A method and system for monitoring performance deterioration of ballastless track joint

Abstract

The application provides a ballastless track joint performance deterioration monitoring method and system, and relates to the technical field of track joint performance monitoring, which comprises the following steps: exciting a ballastless track slab at a track joint by knocking the track joint with a force hammer, collecting a vertical vibration acceleration response signal by using an acceleration sensor, and synchronously recording a knocking time and a static force parameter; preprocessing the vertical vibration acceleration response signal, removing abnormal pulses and baseline drift, forming a vibration event sample, and extracting joint mechanical characteristic parameters, including a vibration frequency parameter reflecting stiffness deterioration and a vibration attenuation parameter reflecting damping; combining the static force parameter to calculate a joint performance evaluation index, comparing the joint performance evaluation index with a preset threshold to evaluate a deterioration grade, triggering a warning signal, providing joint deterioration grade and position information, and realizing monitoring and evaluation of the joint performance.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of track joint performance monitoring, in particular to a ballastless track joint performance deterioration monitoring method and system. BACKGROUND

[0002] Ballastless track has been widely used in high-speed railway, intercity railway and other fields due to its strong integrity, high stability and low maintenance cost. As a weak link in the structure of the ballastless track system, the track joint is subjected to the combined action of various complex factors such as periodic train load, environmental temperature change and foundation settlement for a long time, and is prone to deterioration phenomena such as joint stiffness reduction, damping performance change and local damage of joint structure. These deterioration phenomena will directly affect the overall mechanical performance of the track, causing abnormal vibration phenomena during train operation, and even threatening train operation safety in severe cases. For track joint deterioration monitoring, current methods mainly rely on manual detection or periodic inspection by track detection vehicles. These traditional methods have problems such as long detection period, insufficient real-time performance, high cost and large disturbance to normal operation, which cannot meet the current high-frequency and high-precision track maintenance requirements. In addition, manual detection often relies on experience, and the reliability and consistency of the detection results are poor, with the risk of detection omission and misjudgment.

[0003] Currently, some studies attempt to reflect the track state through vibration signals during train operation, but there are still many technical problems in practical application. First, there is a lot of noise and interference in the train vibration signal, and the vibration signal characteristics at the track joint position are relatively weak, making it difficult to accurately locate the joint position and extract effective signals. In addition, existing methods usually lack effective data processing techniques, making it difficult to extract key feature parameters of track joint deterioration from vibration signals, resulting in insufficient monitoring accuracy. Especially for changes in track joint stiffness and damping performance, there is no mature quantitative evaluation system, which cannot provide accurate judgment basis for the performance deterioration degree of the track joint. In summary, the existing technology still has significant deficiencies in real-time monitoring, data analysis and processing, and quantitative evaluation of track joint performance deterioration, and a new method is needed that can accurately locate the track joint deterioration position, realize real-time quantitative analysis of joint performance and dynamic warning to meet the efficient maintenance and safe operation requirements of railway lines.

[0004] The above information disclosed in the BACKGROUND section is only intended to enhance the understanding of the background of the present disclosure, and therefore it can include information that does not constitute the prior art known to those of ordinary skill in the art. SUMMARY

[0005] The purpose of the present application is to provide a ballastless track joint performance deterioration monitoring method and system to solve the problems raised in the background.

[0006] To achieve the above object, the present application provides the following technical solutions:

[0007] A method for monitoring the performance degradation of a ballastless track joint, comprising the following specific steps:

[0008] S1: A force hammer is used to strike the ballastless track slab at the joint to be monitored to generate an excitation, an acceleration sensor fixedly installed on the base structure corresponding to the joint is used to collect the vertical vibration acceleration response signal of the joint caused by the excitation, the time of striking is recorded, and a vertical vibration acceleration signal segment associated with the joint is obtained; the static force parameters of the joint are synchronously collected, including temperature, pressure and pretightening force;

[0009] S2: The vertical vibration acceleration signal segment is preprocessed to remove abnormal pulse signals and constant baseline drift in the data, and a joint vibration event sample is obtained; the abnormal pulse signals are transient signals exceeding a preset vibration amplitude range, and the constant baseline drift is a fixed offset continuously existing in the data;

[0010] S3: Feature extraction is performed on the joint vibration event sample to obtain a feature parameter set for characterizing the mechanical performance of the track joint, the feature parameter set including a vibration frequency feature parameter reflecting the stiffness degradation of the joint and a vibration attenuation feature parameter reflecting the damping of the joint;

[0011] S4: Based on the vibration frequency feature parameter, the vibration attenuation feature parameter and the static force parameter, a joint performance evaluation index is determined, the joint performance evaluation index is compared with a preset evaluation threshold, based on the comparison result, the degradation level of the track joint to be monitored is determined, and a corresponding warning signal is triggered, the warning signal including the degradation level of the track joint to be monitored and the position information of the joint.

[0012] Further, in S1, the base structure includes a track slab bearing platform, an inner wall of a trackside cable trough or a top of a box girder;

[0013] For the longitudinal joint between track slabs, the acceleration sensor is fixed to the side surface of the track slab bearing platform on both sides of the joint, and is 0.3-0.5m away from the edge of the joint; for the transverse joint, the sensor is installed on the inner wall of the trackside cable trough close to the joint or the top of the box girder directly below the joint; the sensor is connected to the base structure through a stainless steel support;

[0014] The temperature sensor, the pressure sensor and the pretightening force sensor are pre-buried in the joint or the tensioning lock during the track slab width joint treatment construction, and are respectively used to collect the temperature, pressure and pretightening force data of the joint;

[0015] A standard hammer with a force sensor is used to strike the ballastless track slab 1-2 fastener spacings closest to the joint to be monitored in a vertical direction. The force sensor is used to monitor the striking force in real time and ensures that the peak impact force of a single strike is stable within a preset rated range through a feedback device to generate a standard excitation with consistent energy. At the same time, an accelerometer is used to collect the vibration response at the joint to be monitored in real time and continuously record a signal of a fixed duration at a sampling frequency of not less than 10kHz to ensure complete capture of the waveform from the start of excitation, vibration transmission to complete vibration decay. Finally, a complete vertical vibration acceleration signal segment that strictly corresponds to this standard striking excitation is obtained, and the static parameters at the joint, including temperature, pressure and preload, are collected simultaneously.

[0016] Furthermore, abnormal pulse signals are identified in the vertical vibration acceleration signal segment. A preset vibration amplitude range is defined, and the vertical vibration acceleration signal segment is scanned point by point. When the amplitude of a signal point exceeds the preset vibration amplitude range, the signal point and its adjacent signal points that are consecutive and also exceed the range are determined to constitute abnormal pulse signals. For the identified abnormal pulse signals, an interpolation completion method is used for processing, and the closest abnormal pulse signal is used to complete the interpolation. Based on the mean of normal signal points, the complete data corresponding to the abnormal pulse signal is calculated by linear interpolation and replaced with the original abnormal pulse signal data.

[0017] Constant baseline drift identification is performed on the vertical vibration acceleration signal after removing abnormal pulse signals. A stable segment without obvious vibration fluctuations is selected in the signal, and the mean value of all signal points in the stable segment is calculated. This mean value is used as the constant baseline drift amount. The constant baseline drift is removed by subtracting the constant baseline drift amount from the value of each signal point in the entire vertical vibration acceleration signal segment, and the joint vibration event sample is obtained.

[0018] The method for determining the steady segment is as follows: the complete vertical vibration acceleration signal segment is divided into multiple time segments of equal length, and the standard deviation of the vibration signal amplitude of each time segment is calculated according to the following formula:

[0019] ;

[0020] In the formula, Indicates the first The standard deviation of the vibration signal amplitude for each time segment is used to quantify the degree of fluctuation in the signal amplitude within that segment. Index to the time segment; This indicates the total number of data points contained within a time segment. For the index of the data points, This represents the arithmetic mean of the vibration signal amplitudes at all data points within a time interval. Indicates the first vibration signal amplitude at each data point

[0021] By iterating through all time segments, the top 5% of time segments with the smallest standard deviation are selected as stable segments without significant fluctuations.

[0022] The preset vibration amplitude range is determined based on the amplitude statistics of historical vertical vibration acceleration signals under normal conditions of the ballastless track of the operating line.

[0023] Furthermore, the specific execution process of S3 is as follows:

[0024] Frequency domain analysis was performed using Fourier transform on the vibration time samples of the butt joint to obtain the frequency domain signal. The formula used is as follows:

[0025] ;

[0026] In the formula, The vibration time sample of the joint is a time-series signal. For frequency; The imaginary unit; Pi; It is a time variable; It is a natural constant;

[0027] Based on frequency domain signals The power spectral density is calculated using the following formula:

[0028] ;

[0029] In the formula, For the first The power spectral density corresponding to each frequency component is used to reflect the vibration energy distribution of that frequency component. Index of frequency components; Represents the th after Fourier transform One frequency domain component; The fixed sampling frequency of the accelerometer; The total number of signal points in the joint vibration time sample is obtained by counting the number of signal points within the sample.

[0030] In the power spectral density curve In the middle, identify and extract the elements that make The frequency component with the largest value , That is, the main peak frequency. Used to directly reflect the stiffness characteristics of the joint: when the joint stiffness decreases... will be offset to low frequency direction; define the frequency offset as the vibration frequency characteristic parameter, and its calculation formula is as follows:

[0031] ;

[0032] In the formula, is the frequency offset, which is used to quantify the degree of joint stiffness degradation; is the reference peak frequency in the preset joint performance reference parameter set, which is determined according to historical data statistics under normal state of the line.

[0033] Further, the time domain analysis method is used to analyze the attenuation characteristics of the joint vibration event sample, and the damping variation characteristics of the track joint are extracted, and the specific steps are as follows:

[0034] The Hilbert transform is used to extract the vibration envelope of the joint vibration event sample :

[0035] ;

[0036] In the formula, is the vibration envelope, which is used to represent the change trend of the signal vibration amplitude with time; is the joint vibration time sample, is the Hilbert transform of ; is the ratio of the circumference to the diameter; represents the value of the joint vibration time sample at time , is the integral variable;

[0037] The vibration envelope is exponentially fitted to obtain the signal attenuation rate , and the signal attenuation rate is defined as the vibration attenuation characteristic parameter;

[0038] The formula for calculating is as follows:

[0039] ;

[0040] In the formula, is the initial amplitude, is the signal attenuation rate, which is used to represent the change of the joint damping performance; is the system natural frequency; is the time variable;

[0041] The frequency offset and the signal attenuation rate are integrated to form a characteristic parameter set for representing the mechanical properties of the track joint.

[0042] Further, based on the dimensionless vibration frequency characteristic parameter, the vibration attenuation characteristic parameter and the static force parameter, a joint performance evaluation index is determined, and the formula is as follows:

[0043] ;

[0044] In the formula, is the joint performance evaluation index, which is used to reflect the deterioration degree of the joint performance of the monitored ballastless track; is the signal attenuation rate, is the signal attenuation rate reference value; is the frequency offset, 、 and are preset weights; is the static force parameter, is the index of the static force parameter, respectively corresponds to temperature, pressure and pre-tightening force, is the ideal value of the corresponding static force parameter.

[0045] Further, the joint performance evaluation index is compared with a preset evaluation threshold to determine the deterioration level of the monitored track joint:

[0046] If , it is judged that the performance level of the monitored track joint is normal;

[0047] If , it is judged that the performance level of the monitored track joint is slightly deteriorated;

[0048] If , it is judged that the performance level of the monitored track joint is moderately deteriorated;

[0049] If , it is judged that the performance level of the monitored track joint is severely deteriorated;

[0050] In the formula, 、 and are respectively a preset first evaluation threshold, a second evaluation threshold and a third evaluation threshold, which are determined according to statistical analysis of historical normal data and deteriorated data;

[0051] According to the above comparison method, the deterioration level of the monitored track joint is determined, and a corresponding early warning signal is triggered, which contains the deterioration level of the monitored track joint and the position information of the joint.

[0052] The application further provides a ballastless track joint performance deterioration monitoring system for executing the ballastless track joint performance deterioration monitoring method.

[0053] A data acquisition module is configured to generate an excitation by knocking the ballastless track slab at the joint to be monitored by a force hammer, acquire a vertical vibration acceleration response signal of the joint caused by the excitation by using an acceleration sensor fixedly installed on the base structure corresponding to the joint, record a knocking time, and obtain a vertical vibration acceleration signal segment associated with the joint.

[0054] A data processing module is configured to pre-process the vertical vibration acceleration signal segment, remove abnormal pulse signals and constant baseline drift in the data, and obtain a joint vibration event sample.

[0055] A vibration feature extraction module is configured to extract features from the joint vibration event sample, and obtain a feature parameter set for characterizing the mechanical performance of the track joint.

[0056] A joint performance evaluation module is configured to determine a joint performance evaluation index based on the vibration frequency feature parameter, the vibration attenuation feature parameter, and the static force parameter, compare the joint performance evaluation index with a preset evaluation threshold, determine a deterioration grade of the track joint to be monitored based on a comparison result, and trigger a corresponding early warning signal.

[0057] Compared with the prior art, the application has the following beneficial effects:

[0058] The application realizes real-time monitoring and data recording of the track joint performance by collecting vertical vibration acceleration signals by using a vehicle-mounted acceleration sensor during train operation and locating the position of the track joint in combination with mileage position information. The method removes abnormal pulses and baseline drift in the signal by using a pre-processing technique, thereby obtaining clear joint vibration event samples, and further extracts stiffness change and damping change features of the joint by using frequency domain analysis and time domain analysis, thereby constructing a performance evaluation system based on frequency offset and signal attenuation rate. By introducing a joint performance evaluation index, the application realizes quantitative evaluation of the track joint performance, and dynamically triggers an early warning signal according to the deterioration grade, thereby providing a direct basis for subsequent operation and maintenance decisions. BRIEF DESCRIPTION OF DRAWINGS

[0059] Figure 1 The whole method flowchart of the present application is shown in the figure;

[0060] Figure 2 The whole system module of the present application is shown in the figure;

[0061] Figure 3 The parallel coordinate image of each item and dependent variable in the joint performance evaluation index calculation formula is shown in the figure;

[0062] Figure 4 The line segment graph of the frequency offset, signal attenuation rate item and joint performance evaluation index is shown in the figure. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical scheme and advantages of the present application more clear and explicit, the present application is further described in detail below in combination with specific embodiments.

[0064] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present application should be the general meaning understood by those skilled in the art to which the present application belongs. The words "first", "second" and similar words used in the present application do not represent any order, quantity or importance, but are only used to distinguish different components. The words "include" or "contain" and similar words mean that the elements or objects before the words cover the elements or objects listed after the words and their equivalents, without excluding other elements or objects. The words "connect" or "connected" and similar words are not limited to physical or mechanical connection, but can include electrical connection, whether direct or indirect. The words "up", "down", "left", "right" and the like only represent relative positional relationship, which may change accordingly when the absolute position of the described object changes.

[0065] EMBODIMENT

[0066] Please refer to Figure 1 The present application provides a technical scheme:

[0067] A method for monitoring the performance degradation of a ballastless track joint, comprising the following specific steps:

[0068] S1: Excitation is generated by knocking the ballastless track slab at the joint to be monitored with a hammer, vertical vibration acceleration response signals caused by the excitation are collected by using an acceleration sensor fixedly installed on the foundation structure corresponding to the joint, the knocking time is recorded, and a vertical vibration acceleration signal segment associated with the joint is obtained; static parameters at the joint are synchronously collected, including temperature, pressure and pre-tightening force;

[0069] In the embodiment, the foundation structure in S1 includes a track slab bearing platform, a trackside cable trough inner wall or a box girder top;

[0070] For the longitudinal joint between the track slabs, the acceleration sensor is fixed to the side of the rail seat of the track slab on both sides of the joint, 0.3-0.5m away from the edge of the joint; for the transverse joint, the sensor is installed on the inner wall of the cable trench near the joint or the top of the box girder directly below the joint; the sensor is connected to the basic structure through a stainless steel support;

[0071] During the construction of the wide-narrow joint of the track slab, the temperature sensor, the pressure sensor and the pre-tightening force sensor are pre-buried in the joint or the tension lock, and are respectively used to collect the temperature, pressure and pre-tightening force data of the joint.

[0072] A standard force hammer with a force sensor is used to vertically knock the ballastless track slab at 1-2 fastener spacings away from the joint to be monitored, the force sensor is used to monitor the knocking force in real time, and the feedback device is used to ensure that the peak value of the impact force of a single knock is stabilized in the preset rated range, so as to generate a standard excitation with consistent energy; at the same time, an acceleration sensor is used to collect the vibration response of the joint to be monitored in real time, and a signal with a fixed time length is continuously recorded at a sampling frequency of no less than 10 kHz, so as to ensure that the whole process waveform from the start of the excitation, the vibration transmission to the complete attenuation of the vibration is completely captured, and finally a complete vertical vibration acceleration signal segment strictly corresponding to this standard knocking excitation is obtained, and the static force parameters of the joint are synchronously collected, including temperature, pressure and pre-tightening force.

[0073] In the embodiment, the sensor arrangement and collection method are as follows: during the construction of the wide-narrow joint of the track slab, the temperature sensor, the pressure sensor and the pre-tightening force sensor are pre-buried in the joint or the tension lock: the temperature sensor is of PT100 type, is directly buried in the interior of the joint material to monitor the internal temperature distribution; the pressure sensor is of BCLFT-F miniature column type tension and compression force sensor, is buried in the joint to monitor the pressure borne by the joint; the pre-tightening force sensor is of SKP117 type, is installed at the tension lock, and is used to monitor the pre-tightening force state of the tension lock in real time. All the sensor signal lines are vertically introduced into the cable trench, and are protected and fixed through rubber pipes and standard fixtures, and finally are connected to the wide-narrow joint comprehensive monitor to realize the synchronous, continuous collection and remote transmission of data.

[0074] The vertical vibration acceleration response signal and the parameters such as temperature, pressure and pre-tightening force are collected, which is based on the multi-dimensional characteristics of the joint performance deterioration of the ballastless track: the vertical vibration acceleration signal directly reflects the stiffness and damping performance of the joint under dynamic excitation (reflected by frequency offset and attenuation characteristics), which is the core basis for evaluating the mechanical response ability of the joint; the temperature parameter is related to the stress state of the joint due to thermal expansion and contraction, which can capture the crack propagation or joint opening caused by temperature change; the pressure parameter represents the load transfer ability of the joint filling material, and its abnormal change can reflect the structural damage such as material crushing and joint separation; the pre-tightening force parameter reflects the constraint effectiveness of the connecting parts such as tension lock, and is directly related to the overall stability of the joint. By synchronously collecting the above parameters, the dynamic mechanical characteristics and static stress state can be analyzed simultaneously, and various deterioration modes of the joint from material deterioration to structural failure are covered, thereby providing complete data support for accurate evaluation of the joint performance.

[0075] Step S1 generates excitation by hammering the ballastless track slab, collects vibration response signals by combining acceleration sensors fixed on the corresponding base structure of the joint, and synchronously collects static force parameters. This method can obtain complete vibration acceleration signals corresponding to excitation in a standardized and repeatable manner, and at the same time, since the force sensor monitors the hammering force in real time and ensures consistent excitation energy, the accuracy and consistency of data collection are ensured. In addition, the synchronous collection of static force parameters provides key multi-dimensional data support for subsequent evaluation.

[0076] Compared with traditional monitoring techniques, this step can realize more accurate collection of joint vibration response signals through standard hammer excitation and high-precision sensor arrangement, and does not rely on external machinery or vehicle load, thereby avoiding the problem of unstable data caused by changes in environment or operating conditions. At the same time, the optimized design of the sensor installation position effectively improves the sensitivity and applicability of signal collection. In addition, the synchronous collection of static force parameters provides a more reliable basis for comprehensive analysis and diagnosis of joint deterioration causes.

[0077] Step S1 lays the foundation for data collection and quality control of the overall scheme. By obtaining high-quality vertical vibration acceleration signal segments and static force parameters, a reliable data source is provided for signal preprocessing, feature extraction and performance evaluation in subsequent steps, ensuring the accuracy and traceability of the analysis results. At the same time, the standardized operation of this step simplifies the monitoring process, improves the operability and generalizability of the scheme in practical application, and finally realizes efficient monitoring and evaluation of the performance deterioration of the track joint.

[0078] S2: pre-process the vertical vibration acceleration signal segment to remove abnormal pulse signals and constant baseline drift in the data, and obtain joint vibration event samples; the abnormal pulse signal is a transient signal that exceeds the preset vibration amplitude range, and the constant baseline drift is a fixed offset that exists continuously in the data;

[0079] In this embodiment, abnormal pulse signals are identified in the vertical vibration acceleration signal segment. A preset vibration amplitude range is defined, and the vertical vibration acceleration signal segment is scanned point by point. When the amplitude of a signal point exceeds the preset vibration amplitude range, the signal point and its adjacent consecutive signal points with amplitudes also exceeding the range are determined to constitute abnormal pulse signals. For the identified abnormal pulse signals, an interpolation completion method is used for processing, and the signal point closest to the abnormal pulse signal is selected. Based on the mean of normal signal points, the complete data corresponding to the abnormal pulse signal is calculated by linear interpolation and replaced with the original abnormal pulse signal data.

[0080] Constant baseline drift identification is performed on the vertical vibration acceleration signal after removing abnormal pulse signals. A stable segment without obvious vibration fluctuations is selected in the signal, and the mean value of all signal points in the stable segment is calculated. This mean value is used as the constant baseline drift amount. The constant baseline drift is removed by subtracting the constant baseline drift amount from the value of each signal point in the entire vertical vibration acceleration signal segment, and the joint vibration event sample is obtained.

[0081] The method for determining the steady segment is as follows: the complete vertical vibration acceleration signal segment is divided into multiple time segments of equal length, and the standard deviation of the vibration signal amplitude of each time segment is calculated according to the following formula:

[0082] ;

[0083] In the formula, Indicates the first The standard deviation of the vibration signal amplitude for each time segment is used to quantify the degree of fluctuation in the signal amplitude within that segment. The larger the value, the greater the fluctuation of the signal amplitude within that segment; Index for the time segment; This indicates the total number of data points contained within a time segment. For the index of the data points, This represents the arithmetic mean of the vibration signal amplitudes at all data points within a time interval. Indicates the first vibration signal amplitude at each data point

[0084] By iterating through all time segments, the top 5% of time segments with the smallest standard deviation are selected as stable segments without significant fluctuations.

[0085] The preset vibration amplitude range is determined based on the amplitude statistics of historical vertical vibration acceleration signals under normal conditions of the ballastless track of the operating line.

[0086] Step S2 can significantly improve the effectiveness and accuracy of the data by preprocessing the vertical vibration acceleration signal segment, removing abnormal pulse signals and constant baseline drift. The identification and repair of abnormal pulse signals ensure the integrity of the signal and avoid interference from sudden abnormal signals in subsequent analysis. The removal of constant baseline drift eliminates the fixed offset in the signal, making the signal more truly reflect the joint vibration characteristics. This step provides high-quality signal samples for subsequent feature extraction.

[0087] Compared with the prior art, this step innovatively combines abnormal pulse signal identification and constant baseline drift removal, which can more accurately identify and correct interference terms in the signal. Traditional methods often ignore local abnormalities or fixed drifts in the signal, resulting in large errors in the analysis results. After interpolating and repairing abnormal signals and removing offsets, the quality and consistency of the signal are greatly improved, laying a more reliable foundation for subsequent analysis.

[0088] Step S2 plays a key role in signal optimization in the entire scheme. By removing data interference and improving signal quality, it ensures the accuracy and stability of subsequent vibration feature parameter extraction. At the same time, this step can reduce the misjudgment rate and improve the reliability of joint performance degradation evaluation, thereby providing necessary data support for accurately judging the state of the track joint and playing an important role in promoting comprehensive and accurate degradation monitoring.

[0089] S3: performing feature extraction on the joint vibration event sample to obtain a feature parameter set for characterizing the mechanical performance of the track joint, the feature parameter set including a vibration frequency feature parameter reflecting joint stiffness degradation and a vibration attenuation feature parameter reflecting joint damping;

[0090] In this embodiment, the specific execution process of S3 is as follows:

[0091] The Fourier transform is used to perform frequency domain analysis on the joint vibration time sample to obtain a frequency domain signal , and the formula is as follows:

[0092] ;

[0093] In the formula, is the joint vibration time sample, which is a time series signal; is the frequency; is the imaginary unit; is the circular constant; is the time variable; is the natural constant;

[0094] Based on the frequency domain signal , the power spectral density is calculated, and the calculation formula is as follows:

[0095] ;

[0096] In the formula, is the power spectral density corresponding to the th frequency component, which is used to reflect the vibration energy distribution of the frequency component, is the index of the frequency component; represents the th frequency domain component after Fourier transform; is the fixed sampling frequency of the acceleration sensor; is the total number of points of the joint vibration time sample, which is obtained by counting the number of signal points in the sample.

[0097] Dependent variable power spectral density is a physical quantity, which specifically reflects the energy distribution intensity of the vibration signal at the th frequency component. Its technical significance lies in converting the time domain vibration signal into frequency domain energy distribution, thereby clearly revealing the contribution size of different frequency components in the signal. By identifying the peak value of the curve and its corresponding frequency, the dominant vibration frequency of the joint structure can be accurately located, which is a key indicator for characterizing the joint stiffness state. The PSD graph provides an intuitive and effective tool for diagnosing the characteristics of the joint structure from the energy perspective.

[0098] In the power spectral density curve , identify and extract the frequency component that maximizes the value, which is the main peak frequency, which is used to directly reflect the joint stiffness characteristics: when the joint stiffness decreases, it will shift to low frequency direction; define the frequency shift as the vibration frequency characteristic parameter, and its calculation formula is as follows:

[0099] ;

[0100] In the formula, is the frequency shift, which is used to quantify the degree of joint stiffness degradation; is the reference main peak frequency in the preset joint performance reference parameter set, which is determined according to the historical data statistics under the normal state of the line.

[0101] Using time domain analysis method to analyze the attenuation characteristics of the joint vibration event sample, extract the damping variation characteristics of the track joint, the specific steps are as follows:

[0102] Use Hilbert transform to extract the vibration envelope of the joint vibration event sample :

[0103] ;

[0104] is the Hilbert transform of the vibration envelope, is the vibration envelope, used to characterize the trend of signal vibration amplitude over time; is the joint vibration time sample, is the Hilbert transform of the vibration envelope, is the Hilbert transform of the vibration envelope; is the ratio of a circle; represents the value of the joint vibration time sample at time , is the integral variable.

[0105] The core significance of extracting the vibration envelope using the Hilbert transform is to convert the complex oscillation signal into a smooth envelope line that can clearly characterize the overall trend of its amplitude over time. This envelope line strips the details of high-frequency oscillation and highlights the overall decay process of vibration energy, providing essential input data for subsequent quantitative analysis of signal decay characteristics. This step upgrades time-domain analysis from observing oscillation waveforms to quantifying energy decay laws, which is an indispensable technical link for accurately evaluating joint damping performance.

[0106] Exponential fitting is performed on the vibration envelope to obtain the signal decay rate , and the signal decay rate is defined as the vibration decay characteristic parameter;

[0107] The formula for calculation is as follows:

[0108] ;

[0109] in which, is the initial amplitude, is the signal decay rate, used to characterize the speed of joint structure vibration energy dissipation, i.e., its damping characteristics. Its technical significance lies in quantifying the internal friction, micro-crack propagation, and structural connection state of the joint material, etc. hidden damage: An abnormally increased value usually indicates that the joint has broken down, friction has intensified, and other damage has caused energy dissipation to accelerate; while an abnormally decreased value may indicate material aging, elastic failure, or off-joint, leading to a decline in energy dissipation capacity. This parameter provides a key indicator for evaluating changes in the internal state of the joint material and can effectively identify early hidden damage; is the system natural frequency; is the time variable;

[0110] The frequency offset and the signal decay rate are integrated to form a characteristic parameter set for characterizing the mechanical performance of the track joint.

[0111] Step S3 establishes a set of feature parameters that can quantify the mechanical properties of the track joint by feature extraction on the joint vibration event samples, including vibration frequency feature parameters and vibration attenuation feature parameters. This approach can directly capture the dynamic changes of the physical properties of the joint structure, providing quantitative and interpretable evaluation indicators with high sensitivity and reliability. Compared to directly relying on the original signal, extracting feature parameters can more effectively reduce noise interference and improve evaluation accuracy.

[0112] The existing technology usually relies on experience or a single indicator to determine the joint state, which may lead to insufficient evaluation accuracy of the deterioration. However, by comprehensively extracting two types of key parameters, vibration frequency and attenuation characteristics, this step can more deeply reveal the change law of joint stiffness and damping. Especially by extracting the main peak frequency through Fourier transform and calculating the frequency shift, combined with Hilbert transform analysis of vibration attenuation, precise identification and hierarchical evaluation of different deterioration modes can be achieved. This fusion of frequency domain and time domain features greatly improves the comprehensiveness and accuracy of diagnosis.

[0113] Step S3, as the core link of the entire monitoring scheme, converts the preprocessed vibration signal into a set of feature parameters that can fully characterize the mechanical properties of the joint. This provides a high-quality data basis for the subsequent performance evaluation index calculation, ensuring that the evaluation results have higher credibility and interpretability. At the same time, the feature extraction means of this step lays the necessary technical foundation for the system to realize automated and intelligent joint state evaluation, thereby further improving the efficiency and accuracy of joint deterioration monitoring.

[0114] S4: Based on the vibration frequency feature parameters, vibration attenuation feature parameters, and static force parameters, determine the joint performance evaluation index, compare the joint performance evaluation index with the preset evaluation threshold, based on the comparison result, determine the deterioration level of the monitored track joint, and trigger the corresponding warning signal, the warning signal contains the deterioration level of the monitored track joint and the location information of the joint;

[0115] In this embodiment, based on the vibration frequency feature parameters, vibration attenuation feature parameters, and static force parameters after dimensionless processing, the joint performance evaluation index is determined, and the formula is as follows:

[0116] ;

[0117] In the formula, is the joint performance evaluation index, which is used to reflect the deterioration degree of the performance of the monitored ballastless track joint; is the signal attenuation rate, is the signal attenuation rate reference value; is the frequency shift; , and is a preset weight, ， ， ， and 、 、 is determined according to the analytic hierarchy process; is a static parameter, is an index of the static parameter, respectively correspond to temperature, pressure and pre-tightening force, is an ideal value corresponding to the static parameter.

[0118] The above formula sets the weight based on the engineering judgment of the main causes of deterioration of the ballastless track joint. The maximum weight is allocated to the frequency offset , because the stiffness degradation is the most direct and core representation of the joint structural deterioration, and has the most significant impact on driving safety. The weight of the signal attenuation term is second, because it can effectively reflect the internal damage of the material and the change of the damping characteristic, which is an important supplement to the stiffness degradation. The total weight of the static parameter is relatively low, because the environmental load factors such as temperature and pressure have large fluctuations and are usually a slow change process. Although the individual abnormality needs to be concerned, it usually does not immediately cause serious structural safety problems like the sudden change of dynamic parameters. This weight distribution embodies the comprehensive evaluation concept of “giving priority to dynamic parameters reflecting the internal state of the structure, and supplementing environmental and load state parameters”, which ensures the sensitivity of the monitoring system to the core structural diseases.

[0119] In the above formula, the dependent variable is used to comprehensively quantify the overall performance degradation of the ballastless track joint. Its technical significance lies in the fusion of the dynamic characteristics (stiffness and damping) and the static state (temperature, pressure, pre-tightening force) of the joint. By mathematical modeling, multiple heterogeneous parameters are normalized into a single evaluation index, thereby realizing quantitative evaluation and graded early warning of the joint health condition. The greater the value, the more serious the performance degradation of the joint, which provides clear and operable basis for maintenance decision-making.

[0120] The independent variables in the formula include the vibration frequency characteristic parameter , the vibration attenuation characteristic parameter , and the static parameter deviation term . The correlation between these independent variables and the dependent variable results from their direct association with the core performance of the joint: reflects the stiffness degradation of the joint, Reflecting the damping performance degradation, while the static parameter deviation term reflects temperature stress anomaly, load transfer ability decline, constraint failure respectively. The independent variables influence through their respective weights , together constitute the multi-dimensional evidence chain of joint degradation, ensuring can respond to the whole process of joint from slight damage to serious degradation.

[0121] Increase, elevation, static parameter deviation expansion (i.e. temperature, pressure, pre-tightening force deviate from the ideal state) will lead to value rise, indicating that the joint performance degradation intensifies. The square term in the formula strengthens the contribution of significant deviation, while the logarithmic function avoids the sensitivity of linear growth, so that can respond to changes sensitively and maintain numerical stability.

[0122] The formula has obvious form rationality, and its structure design fully considers the practicability of multi-physical quantity fusion and engineering application. The main body of the formula consists of two parts: the first part is the linear combination of frequency deviation and signal attenuation rate deviation, which is effectively fused with the dynamic characteristics parameters of the joint. Nonlinear transformation not only ensures the smoothness of the output value, but also amplifies the sensitivity in the small signal change area; the second part adopts the square sum form of the relative deviation of static parameters, which significantly increases the weight of abnormal value in the comprehensive evaluation, and plays a role in strengthening the early warning. The two parts are organically combined by weighted summation, and the overall function is continuous, derivable and monotonically increasing, which ensures that there is a clear and interpretable positive correlation between the input parameters and the joint performance evaluation index, which meets the intuitive physical meaning of "the more serious the degradation, the higher the index value", and provides a reliable mathematical basis for engineering decision-making.

[0123] Table 1: Joint performance evaluation index statistical table

[0124]

[0125] Please refer to Figures 3-4 , it should be noted that the frequency deviation, signal attenuation rate, temperature, pressure, pre-tightening force, joint performance evaluation index in the above table 1 correspond to , , , , , in the above formula respectively;

[0126] Through comprehensive analysis of the simulation data, it can be clearly observed that there is a significant positive correlation between the joint performance evaluation index and the monitoring parameters. As the frequency offset, signal decay rate deviation, and the degree of deviation of each static force parameter from its reference value increase, the SPEI value presents a clear upward trend. This indicates that the structural stiffness, damping characteristics of the joint, and its mechanical environment state jointly determine the degree of deterioration of its overall performance. The data clearly shows the continuous change process of the joint state from normal, slight deterioration to moderate and severe deterioration.

[0127] The contribution of each parameter to the SPEI value is not a simple linear superposition, but is fused through a specific nonlinear function. Among them, the frequency offset and signal decay rate constitute the basis of the evaluation, while the static force parameters serve as important correction terms, further reflecting the additional impact of environmental load and long-term stress state abnormalities on joint performance. This comprehensive evaluation method can more comprehensively capture the performance state of the joint under the action of multiple factors, avoiding the limitations of single index criteria.

[0128] The overall data trend shows that the evaluation formula can effectively distinguish the joint states of different deterioration levels, with good sensitivity and monotonicity. The distribution of the SPEI value provides a reliable basis for setting multi-level warning thresholds, which can be used to achieve accurate grading warning from "normal" to "severe deterioration", providing quantitative support for preventive maintenance decisions of ballastless track.

[0129] The joint performance evaluation index is compared with the preset evaluation threshold to determine the deterioration level of the monitored track joint:

[0130] If , it is judged that the performance level of the monitored track joint is: normal;

[0131] If , it is judged that the performance level of the monitored track joint is: slight deterioration;

[0132] If , it is judged that the performance level of the monitored track joint is: moderate deterioration;

[0133] If , it is judged that the performance level of the monitored track joint is: severe deterioration;

[0134] In the formula, , and are the first evaluation threshold, the second evaluation threshold, and the third evaluation threshold, respectively, which are determined according to statistical analysis of historical normal data and deterioration data;

[0135] According to the above comparison method, the degradation level of the monitored track joint is determined, and a corresponding early warning signal is triggered, which includes the degradation level of the monitored track joint and the location information of the joint.

[0136] Step S4 establishes a joint performance evaluation index by integrating the vibration frequency characteristic parameter, the vibration attenuation characteristic parameter and the static force parameter, and compares it with a preset evaluation threshold to determine the degradation level. The advantage of this step is that it can quantitatively integrate multi-dimensional parameters to provide a comprehensive evaluation of the joint performance, and through the division of degradation levels by a clear evaluation threshold, it outputs intuitive and operable results, while triggering an early warning signal for feedback of the joint health status and location information. This method is comprehensive and accurate, facilitating actual maintenance and decision-making.

[0137] Compared with the prior art, step S4 integrates vibration frequency, attenuation characteristics and static force parameters through dimensionless processing and weight allocation, overcoming the limitations of traditional methods that rely on a single parameter, significantly improving the accuracy and reliability of the evaluation. In addition, the prior art usually lacks detailed classification of degradation levels, while this step accurately defines multiple evaluation thresholds to determine different degradation levels, thereby achieving graded diagnosis and efficient early warning of the joint state, with stronger practicality and operability.

[0138] In this scheme, step S4 is the core link for realizing the evaluation of the track joint state. It generates a clear and quantitative evaluation result by comprehensively analyzing the feature parameters and static force parameters extracted in the previous steps, providing a scientific basis for the judgment of the degradation state, maintenance decision-making and risk warning. At the same time, the output of the degradation level and the early warning signal makes the entire monitoring scheme more instructive and practical, significantly improving the intelligent level and on-site application effect of track joint monitoring.

[0139] Please refer to Figure 2 A ballastless track joint performance degradation monitoring system, comprising:

[0140] A data acquisition module for exciting the ballastless track plate at the monitored ballastless track joint by knocking it with a force hammer, collecting the vertical vibration acceleration response signal of the joint caused by the excitation using an acceleration sensor fixedly installed on the corresponding base structure of the joint, recording the knocking time, and obtaining a vertical vibration acceleration signal segment associated with the joint; simultaneously collecting static force parameters of the joint, including temperature, pressure and pre-tightening force;

[0141] A data processing module for preprocessing the vertical vibration acceleration signal segment to remove abnormal pulse signals and constant baseline drift in the data, obtaining a joint vibration event sample; the abnormal pulse signal is a transient signal exceeding the preset vibration amplitude range, and the constant baseline drift is a fixed offset that exists continuously in the data;

[0142] a vibration feature extraction module configured to extract features from the joint vibration event samples to obtain a feature parameter set for characterizing the mechanical performance of the track joint, the feature parameter set including a vibration frequency feature parameter reflecting joint stiffness degradation and a vibration decay feature parameter reflecting joint damping;

[0143] a joint performance evaluation module configured to determine a joint performance evaluation index based on the vibration frequency feature parameter, the vibration decay feature parameter and the static force parameter, compare the joint performance evaluation index with a preset evaluation threshold, determine a degradation level of the monitored track joint based on a comparison result, and trigger a corresponding early warning signal, the early warning signal including the degradation level of the monitored track joint and location information of the joint.

[0144] The above formulas are all dimensionless numerical calculations, and the formulas are obtained by software simulation of a large amount of data to obtain a formula of the most recent real situation, and the preset parameters in the formula are set by a person skilled in the art according to the actual situation.

[0145] The above embodiments can be realized wholly or partially by software, hardware, firmware or any combination thereof. When realized by software, the above embodiments can be realized in the form of a computer program product wholly or partially. Those skilled in the art can realize that the units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized by hardware or software methods depends on the specific application and design constraints of the technical solutions.

[0146] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, which can be located in one place or distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0147] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A method of monitoring the performance deterioration of a ballastless track joint, characterized in that, The specific steps include: S1: By knocking the ballastless track slab at the joint to be monitored to generate an excitation, using an acceleration sensor fixedly installed on the base structure corresponding to the joint, collecting the vertical vibration acceleration response signal caused by the excitation, recording the time of knocking, and obtaining a vertical vibration acceleration signal segment associated with the joint; simultaneously collecting the static force parameters at the joint, including temperature, pressure and pretightening force; S2: Preprocessing the vertical vibration acceleration signal segment to remove abnormal pulse signals and constant baseline drift in the data, and obtaining a joint vibration event sample; the abnormal pulse signal is a transient signal exceeding the preset vibration amplitude range, and the constant baseline drift is a fixed offset continuously existing in the data; S3: Feature extraction is performed on the joint vibration event sample to obtain a feature parameter set for characterizing the mechanical properties of the track joint, the feature parameter set including a vibration frequency feature parameter reflecting joint stiffness degradation and a vibration attenuation feature parameter reflecting joint damping; S4: Based on the vibration frequency feature parameter, the vibration attenuation feature parameter and the static force parameter, a joint performance evaluation index is determined, the joint performance evaluation index is compared with a preset evaluation threshold, based on the comparison result, the degradation level of the track joint to be monitored is determined, and a corresponding warning signal is triggered, the warning signal including the degradation level of the track joint to be monitored and the position information of the joint.

2. The method for monitoring the performance deterioration of a ballastless track joint according to claim 1, characterized in that: In S1, the base structure includes: a track slab bearing platform, a trackside cable trough inner wall or a box girder top; For longitudinal joints between track slabs, the acceleration sensor is fixed to the side of the track slab bearing platform on both sides of the joint, 0.3-0.5m away from the edge of the joint; for transverse joints, the sensor is installed on the inner wall of the trackside cable trough near the joint or the top of the box girder directly below the joint; the sensor is connected to the base structure through a stainless steel bracket; The temperature sensor, pressure sensor and pretightening force sensor are pre-buried in the joint or tension lock during the track slab width joint treatment construction, respectively used for collecting temperature, pressure and pretightening force data at the joint; A standard hammer with a force sensor on the hammer head is used to vertically knock the ballastless track slab at 1-2 fastener spacings closest to the joint to be monitored, the force sensor is used to monitor the knocking force in real time, and the feedback device is used to ensure that the peak impact force of a single knock is stable within the preset rated range, so as to generate a standard excitation with consistent energy; at the same time, an acceleration sensor is used to collect the vibration response at the joint to be monitored in real time, and a fixed time length of signal is continuously recorded at a sampling frequency of no less than 10kHz, so as to ensure that the whole process waveform from the beginning of the excitation, vibration transmission to complete vibration attenuation is completely captured, and finally a complete vertical vibration acceleration signal segment strictly corresponding to this standard knocking excitation is obtained, and the static force parameters at the joint are simultaneously collected, including temperature, pressure and pretightening force.

3. The method for monitoring the performance deterioration of a ballastless track joint according to claim 2, characterized in that: The abnormal pulse signal identification is performed on the vertical vibration acceleration signal segment, a preset vibration amplitude range is set, a point-by-point traversal method is used to scan the vertical vibration acceleration signal segment, when it is detected that the amplitude of a signal point exceeds the preset vibration amplitude range, it is determined that the signal point and adjacent signal points which are continuous with the signal point and have amplitudes exceeding the range constitute an abnormal pulse signal; For the identified abnormal pulse signals, an interpolation completion method is used for processing, using the closest pulse signal to the abnormal pulse signal. Based on the mean of normal signal points, the complete data corresponding to the abnormal pulse signal is calculated by linear interpolation and replaced with the original abnormal pulse signal data. The constant baseline drift identification is performed on the vertical vibration acceleration signal after the abnormal pulse signal is removed, a smooth section without obvious vibration fluctuation in the signal is selected, the mean value of all signal points in the smooth section is calculated, and the mean value is taken as the constant baseline drift amount; the constant baseline drift is removed by subtracting the constant baseline drift amount from the value of each signal point in the entire vertical vibration acceleration signal segment, and a joint vibration event sample is obtained; The determination method of the smooth section is that the complete vertical vibration acceleration signal segment is divided into a plurality of equal-length time sub-sections, and the standard deviation of the vibration signal amplitude of each time sub-section is calculated according to the following formula: ； In the formula, Indicates the first The standard deviation of the vibration signal amplitude for each time segment is used to quantify the degree of fluctuation in the signal amplitude within that segment. Index for the time segment; This indicates the total number of data points contained within a time segment. For the index of the data points, This represents the arithmetic mean of the vibration signal amplitudes at all data points within a time interval. Indicates the first vibration signal amplitude at each data point All time sub-sections are traversed, and the first 5% of the time sub-sections with the smallest standard deviation are selected as the smooth section without obvious vibration fluctuation; The preset vibration amplitude range is determined based on the amplitude statistical result of the historical vertical vibration acceleration signal under the normal state of the operating line ballastless track.

4. The method for monitoring the performance deterioration of a ballastless track joint according to claim 1, characterized in that: The specific execution process of S3 is as follows: The time sample of joint vibration is analyzed in frequency domain by Fourier transform, and the frequency domain signal is obtained The formula is as follows: ； wherein is the joint vibration time sample, which is a time series signal; is the frequency; is the imaginary unit; is the mathematical constant pi; is the time variable; is the mathematical constant e. Frequency domain signal The power spectral density is calculated as follows: ； In the formula, is the power spectral density corresponding to the th frequency component, used to reflect the vibration energy distribution of the frequency component, is the index of the frequency component; represents the th frequency domain component after Fourier transform; is the fixed sampling frequency of the acceleration sensor; is the total number of points of the joint vibration time sample, obtained by counting the number of signal points in the sample; In the power spectral density curve , the frequency component that makes the value maximum is identified and extracted , , that is, the main peak frequency, is used to directly reflect the joint stiffness characteristics: when the joint stiffness decreases, , it will shift to low frequency direction; the frequency shift is defined as the vibration frequency characteristic parameter, and its calculation formula is as follows: ； In the formula, is a frequency offset, used to quantify the degree of joint stiffness degradation; is a reference main peak frequency in the preset joint performance reference parameter set, determined according to historical data statistics under a normal state of the line.

5. The method for monitoring the performance deterioration of a ballastless track joint according to claim 4, characterized in that: The attenuation characteristics of the joint vibration event sample are analyzed by using a time domain analysis method, and the damping variation characteristics of the track joint are extracted, and the specific steps are as follows: Extracting a vibration envelope of a joint vibration event sample using a Hilbert transform : ； wherein is the vibration envelope, used to characterize the trend of the signal vibration amplitude over time; is the joint vibration time sample, is the Hilbert transform of is the mathematical constant pi; denotes the value of the joint vibration time sample at time , is the integration variable; to the vibration envelope An exponential fit is performed to obtain a signal decay rate and the signal decay rate is defined as a vibration decay characteristic parameter; The formula for calculation is as follows: ； wherein is the initial amplitude, is the signal decay rate, used to characterize the change in joint damping performance; is the system natural frequency; is the time variable; The frequency offset amount And signal attenuation rate Integration, constitute a set of characteristic parameters for characterization of track joint mechanical properties.

6. The method for monitoring the performance deterioration of a ballastless track joint according to claim 5, characterized in that: Based on the dimensionless vibration frequency characteristic parameter, the vibration attenuation characteristic parameter and the static force parameter, a joint performance evaluation index is determined, and the formula is as follows: ； In the formula, is a joint performance evaluation index, used to reflect the degree of deterioration of the joint performance of the monitored ballastless track; is a signal attenuation rate, is a signal attenuation rate reference value; is a frequency offset amount; , and are preset weights; is a static force parameter, is an index of the static force parameter, respectively correspond to temperature, pressure and pre-tightening force, is an ideal value corresponding to the static force parameter.

7. The method for monitoring the performance deterioration of a ballastless track joint according to claim 6, characterized in that: said joint performance evaluation index comparing the joint performance evaluation index with a pre-set evaluation threshold, determining a deterioration level of the track joint to be monitored: If then the track joint performance level to be monitored is determined to be: normal; If then the track joint performance level to be monitored is determined to be: slight deterioration; If then the performance level of the track joint to be monitored is determined to be: moderate deterioration; If then the performance level of the track joint to be monitored is determined to be: severe deterioration; In the formula, , and are respectively preset first evaluation threshold, second evaluation threshold and third evaluation threshold, which are determined according to statistical analysis of historical normal data and degradation data. According to the above comparison method, the degradation level of the monitored track joint is determined, and a corresponding early warning signal is triggered, and the early warning signal includes the degradation level of the monitored track joint and the position information of the joint.

8. A system for monitoring performance degradation of a ballastless track joint, the system comprising: The ballastless track joint performance degradation monitoring system is used to execute the ballastless track joint performance degradation monitoring method of any one of claims 1-7, and includes: The data acquisition module is used to generate an excitation by knocking the ballastless track at the monitored ballastless track joint by using a force hammer, collect the vertical vibration acceleration response signal of the joint caused by the excitation by using an acceleration sensor fixedly installed on the base structure corresponding to the joint, record the knocking time, and obtain a vertical vibration acceleration signal segment associated with the joint; and simultaneously collect the static force parameters of the joint, including temperature, pressure and pre-tightening force; The data processing module is used to pre-process the vertical vibration acceleration signal segment, remove the abnormal pulse signal and the constant baseline drift in the data, and obtain a joint vibration event sample; the abnormal pulse signal is a transient signal exceeding the preset vibration amplitude range, and the constant baseline drift is a fixed offset existing in the data; The vibration characteristic extraction module is used to extract the characteristic parameters set for reflecting the mechanical performance of the track joint from the joint vibration event sample, and the characteristic parameters set includes a vibration frequency characteristic parameter reflecting the stiffness degradation of the joint and a vibration attenuation characteristic parameter reflecting the damping of the joint. The joint performance evaluation module determines a joint performance evaluation index based on the vibration frequency characteristic parameter, the vibration attenuation characteristic parameter and the static force parameter, compares the joint performance evaluation index with a preset evaluation threshold, determines a deterioration level of the to-be-monitored track joint based on a comparison result, and triggers a corresponding early warning signal, wherein the early warning signal includes the deterioration level of the to-be-monitored track joint and position information of the joint.

Images