Rail transit ballast bed disease early warning method and device based on grating array and medium

Abstract

The invention relates to a rail transit ballast bed disease early warning method and device based on a grating array and a medium, and belongs to the technical field of rail transit, and the method comprises the steps: collecting a driving vibration signal of a rail transit ballast bed through an optical fiber distributed acoustic sensing system, and carrying out the preprocessing of the driving vibration signal to obtain an effective vibration signal; determining a first median corresponding to the variance and a second median corresponding to the power spectrum entropy based on the variance and the power spectrum entropy of the effective vibration signal; and based on the first median and the second median, carrying out disease early warning on the track traffic ballast bed. According to the rail transit ballast bed disease early warning method based on the grating array, the optical fiber distributed acoustic sensing technology is adopted, whole-line and full-time monitoring of the rail is achieved, interference of human factors is eliminated, potential diseases can be detected and early warned in real time, and expansion of the diseases and increase of the repair cost are effectively avoided.

Description

Method, device and medium for early warning of track bed defects in rail transit based on grating array Technical Field

[0001] This invention relates to the field of rail transit technology, and in particular to a method, device and medium for early warning of track bed defects based on grating array. Background Technology

[0002] Subways are underground, long-distance linear engineering projects. A crucial prerequisite for their safe operation is the safety of their engineering structures; therefore, health monitoring and safety assessments are essential. The track is one of the main technical facilities of a subway line and the foundation for train operation. The track guides vehicle movement, directly bears the train's load, and transfers the load to the roadbed, bridges, tunnels, and other structures. Due to the influence of wheel-rail relationships and the stability of the track bed, roadbed, bridges, and tunnel structures, uneven settlement of the foundation structure or sleeper voids and fractures can occur in operating lines, causing abrupt changes in track shape and seriously affecting the safety and comfort of train operation.

[0003] Currently, the railway engineering professionals in China mainly use two methods for inspecting track bed defects: manual inspection and vehicle inspection.

[0004] Traditional manual inspections primarily rely on visual observation. For the track bed surface and fastener condition, visual inspection is used to check for gaps, exposed reinforcement, surface dirt, water seepage, mud pumping, insufficient ballast, and loose or malfunctioning fasteners. However, for more serious internal track bed defects, effective detection methods are currently lacking. The primary method is to ride the track, but this is limited by the skill level and individual differences in perception, making it difficult to detect structural defects in a timely manner. The most economical and safest window for remediation may be missed due to the inability to detect the defects. Often, structural defects are only discovered or taken seriously when they have caused significant changes in track geometry, such as severe triangular pits or unevenness, resulting in a noticeable "dropping" or "swaying" sensation during train operation. At this point, remediation often involves significantly increased costs and a substantial increase in operational safety risks.

[0005] Vehicle inspection mainly refers to installing inspection equipment on inspection trains to photograph the appearance of the track, and designing corresponding image recognition systems to intelligently analyze and process the recorded images to detect track defects. In China's subway cities, the most commonly used inspection and analysis systems primarily employ optical-based non-contact inspection technology, using line scan cameras to acquire and store track images. The system separates the light source and camera, possessing some automatic recognition capabilities, but only for analyzing fastener integrity, ballast surface characteristics, and track linearity.

[0006] Traditional inspection methods mainly rely on manual and vehicle inspections, which depend on human eyes and instrument inspections. These methods require highly skilled inspectors and make it difficult to ensure safe operation. Summary of the Invention

[0007] In view of this, it is necessary to provide a method, device and medium for early warning of track bed defects based on grating array, so as to eliminate human interference and achieve the purpose of real-time detection and early warning of potential defects in track bed.

[0008] To achieve the above objectives, in a first aspect, the present invention provides a method for early warning of track bed defects based on a grating array, comprising: acquiring the vibration signal of the track bed from train operation through a fiber optic distributed acoustic sensing system and preprocessing it to obtain an effective vibration signal; determining a first median corresponding to the variance and a second median corresponding to the power spectral entropy based on the variance and power spectral entropy of the effective vibration signal; and providing early warning of track bed defects based on the first median and the second median.

[0009] In one possible implementation, before determining the first median corresponding to the variance and the second median corresponding to the power spectral entropy based on the variance and power spectral entropy of the effective vibration signal, the method further includes: performing a discrete Fourier transform on the sampling point sequence of the effective vibration signal to determine the power spectrum of the sampling point sequence; and determining the power spectral entropy based on the probability density function of the power spectrum.

[0010] In one possible implementation, the step of providing early warning of track bed defects based on the first median and the second median includes: identifying track bed defects when the first median is greater than a first preset value and the second median is greater than a second preset value.

[0011] In one possible implementation, the first preset value is 125 and the second preset value is 0.4.

[0012] In one possible implementation, the power spectrum is expressed as follows:

[0013] in, Represents the sequence of sampling points The power spectrum, Represents the sequence of sampling points Discrete Fourier Transform, This indicates the number of spectral lines in the power spectrum.

[0014] In one possible implementation, the expression for the power spectral entropy is as follows:

[0015] in, Represents the power spectral entropy. This represents the probability density function of the power spectrum.

[0016] Secondly, the present invention also provides a rail transit track bed defect early warning device based on a grating array, comprising: a data acquisition unit for acquiring the train vibration signal of the rail transit track bed through a fiber optic distributed acoustic sensing system and preprocessing it to obtain an effective vibration signal; a determination unit for determining a first median corresponding to the variance and a second median corresponding to the power spectral entropy based on the variance and power spectral entropy of the effective vibration signal; and an early warning unit for providing early warning of rail transit track bed defects based on the first median and the second median.

[0017] Thirdly, the present invention also provides an electronic device, including a memory and a processor, wherein the memory is used to store a program; the processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the grating array-based early warning method for track bed defects in any of the above implementations.

[0018] Fourthly, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instruction, wherein the program or instruction, when executed by a processor, is capable of implementing the steps in the grating array-based early warning method for track bed defects in any of the above implementations.

[0019] Fifthly, the present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps in the grating array-based early warning method for track bed defects in any of the above implementations.

[0020] The beneficial effects of this invention are as follows: The method, device, and medium for early warning of track bed defects based on grating array provided by this invention collect the vibration signals of the track bed through a fiber optic distributed acoustic sensing system, and preprocess them to obtain effective vibration signals. Utilizing the all-time, all-domain characteristics of fiber optic array sensing, long-term data acquisition of the entire track line is achieved. Combined with signal processing techniques, the invention proposes using variance and spectral entropy to measure the uncertainty of signal fluctuations and frequency components. Based on the median of variance and power spectral entropy, early warning of track bed defects is provided. By employing fiber optic distributed acoustic sensing technology, full-line, all-time monitoring of the track is achieved, eliminating interference from human factors. It can detect and warn of potential defects in real time, effectively avoiding the expansion of defects and increased repair costs. 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 1 is a flowchart illustrating an embodiment of the rail transit track bed defect early warning method based on grating array provided by the present invention; Figure 2 is a schematic diagram of the DAS system based on UWFBG array provided by the present invention; Figure 3 is a schematic diagram comparing normal and abnormal typical vibration signals sensed by the system provided by the present invention; Figure 4 is a flowchart illustrating the anomaly identification algorithm provided by the present invention; Figure 5 is a waveform diagram of normal typical vibration signals and a normalized schematic diagram of their spectral energy ratio provided by the present invention; Figure 6 is a waveform diagram of track slab fracture defect signals and a normalized schematic diagram of their spectral energy ratio provided by the present invention; Figure 7 is a scatter plot of track bed defect early warning on day T provided by the present invention; Figure 8 is a scatter plot of track bed defect identification on day T+7 provided by the present invention; Figure 9 is a scatter plot of track bed defect identification on day T+14 provided by the present invention; Figure 10 is a scatter plot of track bed defect early warning on day T+21 provided by the present invention; Figure 11 is a scatter plot of track bed defect early warning on day T+28 provided by the present invention; Figure 12 is a structural schematic diagram illustrating an embodiment of the rail transit track bed defect early warning device based on grating array provided by the present invention; Figure 13 is a structural schematic diagram illustrating an embodiment of the electronic device provided by the present invention. Detailed Implementation

[0023] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0024] In the description of the embodiments of the present invention, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0025] The terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a technical feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0026] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0027] This invention provides a method, device, and medium for early warning of track bed defects in rail transit based on grating arrays, which will be described below.

[0028] Figure 1 is a schematic flowchart of an embodiment of the rail transit track bed defect early warning method based on grating array provided by the present invention. As shown in Figure 1, the rail transit track bed defect early warning method based on grating array includes: S101, collecting the train vibration signal of the rail transit track bed through an optical fiber distributed acoustic sensing system and preprocessing it to obtain an effective vibration signal; S102, determining the first median corresponding to the variance and the second median corresponding to the power spectral entropy based on the variance and power spectral entropy of the effective vibration signal; S103, providing early warning of defects in the rail transit track bed based on the first median and the second median.

[0029] In S101, the Distributed Acoustic Sensors (DAS) system can continuously monitor vibration signals over a range of tens of kilometers, thus enabling all-time, all-domain safety monitoring. Furthermore, because the DAS system's sensing principle is fiber optic sensing, it boasts strong electromagnetic interference resistance, low cost, and facilitates large-scale sensor reuse. A typical DAS system is the phase-sensitive optical time-domain reflectometer (Φ-OTDR), which, compared to general DAS systems, offers higher sensitivity and faster response speed, thus attracting widespread attention since its inception. Moreover, modifying the fiber structure or type is a crucial means to further improve the signal-to-noise ratio of the Φ-OTDR; for example, replacing the grating array with an ultra-weak fiber Bragg grating array (UWFBG).

[0030] Figure 2 is a schematic diagram of the DAS system based on a UWFBG array provided by this invention, illustrating the basic principle of the DAS system used in this invention. As shown in Figure 2, in the DAS system, continuous light emitted by a narrow-linewidth laser is modulated into a sequence of optical pulses after passing through a photoelectric modulator. Then, the optical pulse sequence is amplified by an erbium-doped fiber amplifier and injected into the UWFBG array. The pulsed light reflected from the UWFBG array enters an unbalanced Michelson interferometer, which consists of a 3x3 coupler, two Faraday rotators, and a delay fiber. The length of the delay fiber is consistent with the distance between adjacent UWFBGs, thus forming a sensor for every two adjacent UWFBGs and the fiber between them. Finally, the output of the coupler enters three photodetectors. The subway train vibration signal is obtained through a signal detection module.

[0031] The vibration signals of the rail transit track bed are collected by the DAS system, and the effective vibration signals are obtained through preprocessing.

[0032] In S102, to more clearly describe the signals generated when a vehicle passes over a normal track bed and a damaged track bed, the two types of signals will be represented by normal signals and abnormal signals. Figure 3 is a schematic diagram comparing typical normal and abnormal vibration signals sensed by the system provided by this invention. As shown in Figure 3, a typical comparison of the two types of vibration signals is presented. The time-domain waveform of the normal signal is smooth and accompanied by regular fluctuations; the time-domain waveform of the abnormal signal is the opposite, with a more chaotic waveform and a significantly increased amplitude.

[0033] Based on the above analysis, in order to automatically identify defective roadbeds, this invention proposes a new roadbed defect identification algorithm. Figure 4 is a schematic diagram of the anomaly identification algorithm provided by this invention. As shown in Figure 4, the anomaly identification algorithm mainly includes four parts: preprocessing, calculating feature quantities, statistically analyzing the median, and determining the defect monitoring areas that require early warning based on thresholds.

[0034] As shown in Figure 4, the effective vibration signal detected by the DAS system is first calculated using two characteristic quantities: variance and spectral entropy.

[0035] Among them, signal variance is a statistical indicator used in statistics and signal processing to measure the change or fluctuation of a signal, while spectral entropy refers to the uncertainty of signal energy at frequency components.

[0036] Figure 5 shows the waveform of a typical normal vibration signal provided by this invention and its spectral energy ratio normalization diagram. Figure 6 shows the waveform of a track slab fracture fault signal provided by this invention and its spectral energy ratio normalization diagram. Figures 5 and 6 show a comparison of the frequency composition of the two signals. When the frequency composition of the signal is simple, the spectral entropy is small due to the sparse frequency spectral lines. Conversely, when the frequency composition of the signal is complex, the frequency spectral lines are dense, and the spectral entropy is large. Therefore, spectral entropy realizes a quantitative description of the complexity of the energy distribution of the signal in the frequency domain.

[0037] For example, take a segment of length as The sampling points contain a complete segment of vehicle vibration signal, thereby performing feature extraction to obtain the variance and power spectral entropy of the effective vibration signal, and further determining the first median corresponding to the variance and the second median corresponding to the power spectral entropy, respectively.

[0038] After obtaining the feature information of this sampling point, feature extraction was performed on long-term continuous driving using this as an example. Two sets of feature information of all driving signals in each test area were obtained and imported into the MySQL database respectively. Then, feature statistical sequences were constructed based on the historical information of the two sets of feature quantities.

[0039] In the above process, two sets of statistics were constructed respectively, and then the median of the two sets of statistics was calculated to statistically analyze the overall situation of the survey area.

[0040] In S103, the obtained median value (i.e., the first median and the second median) is used as the representative characteristic of the test area. Combined with the characteristic of the test area with disease that has occurred in engineering practice (variance greater than 125 and spectral entropy greater than 0.4), it is used as the threshold for evaluating whether the test area has disease. Test areas that exceed the threshold are regarded as potential disease test areas and are given early warning.

[0041] Leveraging the high sensitivity and response speed of grating arrays, this invention employs a DAS system to achieve long-term data acquisition across the entire rail transit line and store the demodulated data. Further, the stored data is used to reconstruct signals during train operation, and the signals are quantized using variance and spectral entropy. The median of the two quantization results is then used as the characteristic quantity of the measurement area in both the time and frequency domains and imported into a MySQL database for long-term monitoring. Combining the characteristic quantities corresponding to previously identified defects in the measurement area with those observed in engineering practice, a threshold is used to evaluate whether defects have occurred in the measurement area. Measurement areas exceeding the threshold are considered potential defect areas and are given early warning.

[0042] In summary, the rail transit track bed defect early warning method based on grating array provided by this invention collects the train vibration signal of the rail transit track bed through a fiber optic distributed acoustic sensing system, and performs preprocessing to obtain an effective vibration signal. Utilizing the all-time, all-domain sensing characteristics of the fiber optic array, it achieves long-term data acquisition across the entire rail transit line. Combined with signal processing techniques, it proposes using variance and spectral entropy to measure the uncertainty of signal fluctuation and frequency components. Based on the median of variance and power spectral entropy, it provides early warning of rail transit track bed defects. By employing fiber optic distributed acoustic sensing technology, it achieves full-line, all-time monitoring of the track, eliminates interference from human factors, and enables real-time detection and early warning of potential defects, effectively avoiding the expansion of defects and increased repair costs.

[0043] In some embodiments of the present invention, before determining the first median corresponding to the variance and the second median corresponding to the power spectral entropy based on the variance and power spectral entropy of the effective vibration signal, the method further includes: performing a discrete Fourier transform on the sampling point sequence of the effective vibration signal to determine the power spectrum of the sampling point sequence; and determining the power spectral entropy based on the probability density function of the power spectrum.

[0044] In some embodiments of the present invention, the power spectrum is expressed as follows:

[0045] in, Represents the sequence of sampling points The power spectrum, Represents the sequence of sampling points Discrete Fourier Transform, This indicates the number of spectral lines in the power spectrum.

[0046] In some embodiments of the present invention, the expression for the power spectral entropy is as follows:

[0047] in, Represents the power spectral entropy. This represents the probability density function of the power spectrum.

[0048] For example, take a segment of length as The sampling points contain a complete vehicle vibration signal. Taking this as an example, feature extraction is performed. The steps are as follows: (1) Calculate the variance of this set of sampling points:

[0049] in, As one of these sampling points, The mean of this set of sampling points, Let V be the variance of this set of sampling points.

[0050] (2) Calculate the spectral entropy of this set of sampling points:

[0051] in, For this set of sampling point sequences, for Discrete Fourier Transform

[0052] in, for The number of spectral lines in the power spectrum. for The power spectrum.

[0053]

[0054] in, for The probability density function represents the ratio of the energy at each frequency point of the power spectrum to the total energy.

[0055]

[0056] in, represent The power spectral entropy.

[0057] After obtaining the feature information of this sampling point, feature extraction was performed on long-term continuous driving data using this as an example. Two sets of feature information for all driving signals in each test area were obtained and imported into a MySQL database. Then, a feature statistical sequence was constructed based on the historical information of the two sets of feature quantities.

[0058] In some embodiments of the present invention, the step of providing early warning of track defects based on the first median and the second median includes: identifying track defects when the first median is greater than a first preset value and the second median is greater than a second preset value.

[0059] In some embodiments of the present invention, the first preset value is 125 and the second preset value is 0.4.

[0060] In the above process, two sets of statistics were constructed respectively, and then the median of the two sets of statistics was calculated to statistically analyze the overall situation of the survey area.

[0061] The obtained median value is used as the representative characteristic of the test area. Combined with the characteristic values ​​(variance greater than 125 and spectral entropy greater than 0.4) of the test areas that have already experienced disease in engineering practice, the threshold for evaluating whether the test area has experienced disease is used. Test areas that exceed the threshold are regarded as potential disease test areas and are given early warning.

[0062] For example, if the first median corresponding to the variance is greater than 125 and the second median corresponding to the spectral entropy is greater than 0.4, it is considered a potential disease monitoring area and an early warning is issued.

[0063] The following example uses partial results data from continuous monitoring of a certain interval in a certain embodiment of the present invention. Based on the above algorithm, two characteristic quantities of each measurement area in the interval are calculated to detect abnormal measurement areas within the interval.

[0064] Figures 7-11 show the scatter plots and identification scatter plots of track bed defects on different dates provided by the invention. Figure 7 is the scatter plot of track bed defects on day T provided by the invention. As can be seen from Figure 7, everything in the test area within this interval is normal and there are no abnormal phenomena.

[0065] Figure 8 is a scatter plot of track bed defects identification on T+7 days provided by the present invention. At this time, the 112 test area in this interval is suspected to be a defect test area and is gradually developing in an abnormal direction.

[0066] Figure 9 is a scatter plot of track bed defects identification on T+14 days provided by the present invention. At this time, the 112 test areas in this interval are identified as defect test areas according to the threshold warning.

[0067] Figure 10 is a scatter plot of track bed defect early warning on T+21 provided by the present invention, and Figure 11 is a scatter plot of track bed defect early warning on T+28 provided by the present invention. On the evening of T+25, subway inspection personnel confirmed through on-site inspection that there was a defect of track slab separation from the base layer in test area 112 of this section. By T+28, the test area with the early warning had returned to normal after being inspected and repaired by maintenance personnel.

[0068] On day T, everything in the monitoring area within that section was normal, with no abnormalities observed. As time progressed, the spatial distribution of the monitoring areas changed. By day T+7, based on the previously established threshold, monitoring area 112 was gradually moving away from the coordinate axis and approaching the threshold set by this invention; therefore, we will conduct long-term monitoring of this area. By day T+14, monitoring area 112 had exceeded the established threshold, at which point it was flagged as a defect monitoring area and monitoring continued. From day T+21 to day T+28, subway maintenance personnel inspected the flagged defect monitoring area on day T+25. Afterward, the distribution of the flagged defect monitoring area gradually moved closer to the coordinate axis, eventually returning to normal, and the warning was lifted. This invention demonstrates the entire process of daily monitoring of normal monitoring areas and early warning of defect monitoring areas, and the expected detection results are completely consistent with the judgment results of subway inspection personnel.

[0069] This invention proposes a method for early warning of track bed defects based on grating arrays, solving the following technical problems: 1. Low efficiency and strong subjectivity of manual inspection: Currently, manual inspection mainly relies on the naked eye observation and sensory experience of workers, which has obvious subjective differences. Due to the experience level and perception differences of technicians, it is often difficult to detect track structure defects in a timely and accurate manner, especially serious defects inside the track bed structure. In many cases, after the defects occur, they have already caused significant changes in the track geometry, and it is difficult to carry out effective repairs in a timely manner, resulting in high repair costs and increased operational safety risks. This invention, by adopting fiber optic distributed acoustic sensing technology, realizes full-line, real-time monitoring of the track, eliminates the interference of human factors, and can detect and warn of potential defects in real time, avoiding missing the best repair opportunity.

[0070] 2. Limitations of Vehicle Inspection: While vehicle inspection equipment can collect and recognize images of the track surface, existing technologies primarily focus on surface inspection of the track bed, failing to effectively detect deeper structural problems, particularly lacking the ability to monitor defects in the substructure. Furthermore, optical inspection technology is sensitive to environmental factors such as lighting and weather, and is ill-suited for continuous, long-term monitoring across the entire track area. This invention utilizes the high sensitivity and anti-interference capabilities of fiber optic sensing technology to deeply monitor the track bed structure, unaffected by external environmental factors like lighting and weather, achieving continuous, all-weather, and all-area monitoring.

[0071] 3. Traditional monitoring technologies cannot achieve long-term, continuous monitoring: Traditional track defect monitoring methods cannot achieve continuous monitoring of the entire track and all time periods. Furthermore, monitoring equipment is sensitive to electromagnetic interference and easily affected by the surrounding environment, leading to inaccurate monitoring data or incomplete coverage of the entire monitoring area. This invention employs fiber optic distributed acoustic sensing technology, enabling long-term, large-area monitoring with strong resistance to electromagnetic interference, ensuring the accuracy and integrity of monitoring data.

[0072] 4. Lack of an effective early warning mechanism for track defects: Current monitoring systems lack the ability to effectively identify and warn of potential defects. Existing methods only detect defects when they are severe and affect the track alignment, which not only misses the best time for repair but also leads to significant safety hazards. This invention, through precise analysis of monitoring data, extracts characteristic quantities of the track bed structure and establishes thresholds based on historical defect data, enabling early identification and warning of potential defects, effectively preventing the expansion of defects and increased repair costs.

[0073] To better implement the grating array-based early warning method for track bed defects in this invention, as shown in Figure 12, this invention also provides a grating array-based early warning device for track bed defects. The grating array-based early warning device 1200 includes: a data acquisition unit 1201, used to acquire the vibration signal of the track bed through a fiber optic distributed acoustic sensing system and preprocess it to obtain an effective vibration signal; a determination unit 1202, used to determine a first median corresponding to the variance and a second median corresponding to the power spectral entropy based on the variance and power spectral entropy of the effective vibration signal; and an early warning unit 1203, used to provide early warning of track bed defects based on the first median and the second median.

[0074] The rail transit track bed defect early warning device 1200 based on grating array provided in the above embodiments can realize the technical solution described in the above embodiments of the rail transit track bed defect early warning method based on grating array. The specific implementation principle of each module or unit can be found in the corresponding content in the above embodiments of the rail transit track bed defect early warning method based on grating array, and will not be repeated here.

[0075] As shown in Figure 13, the present invention also provides an electronic device 1300. The electronic device 1300 includes a processor 1301, a memory 1302, and a display 1303. Figure 13 only shows some components of the electronic device 1300; however, it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented alternatively.

[0076] In some embodiments, processor 1301 may be a central processing unit (CPU), microprocessor or other data processing chip, used to run program code stored in memory 1302 or process data, such as the grating array-based early warning method for track bed defects in rail transit in this invention.

[0077] In some embodiments, processor 1301 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 1301 may be local or remote. In some embodiments, processor 1301 may be implemented on a cloud platform. In some embodiments, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-cloud, or any combination thereof.

[0078] In some embodiments, memory 1302 may be an internal storage unit of electronic device 1300, such as a hard disk or memory of electronic device 1300. In other embodiments, memory 1302 may also be an external storage device of electronic device 1300, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on electronic device 1300.

[0079] Furthermore, the memory 1302 may include both internal storage units of the electronic device 1300 and external storage devices. The memory 1302 is used to store application software and various types of data installed on the electronic device 1300.

[0080] In some embodiments, display 1303 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an organic light-emitting diode (OLED) touchscreen. Display 1303 is used to display information from electronic device 1300 and to display a visual user interface. Components 1301-1303 of electronic device 1300 communicate with each other via a system bus.

[0081] In one embodiment, when the processor 1301 executes the rail transit track bed defect early warning program based on grating array in the memory 1302, the following steps can be implemented: collecting the train vibration signal of the rail transit track bed through the fiber optic distributed acoustic sensing system and preprocessing it to obtain an effective vibration signal; determining the first median corresponding to the variance and the second median corresponding to the power spectral entropy based on the variance and power spectral entropy of the effective vibration signal; and providing a defect early warning for the rail transit track bed based on the first median and the second median.

[0082] It should be understood that when the processor 1301 executes the grating array-based rail transit track bed defect early warning program in the memory 1302, in addition to the functions mentioned above, it can also perform other functions, as can be found in the description of the corresponding method embodiments above.

[0083] Furthermore, the embodiments of the present invention do not specifically limit the type of electronic device 1300 mentioned. Electronic device 1300 can be a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, laptop computer, or other portable electronic device. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, electronic device 1300 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0084] Accordingly, embodiments of the present invention also provide a computer-readable storage medium for storing computer-readable programs or instructions. When the programs or instructions are executed by a processor, they can implement the steps or functions of the rail transit track bed defect early warning method based on grating array provided in the above-described method embodiments.

[0085] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to perform the steps or functions in the grating array-based early warning method for track bed defects provided in the above-described method embodiments.

[0086] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0087] The above provides a detailed description of the method, device, and medium for early warning of track bed defects based on grating array provided by the present invention. Specific examples have been used to illustrate the principle and implementation of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation and application scope based on the idea of ​​the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for early warning of track bed defects in rail transit based on grating array, characterized in that, include: The vibration signals of the rail transit track bed are collected by a fiber optic distributed acoustic sensing system and preprocessed to obtain effective vibration signals. Based on the variance and power spectral entropy of the effective vibration signal, a first median corresponding to the variance and a second median corresponding to the power spectral entropy are determined; based on the first median and the second median, early warning of track bed defects is provided.

2. The method for early warning of track bed defects in rail transit based on grating array according to claim 1, characterized in that, Before determining the first median corresponding to the variance and the second median corresponding to the power spectral entropy based on the variance and power spectral entropy of the effective vibration signal, the method further includes: performing a discrete Fourier transform on the sampling point sequence of the effective vibration signal to determine the power spectrum of the sampling point sequence; and determining the power spectral entropy based on the probability density function of the power spectrum.

3. The method for early warning of track bed defects in rail transit based on grating array according to claim 1, characterized in that, The method of providing early warning of track defects based on the first median and the second median includes: identifying track defects when the first median is greater than a first preset value and the second median is greater than a second preset value.

4. The method for early warning of track bed defects in rail transit based on grating array according to claim 3, characterized in that, The first preset value is 125, and the second preset value is 0.

4.

5. The method for early warning of track bed defects in rail transit based on grating array according to claim 2, characterized in that, The expression for the power spectrum is as follows: in, Represents the sequence of sampling points The power spectrum, Represents the sequence of sampling points Discrete Fourier Transform, This indicates the number of spectral lines in the power spectrum.

6. The method for early warning of track bed defects in rail transit based on grating array according to claim 5, characterized in that, The expression for the power spectral entropy is as follows: in, Represents the power spectral entropy. This represents the probability density function of the power spectrum.

7. A rail transit track bed defect early warning device based on grating array, characterized in that, include: The acquisition unit is used to acquire the vibration signals of the rail transit track bed through the fiber optic distributed acoustic sensing system and to preprocess them to obtain effective vibration signals. The determining unit is used to determine the first median corresponding to the variance and the second median corresponding to the power spectral entropy based on the variance and power spectral entropy of the effective vibration signal. The early warning unit is used to provide early warning of defects in the rail transit track bed based on the first median and the second median.

8. An electronic device, characterized in that, The system includes a memory and a processor, wherein the memory is used to store a program; and the processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the method for early warning of track bed defects based on grating array as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the grating array-based early warning method for track bed defects of rail transit as described in any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps in the method for early warning of track bed defects based on grating array as described in any one of claims 1 to 6.

Images