A rail defect detection method and device, electronic equipment and storage medium

Abstract

The application discloses a track defect detection method and device, electronic equipment and storage medium, and relates to the field of rail transit. The method comprises the following steps: acquiring a finite element model of a target track, loading a global excitation signal in a first frequency interval on the cross section of the finite element model, and acquiring a first time-frequency diagram of a guided wave time domain signal of a first finite element node; acquiring a guided wave curve diagram of the target track, and acquiring a first mode with the lowest attenuation degree according to the first time-frequency diagram and the guided wave curve diagram; and performing defect detection on the target track according to the first mode; wherein the first mode corresponds to a second frequency interval. The technical scheme of the embodiment of the application greatly improves the detection distance of the defect detection equipment, improves the coverage range of the track defect detection, thereby reducing the number of defect detection equipment installed between railway stations, reducing the hardware cost required for realizing the track defect detection, and reducing the labor cost and time cost required for equipment maintenance.

Description

Technical Field

[0001] This invention relates to the field of rail transit, and more particularly to a method, apparatus, electronic device, and storage medium for detecting track defects. Background Technology

[0002] With the continuous development of science and technology, my country's railway mileage is constantly increasing. At the same time, as an important means to ensure track safety, track defect detection has become an important research topic.

[0003] In existing technologies, multiple defect detection devices are typically installed between two railway stations. Each defect detection device uses ultrasonic guided wave technology to detect the track within a specified section, thereby ensuring the safe operation of the railway track.

[0004] However, existing defect detection equipment is limited by ultrasonic guided wave technology and can only detect tracks over short distances, making it difficult to meet the detection needs of long-distance tracks. The detection effect is also poor. This also means that a large number of devices need to be installed between two railway stations, which increases the installation cost of defect detection equipment as well as the manpower and time costs of subsequent maintenance. Summary of the Invention

[0005] This invention provides a method, apparatus, electronic device, and storage medium for detecting track defects, in order to solve the problem of poor defect detection results for long-distance tracks.

[0006] According to one aspect of the present invention, a method for detecting track defects is provided, comprising:

[0007] A finite element model of the target orbit is obtained, and a global excitation signal in the first frequency range is applied to the cross section of the finite element model to obtain a first time-frequency diagram of the guided wave time domain signal of the first finite element node.

[0008] Obtain the guided wave profile of the target trajectory, and based on the first time-frequency diagram and the guided wave profile, obtain the first mode with the lowest attenuation; wherein, the guided wave profile reflects the numerical relationship between frequency and group velocity.

[0009] Defect detection is performed on the target orbit based on the first mode; where the first mode corresponds to the second frequency range.

[0010] According to another aspect of the present invention, a track defect detection device is provided, comprising:

[0011] The time-frequency diagram acquisition module is used to acquire the finite element model of the target orbit and load a global excitation signal in the first frequency range onto the cross section of the finite element model to acquire the first time-frequency diagram of the guided wave time domain signal of the first finite element node.

[0012] The waveform acquisition module is used to acquire the guided wave curve of the target orbit, and to acquire the first mode with the lowest attenuation based on the first time-frequency diagram and the guided wave curve; wherein, the guided wave curve reflects the numerical relationship between frequency and group velocity.

[0013] The modality acquisition module is used to perform defect detection on the target orbit based on the first mode; wherein, the first mode corresponds to the second frequency range.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the track defect detection method according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the track defect detection method according to any embodiment of the present invention.

[0019] The technical solution of this invention first obtains a finite element model of the target track and applies a global excitation signal in a first frequency range to the cross-section of the finite element model to obtain a first time-frequency diagram of the guided wave time-domain signal of the first finite element node; secondly, it obtains a guided wave curve diagram of the target track; finally, based on the first time-frequency diagram and the guided wave curve diagram, it obtains the first mode with the lowest attenuation and performs defect detection on the target track based on the first mode. This greatly improves the detection distance of the defect detection equipment, increases the coverage of track defect detection, and reduces the number of defect detection devices installed between railway stations, thereby reducing both the hardware cost required for track defect detection and the labor and time costs required for equipment maintenance.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1A This is a flowchart of a track defect detection method provided in Embodiment 1 of the present invention;

[0023] Figure 1B This is a schematic diagram of the finite element model provided in Embodiment 1 of the present invention;

[0024] Figure 1C This is a schematic diagram of the mesh structure of the finite element model provided in Embodiment 1 of the present invention;

[0025] Figure 1D This is a schematic diagram of the global excitation signal provided according to Embodiment 1 of the present invention;

[0026] Figure 1E This is a first time-frequency diagram provided according to Embodiment 1 of the present invention;

[0027] Figure 1F This is a waveguide curve diagram provided according to Embodiment 1 of the present invention;

[0028] Figure 1G It is a superimposed combination diagram of the first time-frequency diagram and the guided wave curve diagram provided in Embodiment 1 of the present invention;

[0029] Figure 2 This is a flowchart of another track defect detection method provided in Embodiment 2 of the present invention;

[0030] Figure 3 This is a flowchart of another track defect detection method provided in Embodiment 3 of the present invention;

[0031] Figure 4A This is a flowchart of another track defect detection method provided in Embodiment 4 of the present invention;

[0032] Figure 4B This is a schematic diagram of the location of the local excitation signal provided in Embodiment 4 of the present invention;

[0033] Figure 4C This is a superimposed combination diagram corresponding to the longitudinal excitation signal at the rail waist center provided in Embodiment 4 of the present invention;

[0034] Figure 4D This is a superimposed combination diagram of the longitudinal excitation signal on the side of the rail web provided in Embodiment 4 of the present invention;

[0035] Figure 4E This is a superimposed combination diagram of the longitudinal excitation signal of the lower jaw of the rail head provided in Embodiment 4 of the present invention;

[0036] Figure 4F This is a superimposed combination diagram corresponding to the longitudinal excitation signal at the railhead center provided in Embodiment 4 of the present invention;

[0037] Figure 5 This is a schematic diagram of the structure of a track defect detection device according to Embodiment 5 of the present invention;

[0038] Figure 6 This is a schematic diagram of the structure of an electronic device that implements the track defect detection method of this invention. Detailed Implementation

[0039] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. 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 should fall within the scope of protection of the present invention.

[0040] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0041] Example 1

[0042] Figure 1A This is a flowchart of a track defect detection method provided in Embodiment 1 of the present invention. This embodiment is applicable to detecting defects in a target track based on the first mode with the lowest attenuation obtained under a global excitation signal. This track defect detection method can be configured in a track defect detection device, which can be implemented in hardware and / or software, and can be configured in electronic equipment (e.g., track defect detection equipment). Figure 1A As shown, the method includes:

[0043] S101. Obtain the finite element model of the target orbit, and load the cross section of the finite element model with a global excitation signal in the first frequency range to obtain the first time-frequency diagram of the guided wave time domain signal of the first finite element node.

[0044] First, such as Figure 1B As shown, a three-dimensional finite element model of the target track is obtained using existing finite element simulation software, such as Comsol, Abaqus, and ANASYS. Next, material property parameters of the target track, such as material density, Poisson's ratio, and Young's modulus, are configured into the finite element model. The target track can be made of materials such as seamless steel rails, composite material rails, and fiberglass rails. In this embodiment of the invention, the material type of the target track is not specifically limited.

[0045] Then, as Figure 1C As shown, the finite element model is meshed to divide its cross-section into multiple meshes; then, a global excitation signal is applied to the entire cross-section of the target orbit to excite as many guided wave modes as possible propagating on the target orbit; where, as Figure 1D As shown, the global excitation signal can be configured as a linear frequency modulated signal; the frequency range of the global excitation signal (i.e., the first frequency interval) can be configured from 3000Hz to 35000Hz. Specifically, the track length of the finite element model can be configured as needed. The longer the track length, the longer the calculation time required by the track detection equipment. To ensure a faster calculation speed, the finite element model can be configured with a shorter distance, for example, configuring the track length of the finite element model to 100 meters.

[0046] As the propagation distance increases, the attenuation degree of different modes of guided wave signals varies. The energy of high-attenuation modes decreases rapidly with increasing propagation distance, while low-attenuation modes can still maintain high energy after propagating a long distance. Therefore, one or more modes with the smallest attenuation in the guided wave time domain signal can be determined by the energy of different modes of the guided wave time domain signal after propagating a certain distance. The guided wave time domain signal on the target track can be obtained by a time domain solver.

[0047] As described in the above technical solution, a node at a first preset distance from the application position of the global excitation signal is selected as the first finite element node. The first preset distance can be configured as needed. In order to ensure that the guided wave signal has propagated a long distance in the finite element model and thus obtain a large number of modes, the first preset distance can be set to a large value, for example, the first preset distance can be set to 30 meters. After obtaining the guided wave time-domain signal of the first finite element node, the guided wave time-domain signal can be processed by data processing methods such as Fourier transform, and the time-frequency diagram of the guided wave time-domain signal (i.e., the first time-frequency diagram) can be obtained based on the data processing results. The first time-frequency diagram reflects the relationship between the frequency and time of the guided wave time-domain signal.

[0048] Optionally, in this embodiment of the invention, obtaining the first time-frequency diagram of the guided wave time-domain signal of the first finite element node includes: performing wavelet transform processing on the guided wave time-domain signal of the first finite element node to obtain the first time-frequency diagram. Specifically, wavelet transform actually decomposes the guided wave time-domain signal using multiple wavelet basis functions. Compared with data processing methods such as Fourier transform, the time-frequency diagram obtained by wavelet transform has multi-resolution transformations, which is beneficial for the separate extraction of different features at each resolution. In addition, wavelet transform is faster than Fourier transform in data processing speed, greatly simplifying the data processing complexity of the guided wave time-domain signal and improving data processing efficiency.

[0049] like Figure 1E As shown, in the first time-frequency diagram of the guided wave time-domain signal at the first finite element node, the horizontal axis represents the frequency of the guided wave, the vertical axis represents time, and the different resolutions (i.e., different colors or different brightness) on the right represent different energy values; since in this embodiment of the invention, the first frequency range is 3000Hz to 35000Hz, therefore in Figure 1E In addition to the lower energy values ​​in the regions near 3000Hz and near 35000Hz due to the influence of frequency control precision, the energy is almost entirely zero in the region outside 3000Hz to 35000Hz. In the region between 3000Hz and 35000Hz, the greater the brightness, the greater the energy value in that region, and the smaller the brightness, the smaller the energy value in that region.

[0050] S102. Obtain the guided wave curve of the target orbit, and obtain the first mode with the lowest attenuation based on the first time-frequency diagram and the guided wave curve; wherein, the guided wave curve reflects the numerical relationship between frequency and group velocity.

[0051] Using discrete element method (DEM) software tools, such as MatDEM and EDEM, the cross-section of the target orbit is discretized into multiple triangular elements. Then, the material properties of the target orbit are substituted into the existing guided wave equation to obtain the guided wave profile of the target orbit. For example, Figure 1F As shown, the guided wave curve reflects the relationship between the frequency and group velocity of the guided wave time-domain signal. Figure 1F Each curve in the diagram represents a mode.

[0052] To overlay the guided wave curve with the first time-frequency diagram, the guided wave curve needs to be transformed so that their coordinate meanings are the same. The corresponding propagation time can be obtained from the propagation distance and group velocity. Thus, the guided wave curve, which reflects the relationship between the frequency and group velocity of the guided wave time-domain signal, is transformed into a guided wave curve that reflects the relationship between the frequency and time of the guided wave time-domain signal, thereby providing a basis for overlay. After overlaying the first time-frequency diagram with the transformed guided wave curve, the overlay combined diagram is obtained.

[0053] like Figure 1G As shown, through image recognition of the superimposed image, the bright area with the largest energy value (the largest energy value means the lowest attenuation) in the superimposed image occurs in the frequency range of 15000Hz to 18000Hz, and there is a mode (i.e., the first mode) in the above bright area. Thus, the first mode still has a large energy value after propagating a first preset distance, and the large energy value allows the first mode to propagate a longer distance; where the above 15000Hz to 18000Hz is the second frequency range.

[0054] S103. Defect detection is performed on the target orbit based on the first mode; wherein, the first mode corresponds to the second frequency range.

[0055] After obtaining the first mode in the second frequency range, when actually detecting the target track, the second frequency range can be used as the frequency range of the excitation signal, which can be triggered by global excitation or local excitation. Thus, by using the first mode in the second frequency range to detect defects in the target track, a longer track distance can be detected, increasing the detection distance of the defect detection equipment and improving the coverage of track defect detection. In particular, the defect detection of the target track can include track fracture detection, as well as the detection of inclusions, scratches, and indentations on the track surface. In this embodiment of the invention, the detection type of track defect detection is not specifically limited.

[0056] The technical solution of this invention first obtains a finite element model of the target track and applies a global excitation signal in a first frequency range to the cross-section of the finite element model to obtain a first time-frequency diagram of the guided wave time-domain signal of the first finite element node; secondly, it obtains a guided wave curve diagram of the target track; finally, based on the first time-frequency diagram and the guided wave curve diagram, it obtains the first mode with the lowest attenuation and performs defect detection on the target track based on the first mode. This greatly improves the detection distance of the defect detection equipment, increases the coverage of track defect detection, and reduces the number of defect detection devices installed between railway stations, thereby reducing both the hardware cost required for track defect detection and the labor and time costs required for equipment maintenance.

[0057] Example 2

[0058] Figure 2 This is a flowchart of a track defect detection method provided in Embodiment 2 of the present invention. The relationship between this embodiment and the above embodiments is that, based on the similarity between the second mode and the first mode under the local excitation signal, a second mode similar to the first mode is obtained. Figure 2 As shown, the method includes:

[0059] S201. Obtain the finite element model of the target trajectory, and apply a global excitation signal in the first frequency range to the cross section of the finite element model to obtain the first time-frequency diagram of the guided wave time domain signal of the first finite element node.

[0060] S202. Obtain the guided wave curve of the target orbit, and based on the first time-frequency diagram and the guided wave curve, obtain the first mode with the lowest attenuation; wherein, the guided wave curve reflects the numerical relationship between frequency and group velocity.

[0061] S203. Apply a local excitation signal in the second frequency range to the cross section of the finite element model to obtain the second time-frequency diagram of the guided wave time domain signal of the first finite element node.

[0062] In practical applications, due to the limitations of the track defect detection equipment's own structure and installation location, as well as the inconvenience of drilling holes in the track cross section, it is often impossible to apply an excitation signal to the entire track cross section, that is, it is impossible to apply a global excitation signal to the cross section. Only a local excitation signal can be applied to a point in the cross section. In this case, after applying a local excitation signal in the second frequency range to the cross section of the finite element model, the second time-frequency diagram of the guided wave time domain signal of the first finite element node is obtained.

[0063] S204. Based on the current second time-frequency diagram and waveguide curve, obtain the second mode with the lowest attenuation.

[0064] As described in the above technical solution, after the waveguide curve is transformed by coordinate axis, the waveguide curve changes from reflecting the numerical change relationship between waveguide frequency and group velocity to reflecting the numerical change relationship between waveguide frequency and time. Then, the second time-frequency diagram is superimposed with the transformed waveguide curve, and the second mode with the largest energy value is obtained from the superimposed combination diagram.

[0065] S205. If it is determined that the similarity between the current second mode and the first mode conforms to the preset similarity rule, defect detection is performed on the target orbit based on the current second mode and the current local excitation signal.

[0066] Since the second mode and the first mode share the same frequency range (i.e., the second frequency range), if the second mode is the same as the first mode, then they obviously need to reach the same position at the same time (i.e., propagate the first preset distance in the same time). Therefore, in their respective superimposed composite diagrams, their vertical axes should have the same propagation time, meaning the second mode and the first mode should appear in the same position. Furthermore, the more similar the waveform (or shape) of the second mode is to the first mode, the greater the probability that they are the same mode. Therefore, the preset similarity rule is that the propagation time is the same (i.e., they appear in the same position in the superimposed composite diagram), and the waveform (or shape) similarity is greater than or equal to a preset similarity threshold.

[0067] S206. If it is determined that the similarity between the current second mode and the first mode does not meet the preset similarity rules, other local excitation signals in the second frequency range are continued to be applied to the cross section of the finite element model to continue to obtain the second time-frequency diagram of the guided wave time domain signal of the first finite element node.

[0068] S207. Continue to obtain the second mode with the lowest attenuation based on the current second time-frequency diagram and guided wave curve diagram until the similarity between the current second mode and the first mode meets the preset similarity rule. Based on the current second mode and the current local excitation signal, perform defect detection on the target trajectory.

[0069] If the similarity between the current second mode and the first mode does not meet the preset similarity rule, it means that the first mode cannot be excited under the current local excitation signal. At this time, other local excitation signals in the second frequency range are continued to be applied to the cross section of the finite element model to continue to obtain the second time-frequency diagram of the guided wave time domain signal of the first finite element node; wherein, different local excitation signals are applied to different locations on the cross section.

[0070] As described in the above technical solution, based on other local excitation signals after the position point change, the corresponding second mode is continuously acquired until the similarity between the current second mode and the first mode meets the preset similarity rule. Based on the current second mode and the current local excitation signal, defect detection is performed on the target track. Thus, the matching second mode can be obtained by filtering through the preset similarity rule, thereby ensuring a strong energy value for the second mode under the local excitation signal during long-distance transmission, thereby realizing long-distance ultrasonic guided wave transmission.

[0071] The technical solution of this invention involves applying a local excitation signal to the cross-section of a finite element model to obtain a second time-frequency diagram of the guided wave time domain signal of the first finite element node. Based on the second time-frequency diagram and the guided wave curve, the second mode with the lowest attenuation is obtained. After determining that the similarity between the second mode and the first mode conforms to a preset similarity rule, defect detection is performed on the target track based on the current second mode and the current local excitation signal. This allows a second mode with strong propagation capability to be obtained by applying a local excitation signal at a specific location, thereby increasing the detection distance of the track defect detection device and improving the coverage and convenience of track defect detection.

[0072] Example 3

[0073] Figure 3 This is a flowchart of a track defect detection method provided in Embodiment 3 of the present invention. The relationship between this embodiment and the above embodiments is that, after determining that the similarity between the current second mode and the first mode conforms to a preset similarity rule, it continues to determine whether the number of modes under the current local excitation signal conforms to a preset number rule. Figure 3 As shown, the method includes:

[0074] S301. Obtain the finite element model of the target trajectory, and load the cross section of the finite element model with a global excitation signal in the first frequency range to obtain the first time-frequency diagram of the guided wave time domain signal of the first finite element node.

[0075] S302. Obtain the guided wave curve of the target trajectory, and obtain the first mode with the lowest attenuation based on the first time-frequency diagram and the guided wave curve; wherein, the guided wave curve reflects the numerical relationship between frequency and group velocity.

[0076] S303. Apply a local excitation signal in the second frequency range to the cross section of the finite element model to obtain the second time-frequency diagram of the guided wave time domain signal of the first finite element node.

[0077] S304. Based on the current second time-frequency diagram and waveguide curve, obtain the second mode with the lowest attenuation.

[0078] S305. If it is determined that the similarity between the current second mode and the first mode conforms to the preset similarity rule, and the number of modes under the current local excitation signal does not conform to the preset number rule, continue to load other local excitation signals under the second frequency range onto the cross section of the finite element model, so as to continue to obtain the second time-frequency diagram of the guided wave time domain signal of the first finite element node.

[0079] S306. If it is determined that the similarity between the current second mode and the first mode conforms to the preset similarity rule, and the number of modes under the current local excitation signal conforms to the preset number rule, then perform defect detection on the target orbit based on the current second mode and the current local excitation signal.

[0080] If the number of modes under the current local excitation signal is large (that is, the number of curves in the second frequency range in the superimposed combination diagram is large), then the detection energy will be dispersed by a large number of modes, and the energy dispersed to each mode is low. Even if the waveform of the second mode obtained at this time is similar to that of the first mode, it still cannot meet the long-distance propagation requirements because the energy of the second mode itself is weak. At this time, other local excitation signals under the second frequency range are continued to be loaded onto the cross section of the finite element model to continue to find other second modes that meet the above propagation requirements. Therefore, the preset number rule is that the number of modes is less than or equal to the preset number threshold.

[0081] If the number of modes under the current local excitation signal is small (that is, the number of curves in the second frequency range in the superimposed combination diagram is small), then the detection energy will be dispersed by a small number of modes, and the energy dispersed to each mode is high. At this time, the second mode is not only similar to the waveform of the first mode, but also has strong energy. The second mode is the first mode mentioned above, that is, the first mode that meets the detection requirements is successfully excited by the current local excitation signal.

[0082] The technical solution of this invention, after determining that the similarity between the second mode and the first mode conforms to a preset similarity rule, if the number of modes under the current local excitation signal conforms to a preset number rule, performs defect detection on the target track based on the current second mode and the current local excitation signal. This ensures that the second mode is not only similar to the waveform of the first mode, but also has strong energy. In other words, it ensures that the first mode that meets the detection requirements can be successfully excited by the local excitation signal. While meeting the long-distance detection requirements, it also improves the triggering convenience of the excitation signal.

[0083] Example 4

[0084] Figure 4A This is a flowchart of a track defect detection method provided in Embodiment 4 of the present invention. The relationship between this embodiment and the above embodiments is that the target local excitation signal is obtained by filtering from various local excitation signals through a pre-constructed modal aggregation degree calculation formula. For example... Figure 4A As shown, the method includes:

[0085] S401. Obtain the finite element model of the target orbit, and load the cross section of the finite element model with a global excitation signal in the first frequency range to obtain the first time-frequency diagram of the guided wave time domain signal of the first finite element node.

[0086] S402. Obtain the guided wave curve of the target orbit, and based on the first time-frequency diagram and the guided wave curve, obtain the first mode with the lowest attenuation; wherein, the guided wave curve reflects the numerical relationship between frequency and group velocity.

[0087] S403. Apply different local excitation signals in the second frequency range to the cross section of the finite element model to obtain multiple third time-frequency maps of the guided wave time domain signal of the first finite element node; wherein, the third time-frequency map is matched one by one with the local excitation signal.

[0088] The application locations of different local excitation signals can be pre-planned, for example, such as... Figure 4B As shown, the local excitation signal may include one or more of the following: the longitudinal excitation signal of the rail web center (i.e., point A), the longitudinal excitation signal of the rail web side (i.e., point B), the longitudinal excitation signal of the rail head jaw (i.e., point C), and the longitudinal excitation signal of the rail head center (i.e., point D); for each local excitation signal, the corresponding third time-frequency diagram is obtained.

[0089] S404. Based on each third time-frequency diagram and guided wave curve, obtain the superimposed combination diagram respectively; wherein, the superimposed combination diagram is matched one-to-one with the local excitation signal.

[0090] Taking the above technical solution as an example, if the local excitation signals include the longitudinal excitation signal at the center of the rail web, the longitudinal excitation signal on the side of the rail web, the longitudinal excitation signal at the lower jaw of the rail head, and the longitudinal excitation signal at the center of the rail head, then, based on the fourth time-frequency diagrams corresponding to the above four local excitation signals, after superimposing them with the guided wave curve diagrams, the resulting superimposed combination diagrams are as follows: Figure 4C , Figure 4D , Figure 4E , Figure 4F As shown.

[0091] S405. The modal aggregation degree of each local excitation signal is obtained by the following equation.

[0092]

[0093] Where W is the modal clustering degree of the current local excitation signal; k is the sampling point number in the current superimposed image; i is the sampling point number of the first mode; K is the total number of sampling points in the current superimposed image; I is the total number of sampling points of the first mode; P kIt is the ratio of the energy value of the current sampling point in the current overlay combined image to the total energy value of all sampling points in the current overlay combined image; f k It is the frequency of the current sampling point in the current overlay image; v k It is the group velocity of the current sampling point in the current overlay graph; f l_i It is the frequency of the current sampling point in the first mode; v l_i It is the group velocity of the current sampling point in the first mode.

[0094] Specifically, taking the modal convergence of the longitudinal excitation signal at the center of the rail waist as an example, in the above technical solution, the second frequency range of the first mode is known to be 15000Hz to 18000Hz, and the frequency sampling step size of the first mode can be pre-configured as needed. Assuming the frequency sampling step size of the first mode is 1000, then the number of sampling points for the first mode is 4 (i.e., I = 4), that is, f l_1 =15000Hz, f l_2 =16000Hz, f l_3 =17000Hz, f l_4 =18000Hz; at the same time, according to Figure 1G As shown in the superimposed combination diagram under the global excitation signal, f l_1 f l_2 f l_3 f l_3 The corresponding v l_1 v l_2 v l_3 v l_4 .

[0095] And in Figure 4C In the superimposed combination diagram of the longitudinal excitation signal at the center of the track waist shown, the frequency sampling step size in this diagram can also be pre-configured as needed. Assuming that the frequency sampling step size is configured to be 5000Hz, the number of sampling points with corresponding time values ​​at each sampling frequency is obtained. For example, at the 0Hz position, there may be a total of 2 time values, and at the 5000Hz position, there may be a total of 4 time values. The sum of the number of time values ​​corresponding to all sampling Hz is the total number of sampling points in the current superimposed combination diagram, which is the K value. k is the number of the above sampling points. Obviously, the value of k ranges from 1 to K.

[0096] At the same time, through Figure 4C It can also determine the frequency of each sampling point (i.e., f). k (value) and the group velocity (i.e., v) at each sampling point k (Value). Furthermore, in Figure 4CIn this process, based on the resolution (i.e., brightness or color) of each sampling point, the energy value of each sampling point can be obtained, and thus the total energy value of all sampling points, P, can be obtained. k This is the ratio of the energy value of the current sampling point k to the total energy value of all sampling points.

[0097] S406. Based on the modal aggregation degree of each local excitation signal, obtain the target local excitation signal with the largest modal aggregation degree value.

[0098] S407. Based on the target local excitation signal, perform defect detection on the target track.

[0099] The larger the modal clustering value, the more singular the guided wave mode excited by the current local excitation function is, and the closer it is to the first mode with the lowest attenuation under the global excitation signal. Taking the above scheme as an example, the modal clustering values ​​of the longitudinal excitation signal at the rail waist center, the longitudinal excitation signal on the rail waist side, the longitudinal excitation signal at the rail head jaw, and the longitudinal excitation signal at the rail head center are calculated to be 0.003, 0.0055, 0.0148, and 0.0216, respectively. Among them, the modal clustering value of the longitudinal excitation signal at the rail head center is the largest, so it is used as the target local excitation signal. In particular, when the longitudinal excitation signal at the rail head center is inconvenient to apply or fails to apply, the longitudinal excitation signal at the rail head jaw with the largest value among the remaining modal clustering values ​​can continue to be selected as the actual detection signal until the excitation signal is successfully applied.

[0100] The technical solution of this invention calculates the modal aggregation degree of each local excitation signal and uses the target local excitation signal with the largest modal aggregation degree as the excitation signal used for track defect detection. This ensures that the guided wave mode excited by the current local excitation signal is relatively simple, and also ensures that the mode is excited to be close to the first mode, thereby increasing the detection distance of the track defect detection device and thus improving the coverage of track defect detection.

[0101] Example 5

[0102] Figure 5 This is a structural block diagram of a track defect detection device provided in Embodiment 5 of the present invention. The device specifically includes:

[0103] The time-frequency diagram acquisition module 501 is used to acquire the finite element model of the target orbit and load a global excitation signal in the first frequency range onto the cross section of the finite element model to acquire the first time-frequency diagram of the guided wave time domain signal of the first finite element node.

[0104] The waveform acquisition module 502 is used to acquire the guided wave curve of the target orbit, and to acquire the first mode with the lowest attenuation based on the first time-frequency diagram and the guided wave curve; wherein, the guided wave curve reflects the numerical relationship between frequency and group velocity.

[0105] The modality acquisition module 503 is used to perform defect detection on the target track based on the first mode; wherein the first mode corresponds to the second frequency range.

[0106] The technical solution of this invention first obtains a finite element model of the target track and applies a global excitation signal in a first frequency range to the cross-section of the finite element model to obtain a first time-frequency diagram of the guided wave time-domain signal of the first finite element node; secondly, it obtains a guided wave curve diagram of the target track; finally, based on the first time-frequency diagram and the guided wave curve diagram, it obtains the first mode with the lowest attenuation and performs defect detection on the target track based on the first mode. This greatly improves the detection distance of the defect detection equipment, increases the coverage of track defect detection, and reduces the number of defect detection devices installed between railway stations, thereby reducing both the hardware cost required for track defect detection and the labor and time costs required for equipment maintenance.

[0107] Optionally, the time-frequency diagram acquisition module 501 is specifically used to perform wavelet transform processing on the guided wave time-domain signal of the first finite element node to obtain the first time-frequency diagram.

[0108] Optionally, the mode acquisition module 503 is specifically used to apply a local excitation signal in the second frequency range to the cross section of the finite element model to obtain a second time-frequency diagram of the guided wave time domain signal of the first finite element node; based on the current second time-frequency diagram and the guided wave curve, obtain the second mode with the lowest attenuation; if it is determined that the similarity between the current second mode and the first mode conforms to a preset similarity rule, perform defect detection on the target track based on the current second mode and the current local excitation signal.

[0109] Optionally, the mode acquisition module 503 is specifically used to, if it is determined that the similarity between the current second mode and the first mode does not meet the preset similarity rule, continue to load other local excitation signals in the second frequency range onto the cross section of the finite element model to continue to acquire the second time-frequency diagram of the guided wave time domain signal of the first finite element node; continue to acquire the second mode with the lowest attenuation based on the current second time-frequency diagram and the guided wave curve diagram until the similarity between the current second mode and the first mode meets the preset similarity rule; and perform defect detection on the target track based on the current second mode and the current local excitation signal.

[0110] Optionally, the modal acquisition module 503 is specifically used to, if the number of modes under the current local excitation signal does not meet the preset number rule, continue to load other local excitation signals under the second frequency range onto the cross section of the finite element model to continue to acquire the second time-frequency diagram of the guided wave time domain signal of the first finite element node; if the number of modes under the current local excitation signal meets the preset number rule, perform defect detection on the target track according to the current second mode and the current local excitation signal.

[0111] Optionally, the modal acquisition module 503 is specifically used to apply different local excitation signals in a second frequency range to the cross section of the finite element model to obtain multiple third time-frequency maps of the guided wave time-domain signal of the first finite element node; wherein, the third time-frequency map is matched one-to-one with the local excitation signal; according to each third time-frequency map and the guided wave curve, a superimposed combination map is obtained respectively; wherein, the superimposed combination map is matched one-to-one with the local excitation signal; the modal clustering degree of each local excitation signal is obtained through the following equation; according to the modal clustering degree of each local excitation signal, the target local excitation signal with the largest modal clustering degree value is obtained; and according to the target local excitation signal, defect detection is performed on the target track.

[0112]

[0113] Where W is the modal clustering degree of the current local excitation signal; k is the sampling point number in the current superimposed image; i is the sampling point number of the first mode; K is the total number of sampling points in the current superimposed image; I is the total number of sampling points of the first mode; P k It is the ratio of the energy value of the current sampling point in the current overlay combined image to the total energy value of all sampling points in the current overlay combined image; f k It is the frequency of the current sampling point in the current overlay image; v k It is the group velocity of the current sampling point in the current overlay graph; f l_i It is the frequency of the current sampling point in the first mode; v l_i It is the group velocity of the current sampling point in the first mode.

[0114] Optionally, the local excitation signal includes at least one of the following: longitudinal excitation signal at the center of the rail web, longitudinal excitation signal at the side of the rail web, longitudinal excitation signal at the lower jaw of the rail head, and longitudinal excitation signal at the center of the rail head.

[0115] The above-described apparatus can execute the track defect detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the track defect detection method provided in any embodiment of the present invention.

[0116] Example 6

[0117] Figure 6 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, electronic devices, blade electronic devices, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0118] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0119] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0120] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as track defect detection methods.

[0121] In some embodiments, the track defect detection method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed on a heterogeneous hardware accelerator via ROM and / or a communication unit. When the computer program is loaded into RAM and executed by a processor, one or more steps of the track defect detection method described above may be performed. Alternatively, in other embodiments, the processor may be configured to perform the track defect detection method by any other suitable means (e.g., by means of firmware).

[0122] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0123] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or electronic device.

[0124] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0125] To provide user interaction, the systems and techniques described herein can be implemented on a heterogeneous hardware accelerator, which includes: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the heterogeneous hardware accelerator. Other types of devices can also be used to provide user interaction; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or haptic feedback); and input from the user can be received in any form (including sound input, voice input, or haptic input).

[0126] The systems and technologies described herein can be implemented in computing systems that include back-end components (e.g., as data electronic devices), or computing systems that include middleware components (e.g., application electronic devices), or computing systems that include front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0127] A computing system can include clients and electronic devices. Clients and electronic devices are generally geographically separated and typically interact via communication networks. The client-electronic device relationship is created by computer programs running on the respective computers and establishing a client-electronic device relationship between them. Electronic devices can be cloud electronic devices, also known as cloud computing electronic devices or cloud servers, which are hosting products within the cloud computing service ecosystem. These address the shortcomings of traditional physical hosting and VPS services, such as high management difficulty and weak business scalability.

[0128] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0129] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for detecting track defects, characterized in that, include: A finite element model of the target trajectory is obtained, and a global excitation signal in a first frequency range is applied to the cross section of the finite element model to obtain a first time-frequency diagram of the guided wave time domain signal of the first finite element node; wherein, the first finite element node is a node at a first preset distance from the application position of the global excitation signal. Obtain the guided wave profile of the target trajectory, and based on the first time-frequency diagram and the guided wave profile, obtain the first mode with the lowest attenuation; wherein, the guided wave profile reflects the numerical relationship between frequency and group velocity. Defect detection is performed on the target orbit based on the first mode; where the first mode corresponds to the second frequency range.

2. The method according to claim 1, characterized in that, The acquisition of the first time-frequency plot of the guided wave time-domain signal of the first finite element node includes: Wavelet transform is performed on the guided wave time-domain signal of the first finite element node to obtain the first time-frequency diagram.

3. The method according to claim 1, characterized in that, The defect detection of the target orbit based on the first mode includes: A local excitation signal in the second frequency range is applied to the cross section of the finite element model to obtain a second time-frequency diagram of the guided wave time domain signal of the first finite element node; Based on the current second time-frequency diagram and waveguide curve, obtain the second mode with the lowest attenuation. If the similarity between the current second mode and the first mode is determined to meet the preset similarity rules, defect detection is performed on the target orbit based on the current second mode and the current local excitation signal.

4. The method according to claim 3, characterized in that, After obtaining the second mode with the lowest attenuation, the following is also included: If it is determined that the similarity between the current second mode and the first mode does not meet the preset similarity rules, other local excitation signals in the second frequency range are continued to be applied to the cross section of the finite element model to continue to obtain the second time-frequency diagram of the guided wave time domain signal of the first finite element node; Continue to obtain the second mode with the lowest attenuation based on the current second time-frequency diagram and guided wave curve diagram until the similarity between the current second mode and the first mode meets the preset similarity rule. Based on the current second mode and the current local excitation signal, perform defect detection on the target trajectory.

5. The method according to claim 3, characterized in that, After determining that the similarity between the current second modality and the first modality conforms to the preset similarity rules, the process also includes: If the number of modes under the current local excitation signal does not meet the preset number rule, continue to load other local excitation signals under the second frequency range onto the cross section of the finite element model to continue to obtain the second time-frequency diagram of the guided wave time domain signal of the first finite element node; The defect detection of the target orbit based on the current second mode and the current local excitation signal includes: If the number of modes under the current local excitation signal meets the preset number rule, defect detection is performed on the target trajectory based on the current second mode and the current local excitation signal.

6. The method according to claim 1, characterized in that, The step of detecting defects in the target orbit based on the first mode and the global excitation signal includes: Different local excitation signals in the second frequency range are applied to the cross section of the finite element model to obtain multiple third time-frequency maps of the guided wave time domain signal of the first finite element node; wherein, the third time-frequency map is matched one by one with the local excitation signal; Based on each third time-frequency diagram and waveguide curve, a superimposed combination diagram is obtained; wherein, the superimposed combination diagram is matched one-to-one with the local excitation signal. The modal aggregation degree of each local excitation signal is obtained by the following equation; in, It represents the modal aggregation degree of the current local excitation signal; It is the sampling point number in the current overlay diagram; It is the sampling point number of the first mode; This represents the total number of sampling points in the current overlay composite image; This is the total number of sampling points in the first mode; It is the ratio of the energy value of the current sampling point in the current overlay combined image to the total energy value of all sampling points in the current overlay combined image; It is the frequency of the current sampling point in the current overlay image; It is the group velocity of the current sampling point in the current overlay graph; It is the frequency of the current sampling point in the first mode; It is the group velocity of the current sampling point in the first mode; Based on the modal clustering degree of each local excitation signal, obtain the target local excitation signal with the largest modal clustering degree value; Based on the target local excitation signal, defect detection is performed on the target trajectory.

7. The method according to any one of claims 3-6, characterized in that, The local excitation signal includes at least one of the following: longitudinal excitation signal at the center of the rail web, longitudinal excitation signal at the side of the rail web, longitudinal excitation signal at the lower jaw of the rail head, and longitudinal excitation signal at the center of the rail head.

8. A track defect detection device, characterized in that, include: The time-frequency diagram acquisition module is used to acquire the finite element model of the target orbit and apply a global excitation signal in a first frequency range to the cross section of the finite element model to acquire the first time-frequency diagram of the guided wave time domain signal of the first finite element node; wherein, the first finite element node is a node that is spaced at a first preset distance from the application position of the global excitation signal. The waveform acquisition module is used to acquire the guided wave curve of the target orbit, and to acquire the first mode with the lowest attenuation based on the first time-frequency diagram and the guided wave curve; wherein, the guided wave curve reflects the numerical relationship between frequency and group velocity. The modality acquisition module is used to perform defect detection on the target orbit based on the first mode; wherein, the first mode corresponds to the second frequency range.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the track defect detection method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the track defect detection method according to any one of claims 1-7.

Images