Track vibration isolation elastic element state detection system and method

Abstract

The invention provides a track vibration isolation elastic element state detection system and method, and the system comprises a plurality of vibration detection devices comprising vibration acceleration sensors, an excitation device comprising a force sensor, and a calculation analysis device, and the plurality of vibration detection devices are respectively arranged at all preset detection points in a floating slab track. Each measuring point is located on one side of one vibration isolator and is divided into a key measuring point and an adjacent measuring point, and the excitation point is arranged on the lower foundation on one side of the key measuring point, so that excitation can be applied to the excitation point through the excitation device and force signal data can be obtained, and vibration response to excitation can be obtained through the plurality of vibration detection devices; the vibration response is analyzed by combining the distribution and correlation of the measuring points, the relative position relation between the measuring points and the excitation points and the vibration response principle, and the state of the elastic element of the vibration isolator in the floating slab track bed can be determined, so that the problem of steel spring breakage is found in time, and the running safety of a floating slab track is guaranteed.

Description

Technical Field

[0001] The present invention belongs to the technical field of rail transit facility status detection, and in particular relates to a system and method for detecting the status of a rail vibration-damping elastic element. Background Art

[0002] Currently, floating slab trackbeds are used in track systems with special vibration reduction requirements. These typically consist of multiple trackbed slabs and multiple vibration-isolating elastic elements. Each trackbed slab is attached to a lower foundation via multiple elastic elements. When a train passes, the elastic deformation of these elastic elements absorbs vibration energy, reducing the amount of vibration energy transmitted to the lower foundation and achieving effective vibration isolation. Currently used vibration-isolating elastic elements include rubber springs, steel springs, and combined springs. These elastic elements serve as vibration dampeners and key load-bearing components. Damage to these elements, such as a broken steel spring, can seriously impact train safety. Therefore, inspecting these elastic elements is crucial. Traditionally, manual inspections of individual elastic elements are performed, using visual inspection or mechanical tools. This is not only inefficient and results in lengthy maintenance downtime, but also makes it difficult to detect damage, such as a broken steel spring, in a timely manner, posing a safety hazard. Premature replacement of these elastic elements in batches to address these safety risks results in considerable waste and high maintenance costs.

[0003] Therefore, in order to improve the safety of floating slab track, increase detection efficiency, and reduce line stoppage maintenance time, there is an urgent need for a method that can quickly, accurately, and non-destructively detect the state of elastic elements. Summary of the Invention

[0004] The present invention is made to solve the above problems and aims to provide a fast, accurate and non-destructive elastic element status detection method and corresponding system for floating plate track. The present invention adopts the following technical solutions: The present invention provides a track vibration isolation elastic element state detection system, which is arranged in a floating plate track having a lower foundation, a track bed plate, and a plurality of vibration isolators, and is used to detect the state of the elastic elements in the vibration isolators. The system has the following technical features: the system comprises: a plurality of vibration detection devices, respectively arranged at predetermined measuring points in the floating plate track, each including a vibration acceleration sensor for acquiring vibration signal data; an excitation device including a force sensor for exciting predetermined excitation points in the floating plate track and acquiring corresponding force signal data; and a calculation and analysis device for analyzing the vibration response to the excitation based on the force signal data and the vibration signal data of each of the measuring points, and determining the state of the elastic element based on the analysis result, wherein the measuring points include at least one key measuring point and one adjacent measuring point, the key measuring point being located on the upper surface of the track bed plate on one side of the vibration isolators, the adjacent measuring point being located on the upper surface of the track bed plate on the side of another vibration isolator adjacent to the vibration isolator, and the excitation point being located on the lower foundation on the side of the vibration isolator corresponding to the key measuring point.

[0005] The rail vibration isolation elastic element state detection system provided by the present invention may also have the following technical features: the system further includes: a signal acquisition device, respectively connected to the vibration acceleration sensor, the force sensor, and the calculation and analysis device, for collecting the vibration signal data and the force signal data and transmitting them to the calculation and analysis device. The vibration detection device further includes: a metal counterweight block, arranged at the measuring point; and an insulating magnetic base, fixed to the counterweight block by adsorption, and the vibration acceleration sensor is fixed to the counterweight block via the insulating magnetic base. The excitation device is a force hammer with the force sensor built in.

[0006] The track vibration isolation elastic element state detection system provided by the present invention may also have such a technical feature, wherein the adjacent measuring points are one or two. The measuring point is located on the side of the corresponding vibration isolator close to the middle of the track bed plate. The horizontal connection direction of the measuring point and the center of the corresponding vibration isolator, and the horizontal connection direction of the key measuring point and the excitation point are both in the width direction of the floating plate track. The horizontal distance between the measuring point and the center of the corresponding vibration isolator is 15cm~25cm. The lower foundation is the tunnel wall, and the vertical distance between the excitation point and the key measuring point is 1m~1.8m.

[0007] The track vibration isolation elastic element state detection system provided by the present invention may also have such technical features, wherein the calculation and analysis device includes: a vibration signal acquisition unit, used to obtain the corresponding vibration signal data from each of the vibration acceleration sensors; a force signal acquisition unit, used to obtain the force signal data from the force sensor; a data preprocessing unit, used to preprocess the vibration signal data and the force signal data; a state parameter calculation unit, used to calculate multiple state parameters based on the preprocessed vibration signal data and the force signal data; and an elastic element state determination unit, used to determine the state of the elastic element according to the state parameters and predetermined determination rules.

[0008] The track vibration isolation elastic element status detection system provided by the present invention may also have the following technical features: the status parameters include at least the response time of each measuring point to the excitation, the relative energy ratio between the energy corresponding to the force signal data and the vibration signal data, the attenuation rate of the vibration signal, and the natural frequency of the track bed plate including the vibration isolator. The judgment rule includes: when the primary judgment criterion is met and at least one auxiliary judgment criterion is met, or when the primary judgment criterion is not met but more than a predetermined number of auxiliary judgment criterions are met, the elastic element corresponding to the key measuring point is judged to be in an abnormal state. The primary judgment criterion is: the response time of the key measuring point and the response time of the adjacent measuring points do not meet a predetermined response sequence. The multiple auxiliary judgment criteria include: the relative energy ratio of the key measuring point and the relative energy ratio of the adjacent measuring points do not meet a predetermined energy ratio relationship; the attenuation rate deviates from a predetermined attenuation rate reference value by more than a predetermined threshold; and the natural frequency deviates from a predetermined natural frequency reference value by more than a predetermined threshold.

[0009] The rail vibration isolation elastic element state detection system provided by the present invention may also have the following technical features: wherein the response order is such that the response time of all adjacent measuring points is greater than the response time of the key measuring point. The energy ratio relationship is such that the relative energy ratio of all adjacent measuring points is less than the relative energy ratio of the key measuring point.

[0010] The track vibration isolation elastic element state detection system provided by the present invention may also have such technical features, wherein the calculation and analysis device includes: a vibration signal acquisition unit, used to obtain the corresponding vibration signal data from each of the vibration acceleration sensors; a force signal acquisition unit, used to obtain the force signal data from the force sensor; a data preprocessing unit, used to preprocess the vibration signal data and the force signal data; a feature extraction unit, used to extract features from the preprocessed vibration signal data and the force signal data, and obtain a variety of feature parameters that can reflect the structural dynamic characteristics of the floating plate track bed; a feature fusion unit, used to perform feature fusion on the multiple feature parameters, and combine the distribution and correlation information of multiple measuring points to obtain a fused feature vector; and an elastic element state determination unit, used to process the fused feature vector through a trained machine learning model and determine the state of the elastic element.

[0011] The rail vibration isolation elastic element state detection system provided by the present invention may also have such technical features, wherein the feature extraction unit extracts characteristic parameters of the time domain, frequency domain, and time-frequency domain, the characteristic parameters of the time domain include peak acceleration, root mean square value, crest factor, decay time, cross-correlation function peak and delay, the characteristic parameters of the frequency domain include main frequency, peak amplitude, frequency band energy, frequency component complexity, transfer function amplitude / phase, coherence function, the characteristic parameters of the time-frequency domain include fast Fourier transform energy characteristics, the feature fusion unit integrates the characteristic parameters of the time domain, frequency domain, and time-frequency domain, and combines the distribution and correlation information of the measuring points to obtain a fused feature vector, and the machine learning model is a hybrid model of a convolutional neural network and a bidirectional long short-term memory network, which is used to output a classification result for the elastic element state based on the input fused feature vector.

[0012] The track vibration isolation elastic element state detection system provided by the present invention may also have such a technical feature, wherein the multiple vibration isolators corresponding to a track bed plate are all set to a normal state, and several of the multiple vibration isolators corresponding to a track bed plate are set to an abnormal state, and the key measuring points and the excitation points are set on one side of each of the vibration isolators in turn, and the vibration signal data and the force signal data are respectively collected and corresponding label information is set to serve as training data for training the machine learning model.

[0013] The present invention provides a method for detecting the state of a track vibration isolation elastic element, which has the following technical features: step S1, setting the above-mentioned track vibration isolation elastic element state detection system in a floating plate track having a lower foundation, a track bed plate and multiple vibration isolators, wherein the vibration isolators include elastic elements; step S2, using the excitation device to excite at the excitation point and obtain force signal data during excitation; step S3, respectively collecting vibration signal data at each of the measuring points through multiple vibration detection devices; step S4, analyzing the vibration response to the excitation based on the force signal data and the vibration signal data of each of the measuring points, and determining the state of the elastic element according to the analysis result.

[0014] Functions and effects of the invention The present invention provides a system and method for detecting the status of track vibration isolation elastic elements. The system includes multiple vibration detection devices including vibration acceleration sensors, an excitation device including a force sensor, and a calculation and analysis device. The multiple vibration detection devices are respectively arranged at predetermined measuring points in the floating slab track. Each measuring point is located on one side of a vibration isolator on the floating slab trackbed. The measuring points are divided into key measuring points and adjacent measuring points. The excitation point is arranged on the lower foundation on the side of the key measuring point. Therefore, the excitation device can apply excitation (instantaneous force) to the excitation point and obtain corresponding force signal data. The multiple vibration detection devices can also obtain the vibration response to the excitation. By analyzing the vibration response based on the distribution and correlation of the multiple measuring points, the relative position relationship between the measuring points and the excitation point, and the principle of vibration response, the system can accurately determine the status of the elastic elements of the vibration isolators in the floating slab trackbed, thereby promptly detecting failures such as steel spring breakage and ensuring the operational safety of the floating slab track. Furthermore, the system and method only require the deployment of vibration detection devices on the surface of the trackbed and the excitation on the lower foundation. No operations such as lifting the trackbed or removing the vibration isolators are required, making detection very convenient and efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a structural block diagram of a track vibration isolation elastic element state detection system in a first embodiment of the present invention; Figure 2 1 is a schematic structural diagram of a vibration detection device in a first embodiment of the present invention; Figure 3 This is a schematic diagram of the distribution of predetermined points in the track in Example 1 of the present invention. Figure 1 ; Figure 4 This is a schematic diagram of the distribution of predetermined points in the track in Example 1 of the present invention. Figure 2 ; Figure 5 This is a schematic diagram of the distribution of predetermined points in the track in Example 1 of the present invention. Figure 3 ; Figure 6 is a structural block diagram of the computing and analyzing device in the first embodiment of the present invention; Figure 7 This is a flow chart of a method for detecting the state of a track vibration isolation elastic element in a first embodiment of the present invention; Figure 8 is a structural block diagram of a computing and analyzing device in a second embodiment of the present invention; Figure 9 This is a flow chart of a method for detecting the state of a track vibration isolation elastic element in the second embodiment of the present invention.

[0016] Reference numerals: Track vibration isolation elastic element state detection system 100; vibration detection device 110; vibration acceleration sensor 111; counterweight 112; insulating magnetic base 113; signal acquisition device 120; excitation device 130; force sensor 131; calculation and analysis device 140; data storage unit 1401; vibration signal acquisition unit 1402; force signal acquisition unit 1403; metadata acquisition unit 1404; data preprocessing unit 1405; state parameter calculation unit 1406; elastic element state determination unit 1407; analysis side control unit 1408; feature extraction unit 1409; feature fusion unit 1410; floating slab track 200; lower foundation 210; trackbed slab 220; vibration isolator 230; rail 240; excitation point A1; adjacent measuring points C1 and C3; key measuring point C2; vibration isolator centers O1 to O8. DETAILED DESCRIPTION

[0017] In order to make the technical means, creative features, objectives and effects achieved by the present invention easier to understand, the following detailed description of the method and system for detecting the state of the track vibration isolation elastic element of the present invention is given in conjunction with the embodiments and drawings.

[0018] <Example 1> This embodiment provides a method and system for detecting the status of a track vibration isolation elastic element. The following will first describe the structure of the system, and then describe the specific detection method in conjunction with the system structure.

[0019] Figure 1 It is a structural block diagram of the track vibration isolation elastic element status detection system in this embodiment.

[0020] like Figure 1 As shown, the rail vibration isolation elastic element state detection system 100 includes multiple vibration detection devices 110 , one or more signal acquisition devices 120 , one or more excitation devices 130 and a calculation and analysis device 140 .

[0021] The vibration detection device 110 at least includes a vibration acceleration sensor, which is used to be arranged in the actual floating plate track bed to detect and obtain a vibration acceleration signal related to the vibration isolation elastic element of the floating plate.

[0022] Figure 2 Schematic diagram of the structure of the vibration detection device in this embodiment.

[0023] like Figure 2 As shown, in this embodiment, the vibration detection device 110 includes a vibration acceleration sensor 111 , a counterweight 112 and an insulating magnetic base 113 .

[0024] The vibration acceleration sensor 111 is a three-axis vibration acceleration sensor, which can measure vibration acceleration data and has a measurement range of ±10g.

[0025] The counterweight 112 is installed in the floating slab track and is used to house the vibration acceleration sensor 111, ensuring that the vibration acceleration sensor 111 remains stable during testing. In this embodiment, the counterweight 112 is a rectangular metal counterweight that can be magnetically attracted and has dimensions of 100 mm * 50 mm * 10 mm (length * width * height).

[0026] The insulating magnetic base 113 is cylindrical in shape as a whole and has a mounting hole in the middle thereof for fixing the vibration acceleration sensor 111 on the counterweight 112 by magnetic attraction.

[0027] During use, securely attach the insulating magnetic base 113 to the designated mounting point on the counterweight 112 to ensure reliable mechanical coupling. Also, pay attention to the installation orientation, ensuring that the sensitive axis (usually the Z-axis) of the vibration accelerometer 111 is pointing vertically upward or downward to effectively measure vertical vibration.

[0028] The signal acquisition device 120 is connected to the plurality of vibration detection devices 110 via cables to collect vibration acceleration signal data detected by the sensors of the vibration detection devices 110. In this embodiment, the model of the signal acquisition device 120 is INV3062V, and its measurement range is ±10V.

[0029] The excitation device 130 is used to apply a certain excitation to the lower foundation, thereby causing the lower foundation to generate a certain vibration. The vibration will be transmitted to a plurality of vibration isolation elastic elements in contact with the lower foundation, so as to perform status detection on the vibration isolation elastic elements. In this embodiment, the excitation device 130 is a force hammer, which is used to perform percussion excitation on the lower foundation. Preferably, at least the hammer head of the force hammer is made of rubber. Preferably, the force hammer has a built-in force sensor 131, which can record the percussion force pulse, thereby facilitating the control of the energy input consistency of multiple percussion of the force hammer. The signal acquisition device 120 is also connected to the force sensor 131 through a cable, and is used to collect the force signal data measured by the force sensor 131.

[0030] In an alternative embodiment, the excitation device 130 may also be an automated device. For example, the excitation device 130 includes a power hammer with a built-in force sensor, a rotating mechanism, and a fixing mechanism. The fixing mechanism is used to temporarily fix the excitation device 130 at a specific position on the lower foundation. The rotating mechanism is arranged on the fixing mechanism to drive the power hammer to strike the excitation point on the lower foundation with a predetermined force.

[0031] The calculation and analysis device 140 is connected to the signal acquisition device 120 via a cable or wirelessly, and is used to obtain the signals collected by the signal acquisition device 120 and perform calculation and analysis based on these signals to obtain status information of the elastic element, etc.

[0032] The following will first describe the specific layout of the sensors and the corresponding collected signals, and then specifically describe the functions implemented by the calculation and analysis device 140 in conjunction with the signals.

[0033] Figure 3 This is a schematic diagram of the distribution of predetermined points in the track in this embodiment. Figure 1 (Sketch of track viewed from above), Figure 4 This is a schematic diagram of the distribution of predetermined points in the track in this embodiment. Figure 2 (Sketch of the trackbed plate viewed from above), Figure 5 This is a schematic diagram of the distribution of predetermined points in the track in this embodiment. Figure 3 (Schematic diagram of track cutaway).

[0034] like Figures 3 to 5As shown, the floating slab track 200 includes a lower foundation 210, multiple sequentially arranged track slabs 220, a plurality of vibration isolators 230, and rails 240. The lower foundation 210 can be a flat ground surface or a tunnel wall, for example. The track slab 220 is a monolithic concrete track slab with multiple vibration isolator mounting holes extending through its thickness. For example, there are six, eight, or other equally spaced holes arranged in two rows along the length of the track slab 220. Each vibration isolator mounting hole is equipped with a vibration isolator 230. The track slab 220 is floated on the lower foundation 210 by the multiple vibration isolators 230. Two rails 240 are placed parallel to each other on the track slab 220 and are located above or to the sides of the two rows of vibration isolators 230. For ease of description, the centers of the eight vibration isolators 230 on a track slab 220 in this embodiment, when viewed from above, are designated as O1 to O8.

[0035] Each vibration isolator 230, for example, comprises an outer sleeve embedded in the track bed slab 220 and an elastic unit disposed below the outer sleeve. The inner wall of the outer sleeve has a circle of load-bearing protrusions that match the elastic unit. The upper end of the elastic unit abuts against the circle of load-bearing protrusions, while the lower end rests on the lower foundation. The elastic unit includes an elastic element, which can be, for example, a coiled steel spring or a rubber spring. The structure of the vibration isolator 230 is conventional and will not be described in detail.

[0036] The excitation device 140 applies excitation at predetermined excitation points on the lower foundation. This excitation point is located next to one of the isolators 230, with the horizontal line connecting the excitation point and the center of the isolator 230 (the central axis of its outer sleeve) oriented along the track width. In this embodiment, excitation point A1 is located on the tunnel wall next to and above an isolator 230 in the middle of the trackbed slab 220. The vertical distance h1 between excitation point A1 and the top surface of the trackbed slab 220 can be 1m to 1.8m, preferably 1.5m. During testing, the excitation device 140 (hammer) applies a momentary vertical tap (perpendicular to the tunnel wall at excitation point A1) to excite the track. The tapping should be crisp and rapid to ensure consistent energy input.

[0037] Multiple vibration detection devices 110 are installed at multiple predetermined test points (hereinafter referred to as test points) on the track. Each of the multiple test points is located on the upper surface of the trackbed plate 220 and inside the rail. Each test point is located adjacent to a vibration isolator 230, and the horizontal line connecting the center of the test point and the corresponding vibration isolator 230 is oriented along the width of the track. The multiple test points include at least one key test point and one or two adjacent test points. The key test point is the test point closest to the excitation point among the multiple test points. The vibration isolators 230 corresponding to the adjacent test point and the key test point are adjacent to each other.

[0038] In this embodiment, each trackbed slab 220 is equipped with eight vibration isolators 230, with three measuring points: a key measuring point C2 and two adjacent measuring points C1 and C3, each located adjacent to the three sequentially arranged vibration isolators 230. The two adjacent measuring points C1 and C3 are symmetrically positioned on either side of key measuring point C2. The three measuring points C1-C3 are collinear and located on one side of the corresponding vibration isolator near the center of the trackbed slab. The horizontal distance d1 between each measuring point and the center of the corresponding vibration isolator 230 (i.e., between key measuring point C2 and isolator center O6, between adjacent measuring point C1 and isolator center O4, and between adjacent measuring point C3 and isolator center O8) is 15 cm to 25 cm, preferably 20 cm. Alternatively, only key measuring point C2 and adjacent measuring point C1, or only key measuring point C2 and adjacent measuring point C3, may be provided. For example, when key measuring point C2 is positioned on either side of a vibration isolator 230 at one end of the trackbed slab 220, only one adjacent measuring point is required.

[0039] Through such a measurement point setting, the excitation generated at the excitation measurement point A1 can be transmitted to the three measurement points C1 to C3 relatively evenly and simultaneously, and it is convenient to conduct a comparative analysis of the synchronous response of the key measurement point C2 and the adjacent measurement points C1 or C3, thereby reflecting the status of the supporting structure (i.e., multiple vibration isolators 230 in a track bed plate 220).

[0040] Figure 6 It is a structural block diagram of the computing and analyzing device in this embodiment.

[0041] like Figure 6 As shown, the computing and analyzing device 140 includes a data storage unit 1401, a vibration signal acquisition unit 1402, a force signal acquisition unit 1403, a metadata acquisition unit 1404, a data preprocessing unit 1405, a state parameter calculation unit 1406, an elastic element state determination unit 1407, an analysis side control unit 1408, an input display unit 1411, and an analysis side communication unit 1412.

[0042] The data storage unit 1401 stores various predetermined detection parameters and calculation and analysis parameters, and is also used to store acquired vibration acceleration signals, calculation and analysis results, and determined vibration isolation elastic element status information. Detection parameters include the size of the acquisition time window, etc.

[0043] The vibration signal acquisition unit 1402 is used to acquire, through the signal acquisition device 120, vibration acceleration signals at different points measured by the vibration acceleration sensors 111 of the multiple vibration detection devices 110. In this embodiment, the vibration acceleration signal data at the three measurement points is acquired as three-channel signal data. The vibration acceleration signal data is raw waveform data including a timestamp. Furthermore, the size of the predetermined acquisition time window ensures that the acquired three-channel signal includes the complete impulse response attenuation process, ensuring that the three-channel signal covers the main modal response.

[0044] The force signal acquisition unit 1403 is used to acquire force signal data of the force measured by the force sensor 131 when the excitation device 130 is energized by the signal acquisition device 120. Similarly, the size of the predetermined acquisition time window ensures that the acquired force signal data includes the complete impact response decay process.

[0045] The metadata acquisition unit 1404 is used to acquire other metadata required for analysis. In this embodiment, the metadata acquisition unit 1404 is used to provide a corresponding interactive interface for the tester to enter metadata such as the test number, time, tester information, and environmental conditions. The environmental conditions information may include, for example, the temperature, humidity, and ambient noise of the test environment.

[0046] The data preprocessing unit 1405 is used to preprocess the collected three-channel signal data and force signal data to improve the quality of the signal data. The preprocessing may include eliminating trend items, filtering, windowing, etc.

[0047] The state parameter calculation unit 1406 performs calculations based on the pre-processed three-channel signal data and the force signal data to obtain a variety of state parameters.

[0048] In this embodiment, the calculated state parameters include at least the response time of each measuring point to the excitation, the relative energy ratio between the force signal and the vibration signal, the attenuation rate of the vibration signal, and the natural frequency of the floating slab trackbed. These state parameters can all be calculated using methods known in the art. For example, the response time can be calculated based on the time of the peak in the force signal data and the time of the peak in the vibration signal data at each measuring point. By integrating the force signal data and the vibration signal data, the force signal energy and the vibration energy can be obtained, and these can be used as the input energy and output energy, respectively, to calculate the relative energy ratio.

[0049] The elastic element status determination unit 1407 is used to determine the status of the elastic elements in the floating slab trackbed's support structure (the outer sleeve and elastic element area of ​​the isolator) based on multiple status parameters and predetermined determination rules. In this embodiment, the determination rules include: if the primary determination criterion and at least one auxiliary determination criterion are met, or if the primary determination criterion is not met but more than a predetermined number (e.g., two or more) of the auxiliary determination criteria are met, the elastic element in the isolator corresponding to the key measuring point is determined to be in an abnormal state. If the primary determination criterion is met but all auxiliary determination criteria are not met, the elastic element corresponding to the key measuring point is determined to be in a pending state.

[0050] The main judgment basis is: the response time of the key measuring point and the response time of the adjacent measuring points do not meet the predetermined response sequence.

[0051] When the elastic element in the vibration isolator 230 (centered at O6) corresponding to key measuring point C2 is in a normal state (i.e., if it is a steel spring and has not broken), since this elastic element is closest to the excitation point A1, the vibration will be transmitted to this elastic element first. The response time of the vibration acceleration sensor 111 located at key measuring point C2 (i.e., the energy transfer time of the impact excitation) should be the shortest, and the response time of adjacent measuring points should be longer than that of key measuring point C2. However, if the elastic element corresponding to key measuring point C2 is in an abnormal state (e.g., if the steel spring has broken), the vibration will bypass this elastic element and be transmitted to the elastic element of the adjacent vibration isolator 230, causing the response time of adjacent measuring points C1 / C3 to be earlier than that of key measuring point C2.

[0052] Multiple auxiliary judgment criteria include: the natural frequency of the track bed plate including the vibration isolator is offset compared to the predetermined natural frequency reference value, and the offset value exceeds the predetermined threshold value; the relationship between the relative energy ratio of the key measuring point and the relative energy ratio of the adjacent measuring points does not meet the predetermined energy ratio relationship; the attenuation rate of the vibration signal is offset compared to the predetermined attenuation rate reference value, and the offset value exceeds the predetermined threshold value.

[0053] Among them, for the natural frequency shift, based on the collected vibration acceleration signal data, the natural frequency of the floating slab track bed can be analyzed through the excitation response method. The predetermined natural frequency reference value can be calculated according to the following formula:

[0054] Where, k is the total stiffness of multiple elastic elements, m is the total mass of the track bed plate including the vibration isolator. In this embodiment, the reference value of the natural frequency is 11 Hz ± 5%.

[0055] When the elastic unit is in an abnormal state (such as a broken steel spring), the natural frequency of the entire / local floating slab track bed will change due to the stiffness. k Therefore, if the natural frequency calculated and analyzed from the measured data is significantly different from the predetermined natural frequency reference value, it can be used as an auxiliary basis for determining that one or more of the multiple elastic units are in an abnormal state.

[0056] For energy relative ratio, since the key measuring point C2 is closest to the excitation point A1, the vibration acceleration sensor 111 set at the key measuring point C2 should receive the maximum energy. The energy relative ratio (the ratio of output energy to input energy) E r =E out / Ein The energy relative ratios of the adjacent measuring points C1 / C3 should be the largest, and the energy relative ratios of the adjacent measuring points C1 / C3 are all smaller than the energy relative ratio of the key measuring point C2. If the energy relative ratio of the adjacent measuring points C1 / C3 is greater than the energy relative ratio of the key measuring point C2, and the difference between the energy relative ratios of the adjacent measuring points and the energy relative ratio of the key measuring point exceeds a predetermined threshold, this can be used as an auxiliary basis for determining that the elastic unit corresponding to the key measuring point C2 is in an abnormal state.

[0057] The attenuation rate reference value can be obtained by, for example, performing multiple tests on the vibration signal attenuation rate of elastic elements in normal state in the same type of floating plate track and taking the average value. The predetermined threshold value can be set to, for example, ±5% to ±20% of the reference value.

[0058] In addition, optionally, time domain waveform difference features, such as waveform duration, number of peaks, etc., can be extracted through a large number of experimental samples for classification and identification, thereby assisting in determining the state of the elastic element.

[0059] In addition, optionally, different weight values ​​can be set for multiple auxiliary judgment criteria, and a score can be calculated based on the number of auxiliary judgment criteria that meet the requirements and their weight values. When the main judgment criteria do not meet the requirements, the elastic element status is determined to be normal based on the score and the predetermined score threshold.

[0060] Input and display unit 1411 allows testers to set parameters, initiate data calculation and analysis, and display raw signal data, intermediate data (preprocessed signal data, calculated state parameters, etc.), and determined state information. Metadata acquisition unit 1404 and input and display unit 1411 may function as the same unit.

[0061] The analysis side communication unit 1412 is used to communicate with other devices, such as other computing and analysis devices, to transmit the original signal data, determined status information, etc. to other computing and analysis devices for further analysis, or to communicate with terminals held by testers and managers, to send status information to the terminals, and so on.

[0062] The analysis side control unit 1408 is used to control the operation of the above-mentioned functional units, including controlling the data storage unit 1401 to store these original signal data after the vibration signal acquisition unit 1402 and the force signal acquisition unit 1403 acquire the corresponding vibration acceleration signal data and force signal data; controlling the data preprocessing unit 1405, the state parameter calculation unit 1406, and the elastic element state determination unit 1407 in turn to perform data preprocessing, calculation of multiple state parameters, and state determination of the elastic element, and in this process controlling the data storage unit 1401 to store the preprocessed data, the calculated state parameters, and the determined state information; and controlling the input display unit 1411 to display the intermediate data, state information, etc.

[0063] Figure 7 4 is a flow chart of the method for detecting the state of the track vibration isolation elastic element in this embodiment.

[0064] like Figure 7 As shown, based on the above-mentioned track vibration isolation elastic element state detection system 100, in this embodiment, the corresponding detection method includes the following steps: Step S1: Setting a track vibration isolation elastic element status detection system in the floating plate track.

[0065] Step S2: using an excitation device to excite at an excitation point in the floating plate track, and obtaining force signal data during the excitation.

[0066] Step S3: collecting vibration signal data at each test point using multiple vibration detection devices.

[0067] Step S4: analyzing the force signal data and the vibration signal data of each measuring point, and determining the state of the vibration isolation elastic element according to the analysis result.

[0068] The above steps will be described in detail below.

[0069] Step S1: Setting a track vibration isolation elastic element status detection system in the floating plate track.

[0070] As described above, a vibration isolator 230 is selected in the middle of the trackbed plate 220. A vibration detection device 110 is installed at a key measuring point C2 on one side of the vibration isolator 230. Vibration detection devices 110 are also installed at adjacent measuring points C2 and / or C3. Each vibration acceleration sensor 111 is connected to a signal acquisition device 120 via a cable, and the signal acquisition device 120 is connected to a computing and analysis device 140. During installation, a counterweight 112 is placed at the measuring point. The vibration acceleration sensor 111 is mounted on an insulating magnetic base 113 and then fixed to the upper surface of the counterweight 112 by adsorption, with the sensitive axis (Z axis) of the vibration acceleration sensor 111 pointing vertically upward or vertically downward.

[0071] Before the formal test begins, debug the equipment and observe whether it is operating normally. In addition, to ensure data reliability and reproducibility, repeat 3 to 5 effective vertical taps at the excitation point A1 and collect signal data separately. After each tap, check the validity of the signal data, such as whether the signal data is obviously saturated, noisy, or has failed taps. After multiple taps, check whether the signal data collected multiple times is highly consistent. If there are problems with the measured signal data or if the signal data collected multiple times is highly inconsistent, check and adjust the equipment.

[0072] Furthermore, before testing begins and throughout data collection, ensure that there are no significant sources of interfering vibration near the test site, such as large equipment in operation, personnel movement, vehicle traffic, or other impacts. If necessary, background sound and vibration measurements can be taken and recorded. In subsequent signal data processing, the measured background sound and vibration can be used to pre-process the signal data to minimize their influence.

[0073] Step S2: using an excitation device to excite at an excitation point in the floating plate track, and obtaining force signal data during the excitation.

[0074] The excitation device 130 (hammer) is used to perform striking excitation at the excitation point A1 on one side of the key measuring point C2 . The force signal acquisition unit 1403 acquires the force signal data measured by the force sensor 131 through the signal acquisition device 120 .

[0075] Step S3: collecting vibration signal data at each measuring point using multiple vibration detection devices.

[0076] The vibration signal acquisition unit 1402 acquires the vibration acceleration signal data measured by the three vibration acceleration sensors 111 at the three measurement points through the signal acquisition device 120 and uses it as three-channel signal data. Optionally, the tester inputs other required metadata.

[0077] Step S4: analyzing the force signal data and the vibration signal data of each measuring point, and determining the state of the vibration isolation elastic element according to the analysis result.

[0078] like Figure 7 As shown in , step S4 specifically includes the following sub-steps: Step S4 - 1 : Preprocess the force signal data and the vibration signal data of each measuring point, which is the preprocessing performed by the data preprocessing unit 1405 .

[0079] In step S4-2, various state parameters are calculated based on the pre-processed force signal data and the vibration signal data of each measuring point, which is the calculation performed by the state parameter calculation unit 1406.

[0080] In step S4-3, the state of the vibration isolation elastic element is determined based on the state parameters and predetermined determination rules and the corresponding state information is output. That is, the determination performed by the elastic element state determination unit 1407 mainly determines the state of the elastic element corresponding to the key measuring point C2.

[0081] Functions and effects of embodiment 1 According to the method and system for detecting the status of track vibration isolation elastic elements provided in this embodiment, the system includes multiple vibration detection devices including vibration acceleration sensors, an excitation device including a force sensor, and a calculation and analysis device. The multiple vibration detection devices are respectively arranged at predetermined measuring points in the floating slab track. Each measuring point is located on one side of a vibration isolator on the floating slab trackbed. The measuring points are divided into key measuring points and adjacent measuring points. The excitation point is arranged on the lower foundation on the side of the key measuring point. Therefore, the excitation device can apply excitation (instantaneous force) to the excitation point and obtain corresponding force signal data. The vibration response to the excitation is then obtained by the multiple vibration detection devices. By analyzing the vibration response based on the distribution and correlation of the multiple measuring points, the relative positional relationship between the measuring points and the excitation point, and the principles of vibration response, the state of the elastic elements of the vibration isolators in the floating slab trackbed can be determined with certainty, thereby promptly detecting failures such as steel spring breakage and ensuring the operational safety of the floating slab track. Furthermore, the system and method only require the deployment of vibration detection devices on the surface of the trackbed and the excitation on the lower foundation. No operations such as lifting the trackbed or removing or installing the vibration isolators are required, making detection very convenient and efficient.

[0082] Furthermore, the vibration detection device also includes a metal counterweight block, which is used to be placed at a specified measuring point on the track bed. The vibration acceleration sensor is fixed to the counterweight block by adsorption through an insulating magnetic base. This not only makes the installation and fixation of the sensor very convenient, but also can create / enhance unbalanced vibration through the counterweight method, which is conducive to the analysis of vibration response.

[0083] Furthermore, since each measuring point is set on the upper surface of the track bed plate on one side of a vibration isolator, and the direction of the line connecting the measuring point and the corresponding vibration isolator center is the track width direction, the horizontal distance between the two is small, so the corresponding relationship between the measuring point and the vibration isolator is intuitive and clear, and the vibration response of the measuring point can well reflect the state of the elastic element in the corresponding vibration isolator, thereby further improving the accuracy of the detection.

[0084] Furthermore, the calculation and analysis device includes a vibration signal acquisition part, a force signal acquisition part, a data preprocessing part, a state parameter calculation part, and an elastic element state judgment part. It can respectively obtain vibration signal data from each vibration acceleration sensor and force signal data from the force sensor, and preprocess the signal data to improve the data quality, and then calculate a variety of predetermined state parameters based on the preprocessed signal data, and automatically judge the state of the elastic element based on the state parameters and predetermined judgment rules. Therefore, the degree of automation is high, and since the calculation of the state parameters and the rule-based judgment are algorithms with low computational complexity, the detection results can be obtained quickly, so that the detection results can be obtained on-site on the floating plate track. The detection and corresponding maintenance, replacement of elastic elements and other operations can be completed during a line stop maintenance, which is more efficient.

[0085] Furthermore, the calculated state parameters include the response time, relative energy ratio, attenuation rate, and natural frequency of the trackbed slab at each measuring point. Based on these parameters, a primary judgment criterion and multiple auxiliary judgment criteria are set. The primary judgment criterion is set based on the response time and the response order of measuring points at different locations. When the primary judgment criterion is met and at least one auxiliary judgment criterion is met, or when the primary judgment criterion is not met but many auxiliary judgment criteria are met, the elastic element is determined to be in an abnormal state. This integrates the various dynamic structural characteristics of the floating slab track, avoiding misjudgments caused by a single method and further improving detection accuracy. Furthermore, when the primary judgment criterion is met but all auxiliary judgment criteria are not met, the elastic element is determined to be in a pending state, further preventing elastic elements in abnormal states from being missed and further ensuring safety.

[0086] Furthermore, various data such as test metadata, original signal data, intermediate data (pre-processed data, calculated state parameters, etc.), and determined state information are all stored. Therefore, after multiple tests, big data related to elastic element state detection can be formed, which can be used for further analysis to discover other diseases or hidden dangers of the floating plate track, or used as training data for machine learning models, etc., to improve the intelligence level of the industry.

[0087] <Example 2> This embodiment provides a method and system for detecting the state of a track vibration isolation elastic element. In this embodiment, the same symbols are assigned to the same components as those in the first embodiment, and the corresponding descriptions are omitted.

[0088] Figure 8 It is a structural block diagram of the computing and analyzing device in this embodiment.

[0089] like Figure 8 As shown, compared with the first embodiment, the difference is that in the system of this embodiment, the structure of the calculation and analysis device is different.

[0090] The computing and analyzing device 140 of this embodiment includes a data storage unit 1401, a vibration signal acquisition unit 1402, a force signal acquisition unit 1403, a metadata acquisition unit 1404, a data preprocessing unit 1405, a feature extraction unit 1409, a feature fusion unit 1410, an elastic element state determination unit 1407, an analysis-side control unit 1408, an input and display unit 1411, and an analysis-side communication unit 1412. The functions of the data storage unit 1401, the vibration signal acquisition unit 1402, the force signal acquisition unit 1403, the metadata acquisition unit 1404, the data preprocessing unit 1405, the input and display unit 1411, and the analysis-side communication unit 1412 are substantially the same as those in the first embodiment.

[0091] The feature extraction unit 1409 is used to extract various characteristic parameters reflecting the structural dynamic characteristics of the floating slab trackbed from the preprocessed signal data. In this embodiment, the effective impact response signal (i.e., the preprocessed signal data) is extracted from multiple perspectives, including the time domain, frequency domain, and time-frequency domain. The extractable characteristic parameters include, but are not limited to: 1) Time domain: peak acceleration, RMS value, crest factor, decay time, cross-correlation function peak value, and delay (delay between measurement points); 2) Frequency domain: dominant frequency, peak amplitude, frequency band energy (e.g., low frequency, mid-frequency, high frequency), frequency component complexity, transfer function amplitude / phase (frequency response function), and coherence function (excitation and response); 3) Time-frequency domain: Fast Fourier Transform (FFT) energy characteristics, such as marginal spectrum energy. These various characteristic parameters can be automatically calculated, for example, using the functions provided by existing vibration and noise testing software.

[0092] Feature fusion unit 1410 is used to fuse the multiple extracted feature parameters to obtain an integrated feature vector. In this embodiment, feature parameters extracted from the time domain, frequency domain, and time-frequency domain are combined with the eigenvalue distribution and correlation of multiple measurement points to construct a multidimensional feature vector. Specifically, the multiple extracted feature parameters, the eigenvalue distribution of the measurement points, the correlation coefficient, and other data are all placed in a single array to form the integrated feature vector.

[0093] The elastic element state determination unit 1407 is configured to analyze the fusion feature vector and determine the state of the elastic element according to the analysis result. For example, the fusion feature vector can be analyzed by using a statistical method (such as comparing with a historical baseline or setting a threshold), a pattern recognition method (such as a support vector machine (SVM) or a decision tree), or a machine learning model (such as a machine learning model trained by historical data), to obtain an analysis result, and further determine the state of the elastic element.

[0094] In this embodiment, the elastic element state determination unit 1407 adopts a hybrid model of a convolutional neural network and a bidirectional long short-term memory network (CNN+BiLSTM), inputs the fusion feature into the model, and outputs a classification result. The input data format is (N, T, C), where N is the number of samples, T is the length of each time series (for example, 10 seconds x 5000 Hz = 50000 points), and C is the number of channels (i.e., the number of vibration acceleration sensors, in this embodiment, three measuring points are provided, so C = 3). After inputting a sample data (T, C) into the model, the model first extracts local time sequence features through a one-dimensional convolution layer (1D Convolution); then the extracted features are processed by a maximum pooling layer (Max Pooling); then long-range dependencies are extracted by a bidirectional long short-term memory network (Bidirectional LSTM); then the features are processed by a dropout layer (Dropout) to prevent overfitting, and then processed by a dense fully connected layer (Dense Fully Connected Layer); and finally, a classification result is output by a Softmax layer. In this embodiment, the classification result includes a normal state, an abnormal state of the elastic element corresponding to measuring point C1, an abnormal state of the elastic element corresponding to measuring point C2, and an abnormal state of the elastic element corresponding to measuring point C3.

[0095] For training the above hybrid model, the elastic elements of the vibration isolators 230 in a track bed plate 220 can be set to a normal state, or some of them can be set to an abnormal state (for example, a steel spring is broken), and the force signal data and the three-channel vibration signal data in the corresponding state are obtained by using the method of steps S1 to S3, the collected data and the corresponding labeled information are combined to form training samples, and a training data set is obtained. Preferably, for the plurality of elastic elements of the track bed plate 220, not less than 50 samples are collected in the normal state and the abnormal state, respectively, that is, key measuring points and excitation points are arranged beside each vibration isolator 230, and the data is collected multiple times, and the knocking force of the excitation device 130 is kept consistent during the sample collection process, so as to control the variables.

[0096] The hybrid model is then trained using the aforementioned training dataset, for example, using PyTorch or TensorFlow, for 100 or more rounds. During training, the hybrid model's classification accuracy and confusion matrix are monitored and the training process adjusted accordingly. After training is complete, the hybrid model automatically outputs a classification result (state determination result) for the elastic element state based on the input fused feature vector. Because the training data includes test data with key measurement points located near each isolator 230, the classification results may include: all elastic elements in a trackbed slab are in a normal state; elastic element 1 is in an abnormal state; elastic element 2 is in an abnormal state, and so on.

[0097] The analysis side control unit 1408 is used to control the operation of the above-mentioned functional units, including controlling the data storage unit 1401 to store these original signal data after the vibration signal acquisition unit 1402 and the force signal acquisition unit 1403 acquire the corresponding vibration acceleration signal data and force signal data; and controlling the data preprocessing unit 1405, the feature extraction unit 1409, the feature fusion unit 1410, and the elastic element state determination unit 1407 in turn to perform data preprocessing, feature extraction, feature fusion, elastic element state determination, etc.

[0098] Figure 9 4 is a flow chart of the method for detecting the state of the track vibration isolation elastic element in this embodiment.

[0099] like Figure 9 As shown, based on the above-mentioned track vibration isolation elastic element state detection system 100, compared with the first embodiment, the method of this embodiment is different only in step S4, which includes the following sub-steps: Step S4-1, pre-processing the force signal data and the vibration signal data of each measuring point respectively. This step is the same as step S4-1 in the first embodiment.

[0100] Step S4-2 performs feature extraction on the preprocessed force signal data and the vibration signal data at each measurement point to extract various feature parameters in the time domain, frequency domain, and time-frequency domain. This is the feature extraction operation performed by the feature extraction unit 1409 described above. This step is identical to step S4-2 in Example 1.

[0101] In step S4-4, the extracted multiple feature parameters are fused and the distribution and correlation information of multiple measurement points are combined to obtain a fused feature vector, which is the feature fusion operation performed by the feature fusion unit 1410.

[0102] In step S4-5, the fused feature vector is input into the trained machine learning model, which outputs the state information of the elastic element. This is the analysis and state determination performed by the elastic element state determination unit 1407, preferably using the CNN+BiLSTM hybrid model, and outputting the classification result as the state information.

[0103] In this embodiment, other structures and method steps are the same as those in the first embodiment, and therefore will not be described again.

[0104] Functions and effects of Example 2 According to the track vibration reduction elastic element status detection method and system provided in this embodiment, on the basis of the functions and effects of the first embodiment, since the system has a feature extraction unit and a feature fusion unit, and the elastic element status determination unit adopts a trained machine learning model, it can automatically extract a variety of feature parameters that can reflect the structural dynamic characteristics of the floating plate track bed from the signal data according to a predetermined algorithm, and after fusing them, realize automatic classification based on the test data through the trained machine learning model to obtain the status information of the elastic element. Therefore, the efficiency of the analysis and processing of the signal data and the status determination is higher, thereby achieving more efficient detection and further reducing the line stoppage and maintenance time.

[0105] Furthermore, the machine learning model preferably uses a CNN + BiLSTM hybrid model. This model takes multidimensional arrays as input, making it more convenient to input multi-channel vibration signal data (multi-sensor data). Furthermore, this model has excellent ability to capture sequence dependencies. Because abnormal conditions of elastic elements (such as broken springs) affect the order of vibration transmission, this model is ideal for analysis and judgment in such scenarios. Furthermore, this model achieves strong classification accuracy and robustness without the need for complex manual feature engineering.

[0106] Furthermore, since force signal data and vibration signal data are collected from the actual floating plate track as training data instead of using simulated data, the trained model has high adaptability and classification accuracy for determining the state of elastic elements in the actual track.

[0107] The above embodiments are merely illustrative of specific implementations of the present invention, and the present invention is not limited to the scope of the description of the above embodiments. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and improvements may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and improvements fall within the scope of the present invention as claimed. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

[0108] For example, in the above embodiment, the method and system for detecting the status of the track vibration-damping elastic element are used to detect the status of the steel spring, especially to detect the broken spring condition of the steel spring. In an alternative solution, the method and system can also be used to detect the status of other types of track vibration-damping elastic elements, such as rubber springs and combined springs.

Claims

1. A track vibration isolation elastic element status detection system, provided in a floating plate track having a lower foundation, a track bed plate, and a plurality of vibration isolators, for detecting the status of elastic elements in the vibration isolators, characterized in that: include: A plurality of vibration detection devices are respectively arranged at predetermined measuring points in the floating plate track, and each of the plurality of vibration detection devices includes a vibration acceleration sensor for acquiring vibration signal data; an excitation device, comprising a force sensor, for exciting a predetermined excitation point in the floating plate track and acquiring corresponding force signal data; as well as a calculation and analysis device for analyzing the vibration response to the excitation based on the force signal data and the vibration signal data of each of the measuring points, and determining the state of the elastic element according to the analysis result; The measuring points include at least one key measuring point and one adjacent measuring point, wherein the key measuring point is located on the upper surface of the roadbed plate on one side of one of the vibration isolators, and the adjacent measuring point is located on the upper surface of the roadbed plate on the other side of the vibration isolator adjacent to the vibration isolator. The excitation point is located on the lower foundation on one side of the vibration isolator corresponding to the key measuring point.

2. The rail vibration isolation elastic element state detection system according to claim 1, characterized in that: Also includes: a signal acquisition device, connected to the vibration acceleration sensor, the force sensor, and the calculation and analysis device, respectively, for acquiring the vibration signal data and the force signal data and transmitting them to the calculation and analysis device; Wherein, the vibration detection device further includes: a metal counterweight, disposed at the measuring point; and The insulating magnetic base is fixed on the counterweight by adsorption, and the vibration acceleration sensor is fixed on the counterweight through the insulating magnetic base. The excitation device is a hammer with the force sensor built in.

3. The rail vibration isolation elastic element status detection system according to claim 1, characterized in that: in, There are one or two adjacent measuring points. The measuring point is located on one side of the corresponding vibration isolator close to the middle of the track bed plate. The horizontal connection direction between the measuring point and the center of the corresponding vibration isolator, and the horizontal connection direction between the key measuring point and the excitation point are both in the width direction of the floating plate track. The horizontal distance between the measuring point and the center of the corresponding vibration isolator is 15 cm to 25 cm. The lower foundation is a tunnel wall, and the vertical distance between the excitation point and the key measuring point is 1m~1.8m.

4. The rail vibration isolation elastic element state detection system according to claim 1, Its characteristics are: Wherein, the computing and analyzing device comprises: a vibration signal acquiring unit, configured to acquire the corresponding vibration signal data from each of the vibration acceleration sensors; a force signal acquiring unit, configured to acquire the force signal data from the force sensor; a data preprocessing unit, configured to preprocess the vibration signal data and the force signal data; a state parameter calculation unit, configured to calculate a plurality of state parameters based on the preprocessed vibration signal data and the force signal data; and The elastic element state determination unit is configured to determine the state of the elastic element according to the state parameter and a predetermined determination rule.

5. The rail vibration isolation elastic element state detection system according to claim 4, Its characteristics are: in, The state parameters include at least the response time of each measuring point to the excitation, the relative energy ratio between the force signal data and the vibration signal data, the attenuation rate of the vibration signal, and the natural frequency of the track bed plate including the vibration isolator. The judgment rule includes: when the main judgment criterion is met and at least one auxiliary judgment criterion is met, or when the main judgment criterion is not met but more than a predetermined number of the auxiliary judgment criterions are met, it is judged that the elastic element corresponding to the key measuring point is in an abnormal state; The main judgment basis is that the response time of the key measuring point and the response time of the adjacent measuring point do not meet the predetermined response order. The multiple auxiliary judgment criteria include: the relative energy ratio of the key measuring point and the relative energy ratio of the adjacent measuring points do not meet the predetermined energy ratio relationship; the attenuation rate deviates from the predetermined attenuation rate reference value by more than a predetermined threshold; the natural frequency deviates from the predetermined natural frequency reference value by more than a predetermined threshold.

6. The rail vibration isolation elastic element status detection system according to claim 5, characterized in that: in, The response order is: the response time of all the adjacent measuring points is greater than the response time of the key measuring point, The energy ratio relationship is: the relative energy ratios of all the adjacent measuring points are smaller than the relative energy ratio of the key measuring point.

7. The rail vibration isolation elastic element state detection system according to claim 1, Its characteristics are: Wherein, the computing and analyzing device comprises: a vibration signal acquiring unit, configured to acquire the corresponding vibration signal data from each of the vibration acceleration sensors; a force signal acquiring unit, configured to acquire the force signal data from the force sensor; a data preprocessing unit, configured to preprocess the vibration signal data and the force signal data; a feature extraction unit, configured to perform feature extraction on the pre-processed vibration signal data and the force signal data to obtain a plurality of feature parameters capable of reflecting the structural dynamic characteristics of the floating slab track bed; a feature fusion unit, configured to perform feature fusion on the plurality of feature parameters and obtain a fused feature vector by combining the distribution and correlation information of the plurality of measurement points; and The elastic element state determination unit is used to process the fused feature vector through a trained machine learning model and determine the state of the elastic element.

8. The rail vibration isolation elastic element status detection system according to claim 7, characterized in that: in, The feature extraction unit extracts feature parameters in the time domain, frequency domain, and time-frequency domain. The characteristic parameters of the time domain include peak acceleration, root mean square value, crest factor, decay time, cross-correlation function peak value and time delay, The characteristic parameters of the frequency domain include main frequency, peak amplitude, frequency band energy, frequency component complexity, transfer function amplitude / phase, and coherence function. The characteristic parameters in the time-frequency domain include fast Fourier transform energy characteristics, The feature fusion unit synthesizes the feature parameters of the time domain, frequency domain, and time-frequency domain, and combines the distribution and correlation information of the measurement points to obtain a fused feature vector. The machine learning model is a hybrid model of a convolutional neural network and a bidirectional long short-term memory network, and is used to output a classification result for the state of the elastic element based on the input fusion feature vector.

9. The rail vibration isolation elastic element status detection system according to claim 7, characterized in that: in, The multiple vibration isolators corresponding to one track bed plate are all set to a normal state, and some of the multiple vibration isolators corresponding to one track bed plate are set to an abnormal state, and the key measuring points and the excitation points are sequentially set on one side of each vibration isolator, and the vibration signal data and the force signal data are respectively collected and corresponding label information is set to serve as training data for training the machine learning model.

10. A method for detecting the state of a track vibration isolation elastic element, characterized in that: include: Step S1, installing a track vibration isolation elastic element state detection system according to any one of claims 1 to 9 in a floating slab track having a lower foundation, a track bed plate, and a plurality of vibration isolators, wherein the vibration isolators include elastic elements; Step S2, using the excitation device to excite at the excitation point and obtaining force signal data during the excitation; Step S3, respectively collecting vibration signal data at each of the measuring points using the plurality of vibration detection devices; Step S4 , analyzing the vibration response to the excitation based on the force signal data and the vibration signal data of each of the measuring points, and determining the state of the elastic element according to the analysis result.

Images