High-speed rail gearbox damage state evaluation method and device, electronic terminal and storage medium

Abstract

The invention discloses a high-speed rail gear box damage state evaluation method and device, an electronic terminal and a storage medium in the technical field of high-speed rail wheel rail operation and maintenance. The method comprises the following steps: acquiring a vibration signal of a high-speed rail gear box to be identified; inputting the vibration signal into a pre-trained high-speed rail gearbox damage state evaluation model; respectively extracting coarse-grained domain generalization features and fine-grained domain generalization features in the vibration signals according to a static convolution module and a dynamic convolution module, and constructing dynamic domain generalization features; and inputting the dynamic domain generalization features into a damage state discriminator to obtain multi-dimensional prediction probability data of a plurality of damage states, and determining a damage state evaluation result according to the multi-dimensional prediction probability data corresponding to the plurality of damage states. According to the method, the technical problems that some weak but important domain generalization information is lost due to incomplete domain generalization characteristics of the extracted signal, the damage state evaluation accuracy is reduced, and the operation safety and efficiency of the high-speed rail are difficult to guarantee can be solved.

Description

Technical Field

[0001] The present invention relates to the technical field of high-speed railway wheel-rail intelligent operation and maintenance, and in particular to a method, device, electronic terminal and storage medium for evaluating the damage state of a high-speed railway gearbox. Background Art

[0002] As the core component of the high-speed train transmission system, the high-speed rail gearbox is listed as a key component in the operation of the high-speed rail. If the damage of the high-speed rail gearbox is delayed or mispredicted, it may have a serious impact on the safety and operation efficiency of the high-speed train.

[0003] At present, the high-speed rail gearbox damage status assessment platform using big data technology is gaining increasing attention in the industry. By combining technologies such as machine learning and artificial intelligence, and building specific algorithms and models, it is possible to intelligently assess the damage status of high-speed rail gearboxes, significantly improving maintenance efficiency and the safety of high-speed rail operations.

[0004] However, some existing deep learning-based damage status assessment methods for high-speed rail gearboxes have two defects in practical engineering applications. On the one hand, the operating environment of high-speed railways is complex and changeable, resulting in different distribution characteristics of high-speed train gearbox status data collected under different environments. This inconsistency in data distribution makes it difficult to extract the status characteristics of high-speed train gearboxes. On the other hand, when some existing models use domain generalization learning to identify the damage status of high-speed rail gearboxes, the domain generalization characteristics of the extracted signals are not comprehensive, resulting in the loss of some weak but important domain generalization information, resulting in a decrease in the accuracy of damage status assessment, making it difficult to ensure the safety and efficiency of high-speed rail operation.

[0005] Therefore, there is an urgent need for a high-speed railway gearbox damage status assessment method, device, electronic terminal and storage medium to solve the above technical problems. Summary of the invention

[0006] The purpose of the present invention is to overcome the deficiencies in the prior art and provide a method for assessing the damage status of a high-speed railway gearbox, which can solve the technical problem that when the existing model identifies the damage status of a high-speed railway gearbox through domain generalization learning, the domain generalization characteristics of the extracted signal are incomplete, resulting in the loss of some weak but important domain generalization information, resulting in a decrease in the accuracy of damage status assessment and difficulty in ensuring the safety and efficiency of high-speed railway operation.

[0007] To achieve the above object, the present invention is implemented by adopting the following technical solutions: In a first aspect, the present invention provides a method for assessing the damage status of a high-speed railway gearbox, comprising: Acquire a vibration signal of a high-speed rail gearbox to be identified; Inputting the vibration signal into a pre-trained high-speed railway gearbox damage state assessment model, wherein the high-speed railway gearbox damage state assessment model includes a dynamic domain generalized feature extractor and a damage state discriminator, and the dynamic domain generalized feature extractor includes a static convolution module and a dynamic convolution module; Based on the high-speed railway gearbox damage state assessment model, the coarse-grained domain generalization features and the fine-grained domain generalization features in the vibration signal are extracted according to the static convolution module and the dynamic convolution module respectively, and the dynamic domain generalization features are constructed according to the coarse-grained domain generalization features and the fine-grained domain generalization features; The dynamic domain generalized features are input into a damage state discriminator to obtain multidimensional prediction probability data of multiple damage states, and damage state assessment results are determined based on the multidimensional prediction probability data corresponding to the multiple damage states.

[0008] Furthermore, the high-speed railway gearbox damage state assessment model further includes a dynamic coefficient discriminator, and the training process of the high-speed railway gearbox damage state assessment model includes: The training data under different working conditions are divided into non-overlapping parts according to a specified length standard to form independent subsets, and training class labels are assigned to the independent subsets with known damage types, and training domain labels are assigned to the training data under the different working conditions to obtain a training data set; Inputting the training data set into a dynamic domain generalization feature extractor, extracting coarse-grained domain generalization features and fine-grained domain generalization features in the training data, and constructing dynamic domain generalization features according to the coarse-grained domain generalization features and the fine-grained domain generalization features; Based on the dynamic convolution module and the dynamic coefficient discriminator, a dynamic coefficient discrimination loss function is established to combat the removal of domain information in the fine-grained domain generalization feature. Based on the damage state discriminator and the dynamic domain generalization feature extractor, a dynamic domain generalization feature discrimination loss function is established to combat the removal of domain information in the dynamic domain generalization feature to complete the training.

[0009] Further, according to the static convolution module and the dynamic convolution module, respectively extracting the coarse-grained domain generalization features and the fine-grained domain generalization features in the vibration signal, and constructing the dynamic domain generalization features according to the coarse-grained domain generalization features and the fine-grained domain generalization features includes: The static convolution module is used to extract the coarse-grained domain generalization feature information in one dimension, and the expression is: , in, Indicates vibration signal, and Respectively represent the convolution kernel and bias in the one-dimensional convolution operation, and Represent the convolution kernel and bias in the static convolution module respectively, represents a nonlinear activation function, Represents the coarse-grained features output by the static convolution module; The dynamic convolution module is used to extract fine-grained domain generalization feature information at the one-dimensional level, and the expression is: , , , in, and Represent the convolution kernel and bias in the dynamic convolution module respectively, represents the fine-grained features output by the dynamic convolution module, The dynamic convolution module includes four convolution kernels with the same structure but different parameters. Represents a mask operation, represents the dynamic coefficients generated by the metaregulator in the dynamic convolution module, represents the meta-regulator model parameter, symbol Represents the structural reorganization of the convolution kernel; According to the coarse-grained domain generalization feature and the fine-grained domain generalization feature, a dynamic domain generalization feature is constructed, and the expression includes: , in, Represents dynamic domain generalization features.

[0010] Furthermore, after constructing the dynamic domain generalization feature: Based on the dynamic coefficients generated by the meta-regulator in the dynamic convolution module, the training samples in the training data set are perturbed and the dynamic coefficients are randomly exchanged. The expression is: , , in, and Represents two random training samples respectively and A set of dynamic coefficients generated by the meta-regulator, represents the training data set, represents the dynamic coefficient perturbation operation, symbol Indicates a swap operation; Calculate the dynamic domain generalization feature loss of the same training sample output before and after perturbation, expressed as: , In the formula, is the perturbation loss between the dynamic domain generalization features output before perturbation and the dynamic domain generalization features output after perturbation for the same training sample, represents the total number of training samples, Indicates the first The dynamic domain generalization feature of training samples, the dynamic coefficient is , After the disturbance The dynamic domain generalization feature of training samples, the dynamic coefficient is , Indicates the calculation of the bi-norm value; The perturbation loss is minimized according to the back-propagation and optimization algorithm to extract fine-grained features that are discriminative between different training samples.

[0011] Furthermore, the dynamic coefficient discriminator includes a dynamic coefficient classifier and a dynamic coefficient domain discriminator, and the dynamic coefficient discrimination loss function includes: , In the formula, represents the total number of training samples assigned training class labels in the training dataset, represents the calculation of cross entropy loss, represents the probability prediction function, represents the logarithmic function, represents the dynamic coefficient classifier, represents the dynamic coefficient of the i-th training sample, represents the training class label, represents the total number of training samples in the training data set, represents the dynamic coefficient domain discriminator, represents the training domain label, is the dynamic coefficient discrimination loss; The dynamic convolution module is used to counter the dynamic coefficient domain discriminator to remove the domain information extracted in the dynamic convolution module.

[0012] Furthermore, the damage state discriminator includes a dynamic domain generalized feature classifier and a dynamic domain generalized feature domain discriminator, and the dynamic domain generalized feature discrimination loss function includes: , In the formula, represents the total number of training samples assigned training class labels in the training dataset, represents the calculation of cross entropy loss, represents the probability prediction function, represents the logarithmic function, represents the dynamic domain generalization feature classifier, represents the dynamic domain generalization feature of the i-th sample, represents the training class label, represents the total number of training samples in the training data set, represents the dynamic domain generalization feature domain discriminator, represents the training domain label, It is the discriminative loss of dynamic domain generalization features; The domain information in the dynamic domain generalization feature is removed by the dynamic domain generalization feature extractor and the dynamic domain generalization feature domain discriminator.

[0013] Furthermore, the optimization algorithm adopts one of an adaptive moment estimation algorithm, a stochastic gradient descent algorithm and a root mean square transfer algorithm.

[0014] In a second aspect, the present invention provides a high-speed railway gearbox damage status assessment device, comprising: An acquisition module, used to obtain the vibration signal of the high-speed rail gearbox to be identified; An input module, used for inputting the vibration signal into a pre-trained high-speed railway gearbox damage state assessment model, wherein the high-speed railway gearbox damage state assessment model comprises a dynamic domain generalized feature extractor and a damage state discriminator, and the dynamic domain generalized feature extractor comprises a static convolution module and a dynamic convolution module; An extraction module is used to extract the coarse-grained domain generalization features and the fine-grained domain generalization features in the vibration signal based on the high-speed railway gearbox damage state assessment model according to the static convolution module and the dynamic convolution module, and construct the dynamic domain generalization features according to the coarse-grained domain generalization features and the fine-grained domain generalization features; The recognition module is used to input the dynamic domain generalization feature into the damage state discriminator to obtain multidimensional prediction probability data of multiple damage states, and determine the damage state assessment result according to the multidimensional prediction probability data corresponding to the multiple damage states.

[0015] In a third aspect, the present invention provides an electronic terminal, comprising a processor and a memory connected to the processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of any of the above methods are performed.

[0016] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any of the above methods when executed by a processor.

[0017] Compared with the prior art, the present invention has the following beneficial effects: The present invention inputs the vibration signal to be identified into a pre-built high-speed railway gearbox damage state assessment model, and extracts the dynamic domain generalization features of the vibration signal to be identified through a dynamic domain generalization feature extractor. The dynamic domain generalization features can fully reflect the domain generalization information in the vibration signal to be identified, prevent the domain generalization features of the extracted signal from being incomplete and some weak but important domain generalization information from being missing, and help improve the performance output of subsequent classifiers, thereby realizing effective online diagnosis of high-speed railway gearboxes. By calculating and optimizing the dynamic coefficient discrimination loss and the dynamic domain generalization feature discrimination loss to learn the domain generalization features between different samples under different working conditions, the defect of traditional deep learning damage state assessment methods that it is difficult to extract cross-working condition state features is overcome, and the accuracy of high-speed rail gearbox damage state assessment is effectively improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flowchart of a method for assessing the damage status of a high-speed railway gearbox provided in Embodiment 1 of the present invention; Figure 2 It is a schematic diagram of the structure of a dynamic convolution module of a high-speed railway gearbox damage status assessment method provided in the first embodiment of the present invention; Figure 3 It is a schematic diagram of the structure of a high-speed rail gearbox damage status assessment model of a high-speed rail gearbox damage status assessment method provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0019] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0020] The term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0021] Non-overlap segmentation: Non-overlap segmentation of vibration signals usually means that during signal processing, the signal is segmented into multiple consecutive segments with no overlapping parts between each segment. It allows to obtain higher resolution in the frequency domain while reducing signal distortion caused by window functions; In practical applications, the method to be chosen depends on the characteristics of the signal and the analysis objectives. If non-overlapping segmentation is required, the maximum overlap discrete wavelet transform (MODWT) can be considered. These methods can process signals of arbitrary length and avoid a series of problems caused by overlap.

[0022] Embodiment 1: Figure 1 This flowchart only shows the logical sequence of the method described in this embodiment. In other possible embodiments of the present invention, different methods may be used without conflict. Figure 1 The steps shown or described are accomplished in the order shown.

[0023] The high-speed rail gearbox damage status assessment method provided in this embodiment can be applied to a terminal and can be executed by a high-speed rail gearbox damage status assessment device, which can be implemented by software and / or hardware, and can be integrated in a terminal, for example: any smart phone, tablet computer or computer device with communication function. Figure 1 , Figure 2 and Figure 3 As shown, the method of this embodiment specifically includes the following steps: Step 1: Obtain the vibration signal of the high-speed rail gearbox to be identified, and use sensors to collect the vibration signals of the high-speed rail wheel and rail under different working conditions.

[0024] Step 2: Input the vibration signal into a pre-trained high-speed railway gearbox damage state assessment model, wherein the high-speed railway gearbox damage state assessment model includes a dynamic domain generalized feature extractor and a damage state discriminator, and the dynamic domain generalized feature extractor includes a static convolution module and a dynamic convolution module.

[0025] Step 3: Based on the high-speed rail gearbox damage state assessment model, the coarse-grained domain generalization features and the fine-grained domain generalization features in the vibration signal are extracted according to the static convolution module and the dynamic convolution module respectively, and the dynamic domain generalization features are constructed according to the coarse-grained domain generalization features and the fine-grained domain generalization features: The static convolution module is used to extract the coarse-grained domain generalization feature information in one dimension, and the expression is: , in, Indicates vibration signal, and Respectively represent the convolution kernel and bias in the one-dimensional convolution operation, and Represent the convolution kernel and bias in the static convolution module respectively, represents a nonlinear activation function, Represents the coarse-grained features output by the static convolution module; The dynamic convolution module is used to extract fine-grained domain generalization feature information at the one-dimensional level, and the expression is: , , , in, and Represent the convolution kernel and bias in the dynamic convolution module respectively, represents the fine-grained features output by the dynamic convolution module, The dynamic convolution module includes four convolution kernels with the same structure but different parameters. Represents a mask operation, represents the dynamic coefficients generated by the metaregulator in the dynamic convolution module, represents the meta-regulator model parameter, symbol Represents the structural reorganization of the convolution kernel; According to the coarse-grained domain generalization feature and the fine-grained domain generalization feature, a dynamic domain generalization feature is constructed, and the expression includes: , in, Represents dynamic domain generalization features; In this embodiment, after constructing the dynamic domain generalization feature: Based on the dynamic coefficients generated by the meta-regulator in the dynamic convolution module, the training samples in the training data set are perturbed and the dynamic coefficients are randomly exchanged. The expression is: , , in, and Represent two random training samples respectively and The dynamic coefficient set generated by the meta-regulator, represents the training data set, represents the dynamic coefficient perturbation operation, symbol Indicates a swap operation; Calculate the dynamic domain generalization feature loss of the same training sample output before and after perturbation, expressed as: , In the formula, is the perturbation loss between the dynamic domain generalization features output before perturbation and the dynamic domain generalization features output after perturbation for the same training sample, represents the total number of training samples, Indicates the first The dynamic domain generalization feature of training samples, the dynamic coefficient is , After the disturbance The dynamic domain generalization feature of training samples, the dynamic coefficient is , Indicates the calculation of the bi-norm value; The perturbation loss is minimized according to the back-propagation and optimization algorithm to extract fine-grained features that are discriminative between different training samples, wherein the discriminability means that in this application, after the same sample is perturbed by the dynamic coefficients of different samples, the dynamic domain generalization features extracted by the dynamic domain generalization feature device are different but the differences are small, so as to enhance the generalization of the model.

[0026] Step 4: input the dynamic domain generalization feature into the damage state discriminator to obtain multidimensional prediction probability data of multiple damage states, and determine the damage state assessment result according to the multidimensional prediction probability data corresponding to the multiple damage states; Among them, the damage state discriminator includes a dynamic domain generalized feature classifier and a dynamic domain generalized feature domain discriminator, both of which are a kind of common classifiers in the neural network model, including a fully connected layer and a SoftMax function layer. The dynamic domain generalized feature is input into the damage state discriminator, and the dynamic domain generalized feature classifier obtains multidimensional prediction probability data of samples corresponding to multiple damage states, and the dynamic domain generalized feature domain discriminator obtains multidimensional prediction probability data of samples corresponding to different domains. How to "obtain multidimensional prediction probability data of multiple damage states according to the damage state discriminator" is explained as follows: after extracting the dynamic domain generalized feature of the corresponding sample, input it into the "dynamic domain generalized feature classifier" under the damage state discriminator. ", which includes a fully connected layer and a SoftMax function layer. The dynamic domain generalization features are processed by the fully connected layer to output low-dimensional features corresponding to the number of damage states, which are converted into probabilities through the SoftMax function layer. Finally, multi-dimensional prediction probability data of multiple damage states are obtained. The damage state refers to the known damage type.

[0027] The high-speed railway gearbox damage state assessment model further includes a dynamic coefficient discriminator, and the training process of the high-speed railway gearbox damage state assessment model includes: The training data under different working conditions are divided into non-overlapping parts according to a specified length standard to form independent subsets, and training class labels are assigned to the independent subsets with known damage types, and training domain labels are assigned to the training data under the different working conditions to obtain a training data set; The training class labels refer to labels for different known damage types in the independent subsets. The training class labels for the same known damage type are consistent, while the training class labels for different known damage types are inconsistent. The training domain labels refer to labels for training data collected under different working conditions. The training domain labels for training data collected under the same working condition are consistent, while the training domain labels for training data collected under different working conditions are inconsistent. Inputting the training data set into a dynamic domain generalization feature extractor, extracting coarse-grained domain generalization features and fine-grained domain generalization features in the training data, and constructing dynamic domain generalization features according to the coarse-grained domain generalization features and the fine-grained domain generalization features; Based on the dynamic convolution module and the dynamic coefficient discriminator, a dynamic coefficient discrimination loss function is established to combat the removal of domain information in the fine-grained domain generalization feature. Based on the damage state discriminator and the dynamic domain generalization feature extractor, a dynamic domain generalization feature discrimination loss function is established to combat the removal of domain information in the dynamic domain generalization feature to complete the training.

[0028] The dynamic coefficient discriminator includes a dynamic coefficient classifier and a dynamic coefficient domain discriminator, and the dynamic coefficient discriminant loss function includes: , In the formula, represents the total number of training samples assigned training class labels in the training dataset, represents the calculation of cross entropy loss, represents the probability prediction function, represents the logarithmic function, represents the dynamic coefficient classifier, represents the dynamic coefficient of the i-th training sample, represents the training class label, represents the total number of training samples in the training data set, represents the dynamic coefficient domain discriminator, represents the training domain label, is the dynamic coefficient discrimination loss; The dynamic convolution module is confronted with the dynamic coefficient domain discriminator to remove the domain information extracted in the dynamic convolution module. Specifically, the dynamic convolution module generates dynamic coefficients, and the dynamic coefficient domain discriminator continuously learns to better distinguish the dynamic coefficient domain labels, that is, the training domain labels corresponding to the training samples. The dynamic coefficient discrimination loss is minimized according to the back propagation and optimization algorithm, so that the dynamic coefficients generated by the dynamic convolution module in the model optimization process do not contain domain information, so that the dynamic coefficient domain discriminator cannot correctly distinguish the dynamic coefficient domain labels, that is, the training domain labels corresponding to the training samples. The dynamic coefficient discrimination loss is minimized by the back propagation and optimization algorithm, so that the mutual confrontation between the dynamic convolution module and the dynamic coefficient domain discriminator is realized, and the domain information extracted in the dynamic convolution module is removed.

[0029] The damage state discriminator includes a dynamic domain generalized feature classifier and a dynamic domain generalized feature domain discriminator, and the dynamic domain generalized feature discrimination loss function includes: , In the formula, represents the total number of training samples assigned training class labels in the training dataset, represents the calculation of cross entropy loss, represents the probability prediction function, represents the logarithmic function, represents the dynamic domain generalization feature classifier, represents the dynamic domain generalization feature of the i-th sample, represents the training class label, represents the total number of training samples in the training data set, represents the dynamic domain generalization feature domain discriminator, represents the training domain label, It is the discriminative loss of dynamic domain generalization features; The domain information in the dynamic domain generalization feature is removed by the confrontation between the dynamic domain generalization feature extractor and the dynamic domain generalization feature domain discriminator. Specifically, the dynamic domain generalization feature extractor extracts the dynamic domain generalization feature, while the dynamic domain generalization feature domain discriminator continuously learns to better distinguish the dynamic coefficient domain labels, that is, the training domain labels corresponding to the training samples. The dynamic domain generalization feature discrimination loss is minimized according to the back propagation and optimization algorithm, so that the dynamic domain generalization feature extracted by the dynamic domain generalization feature extractor during the model optimization process does not contain domain information, so that the dynamic domain generalization feature domain discriminator cannot correctly distinguish the dynamic coefficient domain labels, that is, the training domain labels corresponding to the training samples. The dynamic domain generalization feature discrimination loss is minimized by the back propagation and optimization algorithm, so that the mutual confrontation between the dynamic domain generalization feature extractor and the dynamic domain generalization feature domain discriminator is realized, and the domain information extracted in the dynamic domain generalization feature extractor is removed.

[0030] Furthermore, the optimization algorithm adopts one of an adaptive moment estimation algorithm, a stochastic gradient descent algorithm and a root mean square transfer algorithm, all of which belong to the prior art and will not be described in detail here.

[0031] The back propagation refers to: The gradient of the calculated loss is calculated, and then the optimization algorithm updates the network parameters according to the calculated gradient, which can be expressed as follows: , , , , , In the formula, represents the calculation of gradient, , , and represents the network parameters of the dynamic domain generalized feature extractor, the dynamic coefficient classifier and the dynamic coefficient domain discriminator in the dynamic coefficient discriminator, and the damage state classifier and domain discriminator in the damage state discriminator, is the preset learning rate parameter, , is the weight parameter.

[0032] The present embodiment is further described below with reference to the accompanying drawings and experimental cases: 1. Experimental data Take the bearing damage data set collected on the self-made wheelset bearing failure test bench as an example. The test bench can simulate the structural relationship and motion relationship of the high-speed rail gearbox and collect vibration data under three different working conditions. There are 8 types of bearing health states: normal (N), inner ring fault (IF), ball fault (BF), outer ring fault (OF), inner ring and ball combined fault (IBF), outer ring and inner ring combined fault (OIF), outer ring and ball combined fault (OBF), outer ring, inner ring and ball combined fault (OIBF). As shown in Table 1, under different working conditions (B1, B2, B3 and B4), the data collected for each health state is divided into 100 samples without overlap, and the sample length is 4096 points.

[0033] Table 1 Sample information of different working conditions

[0034] 2. Method Validation In order to verify the effectiveness and superiority of the proposed invention, this experimental case implemented 8 damage state assessment tasks under different domain generalization diagnosis tasks. Each domain generalization diagnosis task can be expressed as B1B3B4→B4, where the bold B1 represents a training set with a damage state label for one of the working conditions, B3 and B4 represent training sets without damage state labels for the other two working conditions, and B2 represents a test set under another working condition. In order to verify the effectiveness of the high-speed rail gearbox damage state assessment method driven by a dynamic domain generalization feature proposed in the present invention, it was compared with five other advanced diagnosis methods, including M1: conventional domain adversarial neural network DANN, M2: replacing the residual block in M1 with the dynamic residual module in the dynamic domain generalization feature extractor disclosed in this application, M3: a new hybrid generalization network - inner and outer domain generalization network IEDGNet, M4: an advanced causal disentanglement domain generalization method CDDG, M5: a comparison auxiliary domain specific removal network CDSRN, which extracts transferable features from the perspective of domain specific removal. In the present invention, the initial learning rate is 0.001, the batch size is 20, and the training cycle is 200. In order to speed up the convergence speed of the model, an exponential decay strategy is adopted.

[0035] Compared with other high-speed railway gearbox damage assessment methods, the recognition accuracy of the proposed method has achieved better results in most domain generalization diagnosis tasks. The comparison results are shown in Table 2.

[0036] Table 2 Experimental results

[0037] Embodiment 2: Embodiment 2 of the present invention provides a high-speed railway gearbox damage status assessment device, comprising: An acquisition module, used to obtain the vibration signal of the high-speed rail gearbox to be identified; An input module, used for inputting the vibration signal into a pre-trained high-speed railway gearbox damage state assessment model, wherein the high-speed railway gearbox damage state assessment model comprises a dynamic domain generalized feature extractor and a damage state discriminator, and the dynamic domain generalized feature extractor comprises a static convolution module and a dynamic convolution module; An extraction module is used to extract the coarse-grained domain generalization features and the fine-grained domain generalization features in the vibration signal based on the high-speed railway gearbox damage state assessment model according to the static convolution module and the dynamic convolution module, and construct the dynamic domain generalization features according to the coarse-grained domain generalization features and the fine-grained domain generalization features; The recognition module is used to input the dynamic domain generalization feature into the damage state discriminator to obtain multidimensional prediction probability data of multiple damage states, and determine the damage state assessment result according to the multidimensional prediction probability data corresponding to the multiple damage states.

[0038] The high-speed railway gearbox damage status assessment device provided in the second embodiment of the present invention can execute the high-speed railway gearbox damage status assessment method provided in the first embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0039] Embodiment three: Embodiment 3 of the present invention further provides an electronic terminal, including a processor and a memory connected to the processor, wherein a computer program is stored in the memory, and the processor is configured to operate according to the instructions to execute the steps of the method described in embodiment 1.

[0040] The electronic terminal provided in the third embodiment of the present invention can execute the high-speed railway gearbox damage status assessment method provided in the first embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0041] Embodiment 4: Embodiment 4 of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in Embodiment 1 are implemented, and the computer program has functional modules and beneficial effects corresponding to the execution method.

[0042] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, devices, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, 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 disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0043] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (apparatus), 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 generate 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.

[0044] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0045] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0046] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for assessing the damage status of a high-speed railway gearbox, characterized in that: include: Acquire a vibration signal of a high-speed rail gearbox to be identified; Inputting the vibration signal into a pre-trained high-speed railway gearbox damage state assessment model, wherein the high-speed railway gearbox damage state assessment model includes a dynamic domain generalized feature extractor and a damage state discriminator, and the dynamic domain generalized feature extractor includes a static convolution module and a dynamic convolution module; Based on the high-speed railway gearbox damage state assessment model, the coarse-grained domain generalization features and the fine-grained domain generalization features in the vibration signal are extracted according to the static convolution module and the dynamic convolution module respectively, and the dynamic domain generalization features are constructed according to the coarse-grained domain generalization features and the fine-grained domain generalization features; The dynamic domain generalized features are input into a damage state discriminator to obtain multidimensional prediction probability data of multiple damage states, and damage state assessment results are determined based on the multidimensional prediction probability data corresponding to the multiple damage states.

2. A high-speed railway gearbox damage status assessment method according to claim 1, characterized in that: The high-speed railway gearbox damage state assessment model further includes a dynamic coefficient discriminator, and the training process of the high-speed railway gearbox damage state assessment model includes: The training data under different working conditions are divided into non-overlapping parts according to a specified length standard to form independent subsets, and training class labels are assigned to the independent subsets with known damage types, and training domain labels are assigned to the training data under the different working conditions to obtain a training data set; Inputting the training data set into a dynamic domain generalization feature extractor, extracting coarse-grained domain generalization features and fine-grained domain generalization features in the training data, and constructing dynamic domain generalization features according to the coarse-grained domain generalization features and the fine-grained domain generalization features; Based on the dynamic convolution module and the dynamic coefficient discriminator, a dynamic coefficient discrimination loss function is established to combat the removal of domain information in the fine-grained domain generalization feature. Based on the damage state discriminator and the dynamic domain generalization feature extractor, a dynamic domain generalization feature discrimination loss function is established to combat the removal of domain information in the dynamic domain generalization feature to complete the training.

3. A high-speed railway gearbox damage status assessment method according to claim 2, characterized in that: According to the static convolution module and the dynamic convolution module, respectively extracting the coarse-grained domain generalization features and the fine-grained domain generalization features in the vibration signal, and constructing the dynamic domain generalization features according to the coarse-grained domain generalization features and the fine-grained domain generalization features includes: The static convolution module is used to extract the coarse-grained domain generalization feature information in one dimension, and the expression is: ， in, Indicates vibration signal, and Respectively represent the convolution kernel and bias in the one-dimensional convolution operation, and Represent the convolution kernel and bias in the static convolution module respectively, represents a nonlinear activation function, Represents the coarse-grained features output by the static convolution module; The dynamic convolution module is used to extract fine-grained domain generalization feature information at the one-dimensional level, and the expression is: ， ， ， in, and Represent the convolution kernel and bias in the dynamic convolution module respectively, represents the fine-grained features output by the dynamic convolution module, The dynamic convolution module includes four convolution kernels with the same structure but different parameters. Represents a mask operation, represents the dynamic coefficients generated by the metaregulator in the dynamic convolution module, represents the meta-regulator model parameter, symbol Represents the structural reorganization of the convolution kernel; According to the coarse-grained domain generalization feature and the fine-grained domain generalization feature, a dynamic domain generalization feature is constructed, and the expression includes: ， in, Represents dynamic domain generalization features.

4. A high-speed railway gearbox damage status assessment method according to claim 3, characterized in that: After constructing the dynamic domain generalization features: Based on the dynamic coefficients generated by the meta-regulator in the dynamic convolution module, the training samples in the training data set are perturbed and the dynamic coefficients are randomly exchanged. The expression is: ， ， in, and Represents two random training samples respectively and A set of dynamic coefficients generated by the meta-regulator, represents the training data set, represents the dynamic coefficient perturbation operation, symbol Indicates a swap operation; Calculate the dynamic domain generalization feature loss of the same training sample output before and after perturbation, expressed as: ， In the formula, is the perturbation loss between the dynamic domain generalization features output before perturbation and the dynamic domain generalization features output after perturbation for the same training sample, represents the total number of training samples, Indicates the first The dynamic domain generalization feature of training samples, the dynamic coefficient is , After the disturbance The dynamic domain generalization feature of training samples, the dynamic coefficient is , Indicates the calculation of the bi-norm value; The perturbation loss is minimized according to the back-propagation and optimization algorithm to extract fine-grained features that are discriminative between different training samples.

5. A high-speed railway gearbox damage status assessment method according to claim 2, characterized in that: The dynamic coefficient discriminator includes a dynamic coefficient classifier and a dynamic coefficient domain discriminator, and the dynamic coefficient discrimination loss function includes: ， In the formula, represents the total number of training samples assigned training class labels in the training dataset, represents the calculation of cross entropy loss, represents the probability prediction function, represents the logarithmic function, represents the dynamic coefficient classifier, represents the dynamic coefficient of the i-th training sample, represents the training class label, represents the total number of training samples in the training data set, represents the dynamic coefficient domain discriminator, represents the training domain label, is the dynamic coefficient discrimination loss; The dynamic convolution module is used to counter the dynamic coefficient domain discriminator to remove the domain information extracted in the dynamic convolution module.

6. A high-speed railway gearbox damage status assessment method according to claim 2, characterized in that: The damage state discriminator includes a dynamic domain generalized feature classifier and a dynamic domain generalized feature domain discriminator, and the dynamic domain generalized feature discrimination loss function includes: ， In the formula, represents the total number of training samples assigned training class labels in the training dataset, represents the calculation of cross entropy loss, represents the probability prediction function, represents the logarithmic function, represents the dynamic domain generalization feature classifier, represents the dynamic domain generalization feature of the i-th sample, represents the training class label, represents the total number of training samples in the training data set, represents the dynamic domain generalization feature domain discriminator, represents the training domain label, It is the discriminative loss of dynamic domain generalization features; The domain information in the dynamic domain generalization feature is removed by the dynamic domain generalization feature extractor and the dynamic domain generalization feature domain discriminator.

7. A high-speed railway gearbox damage status assessment method according to claim 4, characterized in that: The optimization algorithm adopts one of an adaptive moment estimation algorithm, a stochastic gradient descent algorithm and a root mean square transfer algorithm.

8. A high-speed railway gearbox damage status assessment device, characterized in that: include: An acquisition module, used to obtain the vibration signal of the high-speed rail gearbox to be identified; An input module, used for inputting the vibration signal into a pre-trained high-speed railway gearbox damage state assessment model, wherein the high-speed railway gearbox damage state assessment model comprises a dynamic domain generalized feature extractor and a damage state discriminator, and the dynamic domain generalized feature extractor comprises a static convolution module and a dynamic convolution module; An extraction module is used to extract the coarse-grained domain generalization features and the fine-grained domain generalization features in the vibration signal based on the high-speed railway gearbox damage state assessment model according to the static convolution module and the dynamic convolution module, and construct the dynamic domain generalization features according to the coarse-grained domain generalization features and the fine-grained domain generalization features; The recognition module is used to input the dynamic domain generalization feature into the damage state discriminator to obtain multidimensional prediction probability data of multiple damage states, and determine the damage state assessment result according to the multidimensional prediction probability data corresponding to the multiple damage states.

9. An electronic terminal, characterized in that: The method comprises a processor and a memory connected to the processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 7 are executed.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images