L is the set of all domain adaptation layers;

[0022] Classification loss of Deep Subdomain Adaptation Network (DSAN);

[0023]

[0024] in, is the categorical cross entropy loss, is the total number of simulation and test samples, and are sample features and corresponding labels.

[0025] A hybrid drive-based machine tool milling stability prediction system includes a simulation module, a test module, a classification prediction module, a difference loss module and a prediction module;

[0026] Simulation module, which generates simulation data sets based on the milling stability prediction mechanism model and machining condition parameters;

[0027] The test module performs chatter stability testing on the milling process of the machine tool and obtains milling process signals, and constructs a test data set based on the milling process signals;

[0028] The classification prediction module uses a deep subdomain adaptation network model to extract features from simulation and test datasets for classification prediction of milling chatter stability states;

[0029] A difference loss module calculates the distribution difference between the simulation data and the flutter test data based on the extracted features in the simulation data set and the test data set, and calculates the distribution difference loss based on the distribution difference;

[0030] The prediction module uses the simulation data set and the test data set to train the prediction network, and then uses the distribution difference loss to reversely train the prediction network through the back propagation algorithm to complete the domain adaptation of the simulation domain and the test domain, thereby obtaining the milling vibration stability prediction model. The obtained milling vibration stability prediction model is used to predict the milling stability of the milling machine according to the milling machine processing parameters.

[0031] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned hybrid drive-based intelligent milling stability prediction method are implemented.

[0032] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned hybrid drive intelligent milling stability prediction method.

[0033] Compared with the prior art, the present invention has the following beneficial technical effects:

[0034] The present invention provides a hybrid-drive-based method for predicting machine tool milling stability. This method uses simulation and test datasets to train a prediction network. This network is then back-trained using a distribution difference loss algorithm through a back-propagation algorithm to achieve domain adaptation between the simulation and test domains. This results in a milling chatter stability prediction model. The obtained milling chatter stability prediction model is used to predict the milling stability of the milling machine based on its machining parameters. This method can more effectively address nonlinearity and uncertainty issues, effectively addressing chatter stability domain deviations caused by spindle system nonlinearity and model parameter uncertainty. The local maximum mean difference indicator can extract distribution differences between simulation and test chatter data, fully extracting the correlation information contained in the data.

[0035] Preferably, the loss function of the feedforward neural network is expanded based on the local maximum mean difference. Combined with the backpropagation algorithm, the algorithm automatically completes the distribution difference evaluation and shrinkage during the iteration process, realizes end-to-end training, avoids additional operations such as human intervention and feature engineering, has high analysis efficiency, and has good practical application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 This is a flow chart of a method for predicting stability of intelligent milling based on hybrid drive in an embodiment of the present invention.

[0037] Figure 2 It is the deep sub-domain adaptive network model in the embodiment of the present invention.

[0038] Figure 3 Schematic diagram of the subdomain adaptation process in an embodiment of the present invention.

[0039] Figure 4 1 is a diagram of the vibration stability prediction result and the experimental result in an embodiment of the present invention.

[0040] Figure 5 This is the experimental result based on the sample size dependence experiment in the embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0042] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0043] like Figure 1As shown, the present invention provides a method for predicting the milling stability of a machine tool based on hybrid drive, which is used to effectively detect the stability of hybrid drive intelligent milling, and specifically includes the following steps:

[0044] S1, generating simulation data sets based on the milling stability prediction mechanism model and machining condition parameters;

[0045] S2, conducts chatter stability test on the milling process of the machine tool and obtains milling process signals, and constructs a test data set based on the milling process signals;

[0046] S3, using a deep subdomain adaptation network model to extract features from simulation and test datasets for classification and prediction of milling chatter stability states;

[0047] S4, calculating the distribution difference between the simulation data and the flutter test data based on the extracted features in the simulation data set and the test data set, and calculating the distribution difference loss based on the distribution difference;

[0048] S5, the prediction network is trained using the simulation data set and the test data set, and then the prediction network is reversely trained through the back propagation algorithm using the distribution difference loss to complete the domain adaptation of the simulation domain and the test domain, thereby obtaining the milling chatter stability prediction model. The obtained milling chatter stability prediction model is used to predict the milling stability of the milling machine according to the milling machine processing parameters.

[0049] In the specific implementation of the present application, the milling stability prediction mechanism model includes a milling cutting mechanics model, a machine tool processing dynamics model and a chatter prediction model. According to the definition of transfer learning, the simulation data set constitutes the source domain, which is expressed as , which contains Labeled simulation samples. Input For cutting condition parameters, input parameter definition ,in 、 、 and Represents the spindle speed, axial cutting depth, radial cutting depth and the clamping length of the tool in the tool holder. All optional working conditions together constitute the feature space In this paper, milling stability analysis is considered as a classification problem, so the label space is defined as , where 0 indicates that the milling process is in a stable state, and 1 indicates that the milling process is in a chattering state. is input The corresponding label.

[0050] Specifically, a chatter stability test is conducted on a machine tool's milling process. A data acquisition system and sensor system are used to collect signals during the milling process. These signals can be acoustic or cutting force signals. Signal processing techniques are used to generate a signal spectrum, which can be used to determine the stability state, i.e., whether chatter is occurring. A test data set is then constructed based on this determination. Specifically, the signal processing technique uses the fast Fourier transform method to convert the collected signals into a signal spectrum.

[0051] According to the definition of transfer learning, the test dataset is defined as the target domain , which contains labeled test samples. is input The corresponding label. The feature space of the target domain is , contains the same features as the feature space of the source domain, and assumes that the target domain and the source domain share the same label space.

[0052] Use the deep subdomain adaptation network model to extract features from simulation data and test data: Deep Subdomain Adaptation Network DSAN model structure reference Figure 2 ; Based on the general deep network model structure, this network model adds several final domain adaptation layers to align the source domains extracted from these hidden layers. and target domain Features, shrink the data distribution of the source domain and the target domain, and more effectively extract information from the source domain and the target domain.

[0053] The distribution difference between the simulation data and the flutter test data is calculated based on the extracted features in the simulation data set and the test data set. Specifically, the local maximum mean distribution difference (LMMD) evaluation index is constructed to evaluate the distribution difference between the simulation data and the flutter test data.

[0054] 4.1) The calculation process of the local maximum mean distribution difference (LMMD) between simulation data and flutter test data is as follows:

[0055] The calculation formula of the local maximum mean difference is as follows:

[0056]

[0057] Where p and q represent the source domain respectively and target domain The marginal probability distribution of and yes and In the present invention, the subdomain is defined as It is divided according to the label category. Since milling stability has two categories: stable 0 and chatter 1, and Each contains two subdomains. and Is a subdomain and The marginal probability distribution of . It means that the sample features are mapped to the regenerated Hilbert RKHS space, which has a feature kernel function k. Represents some feature maps that can map the original samples into the RKHS space. represents the mathematical expectation of category c.

[0058] The local maximum mean difference (LMMD) measures the local distribution differences between simulation and chatter test data for stable and chatter samples, respectively. By minimizing this metric in a deep network, the distribution differences between related subdomains within the same category are reduced.

[0059] The characteristic kernel function k of the regenerated Hilbert RKHS space can be expressed as ,in Represents the vector inner product.

[0060] The local maximum mean difference can be estimated as follows

[0061]

[0062] in and Represents simulation samples and test samples The calculation process of sample weight is as follows:

[0063]

[0064] therefore and For simulation or test samples, the expression Both represent the weighted sum of samples for category c.

[0065] In the domain adaptation layer l, the features of the simulation samples and test samples extracted by the neurons are and Using the aforementioned kernel function k, the local maximum mean difference estimation formula of the simulation and test samples is directly calculated by the following formula

[0066] Substituting the features extracted from the hidden layer into the calculation formula, the local maximum mean difference LMMD of the simulation and test samples can be obtained.

[0067] The total difference between simulation data and test samples is based on LMMD. Multi-kernel local maximum mean difference (MK-LMMD) is used to more fully extract distribution difference features. MK-LMMD is implemented by using multiple Gaussian kernel functions with different parameters.

[0068] 4.2) The distribution difference loss is calculated based on the local maximum mean difference of the simulation and test samples based on the vibration, and the classification loss of the model together constitutes the total loss of the model training.

[0069] The distribution difference loss is expressed as

[0070]

[0071] where L is the set of all domain adaptation layers.

[0072] Classification loss for Deep Subdomain Adaptation Network (DSAN).

[0073]

[0074] in, is the categorical cross entropy loss, is the total number of simulation and test samples, and are sample features and corresponding labels.

[0075] The prediction model is trained using the simulation data set and the test data set; first the samples are normalized, and then the normalized samples are used for training:

[0076] 5.1) Through pre-training, the network model learns the basic correlation relationship in the chatter prediction and analysis task. Input simulation sample set , train to obtain the weight matrix W. Fix the weights W1~WN1 of the first N1 layers of the network, corresponding to the common features of the prediction task.

[0077] 5.2) Further, using the vibration test sample set Fine-tune the model. Based on the weight matrix W, input the test sample set , get the updated weight matrix, and then fix the network weights WN1+1~WN1+N2 of the N1+1~N1+N2 layers. The features extracted by this part of the network are still relatively preliminary.

[0078] 5.3) N3 training is completed using the distribution difference loss and back propagation algorithm. The optimization objective function for training DSAN for chatter prediction analysis is:

[0079]

[0080] The training process uses the adaptive motion estimation algorithm Adam. The principle of the subdomain adaptation process is referenced Figure 3 This process does not require manual operation and can be automatically calculated during the iteration process.

[0081] The test samples are input into the model to verify the validity of the model. The present invention is further described below with reference to a specific case study of flutter prediction.

[0082] A vertical machining center was used, with a spindle speed range of [5000 rpm, 11000 rpm], a radial depth of cut range of [50%*D, D], where D is the tool diameter, and a tool clamping length range of [25 mm, 45 mm]. The chatter stability map was determined based on these three parameters. A total of 15 random combinations were selected, constituting 15 cutting cases. Within each case, 25 different speed values ​​(at intervals of 250 rpm) were uniformly sampled, along with five uniform axial depths of cut, resulting in 125 sample points per case. A total of 1875 test samples were collected.

[0083] For this sample set, 400 sample points are randomly selected to form training sets of different sizes, and 1441 sample points are selected from these 100 sample points as test sets.

[0084] First, 100 sample points are randomly selected to form a training set for training. Figure 4 The test and prediction results for a clamping length of 25 mm and a radial cutting depth of 0.55*D are presented. The prediction results include the vibration stability boundary of the mechanism model and the boundary predicted by the method proposed in this invention. It can be seen that the method proposed in this invention can significantly improve the accuracy of the prediction results. The prediction accuracy is defined as the ratio of the number of samples with correct stability prediction to the total number of samples in the validation set. According to the verification results of the complete test set, the prediction accuracy using the mechanism model is 64.1%, while the prediction accuracy using the method proposed in this invention is 84.04%.

[0085] Figure 5 This is a diagram showing the validation accuracy achieved by this method using training sample sets of different sizes. It can be seen that when the number of training samples increases, this method still performs better than other methods, and the prediction accuracy improves with the increase in training samples.

[0086] Through the above embodiments and experimental results, it can be found that the present invention can effectively predict the chatter stability state of the machining condition, helping to effectively avoid the occurrence of chatter during the machining process.

[0087] A hybrid drive-based machine tool milling stability prediction system includes a simulation module, a test module, a classification prediction module, a difference loss module and a prediction module;

[0088] Simulation module, which generates simulation data sets based on the milling stability prediction mechanism model and machining condition parameters;

[0089] The test module performs chatter stability testing on the milling process of the machine tool and obtains milling process signals, and constructs a test data set based on the milling process signals;

[0090] The classification prediction module uses a deep subdomain adaptation network model to extract features from simulation and test datasets for classification prediction of milling chatter stability states;

[0091] A difference loss module calculates the distribution difference between the simulation data and the flutter test data based on the extracted features in the simulation data set and the test data set, and calculates the distribution difference loss based on the distribution difference;

[0092] The prediction module uses the simulation data set and the test data set to train the prediction network, and then uses the distribution difference loss to reversely train the prediction network through the back propagation algorithm to complete the domain adaptation of the simulation domain and the test domain, thereby obtaining the milling vibration stability prediction model. The obtained milling vibration stability prediction model is used to predict the milling stability of the milling machine according to the milling machine processing parameters.

[0093] In another embodiment of the present invention, a terminal device is provided, which includes a processor and a memory, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is used to execute the program instructions stored in the computer storage medium. 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. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention is based on the operation of the hybrid drive intelligent milling stability prediction method.

[0094] In another embodiment of the present invention, the present invention further provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a terminal device for storing programs and data. It is understandable that the computer-readable storage medium herein may include both built-in storage media in the terminal device and, of course, extended storage media supported by the terminal device. The computer-readable storage medium provides storage space, which stores the terminal's operating system. In addition, the storage space also stores one or more instructions suitable for being loaded and executed by a processor. These instructions may be one or more computer programs (including program code). It should be noted that the computer-readable storage medium herein may be a high-speed RAM memory or a non-volatile memory, such as at least one disk storage device. The processor may load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the hybrid drive-based intelligent milling stability prediction method in the above-mentioned embodiment.

[0095] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0096] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0097] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0098] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for predicting milling stability of machine tools based on hybrid drive, characterized in that: The following steps are involved: S1, generating simulation data sets based on the milling stability prediction mechanism model and machining condition parameters; S2, conducts chatter stability test on the milling process of the machine tool and obtains milling process signals, and constructs a test data set based on the milling process signals; S3, using a deep subdomain adaptation network model to extract features from simulation and test datasets for classification and prediction of milling chatter stability states; S4, calculating the distribution difference between the simulation data and the flutter test data based on the extracted features in the simulation data set and the test data set, and calculating the distribution difference loss based on the distribution difference; The distribution difference loss is calculated based on the local maximum mean difference of the simulation and test samples of the vibration, and the classification loss of the model together constitutes the total loss of the model training; The distribution difference loss is expressed as: Where L is the set of all domain adaptation layers; Classification loss of Deep Subdomain Adaptation Network (DSAN); in, is the categorical cross entropy loss, is the total number of simulation and test samples, and are sample features and corresponding labels; S5, the prediction network is trained using the simulation data set and the test data set, and then the prediction network is reversely trained through the back propagation algorithm using the distribution difference loss to complete the domain adaptation of the simulation domain and the test domain, thereby obtaining the milling chatter stability prediction model. The obtained milling chatter stability prediction model is used to predict the milling stability of the milling machine according to the milling machine processing parameters.

2. The method for predicting milling stability of a machine tool based on hybrid drive according to claim 1, characterized in that: The milling stability prediction mechanism model includes a milling cutting mechanics model, a machine tool processing dynamics model and a chatter prediction model.

3. The method for predicting milling stability of a machine tool based on hybrid drive according to claim 2, characterized in that: The simulation data set is formed into the source domain, which is expressed as , which contains labeled simulation samples; input For cutting condition parameters, input parameter definition ,in 、 、 and Represents the spindle speed, axial cutting depth, radial cutting depth and the clamping length of the tool in the tool holder. All optional working conditions together constitute the feature space .

4. The method for predicting milling stability of a machine tool based on hybrid drive according to claim 1, characterized in that: The data acquisition system and sensor system are used to collect signals during the milling process of the machine tool. The collected signals are processed through signal processing technology to obtain the signal spectrum. The stability state, that is, whether chatter occurs, can be determined, and a test data set is constructed based on the judgment results.

5. The method for predicting milling stability of a machine tool based on hybrid drive according to claim 1, characterized in that: The local maximum mean distribution difference (LMMD) evaluation index is constructed to evaluate the distribution difference between simulation data and flutter test data.

6. A machine tool milling stability prediction system based on hybrid drive, characterized in that: Includes simulation module, test module, classification prediction module, difference loss module and prediction module; Simulation module, which generates simulation data sets based on the milling stability prediction mechanism model and machining condition parameters; The test module performs chatter stability testing on the milling process of the machine tool and obtains milling process signals, and constructs a test data set based on the milling process signals; The classification prediction module uses a deep subdomain adaptation network model to extract features from simulation and test datasets for classification prediction of milling chatter stability states; A difference loss module calculates the distribution difference between the simulation data and the flutter test data based on the extracted features in the simulation data set and the test data set, and calculates the distribution difference loss based on the distribution difference; The distribution difference loss is calculated based on the local maximum mean difference of the simulation and test samples of the vibration, and the classification loss of the model together constitutes the total loss of the model training; The distribution difference loss is expressed as: Where L is the set of all domain adaptation layers; Classification loss of Deep Subdomain Adaptation Network (DSAN); in, is the categorical cross entropy loss, is the total number of simulation and test samples, and are sample features and corresponding labels; The prediction module uses the simulation data set and the test data set to train the prediction network, and then uses the distribution difference loss to reversely train the prediction network through the back propagation algorithm to complete the domain adaptation of the simulation domain and the test domain, thereby obtaining the milling vibration stability prediction model. The obtained milling vibration stability prediction model is used to predict the milling stability of the milling machine according to the milling machine processing parameters.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the hybrid drive-based intelligent milling stability prediction method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the hybrid drive-based intelligent milling stability prediction method according to any one of claims 1 to 5 are implemented.

Images