A fastener rigidity detection method, device, equipment and storage medium

Abstract

The application discloses a fastener rigidity detection method, device and equipment and a storage medium. The method comprises the following steps: acquiring vehicle parameters and track parameters of a to-be-detected line; acquiring wheel-rail vertical force of the to-be-detected line, and calculating a wheel-rail coupling system base frequency of the to-be-detected line according to the wheel-rail vertical force; inputting the vehicle parameters, the track parameters and the wheel-rail coupling system base frequency of the to-be-detected line into a preset fastener rigidity prediction model, so that the fastener rigidity prediction model predicts fastener rigidity of the to-be-detected line according to the vehicle parameters, the track parameters and the wheel-rail coupling system base frequency, and outputs predicted fastener rigidity of the to-be-detected line. The application can greatly improve the detection efficiency of the fastener rigidity, and significantly reduce the manpower and material resources required for fastener rigidity detection.

Description

Technical Field

[0001] This invention relates to the field of rail transit equipment testing technology, and in particular to a method, apparatus, equipment, and storage medium for testing the stiffness of fasteners. Background Technology

[0002] Fasteners are a crucial component of track structures, transferring the loads exerted by vehicles on the rails to the substructure, ensuring the safety and reliability of vehicle operation. However, under long-term train loads, the elastic pads of the fasteners age, leading to a gradual increase in fastener stiffness. Increased fastener stiffness exacerbates wheel-rail dynamic interaction, increasing the vibration energy transmitted to the substructure and significantly raising the environmental vibration levels around the track. This negatively impacts the daily lives and health of residents in the vicinity, while also accelerating fatigue damage to the track structure and increasing maintenance costs. Therefore, rapidly detecting the fastener stiffness of the entire track has significant social and economic benefits.

[0003] Currently, indoor testing methods for fastener stiffness are relatively mature and have corresponding testing standards. The standard "Test Methods for Fastener Systems of High-Speed ​​Railways Part 3: Determination of Assembly Static Stiffness" (TB / T 3396.3-2015) specifies an indoor testing method for the static stiffness of fastener assembly: a load perpendicular to the bottom surface of the rail is applied to the rail of the assembled fastener system using a testing machine, and the displacement of the rail relative to the sleeper under the load is measured. The fastener stiffness is calculated based on the vertical displacement of the rail at loads of 5kN and 55kN. While this indoor testing method can obtain fastener stiffness relatively accurately, it requires disassembling the fasteners on the track before testing in the laboratory, resulting in low testing efficiency and difficulty in comprehensively obtaining the evolution of fastener stiffness across the entire railway network. Some scholars have also proposed a method to directly infer the stiffness of track components from the measured frequency response function through on-site hammer impact tests. However, this method requires specific equipment and experienced engineering technicians, and the accuracy is greatly affected by the track condition, making it difficult to widely promote across the entire railway network.

[0004] Therefore, while existing methods for testing the stiffness of fasteners can meet the needs of a small number of fastener stiffness tests, they have drawbacks such as requiring high levels of equipment and technical personnel, and cannot yet meet the needs of routine railway engineering projects. Summary of the Invention

[0005] This invention provides a method, apparatus, equipment, and storage medium for testing the stiffness of fasteners, in order to solve the technical problems of existing fastener stiffness testing methods that require high levels of equipment and technical personnel, have low testing efficiency, and are costly.

[0006] To address the aforementioned technical problems, embodiments of the present invention provide a method for detecting the stiffness of fasteners, comprising:

[0007] Obtain vehicle and track parameters for the track to be inspected; wherein, the vehicle parameters include: wheelset mass, wheel radius, and tread type of the track inspection vehicle; the track parameters include: rail elastic modulus, rail moment of inertia about the horizontal axis, and fastener spacing throughout the entire track;

[0008] Obtain the wheel-rail vertical force of the line under test, and calculate the fundamental frequency of the wheel-rail coupling system of the line under test based on the wheel-rail vertical force of the line under test;

[0009] The vehicle parameters, track parameters, and wheel-rail coupling system fundamental frequency of the line to be tested are input into a preset fastener stiffness prediction model. The fastener stiffness prediction model predicts the fastener stiffness of the line to be tested based on the vehicle parameters, track parameters, and wheel-rail coupling system fundamental frequency, and outputs the predicted fastener stiffness of the line to be tested.

[0010] As a preferred embodiment, the step of obtaining the wheel-rail vertical force of the track under test and calculating the fundamental frequency of the wheel-rail coupling system of the track under test based on the wheel-rail vertical force includes:

[0011] The wheel-rail vertical force of the track under test is obtained by using the force-measuring wheelset of the track inspection vehicle in the track under test;

[0012] A Fourier transform is performed on the wheel-rail vertical force of the track to be tested to generate the wheel-rail vertical force spectrum of the track to be tested. Then, the frequency corresponding to the first peak in the wheel-rail vertical force spectrum of the track to be tested is taken as the fundamental frequency of the wheel-rail coupling system of the track to be tested.

[0013] As a preferred embodiment, the generation of the fastener stiffness prediction model includes:

[0014] Obtain the vehicle parameters, track parameters, and fastener stiffness of the sample line, and construct a coupled dynamic model of the vehicle and track based on the vehicle parameters and track parameters of the sample line.

[0015] Using the vehicle parameters and track parameters of the sample route as independent variables, obtain the sample data corresponding to the independent variables;

[0016] Substituting the sample data into the coupled dynamics model, the wheel-rail vertical force of the sample track is obtained;

[0017] Fourier transform is performed on the wheel-rail vertical force of the sample line to generate the wheel-rail vertical force spectrum of the sample line. Then, the frequency corresponding to the first peak in the wheel-rail vertical force spectrum of the sample line is taken as the fundamental frequency of the wheel-rail coupling system of the sample line.

[0018] The vehicle parameters, track parameters, fastener stiffness, and fundamental frequency of the wheel-rail coupling system of the sample line are used as training samples. A preset artificial intelligence algorithm model is trained based on the training samples to obtain the fastener stiffness prediction model.

[0019] As a preferred embodiment, the construction of a coupled dynamics model of the vehicle and track based on the vehicle and track parameters of the sample line includes:

[0020] Based on the vehicle and track parameters of the sample line, and the principles of wheel-rail dynamics, a coupled dynamic model of the vehicle and track is constructed; wherein, the coupled dynamic model includes any one of the following: a two-dimensional coupled dynamic model or a three-dimensional coupled dynamic model.

[0021] As a preferred embodiment, the step of obtaining sample data corresponding to the vehicle parameters and track parameters of the sample route as independent variables includes:

[0022] Using the vehicle parameters and track parameters of the sample route as independent variables, the preset value ranges corresponding to each independent variable are obtained;

[0023] A preset experimental design method is obtained, and the experimental design method is used as a sampling strategy. Then, sampling is performed within the preset value range corresponding to each variable according to the sampling strategy to obtain sample data corresponding to each variable. The experimental design method includes any one of the following: crossover experimental design or central composite design.

[0024] As a preferred embodiment, substituting the sample data into the coupled dynamics model to obtain the wheel-rail vertical force of the sample track includes:

[0025] The sample data is substituted into the coupled dynamics model, and random track irregularities are applied to the wheel-rail contact surface of the coupled dynamics model to obtain the wheel-rail vertical force of the sample track.

[0026] As a preferred embodiment, the artificial intelligence algorithm model includes any one of the following: a deep neural network model, a support vector machine model, or a recurrent neural network model.

[0027] Based on the above embodiments, another embodiment of the present invention provides a device for detecting the stiffness of fasteners, comprising:

[0028] Parameter acquisition module, fundamental frequency calculation module, and fastener stiffness prediction module;

[0029] The parameter acquisition module is used to acquire vehicle parameters and track parameters of the line to be inspected; wherein, the vehicle parameters include: wheelset mass, wheel radius, and tread type of the track inspection vehicle; the track parameters include: rail elastic modulus, rail moment of inertia about the horizontal axis, and fastener spacing throughout the entire line;

[0030] The fundamental frequency calculation module is used to obtain the wheel-rail vertical force of the line under test, and calculate the fundamental frequency of the wheel-rail coupling system of the line under test based on the wheel-rail vertical force of the line under test.

[0031] The fastener stiffness prediction module is used to input the vehicle parameters, track parameters, and wheel-rail coupling system fundamental frequency of the line to be tested into a preset fastener stiffness prediction model, so that the fastener stiffness prediction model can predict the fastener stiffness of the line to be tested based on the vehicle parameters, track parameters, and wheel-rail coupling system fundamental frequency, and output the predicted fastener stiffness of the line to be tested.

[0032] Based on the above embodiments, another embodiment of the present invention provides an electronic device, the device including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the fastener stiffness detection method described in the above embodiments of the invention.

[0033] Based on the above embodiments, another embodiment of the present invention provides a storage medium, the storage medium including a stored computer program, wherein, when the computer program is running, it controls the device where the storage medium is located to execute the fastener stiffness detection method described in the above embodiments of the invention.

[0034] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0035] In this invention, vehicle parameters and track parameters of the line to be tested are obtained; the wheel-rail vertical force of the line to be tested is obtained, and the fundamental frequency of the wheel-rail coupling system of the line to be tested is calculated based on the wheel-rail vertical force; the vehicle parameters, track parameters, and fundamental frequency of the wheel-rail coupling system of the line to be tested are input into a preset fastener stiffness prediction model, so that the fastener stiffness prediction model predicts the fastener stiffness of the line to be tested based on the vehicle parameters, track parameters, and fundamental frequency of the wheel-rail coupling system, and outputs the predicted fastener stiffness of the line to be tested.

[0036] This invention utilizes a pre-trained fastener stiffness prediction model. By inputting the vehicle parameters, track parameters, and the fundamental frequency of the wheel-rail coupling system of the track under test into the model, the predicted fastener stiffness of the track can be output. This invention comprehensively considers the influence of vehicle and rail parameters on the fastener stiffness detection effect. It directly uses the vehicle and track parameters of the track under test to infer the fastener stiffness, eliminating the need to remove fasteners from the track for indoor testing. Furthermore, it requires less sophisticated equipment and technical personnel. This invention can significantly improve the efficiency of fastener stiffness detection and substantially reduce the manpower and material resources required for fastener stiffness testing, thus possessing broad application prospects. Attached Figure Description

[0037] Figure 1 This is a flowchart illustrating a method for detecting the stiffness of fasteners according to an embodiment of the present invention;

[0038] Figure 2 This is a schematic diagram of a two-dimensional vehicle-track coupled dynamics model;

[0039] Figure 3 This is a schematic diagram of a three-dimensional vehicle-track coupled dynamics model;

[0040] Figure 4 It is a time history diagram of the vertical force between the wheel and rail;

[0041] Figure 5 This is a spectrum diagram of vertical force between the wheel and rail;

[0042] Figure 6 This is a schematic diagram of a fastener stiffness detection device provided in an embodiment of the present invention. Detailed Implementation

[0043] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] Example 1

[0045] Please refer to Figure 1 The following is a flowchart illustrating a method for detecting the stiffness of a fastener according to an embodiment of the present invention, including the following specific steps:

[0046] S1. Obtain vehicle parameters and track parameters for the line to be inspected; wherein, the vehicle parameters include: wheelset mass, wheel radius, and tread type of the track inspection vehicle; the track parameters include: rail elastic modulus, rail moment of inertia about the horizontal axis, and fastener spacing throughout the entire line;

[0047] When testing the fastener stiffness of the track under inspection, the vehicle parameters and track parameters of the track under inspection are first obtained. The vehicle parameters include the wheelset mass, wheel radius, and tread type of the track inspection vehicle. The track parameters include the elastic modulus of the rails, the moment of inertia of the rails about the horizontal axis, and the fastener spacing throughout the track.

[0048] S2. Obtain the wheel-rail vertical force of the line to be tested, and calculate the fundamental frequency of the wheel-rail coupling system of the line to be tested based on the wheel-rail vertical force of the line to be tested;

[0049] Preferably, the step of obtaining the wheel-rail vertical force of the track to be tested and calculating the fundamental frequency of the wheel-rail coupling system of the track to be tested based on the wheel-rail vertical force of the track to be tested includes: obtaining the wheel-rail vertical force of the track to be tested through the force-measuring wheelset of the track inspection vehicle in the track to be tested; performing a Fourier transform on the wheel-rail vertical force of the track to be tested to generate the wheel-rail vertical force spectrum of the track to be tested, and then taking the frequency corresponding to the first peak in the wheel-rail vertical force spectrum of the track to be tested as the fundamental frequency of the wheel-rail coupling system of the track to be tested.

[0050] After obtaining the vehicle and track parameters of the line to be tested, the wheel-rail vertical force of the line to be tested is obtained through the force-measuring wheelset on the track inspection vehicle. The time history data of the wheel-rail vertical force is subjected to Fourier transform to obtain the frequency corresponding to the first obvious peak in the wheel-rail vertical force spectrum, which is the fundamental frequency (f / Hz) of the wheel-rail coupling system.

[0051] S3. Input the vehicle parameters, track parameters, and wheel-rail coupling system fundamental frequency of the line to be tested into a preset fastener stiffness prediction model, so that the fastener stiffness prediction model can predict the fastener stiffness of the line to be tested based on the vehicle parameters, track parameters, and wheel-rail coupling system fundamental frequency, and output the predicted fastener stiffness of the line to be tested.

[0052] After obtaining the vehicle parameters, track parameters, and wheel-rail coupling system fundamental frequency of the line to be tested, the vehicle parameters, track parameters, and wheel-rail coupling system fundamental frequency of the line to be tested are input into the fastener stiffness prediction model pre-trained in this invention. The fastener stiffness prediction model can then predict the fastener stiffness of the line to be tested and output the predicted fastener stiffness of the line to be tested.

[0053] Preferably, the generation of the fastener stiffness prediction model includes: acquiring vehicle parameters, track parameters, and fastener stiffness of the sample line; constructing a coupled dynamics model of the vehicle and track based on the vehicle parameters and track parameters of the sample line; acquiring sample data corresponding to the vehicle parameters and track parameters of the sample line as independent variables; substituting the sample data into the coupled dynamics model to obtain the wheel-rail vertical force of the sample line; performing a Fourier transform on the wheel-rail vertical force of the sample line to generate the wheel-rail vertical force spectrum of the sample line, and then using the frequency corresponding to the first peak in the wheel-rail vertical force spectrum of the sample line as the fundamental frequency of the wheel-rail coupling system of the sample line; using the vehicle parameters, track parameters, fastener stiffness, and fundamental frequency of the wheel-rail coupling system of the sample line as training samples, and training a preset artificial intelligence algorithm model based on the training samples to obtain the fastener stiffness prediction model.

[0054] Preferably, the step of constructing a coupled dynamics model of the vehicle and track based on the vehicle parameters and track parameters of the sample line includes: constructing a coupled dynamics model of the vehicle and track based on the vehicle parameters and track parameters of the sample line and the wheel-rail dynamics principle; wherein, the coupled dynamics model includes any one of the following: a two-dimensional coupled dynamics model or a three-dimensional coupled dynamics model.

[0055] Preferably, the step of obtaining sample data corresponding to the vehicle parameters and track parameters of the sample route as independent variables includes: obtaining a preset value range corresponding to each independent variable using the vehicle parameters and track parameters of the sample route as independent variables; obtaining a preset experimental design method; using the experimental design method as a sampling strategy; and then sampling within the preset value range corresponding to each independent variable according to the sampling strategy to obtain sample data corresponding to each independent variable; wherein, the experimental design method includes any one of the following: cross-tabulation experimental design or central composite design.

[0056] Preferably, the step of substituting the sample data into the coupled dynamics model to obtain the wheel-rail vertical force of the sample track includes: substituting the sample data into the coupled dynamics model and applying random track irregularities to the wheel-rail contact surface of the coupled dynamics model to obtain the wheel-rail vertical force of the sample track.

[0057] Preferably, the artificial intelligence algorithm model includes any one of the following: a deep neural network model, a support vector machine model, or a recurrent neural network model.

[0058] The specific training process of the fastener stiffness prediction model is as follows:

[0059] (1) Collect sufficient vehicle parameters, track parameters and fastener stiffness for several sample routes.

[0060] The vehicle parameters include: wheelset mass (M / kg), wheel radius (R / m), and tread type (conical or worn tread) of the track inspection vehicle; the track parameters include: rail modulus of elasticity (E / Pa) and rail moment of inertia about the horizontal axis (I / m) across the entire track. 4 The wheel-rail contact stiffness in the vehicle-track coupled dynamics model constructed below will also differ depending on the tread type.

[0061] (2) Establish a vehicle-track coupled dynamic model based on the collected vehicle and track parameters.

[0062] The vehicle-track coupled dynamics model is established based on the collected vehicle and track parameters, using the principles of wheel-rail dynamics. It can be a two-dimensional or three-dimensional model. Please refer to [link / reference]. Figure 2 This is a schematic diagram of a two-dimensional vehicle-track coupled dynamics model. When using this model, the vehicle is considered a 10-DOF (degrees of freedom) multi-rigid body, the rails and track slabs are simulated using two-dimensional beam elements, and the vehicle suspension, fasteners, and foundation are simulated using spring-damping elements. The labels in the diagram are: 1-car body, 2-bogie, 3-wheelset, 4-secondary suspension, 5-primary suspension, 6-track irregularity, 7-rail, 8-fastener.

[0063] Please refer to Figure 3 This is a schematic diagram of a three-dimensional vehicle-track coupled dynamics model. When using this model, the vehicle is considered a multi-rigid body with 31 or 35 degrees of freedom. The rails are simulated using three-dimensional beam elements, and the track slab is modeled using shell or solid elements. The vehicle suspension, fasteners, and foundation are simulated using spring-damping elements. Track types can include: integral track bed, trapezoidal sleepers, vibration-damping floating slabs, and steel spring floating slabs, etc.

[0064] (3) Obtain the wheel-rail vertical force of the sample line.

[0065] Using the vehicle and track parameters of the above sample lines as independent variables, orthogonal experimental design and central composite design are used as sampling strategies. Sampling is carried out within the reasonable range of values ​​of each independent variable. The sampled samples are substituted into the established vehicle-track coupled dynamic model. At the same time, in order to excite the vibration of the wheel-rail coupled system, random track irregularities are applied to the wheel-rail contact surface of the coupled dynamic model to obtain the time history data of the wheel-rail vertical force.

[0066] (4) Calculate the fundamental frequency of the wheel-rail coupling system of the sample line.

[0067] Fourier transform was performed on the above wheel-rail vertical force time history data to obtain the frequency corresponding to the first obvious peak in the wheel-rail vertical force spectrum, which is the fundamental frequency (f / Hz) of the wheel-rail coupling system of the sample line.

[0068] (5) Model training process.

[0069] Using the above-mentioned sampled samples and the fundamental frequency of the wheel-rail coupling system of the sampled line as input samples, and the fastener stiffness as output samples, the samples are substituted into an artificial intelligence algorithm model composed of deep neural networks, support vector machines, or recurrent neural networks. The model is then continuously trained, verified, and optimized to fit the complex functional relationship between the fastener stiffness and the vehicle parameters, track parameters, and the fundamental frequency of the wheel-rail coupling system, thereby generating the fastener stiffness prediction model.

[0070] To further illustrate the fastener stiffness prediction model of this invention, a specific implementation example is provided below to explain the training process of the fastener stiffness prediction model:

[0071] S1. Taking a certain urban railway project as an example, the car body mass is 37200kg, the bogie mass is 2700kg, the wheelset mass is 1935kg, the wheel radius is 0.43m, the wheel tread is a wearing type, the design speed is 160km / h, and the rail elastic modulus is 2.059×10⁻⁶. 11 Pa, the moment of inertia of the rail about the horizontal axis is 0.3217 × 10⁻⁶. -4 m 4 The fastener spacing is 0.6m.

[0072] S2. Based on the principle of wheel-rail coupled dynamics, a two-dimensional coupled dynamic model of vehicle-track is established according to the vehicle and track parameters collected in S1. The vertical contact between wheel and track is simulated using a nonlinear load contact model.

[0073] S3. Using the vehicle and track parameters described in S1 as independent variables, a central composite design method is adopted as the sampling strategy. Sampling is carried out within the reasonable range of values ​​of each independent variable. The sampled samples are shown in Table 1 below.

[0074]

[0075]

[0076] Table 1 Sampling Sample

[0077] Substituting the sampled data into the vehicle-track coupled dynamics model established in S2, and using the German low-interference spectrum as the excitation for the wheel-rail system, time history data of the wheel-rail vertical force were obtained. Please refer to... Figure 4 , is the time history diagram of the vertical force on the wheel and rail.

[0078] S4. Perform a Fourier transform on the wheel-rail vertical force time history data described in S3 to obtain the frequency corresponding to the first obvious peak in the wheel-rail vertical force spectrum, i.e., the fundamental frequency (f / Hz) of the wheel-rail coupling system. The fundamental frequency of the wheel-rail coupling system is 46.14Hz. Please refer to [reference needed]. Figure 5 The graph shows the frequency spectrum of the wheel-rail vertical force. The amplitude of the wheel-rail vertical force in a double logarithmic coordinate system is shown below. Figure 5 As shown.

[0079] S5. Using the sampled data from S3 and the corresponding wheel-rail system fundamental frequency from S4 as input samples, and the fastener stiffness as the output sample, these are substituted into an artificial intelligence algorithm model composed of a deep neural network. This model is then continuously trained and validated. Mean square error, root mean square error, and mean absolute error are used to evaluate the accuracy and robustness of the AI ​​algorithm model in predicting the fastener stiffness. If the prediction error does not meet the requirements, the AI ​​algorithm model is optimized, and the above process is repeated until the prediction error meets the corresponding requirements. This allows for the fitting of a complex functional relationship between the fastener stiffness and the parameters described in S1 and the wheel-rail coupling system fundamental frequency.

[0080] S6. Using the force-measuring wheelsets in a track inspection vehicle commonly used in railway engineering, the entire line is inspected to obtain the wheel-rail vertical force at different mileages. A Fourier transform is performed on the wheel-rail vertical force to obtain the fundamental frequency of the wheel-rail coupling system. Substituting the fundamental frequency of the wheel-rail coupling system and the vehicle and track parameters described in S1 into the artificial intelligence algorithm model, the fastener stiffness at different mileages of the line can be predicted. The comparison results of the fastener stiffness prediction results from the artificial intelligence algorithm model with the actual fastener stiffness are shown in Table 2 below.

[0081] Fastener stiffness (kN / mm) 34.08 35.00 2.63％

[0082] Table 2 Error Analysis

[0083] As shown in Table 2, the maximum error between the prediction results of the artificial intelligence algorithm model and the actual fastener stiffness is only 2.63%, which indicates that the artificial intelligence algorithm model can well map the vehicle and track parameters mentioned in S1 as well as the functional relationship between the fundamental frequency of the wheel-rail coupling system and the fastener stiffness.

[0084] Therefore, this invention provides a method for detecting fastener stiffness. Utilizing a pre-trained fastener stiffness prediction model, the vehicle parameters, track parameters, and the fundamental frequency of the wheel-rail coupling system of the line under test are input into the model, which then outputs the predicted fastener stiffness of the line under test. Addressing the shortcomings of existing fastener stiffness detection methods, this invention leverages a vehicle-track coupling dynamics model and artificial intelligence algorithms to fully utilize the inherent relationships between fastener stiffness, the fundamental frequency of the wheel-rail coupling system, and vehicle and track parameters. This enables the detection and evaluation of line-level fastener stiffness, significantly accelerating the transformation of railway engineering towards intelligent operation and maintenance.

[0085] Example 2

[0086] Please refer to Figure 6 This is a schematic diagram of a fastener stiffness detection device according to an embodiment of the present invention. The device includes: a parameter acquisition module, a fundamental frequency calculation module, and a fastener stiffness prediction module.

[0087] The parameter acquisition module is used to acquire vehicle parameters and track parameters of the line to be inspected; wherein, the vehicle parameters include: wheelset mass, wheel radius, and tread type of the track inspection vehicle; the track parameters include: rail elastic modulus, rail moment of inertia about the horizontal axis, and fastener spacing throughout the entire line;

[0088] The fundamental frequency calculation module is used to obtain the wheel-rail vertical force of the line under test, and calculate the fundamental frequency of the wheel-rail coupling system of the line under test based on the wheel-rail vertical force of the line under test.

[0089] The fastener stiffness prediction module is used to input the vehicle parameters, track parameters, and wheel-rail coupling system fundamental frequency of the line to be tested into a preset fastener stiffness prediction model, so that the fastener stiffness prediction model can predict the fastener stiffness of the line to be tested based on the vehicle parameters, track parameters, and wheel-rail coupling system fundamental frequency, and output the predicted fastener stiffness of the line to be tested.

[0090] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0091] Those skilled in the art will clearly understand that, for convenience and simplicity, the specific working process of the device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0092] Example 3

[0093] Accordingly, embodiments of the present invention provide an electronic device, the device including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the fastener stiffness detection method described in the above embodiments of the invention.

[0094] The electronic device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The device may include, but is not limited to, a processor and a memory.

[0095] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the device, connecting various parts of the device via various interfaces and lines.

[0096] Example 4

[0097] Accordingly, embodiments of the present invention provide a storage medium, the storage medium including a stored computer program, wherein, when the computer program is running, it controls the device where the storage medium is located to execute the fastener stiffness detection method described in the above embodiments of the invention.

[0098] The memory can be used to store the computer program. The processor implements various functions of the device by running or executing the computer program stored in the memory and calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc.; the data storage area may store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0099] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When executed by a processor, the computer program can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0100] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for detecting the stiffness of fasteners, characterized in that, include: Obtain vehicle and track parameters for the track to be inspected; wherein, the vehicle parameters include: wheelset mass, wheel radius, and tread type of the track inspection vehicle; the track parameters include: rail elastic modulus, rail moment of inertia about the horizontal axis, and fastener spacing throughout the entire track; Obtain the wheel-rail vertical force of the line under test, and calculate the fundamental frequency of the wheel-rail coupling system of the line under test based on the wheel-rail vertical force of the line under test; The vehicle parameters, track parameters, and wheel-rail coupling system fundamental frequency of the line to be tested are input into a preset fastener stiffness prediction model. The fastener stiffness prediction model predicts the fastener stiffness of the line to be tested based on the vehicle parameters, track parameters, and wheel-rail coupling system fundamental frequency, and outputs the predicted fastener stiffness of the line to be tested.

2. The method for detecting the stiffness of fasteners as described in claim 1, characterized in that, The process of obtaining the wheel-rail vertical force of the track under test and calculating the fundamental frequency of the wheel-rail coupling system of the track under test based on the wheel-rail vertical force includes: The wheel-rail vertical force of the track under test is obtained by using the force-measuring wheelset of the track inspection vehicle in the track under test; A Fourier transform is performed on the wheel-rail vertical force of the track to be tested to generate the wheel-rail vertical force spectrum of the track to be tested. Then, the frequency corresponding to the first peak in the wheel-rail vertical force spectrum of the track to be tested is taken as the fundamental frequency of the wheel-rail coupling system of the track to be tested.

3. The method for detecting the stiffness of fasteners as described in claim 1, characterized in that, The generation of the fastener stiffness prediction model includes: Obtain the vehicle parameters, track parameters, and fastener stiffness of the sample line, and construct a coupled dynamic model of the vehicle and track based on the vehicle parameters and track parameters of the sample line. Using the vehicle parameters and track parameters of the sample route as independent variables, obtain the sample data corresponding to the independent variables; Substituting the sample data into the coupled dynamics model, the wheel-rail vertical force of the sample track is obtained; Fourier transform is performed on the wheel-rail vertical force of the sample line to generate the wheel-rail vertical force spectrum of the sample line. Then, the frequency corresponding to the first peak in the wheel-rail vertical force spectrum of the sample line is taken as the fundamental frequency of the wheel-rail coupling system of the sample line. The vehicle parameters, track parameters, fastener stiffness, and fundamental frequency of the wheel-rail coupling system of the sample line are used as training samples. A preset artificial intelligence algorithm model is trained based on the training samples to obtain the fastener stiffness prediction model.

4. The method for detecting the stiffness of fasteners as described in claim 3, characterized in that, The construction of a coupled dynamic model of vehicles and tracks based on the vehicle and track parameters of the sample line includes: Based on the vehicle and track parameters of the sample line, and the principles of wheel-rail dynamics, a coupled dynamic model of the vehicle and track is constructed; wherein, the coupled dynamic model includes any one of the following: a two-dimensional coupled dynamic model or a three-dimensional coupled dynamic model.

5. The method for detecting the stiffness of fasteners as described in claim 3, characterized in that, The process of obtaining sample data corresponding to the vehicle parameters and track parameters of the sample route as independent variables includes: Using the vehicle parameters and track parameters of the sample route as independent variables, the preset value ranges corresponding to each independent variable are obtained; A preset experimental design method is obtained, and the experimental design method is used as a sampling strategy. Then, sampling is performed within the preset value range corresponding to each variable according to the sampling strategy to obtain sample data corresponding to each variable. The experimental design method includes any one of the following: orthogonal experimental design method or central composite design method.

6. The method for detecting the stiffness of fasteners as described in claim 3, characterized in that, The step of substituting the sample data into the coupled dynamics model to obtain the wheel-rail vertical force of the sample track includes: The sample data is substituted into the coupled dynamics model, and random track irregularities are applied to the wheel-rail contact surface of the coupled dynamics model to obtain the wheel-rail vertical force of the sample track.

7. The method for detecting the stiffness of fasteners as described in claim 3, characterized in that, The artificial intelligence algorithm model includes any one of the following: deep neural network model, support vector machine model, or recurrent neural network model.

8. A device for detecting the stiffness of fasteners, characterized in that, include: Parameter acquisition module, fundamental frequency calculation module, and fastener stiffness prediction module; The parameter acquisition module is used to acquire vehicle parameters and track parameters of the line to be inspected; wherein, the vehicle parameters include: wheelset mass, wheel radius, and tread type of the track inspection vehicle; the track parameters include: rail elastic modulus, rail moment of inertia about the horizontal axis, and fastener spacing throughout the entire line; The fundamental frequency calculation module is used to obtain the wheel-rail vertical force of the line under test, and calculate the fundamental frequency of the wheel-rail coupling system of the line under test based on the wheel-rail vertical force of the line under test. The fastener stiffness prediction module is used to input the vehicle parameters, track parameters, and wheel-rail coupling system fundamental frequency of the line to be tested into a preset fastener stiffness prediction model, so that the fastener stiffness prediction model can predict the fastener stiffness of the line to be tested based on the vehicle parameters, track parameters, and wheel-rail coupling system fundamental frequency, and output the predicted fastener stiffness of the line to be tested.

9. An electronic device, characterized in that, The device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the fastener stiffness detection method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device containing the storage medium to perform the fastener stiffness detection method as described in any one of claims 1 to 7.

Images