Boring mill diagnosis method and device based on data and kinetic model

Abstract

The invention provides a boring machine diagnosis method and device based on data and a dynamical model. Comprising the steps of establishing a dynamical model of boring mill parts; simulating the boring machine parts in different fault modes based on the dynamic model to obtain fault data; establishing a data set according to the fault data; a neural network model is constructed, the neural network model is a Res-EAS-Net model, and the Res-EAS-Net model is obtained by introducing a channel attention mechanism on the basis of a ResNet model; training a neural network model according to the data set to obtain a first fault diagnosis model; training the first fault diagnosis model by adopting transfer learning to obtain a second fault diagnosis model; acquiring current state data of the boring machine part; and determining the current state of the boring machine part according to the current state data of the boring machine part and the second fault diagnosis model of the boring machine part.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent manufacturing, and in particular relates to a boring machine diagnosis method and device based on data and dynamic models. Background Art

[0002] Gears, bearings and other rotating mechanical components on heavy equipment often work under high impact, continuous high temperature, heavy load or other complex working conditions, so they are prone to failure, thereby reducing the transmission accuracy, production efficiency and reliability of the equipment.

[0003] Currently, rolling bearing fault diagnosis is mainly divided into model-based methods, data-driven methods, and hybrid methods. Model-based methods aim to model the failure mechanism or degradation process of rolling bearings by establishing high-fidelity physical or mathematical models, thereby inferring whether there is a fault or the time of failure threshold. This type of method aims to derive the dynamic differential equations of the target physical system and solve them to achieve analytical modeling. Although model-based methods have strong interpretability, the parameter setting of this method requires expert experience and is highly targeted. That is, when the application scenario or object is changed, the robustness of the model is poor, which will lead to a decrease in diagnostic accuracy.

[0004] Unlike traditional model-based approaches, data-driven methods do not rely on a precise physical model of the system. Instead, they leverage machine learning, or even deep learning, and data analysis techniques to adaptively extract complex features to construct a mapping relationship between sensor signals and bearing health status, thereby building a model. Data-driven methods achieve system fault diagnosis through a complete process of data acquisition, feature extraction, model training, and evaluation. However, models built using data-driven methods require a large amount of valid data for training and evaluation, which is difficult to obtain in actual production processes.

[0005] In recent years, with the development of technologies such as cyber-physical systems, the Industrial Internet of Things (IIoT), and virtual reality (VR), the concept of digital twins (DT) has garnered widespread attention in various areas of intelligent manufacturing, such as job shop scheduling and decision optimization. DT is a technology that integrates the physical and digital worlds. Its core is to establish real-time interaction between physical and virtual models through sensors, the Internet of Things (IoT), and data analytics, thereby enabling the monitoring and optimization of physical systems. Based on accurate real-world physical models, DT can generate high-fidelity digital models, enabling the generation of realistic simulation data. This capability means that DT can provide a wealth of data for data-driven diagnostic models, addressing the scarcity of effective data in actual production. Therefore, DT has become a bridge for applying data-driven models to real-world production practices.

[0006] However, existing research faces the following challenges. First, few researchers have combined bearing mechanisms with data-driven approaches, resulting in a lack of interpretability in fault diagnosis models. Second, collecting real-world fault data during actual production is difficult, which complicates the development of diagnostic models. Third, models built using data-driven approaches exhibit poor diagnostic performance when faced with drastic changes in operating conditions, making their direct application to other scenarios difficult. Summary of the Invention

[0007] The purpose of the present invention is to provide a boring machine diagnosis method and device based on data and dynamic models to realize fault diagnosis of the boring machine.

[0008] In a first aspect, a boring machine diagnosis method based on data and dynamic models is provided, comprising: Establish dynamic models of boring machine parts; Based on the dynamic model, the boring machine parts are simulated under different failure modes to obtain the failure data of the boring machine parts; Establish a data set based on fault data; Constructing a neural network model, wherein the neural network model is a Res-EAS-Net model, and the Res-EAS-Net model is obtained by introducing a channel attention mechanism on the basis of the ResNet model; The neural network model is trained based on the data set to obtain the first fault diagnosis model of the boring machine parts; Transfer learning is used to train the first fault diagnosis model to obtain a second fault diagnosis model for boring machine parts; Get the current status data of boring machine parts; The current state of the boring machine component is determined according to the current state data of the boring machine component and the second fault diagnosis model of the boring machine component.

[0009] Optionally, the failure modes of the boring machine component include rolling element defects, inner race failures and outer race failures.

[0010] Optionally, the kinetic model includes: Kinetic equation:

[0011] in, Indicates the mass of the inner ring shaft in the boring machine bearing; Indicates the mass of the outer ring base of the boring machine bearing; Indicates the horizontal displacement of the inner ring; Represents the second derivative of the horizontal displacement of the inner ring with respect to time; Indicates the vertical displacement of the inner ring, The second derivative of the horizontal displacement of the outer ring with respect to time, Indicates the horizontal displacement of the outer ring; Indicates the vertical displacement of the outer ring; Indicates the external load applied to the inner and outer rings in the horizontal direction; Indicates the external load applied to the inner and outer rings in the vertical direction; Indicates the contact force between the ball and the inner and outer rings in the horizontal direction; Indicates the contact force between the ball and the inner and outer rings in the vertical direction; Indicates the damping coefficient of the inner ring; Indicates the damping coefficient of the outer ring; Indicates the elastic modulus of the inner ring; Indicates the elastic modulus of the outer ring; Nonlinear contact force equation:

[0012]

[0013]

[0014] in, Indicates the contact force between the ball and the raceway in the horizontal direction; Indicates the contact force between the ball and the raceway in the horizontal direction; ; Indicates the total contact stiffness of the bearing; The contact deformation between the ball and the inner ring raceway and the outer ring raceway; Indicates the angular position of the ball; Indicates the additional deformation caused by the fault; The total contact stiffness equation of the bearing is:

[0015]

[0016]

[0017] in, Indicates the contact stiffness of the inner ring; Indicates the contact stiffness of the outer ring; Indicates the elastic modulus of the material; represents the Poisson's ratio of the material; Indicates the contact displacement characteristics of the inner ring raceway, Indicates the raceway contact displacement characteristics of the outer ring; Indicates the raceway curvature of the inner ring; Indicates the raceway curvature of the outer ring and; The additional deformation equations caused by faults include the additional deformation equations caused by inner ring faults, the additional deformation equations caused by outer ring faults, and the additional deformation equations caused by ball faults; The additional deformation equation caused by inner ring fault is:

[0018] in, is the fault angle of the inner race fault; The additional deformation equation caused by outer ring fault is:

[0019] in, is the fault angle of the outer race fault; The additional deformation equation caused by ball failure is:

[0020] in, is the failure angle of rolling element failure, Indicates the angular velocity of the rolling element's rotation.

[0021] Optionally, the step of establishing a data set based on the fault data includes: The fault data is converted into time-frequency images through continuous wavelet transform, and a data set is constructed based on the time-frequency images.

[0022] Optionally, the channel attention mechanism is as follows: Perform a global average pooling operation on each channel of the input feature map to obtain the descriptor of each channel; the formula for global average pooling is as follows: , where Indicates the Global descriptor for each channel; and Represent the height and width of the feature map respectively; Indicates the first Channels at position The value at The obtained descriptor of each channel is used as the input of the one-dimensional convolution layer, and the channel attention weight of each channel is generated through the one-dimensional convolution operation; the convolution kernel of the one-dimensional convolution layer is calculated as follows: , where Indicates the number of channels With convolution kernel The functional relationship between Is the proportional coefficient used to adjust right The degree of impact, is the bias term, Is the proportional coefficient used to adjust right the extent of the impact; According to the channel attention weight of each channel, the features of each channel are Perform weighting to obtain the weighted feature map .

[0023] Optionally, based on the introduction of the channel attention mechanism, an adaptive calibration jump connection mechanism is introduced for the Res-EAS-Net model; wherein the adaptive calibration jump connection mechanism is as follows: Feature extraction step: output feature map of the previous residual module in the Res-EAS-Net model , perform identity mapping or linear transformation to obtain the skip connection feature ; Adaptive weight generation step: Introducing weight generation function , generates weight coefficients for skip connection features; where the weight coefficients The generation formula is: , where 、 represents the learnable parameters, express activation function, represents global average pooling; Feature calibration step: using weight coefficients , for skip connection features Perform weighting; Feature fusion step: combine the weighted jump connection features with the main path output features Add together to get the final output features .

[0024] Optionally, the step of using transfer learning to train the first fault diagnosis model to obtain a second fault diagnosis model for boring machine parts includes: Select time-frequency data under two different working conditions as the source domain and target domain respectively as the transfer learning dataset; Freeze the parameter updates of the weight layers except the fully connected layers in the Res-EAS-Net model, and only update the parameters of the fully connected layers through the backpropagation algorithm; Map the data of both the source and target domains into the reproducing kernel Hilbert space, and align the features of the source and target domains by maximum mean difference; The new loss function is defined as , and train the first fault diagnosis model according to the new loss function to obtain the second fault diagnosis model; in the above formula, represents the classification loss, represents the migration loss calculated by maximizing the mean difference, Represents the weight of the transfer loss calculated by maximizing the mean difference.

[0025] Secondly, a digital twin diagnostic device for a boring machine based on data and dynamic models is provided, including: Dynamic model building module, used to build dynamic models of boring machine parts; The simulation module is used to simulate the boring machine parts under different failure modes based on the dynamic model to obtain the failure data of the boring machine parts; A data set construction module is used to build a data set based on fault data; A neural network model construction module is used to construct a neural network model, wherein the neural network model is a multi-scale feature extraction network based on a sparse convolutional autoencoder; A first training module is used to train a neural network model according to a data set to obtain a first fault diagnosis model of the boring machine parts; A second training module is used to train the first fault diagnosis model using transfer learning to obtain a second fault diagnosis model for boring machine parts; The acquisition module is used to obtain the current status data of the boring machine parts; The diagnosis module is used to determine the current state of the boring machine component according to the current state data of the boring machine component and the second fault diagnosis model of the boring machine component.

[0026] In a third aspect, an electronic device is provided, comprising the digital twin diagnostic device for a boring machine based on data and dynamic models as described above.

[0027] In a fourth aspect, a computer-readable storage medium is provided, wherein at least one program code is stored in the computer-readable storage medium, and the program code is executed by a processor to implement the boring machine diagnosis method based on data and dynamic models as described in any one of the above items.

[0028] The technical solution provided by the present invention has the following beneficial effects: The present invention provides a boring machine diagnosis method based on data and dynamic models. By building a dynamic model of the bearing and solving it, simulated fault data is obtained to form a data set. A Res-EAS-Net model is constructed, and the Res-EAS-Net model is trained based on the simulated fault data to obtain a first fault prediction model. The performance of the model is improved by improving the structure of the neural network model. The first fault prediction model is trained using transfer learning to obtain a second fault prediction model for the boring machine components. By means of feature migration, the second fault prediction model can be applied to fault diagnosis under different working conditions. Finally, a high-fidelity digital twin model of the boring machine and its spindle is established to achieve real-time synchronization between the twin boring machine and the physical boring machine; the data of the physical boring machine is synchronously collected through the data twin, and diagnosis is performed through the diagnostic model, so that the status of each component of the boring machine can be updated in real time in the data twin model. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0030] Figure 1 A flow chart of a boring machine diagnosis method based on data and dynamic models provided by the present invention; Figure 2 A schematic diagram of a kinetic model provided by the present invention; Figure 3 A schematic diagram of another kinetic model provided by the present invention; Figure 4 The simulated signal and real signal and their envelope diagrams under the healthy state provided by the present invention; Figure 5 The simulated signal and real signal and their envelope diagram under the outer ring fault state provided by the present invention; Figure 6 The simulated signal and real signal and their envelope diagram under the inner ring fault condition provided by the present invention; Figure 7 The simulated signal and the real signal and their envelope diagram under the rolling element fault condition provided by the present invention; Figure 8 A schematic diagram of the structure of a Resnet18 model provided by the present invention; Figure 9 A schematic diagram of the structure of another Resnet18 model provided by the present invention; Figure 10A schematic diagram of a training process of a second fault diagnosis model provided by the present invention; Figure 11 A schematic diagram of a training process of another second fault diagnosis model provided by the present invention; Figure 12 A schematic diagram of an experimental result provided by the present invention; Figure 13 This is a structural block diagram of a digital twin diagnostic device for a boring machine based on data and dynamic models provided by the present invention; Figure 14 This is a structural block diagram of an electronic device provided by the present invention.

[0031] The reference numerals are as follows: 11: Dynamic model construction module; 12: Simulation module; 13: Data set construction module; 14: Neural network model construction module; 15: First training module; 16: Second training module; 17: Acquisition module; 18: Diagnosis module; 21: Processor; 22: Memory. DETAILED DESCRIPTION

[0032] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0033] Figure 1 This is a flow chart of a boring machine diagnosis method based on data and dynamic models provided by the present invention. Figure 1 ,include: S101. Establish a dynamic model of boring machine bearings.

[0034] In one example, the kinetic model includes: Kinetic equation:

[0035] in, Indicates the mass of the inner ring shaft in the boring machine bearing; Indicates the mass of the outer ring base of the boring machine bearing; Indicates the horizontal displacement of the inner ring; Represents the second derivative of the horizontal displacement of the inner ring with respect to time; Indicates the vertical displacement of the inner ring, The second derivative of the horizontal displacement of the outer ring with respect to time, Indicates the horizontal displacement of the outer ring; Indicates the vertical displacement of the outer ring; Indicates the external load applied to the inner and outer rings in the horizontal direction; Indicates the external load applied to the inner and outer rings in the vertical direction; Indicates the contact force between the ball and the inner and outer rings in the horizontal direction; Indicates the contact force between the ball and the inner and outer rings in the vertical direction; Indicates the damping coefficient of the inner ring; Indicates the damping coefficient of the outer ring; Indicates the elastic modulus of the inner ring; Indicates the elastic modulus of the outer ring; Nonlinear contact force equation:

[0036]

[0037]

[0038] in, Indicates the contact force between the ball and the raceway in the horizontal direction; Indicates the contact force between the ball and the raceway in the horizontal direction; ; Indicates the total contact stiffness of the bearing; The contact deformation between the ball and the inner ring raceway and the outer ring raceway; Indicates the angular position of the ball; Indicates the additional deformation caused by the fault; The total contact stiffness equation of the bearing is:

[0039]

[0040]

[0041] in, Indicates the contact stiffness of the inner ring; Indicates the contact stiffness of the outer ring; Indicates the elastic modulus of the material; represents the Poisson's ratio of the material; Indicates the contact displacement characteristics of the inner ring raceway, Indicates the raceway contact displacement characteristics of the outer ring; Indicates the raceway curvature of the inner ring; Indicates the raceway curvature of the outer ring and; In this embodiment, , .

[0042] in, , , , , , , .

[0043] In the above formula, 、 represents the ball curvature function; 、 represents the inner raceway curvature function; 、 represents the outer raceway curvature function; 、 Indicates the curvature factor of the inner and outer raceways; Indicates the ball diameter; Indicates the bearing pitch diameter; Indicates the raceway inclination angle.

[0044] The additional deformation equations caused by faults include the additional deformation equations caused by inner ring faults, the additional deformation equations caused by outer ring faults, and the additional deformation equations caused by ball faults; The additional deformation equation caused by inner ring fault is:

[0045] in, is the fault angle of the inner race fault; The additional deformation equation caused by outer ring fault is:

[0046] in, is the fault angle of the outer race fault; The additional deformation equation caused by ball failure is:

[0047] in, is the failure angle of rolling element failure, Indicates the angular velocity of the rolling element's rotation.

[0048] In this embodiment, , , .

[0049] S102. Simulate the boring machine bearing under different failure modes based on the dynamic model to obtain failure data of the boring machine bearing.

[0050] In one example, the fault data of the boring machine bearing includes the vibration data of the boring machine bearing. In the dynamic model in step S101, the vibration data is reflected as the second-order derivative of the displacement of the inner ring in the horizontal direction relative to time. , the second derivative of the vertical displacement of the inner ring with respect to time , and the second derivative of the horizontal displacement of the outer ring with respect to time , the second derivative of the vertical displacement of the outer ring with respect to time .

[0051] The simulation step in step S102 is to simulate the 、 、 、 The solution process.

[0052] In this embodiment, a four-degree-of-freedom fault simulation model of the rolling bearing failure mechanism (i.e., the dynamic model in step S101) is established in MATLAB. The ODE45 solver based on the Runge-Kutta method is used to solve the dynamic equations. By inputting various bearing parameters according to actual conditions, the vibration response signals of the rolling bearing containing various failure modes can be obtained.

[0053] This article uses a rolling bearing experiment conducted at Case Western Reserve University (CWRU) as a foundation to illustrate the specific process of establishing a rolling bearing dynamics simulation model. The test bench primarily consists of a motor, a rolling bearing on the motor drive end, a dynamometer, and a torque sensor. The rolling bearing on the motor drive end is an SKF-6205. An accelerometer is mounted on the motor housing at the drive end to collect vibration signals from the rolling bearing. The CWRU bearing experiment tests rolling bearings in four health states: normal, inner race fault, outer race fault, and rolling element fault. Defects in faulty rolling bearings are obtained by electrospark machining.

[0054] See Figure 2 , which is a schematic diagram of a dynamic simulation model provided by the present invention, in which the structure of the bearing is specifically shown.

[0055] In one example, failure modes of a boring machine bearing include rolling element defects, inner race failure, and outer race failure.

[0056] See Figure 3 , Figure 3 (a) in the figure specifically shows the location of the fault point when the bearing inner ring fails. Figure 3 (b) in the figure specifically shows the location of the fault point when the bearing inner ring fails.

[0057] The rolling bearing experiments conducted at Case Western Reserve University (CWRU) primarily involved four operating conditions. The simulations were conducted at a rotational speed of 1750 RPM. The bearing faults were cracks measuring 0.007 inches, 0.014 inches, and 0.021 inches (approximately 0.18 mm, 0.36 mm, and 0.54 mm), respectively. The sampling frequency at the drive end was 12 kHz. To accurately reflect the sampling conditions of the sensor located at the drive end during the experiments, the simulation data used the vibration acceleration signal at the inner ring shaft and added a certain amount of noise to closely replicate the actual conditions.

[0058] In the above dynamic model, the actual parameters of the CWRU bearing experimental platform are set, and the solution step size is set to 8.33×10 -5 s, the acceleration vibration signals of the rolling bearing in healthy state, inner and outer ring fault state and rolling element fault state can be obtained respectively.

[0059] According to the dynamics theory, the failure frequencies of the main components of rolling bearings are as follows: Outer race fault characteristic frequency:

[0060] Inner race fault characteristic frequency:

[0061] Rolling element failure characteristic frequency:

[0062] By comparing the distribution patterns of simulation data and real data in the time-frequency domain, the reliability of the finite element dynamics simulation model can be further explored.

[0063] See also Figure 4 , Figure 4 The simulated signal and its envelope diagram, and the actual signal and its envelope diagram in the healthy state are shown. Figure 4 (a) is the simulated signal in the healthy state. Figure 4 (b) is the actual signal in a healthy state. Figure 4 (c) in the figure is the envelope spectrum analysis of the simulation signal under healthy conditions. Figure 4 (d) in the figure is the envelope spectrum analysis of the actual signal under healthy conditions.

[0064] It can be seen that both the simulated signal and the actual signal can clearly show the rotational frequency and its multiple frequencies, which can illustrate the high reliability of the dynamic simulation model under a healthy and normal motion state and the high credibility of the simulation data.

[0065] See also Figure 5 , Figure 5 The simulated signal and its envelope diagram, and the actual signal and its envelope diagram under the outer race fault state are shown. Figure 5 (a) is the simulation signal under the outer ring fault state. Figure 5 (b) is the actual signal in the outer ring fault state. Figure 5 (c) in the figure is the envelope spectrum analysis of the simulation signal under the outer race fault state. Figure 5 (d) in the figure is the envelope spectrum analysis of the actual signal under the outer race fault state.

[0066] It can be observed that in the simulated signal, the interval between two adjacent shock wave peaks is 9.5ms; in the real signal, the interval between two adjacent shock wave peaks is 9.6ms, which is basically consistent with the theoretical calculation formula. In addition, the frequency domain distribution of the envelope spectrum of the two is basically the same, which is also consistent with the theoretical calculation results. This shows that the constructed dynamic model clearly reflects the outer race fault and the difference between it and the actual situation is very small, showing high reliability.

[0067] Figure 6 The simulated signal and its envelope diagram, and the actual signal and its envelope diagram under the inner race fault state are shown. Figure 6 (a) is the simulation signal under the inner ring fault state. Figure 6 (b) is the actual signal under the inner ring fault condition. Figure 6 (c) is the envelope spectrum analysis of the simulation signal under the inner race fault state. Figure 6 (d) in the figure is the envelope spectrum analysis of the actual signal under the inner race fault state.

[0068] It can be observed that the interval between the two shock wave peaks in the simulated signal and the actual signal is around 6.1-6.4ms, which is very close to the 6.3ms obtained by theoretical calculation. In addition, by observing its waveform and envelope spectrum distribution, on the basis of its characteristic frequency, the characteristic frequency caused by the inner ring rotation can also be found. Both the simulated signal and the actual signal have relatively obvious characteristics, which further demonstrates the high reliability of the simulation model.

[0069] Figure 7 The simulated signal and its envelope diagram, and the actual signal and its envelope diagram under the rolling element fault condition are shown. Figure 7 (a) is the simulation signal under rolling element failure condition. Figure 7 (b) is the actual signal under rolling element failure condition. Figure 7 (c) is the envelope spectrum analysis of the simulation signal under the condition of rolling element failure. Figure 7 (d) in the figure is the envelope spectrum analysis of the actual signal under rolling element fault conditions.

[0070] Observing the envelope spectrum frequency domain distribution, it can be found that the vibration signal caused by the rolling element failure is relatively messy and weak, whether in simulation or in practice, but it can still be found that the vibration signal caused by the rolling element failure is relatively messy and weak, but it can still be found that the vibration signal caused by the rolling element failure is relatively weak, which is not obvious in the cage rotation frequency. Under the influence of , the characteristics at its frequency doubling are more obvious, and the simulated signal is also highly consistent with the actual signal.

[0071] The bearing simulation fault data obtained through the dynamic model proposed in the present invention is highly similar to the real data, laying the foundation for the subsequent fault diagnosis model obtained by training based on simulation data to be used in actual scenarios.

[0072] S103: Create a data set based on the fault data.

[0073] In one example, step S103 includes: The fault data is converted into time-frequency images through continuous wavelet transform, and a data set is constructed based on the time-frequency images.

[0074] The specific steps are as follows: A MATLAB script was used to convert the vibration signal into a time-frequency image. The time scale t was calculated based on the sensor's sampling frequency of 25.8 kHz (this sensor was used to collect data in the subsequent data twin model). The complex Gaussian wavelet cgau8 was selected as the wavelet basis function, with a wavelet scale of 128. The center frequency corresponding to cgau8 was calculated using the centfrq function, and the scale was converted to frequency using scal2freq. The vibration signal, scale, and wavelet function were input into the cwt function to obtain the continuous wavelet coefficients. The imagesc function was used to generate a time-frequency image for every 1024 vibration signal data points. To better reflect real-world scenarios, the time-frequency image dataset does not include sample labels.

[0075] In this embodiment, on the one hand, considering that the fault data generated under different working conditions have different characteristic distributions and may cause negative migration, converting the generated one-dimensional fault data into a two-dimensional time-frequency image can make the data of different faults more similar for migration; on the other hand, noise can be suppressed to a certain extent through time-frequency image processing.

[0076] S104. Construct a neural network model, where the neural network model is a Res-EAS-Net model. The Res-EAS-Net model is obtained by introducing a channel attention mechanism on the basis of the ResNet model.

[0077] In the feature extraction part, the present invention uses the ResNet18 pre-trained model provided in the open source framework PyTorch as the core feature extraction network. ResNet18 has the optimal weight parameters for classification tasks on large-scale datasets (such as ImageNet) and has powerful feature extraction capabilities. ResNet18 contains 18 weight layers (convolutional layers and fully connected layers), and its overall network architecture is realized by introducing basic residual blocks (Basic Block) and skip connections (Skip Connection). The specific parameters are as follows: Figure 10 and Figure 11 shown.

[0078] Since the main bearing states of the boring machine spindle mainly include four health states: health (Health, H), outer race faults (OF), inner race faults (IF) and rolling element faults (BF). Therefore, in the fully connected layer of ResNet18, the number of output categories is changed to 4. In addition, since ResNet18 performs well in image classification tasks, the original pre-trained weights are no longer applicable when facing structured data such as one-dimensional vibration signals. Therefore, the present invention only uses the excellent network architecture of ResNet18 (such as Figure 8 and Figure 9 ), rather than using pre-trained weight parameters. Furthermore, because ResNet18 was originally designed for image classification tasks, whose input dimensionality is higher than one-dimensional inputs like vibration signals, the original two-dimensional convolution of ResNet18 was replaced with one-dimensional convolution to adapt to structured data.

[0079] The classic ResNet18 architecture includes convolutional layers with 128, 256, and 512 channels. This results in redundancy in the feature maps extracted by each channel, increasing model training costs. Therefore, by introducing a channel-attention mechanism that weights channels, the network focuses on important feature channels and suppresses features from less important channels. This approach enables the network to adaptively learn which channels are more important for specific tasks, thereby enhancing network performance.

[0080] ECA-Net is an efficient channel attention mechanism designed to enhance the feature selection capabilities of convolutional neural networks by reducing computational cost. ECA-Net's design principle maximizes information flow while minimizing computational overhead. This allows it to effectively enhance network performance even with limited computing resources, making it particularly suitable for environments with limited computing resources, such as edge or embedded devices.

[0081] The core idea of ECA-Net is to use one-dimensional convolution to calculate channel attention, avoiding the complex fully connected layer structure and thus achieving efficient calculation.

[0082] The channel attention mechanism in this invention is as follows: The first step is to perform a global average pooling operation on each channel of the input feature map to obtain the descriptor of each channel. The formula for global average pooling is as follows: , where Indicates the Global descriptor for each channel; and Represent the height and width of the feature map respectively; Indicates the first Channels at position The value at .

[0083] In the second step, the descriptor of each channel is used as the input of the one-dimensional convolution layer. , the channel attention weight of each channel is generated through a one-dimensional convolution operation , Indicates the The attention weight of each channel; the convolution kernel of the one-dimensional convolution layer is calculated as follows: , where Indicates the number of channels With convolution kernel The functional relationship between Is the proportional coefficient used to adjust right The degree of impact, is the bias term, Is the proportional coefficient used to adjust right degree of impact.

[0084] Since ECA-Net aims to properly capture local cross-channel information interactions, it is necessary to determine the approximate range of channel interaction information (i.e., the convolution kernel size of 1D convolution). ). It also represents the coverage of local cross-channel interactions, that is, there are neighboring channels participate in the attention weight calculation of this channel. Therefore, Value and number of channels Should be in direct proportion.

[0085] The third step is to weight the features of each channel according to the channel attention weight of each channel to obtain the weighted feature map.

[0086] The weighted formula is: ; The weighted feature map is .

[0087] In this embodiment, on the basis of introducing the channel attention mechanism, an adaptive calibration jump connection mechanism can be introduced for the Res-EAS-Net model; wherein the adaptive calibration jump connection mechanism is as follows: The first step is feature extraction: the output feature map of the previous residual module in the Res-EAS-Net model , perform identity mapping or linear transformation to obtain the skip connection feature .

[0088] The second step is the adaptive weight generation step: introducing the weight generation function , generates weight coefficients for skip connection features; where the weight coefficients The generation formula is: , where 、 represents the learnable parameters, express activation function, Represents global average pooling.

[0089] The third step is feature calibration: using weight coefficients , for skip connection features Perform weighting.

[0090] The fourth step is the feature fusion step: the weighted jump connection features are combined with the main path output features Add together to get the final output features .

[0091] In ResNet18, the skip connection effectively alleviates the problems of gradient vanishing and network degradation by directly passing the input features to the output end. However, traditional skip connections use fixed identity mappings or simple linear transformations, which fail to fully consider the differences in the importance of input features. To this end, the present invention proposes an adaptive calibration skip connection (ACSC) mechanism, which dynamically adjusts the feature weights of the skip connection to enhance the model's ability to focus on key features, thereby improving feature expression capabilities and model performance. The core idea of ACSC is to dynamically calibrate the features of the skip connection by introducing learnable weight parameters. Specifically, the mechanism generates a set of weight coefficients based on the global or local information of the input features, and performs weighted adjustment on the features of the skip connection to make them more adaptable to the output features of the main path. This dynamic calibration can effectively capture the key information in the input features while suppressing redundant or noisy features.

[0092] S105: Training a neural network model according to the data set to obtain a first fault diagnosis model for the boring machine parts.

[0093] In the training part of Res-EAS-Net, the generated simulation data is divided into training set, validation set and test set in a ratio of 6:2:2. The cross entropy loss function (CrossEntropyLoss) is selected as the loss function:

[0094] Where, is the number of samples, is the number of categories, and Respectively represent The true label and predicted probability of each sample in the category.

[0095] In terms of hyperparameter selection, the number of training epochs was set to 100, and an early stopping strategy was employed. This strategy checks the loss at the end of each epoch. If the loss does not significantly decrease within the specified epoch, the model is considered to have converged and training is terminated. Accordingly, the initial learning rate was set to 0.01, and the ReduceLROnPlateau learning rate decay strategy from the lr_scheduler package was used to avoid getting stuck in local optima during training. This strategy shares the core concept of Early Stopping, differing in that after the learning rate decays according to a certain ratio, a cool-down period is entered to avoid frequent triggering of learning rate decay. The Dataloader from torch.utils.data was used as a batch loader to read a certain number of samples from the dataset for training (or testing). The batch_size was set to 16, and shuffle=True. At the end of training, the weights of the optimal model were stored as a dictionary and saved in pth format.

[0096] S106: Using transfer learning to train the first fault diagnosis model to obtain a second fault diagnosis model for boring machine parts.

[0097] In one example, step S106 includes: In the first step, time-frequency data under two different working conditions are selected as the source domain and target domain respectively as the transfer learning dataset; The second step is to freeze the parameter updates of the weight layers except the fully connected layers in the Res-EAS-Net model, and only update the parameters of the fully connected layers through the back-propagation algorithm; The third step is to map the data of both the source and target domains into the reproducing kernel Hilbert space, and align the features of the source and target domains by the maximum mean difference. The fourth step is to define the new loss function as , and train the first fault diagnosis model according to the new loss function to obtain the second fault diagnosis model; in the above formula, represents the classification loss, represents the migration loss calculated by maximizing the mean difference, Represents the weight of the transfer loss calculated by maximizing the mean difference.

[0098] The calculation formula is as follows:

[0099] in, represents the kernel function mapping, Represents the characteristics of the source domain, Represents the characteristics of the target domain, represents the reproducing kernel Hilbert space.

[0100] Relying on this loss function, the Res-EAS-Net model is trained again, and the training strategy and parameter settings are the same as step S105. After obtaining the optimal parameters of the fully connected layer, the Res-EAS-Net is tested on the test set to achieve migration diagnosis of real data.

[0101] See also Figure 10 and Figure 11 , specifically showing the training process of the second fault diagnosis model.

[0102] See also Figure 12 To further verify the performance of the Res-EAS-Net model, the test set uses the LetNet model, AlexNet model, VGG16 model and the original ResNet18 model as the control group to verify the performance of the Res-EAS-Net model. The verification results are as follows Figure 12 As shown in the figure, it can be seen that thanks to transfer learning, the four indicator scores of the proposed model Res-EAS-Net are the highest, among which the Recall value reaches 0.903, which means that Res-EAS-Net can more accurately identify the three types of fault samples. The highest Gmean indicates that the overall classification performance of the model is optimal.

[0103] exist Figure 12 In , Precision represents the accuracy, Recall represents the recall rate, and Gmean represents the geometric mean. It is more suitable for measuring the overall performance of the classifier. Only when the classifier performs well in each category can a large Gmean and Recall is suitable for measuring the local performance of the classifier because it focuses more on fault samples.

[0104] Among them, Gmean and The value is calculated as follows:

[0105] in, represents the weight, is 2.

[0106] The calculation formulas for Precision and Recall are as follows: ,

[0107] S107: Acquire current status data of boring machine parts.

[0108] Sensors are set on the X, Y, and Z axes of the main shaft and the gear box housing of the main shaft to sense vibration signals (i.e., acceleration).

[0109] S108 : Determine the current state of the boring machine component according to the current state data of the boring machine component and the second fault diagnosis model of the boring machine component.

[0110] Figure 13 This is a structural diagram of a digital twin diagnostic device for boring machines based on data and dynamic models provided by the present invention. Figure 13 ,include: A dynamic model building module 11 is used to build a dynamic model of the boring machine parts; A simulation module 12 is used to simulate the boring machine parts under different failure modes based on the dynamic model to obtain failure data of the boring machine parts; A data set building module 13 is used to build a data set based on the fault data; A neural network model construction module 14 is used to construct a neural network model, wherein the neural network model is a Res-EAS-Net model, which is obtained by introducing a channel attention mechanism on the basis of the ResNet model; A first training module 15 is used to train a neural network model according to the data set to obtain a first fault diagnosis model for the boring machine parts; A second training module 16 is used to train the first fault diagnosis model using transfer learning to obtain a second fault diagnosis model for the boring machine component; An acquisition module 17 is used to acquire current status data of the boring machine parts; The diagnosis module 18 is used to determine the current state of the boring machine component according to the current state data of the boring machine component and the second fault diagnosis model of the boring machine component.

[0111] Figure 14 This is a structural block diagram of an electronic device provided by the present invention. Figure 14 , electronic devices may include Figure 13 The digital twin diagnostic device for boring machines based on data and dynamic models generally includes a processor 21 and a memory 22 .

[0112] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented in hardware using at least one of the following: a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), or a PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. The memory 22 may include one or more computer-readable storage media, which may be non-transitory. The memory 22 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 22 is used to store at least one instruction, which is executed by the processor 21 to implement the boring machine diagnostic method based on data and dynamic models, provided by an electronic device in the method embodiments of this application.

[0113] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A boring machine diagnosis method based on data and dynamic model, characterized in that: include: Establish dynamic models of boring machine parts; Based on the dynamic model, the boring machine parts are simulated under different failure modes to obtain the failure data of the boring machine parts; Establish a data set based on fault data; Constructing a neural network model, wherein the neural network model is a Res-EAS-Net model, and the Res-EAS-Net model is obtained by introducing a channel attention mechanism on the basis of the ResNet model; The neural network model is trained based on the data set to obtain the first fault diagnosis model of the boring machine parts; Transfer learning is used to train the first fault diagnosis model to obtain a second fault diagnosis model for boring machine parts; Get the current status data of boring machine parts; The current state of the boring machine component is determined according to the current state data of the boring machine component and the second fault diagnosis model of the boring machine component.

2. The boring machine diagnosis method based on data and dynamic model according to claim 1, characterized in that: Failure modes of boring machine components include rolling element defects, inner race failures, and outer race failures.

3. The boring machine diagnosis method based on data and dynamic model according to claim 1, characterized in that: The kinetic model includes: Kinetic equation: in, Indicates the mass of the inner ring shaft in the boring machine bearing; Indicates the mass of the outer ring base of the boring machine bearing; Indicates the horizontal displacement of the inner ring; Represents the second derivative of the horizontal displacement of the inner ring with respect to time; Indicates the vertical displacement of the inner ring, The second derivative of the horizontal displacement of the outer ring with respect to time, Indicates the horizontal displacement of the outer ring; Indicates the vertical displacement of the outer ring; Indicates the external load applied to the inner and outer rings in the horizontal direction; Indicates the external load applied to the inner and outer rings in the vertical direction; Indicates the contact force between the ball and the inner and outer rings in the horizontal direction; Indicates the contact force between the ball and the inner and outer rings in the vertical direction; Indicates the damping coefficient of the inner ring; Indicates the damping coefficient of the outer ring; Indicates the elastic modulus of the inner ring; Indicates the elastic modulus of the outer ring; Nonlinear contact force equation: in, Indicates the contact force between the ball and the raceway in the horizontal direction; Indicates the contact force between the ball and the raceway in the horizontal direction; ; Indicates the total contact stiffness of the bearing; The contact deformation between the ball and the inner ring raceway and the outer ring raceway; Indicates the angular position of the ball; Indicates the additional deformation caused by the fault; The total contact stiffness equation of the bearing is: in, Indicates the contact stiffness of the inner ring; Indicates the contact stiffness of the outer ring; Indicates the elastic modulus of the material; represents the Poisson's ratio of the material; Indicates the contact displacement characteristics of the inner ring raceway, Indicates the raceway contact displacement characteristics of the outer ring; Indicates the raceway curvature of the inner ring and; Indicates the raceway curvature of the outer ring and; The additional deformation equations caused by faults include the additional deformation equations caused by inner ring faults, the additional deformation equations caused by outer ring faults, and the additional deformation equations caused by ball faults; The additional deformation equation caused by inner ring fault is: in, is the fault angle of the inner race fault; The additional deformation equation caused by outer ring fault is: in, is the fault angle of the outer race fault; The additional deformation equation caused by ball failure is: in, is the failure angle of rolling element failure, Indicates the angular velocity of the rolling element's rotation.

4. The boring machine diagnosis method based on data and dynamic model according to claim 1, characterized in that: Based on the fault data, the steps to build a data set include: The fault data is converted into time-frequency images through continuous wavelet transform, and a data set is constructed based on the time-frequency images.

5. The boring machine diagnosis method based on data and dynamic model according to any one of claims 1 to 4, characterized in that: The channel attention mechanism is as follows: Perform a global average pooling operation on each channel of the input feature map to obtain the descriptor of each channel; the formula for global average pooling is as follows: , where Indicates the Global descriptor for each channel; and Represent the height and width of the feature map respectively; Indicates the first Channels at position The value at The obtained descriptor of each channel is used as the input of the one-dimensional convolution layer, and the channel attention weight of each channel is generated through the one-dimensional convolution operation; Among them, the convolution kernel of the one-dimensional convolution layer is calculated as follows: , where Indicates the number of channels With convolution kernel The functional relationship between Is the proportional coefficient used to adjust right The degree of impact, is the bias term, Is the proportional coefficient used to adjust right the extent of the impact; According to the channel attention weight of each channel, the features of each channel are Perform weighting to obtain the weighted feature map .

6. The boring machine diagnosis method based on data and dynamic model according to any one of claims 1 to 5, characterized in that: Based on the introduction of the channel attention mechanism, an adaptive calibrated skip connection mechanism is introduced for the Res-EAS-Net model. The adaptive calibrated skip connection mechanism is as follows: Feature extraction step: output feature map of the previous residual module in the Res-EAS-Net model , perform identity mapping or linear transformation to obtain the skip connection feature ; Adaptive weight generation step: Introducing weight generation function , generates weight coefficients for skip connection features; where the weight coefficients The generation formula is: , where 、 represents the learnable parameters, express activation function, represents global average pooling; Feature calibration step: using weight coefficients , for skip connection features Perform weighting; Feature fusion step: combine the weighted jump connection features with the main path output features Add together to get the final output features .

7. The boring machine diagnosis method based on data and dynamic model according to any one of claims 1 to 5, characterized in that: The steps of using transfer learning to train the first fault diagnosis model to obtain a second fault diagnosis model for boring machine parts include: Select time-frequency data under two different working conditions as the source domain and target domain respectively as the transfer learning dataset; Freeze the parameter updates of the weight layers except the fully connected layers in the Res-EAS-Net model, and only update the parameters of the fully connected layers through the backpropagation algorithm; Map the data of both the source and target domains into the reproducing kernel Hilbert space, and align the features of the source and target domains by maximum mean difference; The new loss function is defined as , and train the first fault diagnosis model according to the new loss function to obtain the second fault diagnosis model; in the above formula, represents the classification loss, represents the migration loss calculated by maximizing the mean difference, Represents the weight of the transfer loss calculated by maximizing the mean difference.

8. A digital twin diagnostic device for boring machines based on data and dynamic models, characterized in that: include: Dynamic model building module, used to build dynamic models of boring machine parts; The simulation module is used to simulate the boring machine parts under different failure modes based on the dynamic model to obtain the failure data of the boring machine parts; A data set construction module is used to build a data set based on fault data; A neural network model construction module is used to construct a neural network model, wherein the neural network model is a multi-scale feature extraction network based on a sparse convolutional autoencoder; A first training module is used to train a neural network model according to a data set to obtain a first fault diagnosis model of the boring machine parts; A second training module is used to train the first fault diagnosis model using transfer learning to obtain a second fault diagnosis model for boring machine parts; The acquisition module is used to obtain the current status data of the boring machine parts; The diagnosis module is used to determine the current state of the boring machine component according to the current state data of the boring machine component and the second fault diagnosis model of the boring machine component.

9. An electronic device, characterized in that: Including the digital twin diagnostic device of a boring machine based on data and dynamic models as described in claim 8.

10. A computer-readable storage medium, characterized in that At least one program code is stored in the computer-readable storage medium, and the program code is executed by a processor to implement the boring machine diagnosis method based on data and dynamic models according to any one of claims 1 to 7.

Images