Reinforced steel ring vibration data monitoring method and system for subway tunnel

Abstract

A reinforced steel ring vibration data monitoring method and system for a subway tunnel. The method comprises the steps of: acquiring a plurality of data points in a vibration data sequence of a reinforced steel ring, so as to obtain data values corresponding to the data points (S1); with any data point in the vibration data sequence serving as a target data point, in a preset local range of the target data point, acquiring the absolute value of a difference value between the data value and a fitted value of each data point, so as to determine a degree of noise manifestation of the target data point (S2); acquiring an average value of the degrees of noise manifestation of all the data points, and determining a bandwidth parameter of the vibration data sequence (S3); denoising the vibration data sequence by using the bandwidth parameter in a VMD algorithm, and processing the denoised vibration data sequence by means of spectral analysis, so as to obtain a vibration frequency and a vibration amplitude of the vibration data sequence (S4); and, on the basis of comparison results between the vibration frequency and a threshold value and between the vibration amplitude and a threshold value, obtaining a vibration data monitoring result of the reinforced steel ring (S5). Thus, the accuracy of vibration data monitoring results of reinforced steel rings can be effectively improved.

Description

A method and system for monitoring vibration data of reinforced steel rings used in subway tunnels Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for monitoring vibration data of reinforced steel rings used in subway tunnels. Background Technology

[0002] Urban rail transit, as a high-speed, high-capacity public transportation system, provides an effective solution to alleviate traffic congestion and insufficient carrying capacity in large cities. However, due to factors such as train operation and the load on the underground tunnel structure itself, the track structure may deform or crack during the operation period, posing significant safety hazards.

[0003] Currently, most methods for repairing subway tunnels involve installing reinforcing steel rings at cracked or leaking areas. For example, patent application CN117195420A discloses a design method, device, equipment, and storage medium for reinforcing steel rings in subway tunnels. This application obtains grayscale images of the tunnel lining structure, recorded defect data, and layout data of the steel ring to be designed for the lining structure. Based on the grayscale images and defect data, it determines the drilling avoidance points for the steel ring to be designed. Based on the drilling avoidance points and layout data, it designs the steel ring to be designed.

[0004] The existing solutions mentioned above mainly focus on improving the reinforcement effect, which to some extent helps ensure the normal use of the tunnel. However, once the reinforcement steel ring fails, the tunnel cracks will become more severe, and groundwater will also seep into the tunnel.

[0005] Therefore, how to accurately obtain the monitoring results of the reinforcing steel rings in subway tunnels is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0006] To address the aforementioned technical problem of how to accurately obtain monitoring results for the reinforcing steel rings in subway tunnels, this invention provides a method and system for monitoring vibration data of reinforcing steel rings in subway tunnels.

[0007] In a first aspect, the present invention provides a method for monitoring vibration data of reinforced steel rings used in subway tunnels, employing the following technical solution:

[0008] A plurality of data points in a vibration data sequence of the reinforced steel ring are acquired to obtain data values corresponding to each data point;Any data point is taken as a target data point, in a preset local range of the target data point, the fitting value of each data point is determined, the absolute value of the difference between the data value and the fitting value of each data point is obtained, the noise performance degree of the target data point is determined, and the noise performance degree is positively correlated with the absolute value of the difference;The average value of the noise performance degree of all data points in the vibration data sequence is obtained, the bandwidth parameter of the vibration data sequence is determined, and the bandwidth parameter is positively correlated with the average value of the noise performance degree;The vibration data sequence is denoised by using the bandwidth parameter in the VMD algorithm, the denoised vibration data sequence is processed by using spectrum analysis, the vibration frequency and the vibration amplitude of the vibration data sequence are obtained, and the vibration data monitoring result of the reinforced steel ring is obtained based on the comparison result of the vibration frequency and the vibration amplitude with the threshold value.

[0009] The present application considers that the monitoring of the reinforced steel ring plays an important role in the normal operation of urban rail transit, so that the monitoring result of the reinforced steel ring is obtained by processing the vibration data of the reinforced steel ring, and considering that there is noise interference in the environment of collecting vibration data, the vibration data sequence of the reinforced steel ring is processed by VMD algorithm, so that the interference of noise data on the monitoring result can be effectively reduced, and the monitoring result can be accurately obtained;In addition, the present application also considers that the fixed bandwidth noise in the VMD algorithm cannot present good denoising effect on all vibration data, based on this, the noise performance degree of the data points in the vibration data sequence in the preset local range is obtained, so that the bandwidth parameter of the vibration data sequence can be accurately obtained, so that the vibration data monitoring result of the reinforced steel ring can be accurately obtained based on the bandwidth parameter, and the accuracy of the obtained monitoring result is effectively improved.

[0010] According to the reinforced steel ring vibration data monitoring method for subway tunnel provided by the present application, the vibration data sequence of the reinforced steel ring in each dimension is obtained by collecting the vibration data of the reinforced steel ring in each dimension through the sensor and preprocessing the vibration data.

[0011] The present application considers that the vibration data change of the vibration data sequence in a single dimension may exist accidentally, so that the noise performance degree of the data points in the vibration data sequence is accurately obtained by analyzing the vibration data change rule of the vibration data sequence in multiple dimensions.

[0012] According to the method for monitoring vibration data of a reinforced steel ring of a subway tunnel provided in the application, the noise performance degree of the target data point is determined by determining the regularity of the target data point, wherein the regularity is negatively correlated with the absolute value of the difference between the data value and the fitting value of each data point in the preset local range of the target data point; and calculating the noise index of the target data point.

[0013] .

[0014] In the formula, Noise index of the target data point, Regularities of the target data point in other two dimensions, Regularities of the target data point in other two dimensions, Regularities of the target data point in other two dimensions, Pre-set hyperparameter, Variance function, Exponential function with e as base; and determining the noise performance degree of the target data point, wherein the noise performance degree is positively correlated with the noise index.

[0015] The application provides a calculation formula of the noise index of the target data point, and the accuracy of the noise performance degree of the target data point obtained based on the calculation formula can be effectively improved by combining data points in different dimensions.

[0016] According to the method for monitoring vibration data of a reinforced steel ring of a subway tunnel provided in the application, the regularity of the target data point satisfies the following relationship:

[0017] .

[0018] In the formula, Regularity of the target data point, Number of data points in the preset local range of the target data point, Fitting value of the jth data point in the preset local range, Data value of the jth data point in the preset local range, Exponential function with e as base, Absolute value symbol.

[0019] According to the method for monitoring vibration data of a reinforced steel ring of a subway tunnel provided in the application, the noise performance degree of the target data point is determined by determining the regularity of the target data point, wherein the regularity is negatively correlated with the absolute value of the difference between the data value and the fitting value of each data point in the preset local range of the target data point; and calculating the noise index of the target data point.

[0020] This invention takes into account the mixing of abnormal data and noise data generated by the reinforcing steel ring itself, and the fact that abnormal data will affect all sensors. Therefore, by analyzing the changes in the vibration data sequences of different sensors, abnormal data and noise data can be distinguished, and the noise performance of the data points can be accurately obtained.

[0021] According to the present invention, a method for monitoring vibration data of a reinforced steel ring for subway tunnels is provided, wherein the bandwidth parameter of the vibration data sequence satisfies the following relationship:

[0022] ;

[0023] In the formula, The bandwidth parameter represents the vibration data sequence. Indicates the reference bandwidth parameter. This indicates the number of data points in the vibration data sequence. Indicating the first vibration data sequence The noise level of each data point This represents an exponential function with base e. This indicates the floor function.

[0024] According to the present invention, a method for monitoring vibration data of reinforced steel rings for subway tunnels is provided. The method for denoising vibration data sequences using bandwidth parameters in the VMD algorithm includes: determining the number of decomposition layers of the VMD algorithm using the kurtosis principle; decomposing the vibration data sequence into multiple IMF components based on the number of decomposition layers and bandwidth parameters; removing the IMF components containing noisy data; and reconstructing the remaining IMF components to obtain the denoised vibration data sequence.

[0025] According to the present invention, a vibration data monitoring method for a reinforcing steel ring used in a subway tunnel is provided. The method for obtaining the vibration data monitoring result of the reinforcing steel ring based on the comparison result of the vibration frequency and vibration amplitude with a threshold includes: setting a preset threshold; if the vibration frequency and / or vibration amplitude is greater than the threshold, the vibration data monitoring result of the reinforcing steel ring is determined to be abnormal; if the vibration frequency and / or vibration amplitude is less than or equal to the threshold, the vibration data monitoring result of the reinforcing steel ring is determined to be normal.

[0026] According to the present invention, a vibration data monitoring method for a reinforced steel ring used in a subway tunnel is provided. After obtaining an abnormal vibration data monitoring result for the reinforced steel ring, the method further includes: determining the data point corresponding to the abnormal monitoring result, associating and marking the data point and the sensor corresponding to the data point, and then issuing an early warning.

[0027] This invention takes into account the significant safety hazards that may arise when the reinforced steel ring malfunctions. Therefore, by issuing early warnings to promptly alert staff to take appropriate action, the potential safety hazards during subway operation can be effectively reduced.

[0028] Secondly, the present invention provides a vibration data monitoring system for reinforced steel rings used in subway tunnels, employing the following technical solution:

[0029] A vibration data monitoring system for reinforced steel rings used in subway tunnels includes a processor and a memory. The memory stores computer program instructions, which, when executed by the processor, implement the aforementioned vibration data monitoring method for reinforced steel rings used in subway tunnels.

[0030] By adopting the above technical solution, a computer program is generated from the above-mentioned method for monitoring vibration data of reinforced steel rings for subway tunnels, and stored in a memory so that it can be loaded and executed by a processor. A terminal device can then be made based on the memory and processor for convenient use.

[0031] The present invention has the following technical effects:

[0032] Based on the above technical solution, when determining the monitoring results of the reinforced steel ring, this invention uses the VMD algorithm to process the vibration data sequence of the reinforced steel ring, which can effectively reduce the interference of noise data on the monitoring results and accurately obtain the monitoring results. In addition, this invention also considers that the fixed bandwidth parameter in the VMD algorithm cannot present a good denoising effect for all vibration data. Based on this, this invention obtains the bandwidth parameter of the vibration data sequence by acquiring the noise performance of data points in the vibration data sequence. Thus, the vibration data monitoring results of the reinforced steel ring can be accurately obtained based on the bandwidth parameter, effectively improving the accuracy of the obtained monitoring results. Attached Figure Description

[0033] The above and other objects, features, and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description taken in conjunction with the accompanying drawings. In the drawings, several embodiments of the invention are illustrated by way of example and not limitation, and like or corresponding reference numerals denote like or corresponding parts.

[0034] Figure 1 is a flowchart illustrating a method for monitoring vibration data of a reinforced steel ring used in subway tunnels, according to an embodiment of the present invention.

[0035] Figure 2 is a schematic diagram of the positional relationship between a reinforcing steel ring and a sensor provided in an embodiment of the present invention. Detailed Implementation

[0036] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0037] It should be understood that when the terms "first," "second," etc., are used in the claims, specification, and drawings of this invention, they are only used to distinguish different objects and not to describe a specific order. The terms "comprising" and "including" used in the specification and claims of this invention indicate the presence of the described features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or collections thereof.

[0038] It should be noted that if the reinforcing steel rings in a subway tunnel fail, the tunnel cracks will become more severe, and groundwater will seep into the tunnel, posing a significant safety hazard. Monitoring the vibration data of the reinforcing steel rings allows staff to obtain timely information on their status, effectively reducing safety risks. However, the collection of vibration data for the reinforcing steel rings is susceptible to interference from noise data. Noise data is mixed with normal data, affecting the accuracy of the monitoring results.

[0039] Based on this, this invention discloses a method for monitoring vibration data of a reinforced steel ring for subway tunnels. Please refer to Figure 1, which is a flowchart illustrating a method for monitoring vibration data of a reinforced steel ring for subway tunnels provided by this invention. The method includes the following steps S1-S5:

[0040] S1: Obtain multiple data points from the vibration data sequence of the reinforced steel ring and obtain the data value corresponding to each data point.

[0041] It should be noted that the vibration data collected from the reinforced steel ring is subject to interference from noise data, affecting the accuracy of the monitoring results. Therefore, Variational Mode Decomposition (VMD) algorithm can be used to denoise the vibration data to obtain the monitoring results for the reinforced steel ring. Furthermore, considering that the choice of bandwidth parameter plays a crucial role in the denoising effect in the VMD algorithm, for example, a smaller bandwidth parameter will produce higher resolution modal components, potentially leading to over-decomposition, i.e., producing too many modal components that may not be accurate; conversely, a larger bandwidth parameter will produce coarser modal components, resulting in the loss of certain data features and reducing the denoising effect.

[0042] Based on this, the embodiments of the present invention analyze the vibration data variation characteristics of the reinforced steel ring to adjust the bandwidth parameter, thereby obtaining the optimal decomposition result, and achieving accurate noise reduction based on the decomposition result.

[0043] For example, in an embodiment of the present invention, obtaining multiple data points in the vibration data sequence of the reinforced steel ring includes: acquiring vibration data of the reinforced steel ring in various dimensions through sensors, preprocessing the vibration data, and obtaining the vibration data sequence of the reinforced steel ring in various dimensions.

[0044] The dimensions can include the X-axis, Y-axis, and Z-axis.

[0045] For example, the sensor can be an accelerometer, vibration sensor, etc., and the specific configuration can be determined according to actual needs. The accelerometer detects changes in acceleration caused by vibration, and the vibration data acquired by the accelerometer is acceleration in three dimensions: X-axis, Y-axis, and Z-axis. When the accelerometer acquires vibration data in the X, Y, and Z axes, the acceleration data on each axis can be independently analyzed to obtain the vibration frequency and amplitude on that axis.

[0046] Specifically, the reinforcing steel rings are kept horizontal during installation to avoid causing unnecessary stress to the tunnel structure or affecting the normal operation of the tunnel. According to design requirements and structural mechanics needs, the reinforcing steel rings are installed at equal intervals on the track to ensure that the structure can withstand uniform pressure and mechanical loads in the underground environment and during subway operation. Sensors are installed on each reinforcing steel ring, as shown in Figure 2. Figure 2 is a schematic diagram of the positional relationship between the reinforcing steel rings and sensors according to an embodiment of the present invention. The sensor is shown in Figure 2. As can be seen from the figure, the horizontal line of the reinforcing steel ring is parallel or nearly parallel to the rail surface. By deploying sensors on the upper, left, and right sides of the reinforcing steel ring and setting the acquisition frequency according to actual needs, the monitoring blind zone can be reduced, ensuring that any abnormal vibrations of the tunnel structure can be captured in a timely manner. Furthermore, when abnormal vibrations are detected, the vibration source can be located more accurately by combining the data from sensors at different locations, providing guidance for subsequent maintenance and reinforcement work.

[0047] It is understandable that, since the same sensor uses the same sampling frequency, the number of data points in the vibration data sequences across the three dimensions is the same. That is, at the same sampling time, the data points in the vibration data sequences along the X, Y, and Z axes correspond one-to-one. To facilitate subsequent data processing, the sampling frequencies of each sensor can be the same. The final data value corresponding to each data point is the data value collected by the sensor, such as the acceleration value collected by an accelerometer.

[0048] Based on the above steps, the vibration data sequence of the reinforced steel ring is obtained. After the data is prepared, the vibration data sequence can be processed according to the following steps.

[0049] S2: Take any data point as the target data point, determine the fitted value of each data point within the preset local range of the target data point, obtain the absolute value of the difference between the data value and the fitted value of each data point, and determine the noise performance of the target data point.

[0050] It should be noted that the environment in subway tunnels is complex, and vibration data are affected by noise differently at different times. The VMD algorithm uses a fixed bandwidth parameter for decomposition, resulting in varying denoising effects for different vibration data. The bandwidth parameter is strongly correlated with the noise level of the vibration data. If the noise level is high, a larger bandwidth parameter is needed to reduce the algorithm's sensitivity to noise; conversely, if the noise level is low, a smaller bandwidth parameter is needed for more precise data decomposition. Therefore, this embodiment of the invention analyzes the data variation characteristics of data points within a preset local range to obtain their noise level, thereby accurately determining the bandwidth parameter.

[0051] For example, when determining the noise level of a target data point, one can first determine the regularity of the target data point. The regularity of the target data point is negatively correlated with the absolute value of the difference between the data value and the fitted value of each data point in the preset local range of the target data point. Then, calculate the noise index of the target data point and determine the noise level of the target data point. The noise level is positively correlated with the noise index.

[0052] The preset local range can be set to 21, which represents the number of data points contained within it. This value can be adjusted according to actual needs. When acquiring the preset local range of a target data point, data points can be equally distributed on both sides of the target data point. The target data point and the data points on both sides together constitute the preset local range of the target data point. If the number of data points on one side is insufficient, they are discarded. This method comprehensively considers the changes in vibration data before and after the target data point, accurately revealing the regularity of the data points.

[0053] When sensors collect data in subway tunnels, noise may occur, which may alter the originally regular vibration data. Based on this, the degree of noise performance of the data points can be obtained by utilizing the regularity of vibration data changes within a local area. The worse the regularity, the higher the degree of noise performance.

[0054] Specifically, to determine the regularity of target data points, the least squares method can be used within a preset local range of the target data points. A curve is fitted with the data collection time corresponding to each data point as the x-axis and the data value corresponding to the data point as the y-axis to obtain the fitted value for each data point. The absolute value of the difference between the data value and the fitted value is the fitting error for that data point. The more regular the data changes, the better the curve fitting effect and the lower the fitting error. By obtaining the mean of the fitting errors of all data points within the preset local range, the regularity of the target data points can be reflected. The larger the fitting error, the worse the regularity of the data points. For details on determining the regularity of target data points, please refer to the following formula:

[0055] ;

[0056] In the formula, This indicates the regularity of the target data points. This indicates the number of data points within a preset local range of the target data points. This represents the fitted value of the j-th data point within a preset local range. This represents the data value of the j-th data point within a preset local range. This represents an exponential function with base e. Represents the absolute value symbol.

[0057] Furthermore, for the same sensor, if it is subject to noise interference, the data values ​​in all three dimensions of the sensor will be affected by the noise, and the regularity of the target data points in a single dimension is random. Based on this, after obtaining the regularity of the data points using the above method, the consistency of the data points' noise interference across the three dimensions can be used as the reliability of the data point regularity, thereby obtaining the noise index of the data points. The consistency of the data points' noise interference across the three dimensions can be reflected by the variance of the regularity of the data points across the three dimensions; the smaller the variance of the regularity, the better the consistency of the data points' noise interference. The calculation of the noise index of the target data points can be specifically referred to in the following formula:

[0058] ;

[0059] In the formula, A noise index representing the target data point. This indicates the regularity of the target data points. , These represent the regularity of the data points corresponding to the target data points in the other two dimensions. This indicates the preset hyperparameters. This indicates the calculation of the variance function. This represents an exponential function with base e.

[0060] In the above formula, the hyperparameters are preset. It can be 0.01, and the specific value can be set according to actual needs; This represents the variance of the regularity of the dataset consisting of the target data point and its corresponding data points in the other two dimensions. It can be understood that if the target data point is on the X-axis, then its corresponding data points in the other two dimensions are the data points on the Y-axis and Z-axis that were sampled at the same time as the target data point.

[0061] It should be noted that while abnormalities in the reinforcing steel rings of subway tunnels can cause irregular variations in vibration data within a localized area, when the reinforcing steel ring itself malfunctions, the data collected by multiple sensors on that ring will be affected, not just the data from a single sensor. Therefore, to avoid misinterpreting such abnormal data values ​​as noise data, the noise index can be corrected by analyzing the patterns between different sensors, thus accurately determining the noise level of the data points.

[0062] For example, in an embodiment of the present invention, when determining the noise performance level of a target data point, other data points corresponding to the target data point can be obtained from the vibration data sequences of all sensors on the reinforced steel ring in each dimension. The product of the variance of the regularity between the target data point and other data points and the noise index is used as the noise performance level of the target data point. The noise performance level is positively correlated with the absolute value of the difference between the data value and the fitted value of each data point.

[0063] It is understandable that three sensors are installed on the reinforcing steel ring, each with vibration data sequences in three dimensions. Therefore, at the same sampling time, there are nine data points corresponding to all sensors. The variance of the regularity among these nine data points is used as the consistency of the regularity among the sensors. The smaller the variance, the higher the consistency, the higher the probability that the target data point is an anomaly, and the lower the probability that it is noisy data. The corresponding target data point exhibits a lower degree of noise. In other words, the variance is positively correlated with the degree of noise of the target data point.

[0064] Based on the above steps, the noise level of the data points in the vibration data sequence of each sensor in each dimension can be obtained. By measuring the noise level of the data points in the vibration data sequence, the bandwidth parameter of the vibration data sequence can be accurately obtained.

[0065] S3: Obtain the mean noise level of all data points in the vibration data sequence and determine the bandwidth parameter of the vibration data sequence.

[0066] It should be noted that after obtaining the noise level of all data points in the vibration data sequence, the noise level of the vibration data sequence can be represented by the mean of the noise level of all data points. Thus, the bandwidth parameter of the vibration data sequence can be obtained based on the noise level of the vibration data sequence, and the bandwidth parameter of the vibration data sequence is positively correlated with the mean of the noise level.

[0067] For example, in an embodiment of the present invention, the bandwidth parameter of the vibration data sequence is determined, and the specific relationship can be found in the following formula:

[0068] ;

[0069] In the formula, The bandwidth parameter represents the vibration data sequence. Indicates the reference bandwidth parameter. This indicates the number of data points in the vibration data sequence. Indicating the first vibration data sequence The noise level of each data point This represents an exponential function with base e. This indicates the floor function.

[0070] In the above formula, This represents the average noise level of all data points in the vibration data sequence. The larger the value, the higher the overall noise level in the vibration data sequence. To obtain accurate decomposition results, the bandwidth parameter needs to be increased.

[0071] The base bandwidth parameter can be 800, and can be set according to actual needs.

[0072] Based on the above steps, the bandwidth parameters of each vibration data sequence of the reinforced steel ring can be obtained, thus enabling accurate noise reduction based on the bandwidth parameters of the vibration data sequence.

[0073] S4: In the VMD algorithm, the bandwidth parameter is used to denoise the vibration data sequence. The denoised vibration data sequence is then processed using spectrum analysis to obtain the vibration frequency and vibration amplitude of the vibration data sequence.

[0074] It should be noted that using the bandwidth parameter obtained from the above steps to denoise the vibration data sequence in the VMD algorithm ensures that the VMD algorithm focuses more on the noise component during the decomposition process, thus more effectively separating it from the original signal. At the same time, due to the accuracy of the bandwidth parameter, the denoised vibration data sequence can better retain the effective information in the original data and reduce signal distortion. In addition, by accurately setting the bandwidth parameter, the VMD algorithm can converge to the optimal solution faster, thereby reducing the number of iterations and computation time, and effectively improving the efficiency of data processing.

[0075] For example, in an embodiment of the present invention, when using the bandwidth parameter in the VMD algorithm to denoise a vibration data sequence, the method includes: determining the number of decomposition layers of the VMD algorithm using the kurtosis principle; decomposing the vibration data sequence into multiple intrinsic mode functions (IMFs) based on the number of decomposition layers and the bandwidth parameter; removing the IMF components containing noisy data; and reconstructing the remaining IMF components to obtain the denoised vibration data sequence.

[0076] When determining the number of decomposition levels for the VMD algorithm using the kurtosis principle, a kurtosis value can be calculated for each IMF component. A larger kurtosis value indicates more outliers in that IMF component. The trend of kurtosis value changing with the number of decomposition levels is observed. Generally, as the number of decomposition levels increases, the kurtosis value first increases and then decreases. Based on the trend of kurtosis value change, the decomposition level at which the kurtosis value reaches its maximum or near maximum is selected as the optimal decomposition level. At this point, the decomposed IMF components can better reflect the main features of the signal, while avoiding spurious components caused by over-decomposition.

[0077] It should be further noted that the specific steps for determining the number of decomposition layers in the VMD algorithm using the kurtosis principle are existing technologies, and will not be elaborated upon in this embodiment of the invention. Similarly, using bandwidth parameters and the number of decomposition layers in the VMD algorithm to obtain the denoised vibration data sequence is also existing technology, and will not be elaborated upon in this embodiment of the invention. Spectral analysis is used to process the denoised vibration data sequence to obtain the vibration frequency and amplitude, which can be achieved using Fast Fourier Transform in Python, and will not be elaborated upon in detail here.

[0078] In this way, by denoising the vibration data sequence with precise bandwidth parameters, the interference of noise on the monitoring results can be effectively avoided, thereby effectively improving the accuracy of the monitoring results obtained based on this.

[0079] After obtaining the vibration frequency and vibration amplitude of the denoised vibration data sequence based on the above steps, the monitoring results of the reinforced steel ring can be obtained based on the threshold comparison results of the vibration frequency and vibration amplitude.

[0080] S5: Based on the comparison results of vibration frequency and vibration amplitude with the threshold, the vibration data monitoring results of the reinforced steel ring are obtained.

[0081] It should be noted that the vibration frequency reflects the characteristics of the vibration system itself, and the vibration amplitude reflects the intensity of the vibration. By obtaining the vibration data monitoring results of the reinforced steel ring based on the vibration frequency and vibration amplitude of the denoised vibration data sequence, the state of the reinforced steel ring can be accurately obtained, the interference of noise on the monitoring results can be avoided, and the accuracy of the monitoring results can be effectively improved.

[0082] For example, in an embodiment of the present invention, the vibration data monitoring result of the reinforced steel ring is obtained based on the comparison result of the vibration frequency and vibration amplitude with a threshold, including: a preset threshold; if the vibration frequency and / or vibration amplitude is greater than the threshold, the vibration data monitoring result of the reinforced steel ring is abnormal; if the vibration frequency and / or vibration amplitude is less than or equal to the threshold, the vibration data monitoring result of the reinforced steel ring is normal.

[0083] The threshold for vibration frequency can be 3 Hz, and the threshold for vibration amplitude can be... The threshold values ​​for vibration frequency and vibration amplitude can be set according to actual needs.

[0084] It should be further clarified that, considering the importance of subway tunnel safety, if either the vibration frequency or vibration amplitude exceeds a threshold, the vibration data monitoring result of the reinforced steel ring can be considered abnormal. An anomaly in any vibration data sequence across the three dimensions of the sensor can also be considered an anomaly in the vibration data monitoring result of the reinforced steel ring. Finally, an anomaly in any of the three sensors can also be considered an anomaly in the vibration data monitoring result of the reinforced steel ring.

[0085] After obtaining the vibration data monitoring results of the reinforced steel ring based on the above method, early warnings can be issued in a timely manner to remind staff to take action.

[0086] For example, in an embodiment of the present invention, after obtaining an abnormal vibration data monitoring result for the reinforced steel ring, the method further includes: determining the data point corresponding to the abnormal monitoring result, associating and marking the data point and the sensor corresponding to the data point, and then issuing an early warning.

[0087] For example, after obtaining the vibration data monitoring results of the reinforced steel ring, inspection reports can be generated periodically, and the monitoring data can be summarized and analyzed to determine whether the reinforced steel ring needs to be repaired or otherwise treated.

[0088] In this way, early warning can effectively reduce safety hazards.

[0089] As can be seen, in this embodiment of the invention, when determining the monitoring results of the reinforced steel ring, multiple data points in the vibration data sequence of the reinforced steel ring can be obtained to obtain the data value corresponding to each data point; any data point is taken as the target data point, and the fitted value of each data point is determined within a preset local range of the target data point. The absolute value of the difference between the data value and the fitted value of each data point is obtained to determine the noise performance level of the target data point, and the noise performance level is positively correlated with the absolute value of the difference; the mean of the noise performance level of all data points in the vibration data sequence is obtained to determine the bandwidth parameter of the vibration data sequence, and the bandwidth parameter is positively correlated with the mean of the noise performance level; the bandwidth parameter is used to denoise the vibration data sequence in the VMD algorithm, and the denoised vibration data sequence is processed by spectrum analysis to obtain the vibration frequency and vibration amplitude of the vibration data sequence; based on the comparison results of the vibration frequency and vibration amplitude with the threshold, the vibration data monitoring results of the reinforced steel ring are obtained.

[0090] Thus, this embodiment of the invention considers that the monitoring of reinforced steel rings plays an important role in the normal operation of urban rail transit. Therefore, by processing the vibration data of the reinforced steel rings, the monitoring results of the reinforced steel rings are obtained. Considering the existence of noise interference in the environment where the vibration data is collected, this embodiment of the invention uses the VMD algorithm to process the vibration data sequence of the reinforced steel rings, which can effectively reduce the interference of noise data on the monitoring results and accurately obtain the monitoring results. In addition, this embodiment of the invention also considers that the fixed bandwidth noise in the VMD algorithm cannot present a good denoising effect for all vibration data. Based on this, this embodiment of the invention obtains the noise performance of data points in the vibration data sequence within a preset local range, which can accurately obtain the bandwidth parameter of the vibration data sequence. Therefore, the monitoring results of the vibration data of the reinforced steel rings can be accurately obtained based on the bandwidth parameter, effectively improving the accuracy of the obtained monitoring results.

[0091] This invention also discloses a vibration data monitoring system for reinforced steel rings used in subway tunnels, including a processor and a memory. The memory stores computer program instructions, which, when executed by the processor, implement a vibration data monitoring method for reinforced steel rings used in subway tunnels according to the present invention.

[0092] The system also includes other components well known to those skilled in the art, such as communication buses and communication interfaces, the settings and functions of which are known in the art and will not be described in detail here.

[0093] In this invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used or combined with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc., or any other medium that can be used to store desired information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible to or connected to a device.

[0094] While this specification has shown and described numerous embodiments of the invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will occur to those skilled in the art without departing from the spirit and essence of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in the practice of this invention.

[0095] The above are all preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Therefore, all equivalent changes made in accordance with the structure, shape and principle of the present invention should be covered within the scope of protection of the present invention.

Claims

A method for monitoring vibration data of reinforced steel rings used in subway tunnels, characterized in that, include: Multiple data points are obtained from the vibration data sequence of the reinforced steel ring, and the corresponding data values ​​for each data point are obtained; Take any data point as the target data point, determine the fitted value of each data point within a preset local range of the target data point, obtain the absolute value of the difference between the data value and the fitted value of each data point, and determine the noise performance level of the target data point. The noise performance level is positively correlated with the absolute value of the difference. The mean noise performance of all data points in the vibration data sequence is obtained, and the bandwidth parameter of the vibration data sequence is determined. The bandwidth parameter is positively correlated with the mean noise performance. The vibration data sequence is denoised using a bandwidth parameter in the VMD algorithm. The denoised vibration data sequence is then processed using spectral analysis to obtain the vibration frequency and vibration amplitude of the vibration data sequence. Based on the comparison results of the vibration frequency and vibration amplitude with the threshold, the vibration data monitoring results of the reinforced steel ring are obtained. A method for monitoring vibration data of reinforced steel rings for subway tunnels according to claim 1, characterized in that, The acquisition of multiple data points in the vibration data sequence of the reinforced steel ring includes: Vibration data of the reinforced steel ring in various dimensions are collected by sensors, and the vibration data is preprocessed to obtain the vibration data sequence of the reinforced steel ring in various dimensions. A method for monitoring vibration data of a reinforced steel ring used in subway tunnels according to claim 2, characterized in that, Determining the noise level of the target data point includes: The regularity of the target data points is determined, and the regularity is negatively correlated with the absolute value of the difference between the data value and the fitted value of each data point in a preset local range of the target data points; Calculate the noise index of the target data point: ； In the formula, A noise index representing the target data point. This indicates the regularity of the target data points. 、 These represent the regularity of the data points corresponding to the target data points in the other two dimensions. This indicates the preset hyperparameters. This indicates the calculation of the variance function. This represents an exponential function with base e; The noise performance level of the target data point is determined, and the noise performance level is positively correlated with the noise index. A method for monitoring vibration data of a reinforced steel ring for subway tunnels according to claim 3, characterized in that, The regularity of the target data points satisfies the following relationship: ； In the formula, This indicates the regularity of the target data points. This indicates the number of data points within a preset local range of the target data points. This represents the fitted value of the j-th data point within a preset local range. This represents the data value of the j-th data point within a preset local range. This represents an exponential function with base e. Represents the absolute value symbol. A method for monitoring vibration data of a reinforced steel ring for subway tunnels according to claim 3, characterized in that, Determining the noise level of the target data point includes: In the vibration data sequence of all dimensions collected by all sensors on the reinforced steel ring, other data points corresponding to the target data point are obtained. The product of the regularity variance of the target data point and other data points and the noise index is used as the noise performance degree of the target data point. A method for monitoring vibration data of reinforced steel rings for subway tunnels according to claim 1, characterized in that, The bandwidth parameter of the vibration data sequence satisfies the following relationship: ； In the formula, The bandwidth parameter represents the vibration data sequence. Indicates the reference bandwidth parameter. This indicates the number of data points in the vibration data sequence. Indicating the first vibration data sequence The noise level of each data point This represents an exponential function with base e. This indicates the floor function. A method for monitoring vibration data of reinforced steel rings for subway tunnels according to claim 1, characterized in that, The method of using bandwidth parameters in the VMD algorithm to denoise vibration data sequences includes: The number of decomposition layers of the VMD algorithm is determined using the kurtosis principle; based on the number of decomposition layers and bandwidth parameters, the vibration data sequence is decomposed into multiple IMF components, the IMF components containing noisy data are removed, and the remaining IMF components are reconstructed to obtain the denoised vibration data sequence. A method for monitoring vibration data of reinforced steel rings for subway tunnels according to claim 1, characterized in that, The vibration data monitoring results of the reinforced steel ring are obtained based on the comparison results of the vibration frequency and vibration amplitude with the threshold, including: Preset threshold; If the vibration frequency and / or vibration amplitude are greater than the threshold, the vibration data monitoring result of the reinforced steel ring is abnormal. If the vibration frequency and / or vibration amplitude are less than or equal to the threshold, the vibration data monitoring result of the reinforced steel ring is considered normal. A method for monitoring vibration data of a reinforced steel ring used in subway tunnels according to claim 8, characterized in that, The vibration data monitoring result of the reinforced steel ring is found to be abnormal, and the following steps are also included: After identifying the data points corresponding to the abnormal monitoring results, the data points and the corresponding sensors are associated and marked, and then an early warning is issued. A vibration data monitoring system for reinforced steel rings used in subway tunnels, characterized in that, include: A processor and a memory, the memory storing computer program instructions, which, when executed by the processor, implement a method for monitoring vibration data of a reinforced steel ring for subway tunnels according to any one of claims 1-9.

Images