Rail irregularity detection method based on correlation statistical characterization and perception serialization

Abstract

The embodiment of the invention provides a track irregularity detection method based on correlation statistical characterization and perception continuity. The method comprises the steps that operation parameters of an axle box of a running train are obtained; determining the vibration displacement of the running train; determining a moment sequence corresponding to the equal driving distance according to the fluted disc gear tooth moment data; resampling the vibration displacement according to the time sequence to obtain equidistant resampling data; performing median filtering on the equidistant resampling data based on a preset window length to determine smooth vibration displacement data; determining consistent vibration displacement characterization data according to the plurality of pieces of smooth vibration displacement data on the rails with the same position and the same length; calculating a first wavelength and a first wave depth of the track irregularity in the consistent vibration displacement characterization data; the first wavelengths and the first wave depths of a plurality of running trains on the track are obtained to obtain a first wavelength set and a first wave depth set, and a high-confidence irregularity detection result is obtained through standardization processing. The method is used for improving the track irregularity detection efficiency.

Description

Technical Field

[0001] The present application relates to the field of track detection technology, and in particular to a track irregularity detection method based on relevant statistical representation and perception continuity. Background Art

[0002] Track irregularity is a periodic wave-like phenomenon distributed longitudinally on the top surface of the rail. Track irregularity will not only aggravate the damage of track structural components and changes in track geometric dimensions, but also cause vibration fatigue damage to vehicles. Therefore, it is of great significance to detect track irregularity in a timely and accurate manner.

[0003] In the prior art, a track corrugation ruler or a track corrugation instrument is usually used to perform static line detection when there is no train operation plan. However, this method has high labor costs and low detection efficiency. Summary of the invention

[0004] The embodiments of the present application provide a track irregularity detection method based on relevant statistical characterization and perception continuity, so as to achieve the effect of improving the efficiency of track irregularity detection.

[0005] In a first aspect, an embodiment of the present application provides a method for detecting track irregularity based on relevant statistical characterization and perception continuity, which is applied to a computer device, and includes: obtaining the sprocket tooth moment data and vibration acceleration discrete data of the axle box of a running train; performing continuous processing on the vibration acceleration discrete data to determine the vibration displacement of the running train; calculating the moment sequence corresponding to the equal travel distance of the running train according to the sprocket tooth moment data and the number of sprocket teeth; resampling the vibration displacement according to the moment sequence corresponding to the equal travel distance to obtain the equal distance resampled data of the running train; performing median filtering on the equal distance resampled data based on a preset window length to obtain processed smooth vibration displacement data; determining consistent vibration displacement characterization data based on multiple smooth vibration displacement data obtained on the track of the same length at the same position of the running train; calculating the first wavelength and the first wave depth of the track irregularity in the consistent vibration displacement characterization data; obtaining the first wavelength and the first wave depth of multiple running trains on the track to obtain a first wavelength set and a first wave depth set, and performing standardization processing on the first wavelength set and the first wave depth set to obtain a high confidence irregularity detection result; and outputting the irregularity detection result.

[0006] In a possible implementation, a time sequence corresponding to an equal travel distance of a running train is calculated based on the sprocket tooth time data and the number of sprocket teeth, including: calculating the time between each tooth based on the sprocket tooth time data; calculating the wheel rotation distance between two adjacent teeth based on the wheel diameter of the running train and the number of sprocket teeth; calculating the instantaneous speed between each tooth based on the wheel rotation distance between two adjacent teeth and the time between each tooth; performing continuous processing on the instantaneous speed between each tooth to determine the travel distance of the running train at each moment; setting a distance interval to generate an equidistant position sequence; determining the time sequence corresponding to the equal travel distance based on the travel distance of the running train at each moment and the equidistant position sequence.

[0007] In a possible implementation, the sampling formula for the equidistant resampled data of the running train is:

[0008]

[0009] In the formula, represents the equidistant resampled data of the running train, h(0) represents the initial vibration displacement of the running train, v(t) represents the vibration velocity of the axle box of the running train at time t, a(t) represents the acceleration of the axle box of the running train at time t after continuous processing, and B1~B2 represent the effective signal analysis frequency band.

[0010] In a possible implementation, consistent vibration displacement characterization data is determined based on multiple smooth vibration displacement data obtained by a running train on a track of the same position and the same length, including: randomly selecting a preset number of smooth vibration displacement data from the multiple smooth vibration displacement data to determine as an initial cluster center sequence; for any smooth vibration displacement data, calculating the cross-correlation value between any smooth vibration displacement data and each sequence in the initial cluster center sequence to obtain a maximum correlation peak; dividing any smooth vibration displacement data into a cluster center sequence corresponding to the maximum correlation peak; repeatedly executing the steps of "for any smooth vibration displacement data, calculating the cross-correlation value between any smooth vibration displacement data and each sequence in the initial cluster center sequence to obtain a maximum correlation peak; dividing any smooth vibration displacement data into a cluster center sequence corresponding to the maximum correlation peak" until all cluster center sequences remain unchanged; among all cluster center sequences, the cluster center sequence of the largest cluster is determined as the consistent vibration displacement characterization data.

[0011] In a possible implementation, the calculation formula of the first wavelength and the first wave depth of track irregularity is:

[0012]

[0013] In the formula, λ[Λ j di ] represents the sequence Λ jdi The wavelength, ζ[Λ j di ] represents the sequence Λ j di The wave depth, P represents the sequence Λ j di The number of points, ΔL is the equidistant resampling resolution, Λ jw di Represents the sequence Λ j di The w-th value of , Λ j di Indicates less than d i The jth sequence of i It is the i-th consistent vibration displacement characterization data of the running train on the track of the same length at the same position.

[0014] In one possible implementation, a high-confidence roughness detection result includes a wavelength range and a wavelength depth range; accordingly, the first wavelength set and the first wavelength depth set are standardized to obtain a high-confidence roughness detection result, including: in the first wavelength depth set and the first wavelength set, a second wavelength depth set and a second wavelength set whose wavelength exceeds a preset wavelength depth threshold are screened out; the wavelength mean and wavelength variance of the second wavelength set are calculated, and the second wavelength set is normalized; the wavelength depth mean and wavelength depth variance of the second wavelength depth set are calculated, and the second wavelength depth set is normalized; based on a preset confidence level, the wavelength range and wavelength depth range are obtained.

[0015] In a second aspect, an embodiment of the present application provides a track irregularity detection device based on relevant statistical representation and perception continuity, which is applied to a computer device, including:

[0016] The data acquisition module is used to acquire the gear wheel tooth moment data and vibration acceleration discrete data of the axle box of the running train.

[0017] The vibration displacement determination module is used to perform continuous processing on the discrete data of vibration acceleration to determine the vibration displacement of the running train.

[0018] The time sequence calculation module is used to calculate the time sequence corresponding to the equal travel distance of the running train according to the gear plate gear time data and the number of gear plate teeth.

[0019] The resampling module is used to resample the vibration displacement according to the time sequence corresponding to the equal travel distance to obtain the equal distance resampling data of the running train.

[0020] The median filter module is used to perform median filtering on the equidistant resampled data based on a preset window length to obtain processed smooth vibration displacement data.

[0021] The characterization data determination module is used to determine consistent vibration displacement characterization data based on multiple smooth vibration displacement data obtained by a running train on a track of the same position and length.

[0022] The wavelength-wave-depth calculation module is used to calculate the first wavelength and the first wave depth of track irregularity in the consistent vibration displacement characterization data.

[0023] The standardization processing module is used to obtain the first wavelength and the first wave depth of multiple running trains on the track, obtain the first wavelength set and the first wave depth set, and perform standardization processing on the first wavelength set and the first wave depth set to obtain a high-confidence roughness detection result.

[0024] The detection result output module is used to output the roughness detection result.

[0025] In a third aspect, an embodiment of the present application provides a computer device, including: a memory, a processor;

[0026] Memory stores computer-executable instructions;

[0027] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0028] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementations of the first aspect.

[0029] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0030] The track irregularity detection method based on relevant statistical characterization and perception continuity provided in the embodiment of the present application can reduce labor costs and improve detection efficiency by processing the collected gear wheel tooth moment data and vibration acceleration discrete data, and using computer equipment to calculate the wave depth and wavelength of track irregularity. In addition, by continuously processing the discrete data of the vibration acceleration of the axle box, the integral error caused by the conversion of vibration acceleration into vibration displacement can be reduced. By obtaining consistent vibration displacement characterization data and standardizing the first wavelength set and the first wave depth set, a high-confidence irregularity detection result is obtained, which can reduce errors to a certain extent and more accurately detect the wave depth and wavelength of track irregularity. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0032] Figure 1 A schematic diagram of an application scenario of a track irregularity detection method based on relevant statistical representation and perception continuity provided in an embodiment of the present application;

[0033] FIG2(1) is a schematic diagram of a flow chart of a track irregularity detection method based on relevant statistical representation and perception continuity provided in an embodiment of the present application;

[0034] FIG. 2 (2) is an initial cluster center sequence O provided in an embodiment of the present application c (q) and smoothed vibration displacement data H z (q) Schematic diagram of the relationship between sequences;

[0035] Figure 3 A schematic diagram of the structure of a track irregularity detection device based on relevant statistical representation and perception continuity provided in an embodiment of the present application;

[0036] Figure 4 A schematic diagram of the structure of the computer device provided for this application.

[0037] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0038] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0039] First, the terms involved in this application are explained:

[0040] Track irregularity is a periodic wave-like phenomenon distributed longitudinally on the top surface of the rail and is a major form of track damage.

[0041] In order to clearly understand the technical solution of the present application, the solution of the prior art is first introduced in detail. With the rapid development of the national economy and the people's pursuit of portable, punctual, environmentally friendly and comfortable travel, the construction of urban rail in my country is in full swing, and the resulting safety issues of urban rail train operation have become crucial. Track unevenness is a common problem in railway track systems. It will not only aggravate the damage of track structural components and changes in track geometric dimensions, affecting the service life of the rails, but also cause vibration fatigue damage to locomotives and vehicles, increasing maintenance and operating costs. Therefore, it is of great significance to detect track unevenness in a timely and accurate manner and restore the track to a smooth state. In the prior art, the track unevenness detection methods include chord measurement method, image recognition method and inertial reference method. Among them, the chord measurement method includes the use of a track wave grinding ruler or a track wave grinding instrument to perform static line detection when there is no train operation plan. The image recognition method irradiates a laser or structured light onto the track at a certain angle, uses a camera to take pictures to obtain track detection data, and then uses a pattern recognition method to detect the wave grinding in the picture. The consistency benchmark method, as a dynamic detection method, mainly detects track irregularities based on the detection principle of the second integral of vibration acceleration. However, the chord measurement method has high labor costs and low detection efficiency. The image recognition method has high equipment costs and requires a long period of data accumulation to achieve a high recognition accuracy. The consistency benchmark method is based on the second integral method of vibration acceleration. It only integrates discrete acceleration data and does not consider that the acceleration waveform itself has been destroyed. After the integration error is accumulated, it is already quite different from the actual vibration displacement waveform.

[0042] In view of the above technical problems, the inventors have come up with the idea of ​​processing the obtained discrete data of the axle box vibration acceleration continuously, and then integrating the continuous data to generate the continuous data of vibration displacement. According to the relationship between the obtained toothed disc gear moment data and the running train travel distance, the continuous data of vibration displacement is resampled at equal distances to obtain the equidistant resampled data of the running train, and the equidistant resampled data is median filtered, and the data collected by the running train multiple times on the same position and the same length of track are processed to obtain the consistent vibration displacement characterization data. In the consistent vibration displacement characterization data, the first wavelength and the first wave depth of the track irregularity are calculated, and the first wavelength and the first wave depth of multiple running trains on the track are obtained to obtain the first wavelength set and the first wave depth set, and the first wavelength set and the first wave depth set are standardized to obtain the high-confidence irregularity detection result, and the high-confidence irregularity detection result is output. By processing the collected toothed disc gear moment data and the discrete data of vibration acceleration, and using computer equipment to calculate the wave depth and wavelength of the track irregularity, the labor cost can be reduced and the detection efficiency can be improved. In addition, by continuously processing the discrete data of the axle box vibration acceleration, the integral error caused by the conversion of vibration acceleration into vibration displacement can be reduced. By obtaining consistent vibration displacement characterization data and standardizing the first wavelength set and the first wave depth set, high-confidence unevenness detection results can be obtained, which can reduce the error to a certain extent and more accurately detect the wave depth and wavelength of track unevenness.

[0043] Based on the above creative findings, the inventor proposed the technical solution of the present application.

[0044] Figure 1 Schematic diagram of the application scenario of the track irregularity detection method based on relevant statistical representation and perception continuity provided in the embodiment of the present application. Figure 1 As shown, the application scenario of the embodiment of the present application includes: a receiving device 101, a processor 102 and a display device 103. It is understandable that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the track irregularity detection method. In other feasible implementations of the present application, the above architecture may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently, which can be determined according to the actual application scenario and is not limited here. Figure 1 The components shown may be implemented in hardware, software, or a combination of software and hardware.

[0045] In a specific implementation process, the receiving device 101 may be an input / output interface or a communication interface, and is used to obtain the gear tooth timing data and vibration acceleration discrete data of the axle box of the running train.

[0046] The processor 102 can perform continuous processing on discrete vibration acceleration data to determine the vibration displacement of the running train; calculate the time sequence corresponding to the equal travel distance of the running train according to the gear wheel tooth time data and the number of gear wheel teeth; resample the vibration displacement according to the time sequence corresponding to the equal travel distance to obtain the equal distance resampled data of the running train; perform median filtering on the equal distance resampled data based on a preset window length to obtain processed smooth vibration displacement data; determine consistent vibration displacement characterization data based on multiple smooth vibration displacement data obtained on the track of the same length at the same position of the running train; calculate the first wavelength and the first wave depth of the track roughness in the consistent vibration displacement characterization data; obtain the first wavelength and the first wave depth of multiple running trains on the track to obtain the first wavelength set and the first wave depth set, and standardize the first wavelength set and the first wave depth set to obtain a high confidence roughness detection result, and output the roughness detection result.

[0047] The display device 103 can be used to display the roughness detection result.

[0048] The display device may also be a touch display screen, which is used to receive user instructions while displaying the above content to achieve operational interaction with the user.

[0049] It should be understood that the above-mentioned processor can be implemented by the processor reading instructions in the memory and executing the instructions, or it can be implemented by a chip circuit.

[0050] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0051] FIG2(1) is a flow chart of a track irregularity detection method based on relevant statistical representation and perception continuity provided in an embodiment of the present application. As shown in FIG2(1), the method includes:

[0052] S201: Acquire the gear tooth moment data and vibration acceleration discrete data of the axle box of the running train.

[0053] Specifically, the vibration acceleration discrete data collected by the vibration acceleration sensor on the vertical bearing area of ​​the axle box of the running train is obtained, and the vibration acceleration discrete data a(k) is obtained by analog-to-digital conversion of the data acquisition board card (k=0, 1, 2, ..., M-1). The gear wheel tooth time data t collected by the speed sensor installed at the end of the axle of the running train and converted by analog-to-digital conversion of the data acquisition board card is obtained. i ,(i=0,1,2,…,N-1).

[0054] S202: Continuously process the discrete data of vibration acceleration to determine the vibration displacement of the running train.

[0055] Among them, the method for continuous processing of discrete vibration acceleration data can use Fourier transform to convert time domain signals into frequency domain signals.

[0056] Specifically, it includes steps Sa1 to Sa2:

[0057] Sa1: Substitute the discrete vibration acceleration data a(k) into the following formula for continuous processing.

[0058]

[0059] In the formula, a(t) represents the frequency domain signal, which represents the amplitude and phase of the signal at the tth frequency component; a(i) represents the discrete sample in the time domain, which represents the signal value at the i-th time point; B 1 ~B 2 Indicates the effective signal analysis frequency band; e -j2πfit Represents the complex exponential function, which is used to convert discrete signals into the frequency domain.

[0060] Sa2: Integrate the continuous vibration acceleration data to calculate the vibration displacement of the running train.

[0061] Specifically, the formula for calculating the vibration displacement of a running train is:

[0062]

[0063] Wherein, the initial vibration displacement of the running train h(0)=0, the initial vibration velocity v(0)=0, v(t) represents the vibration velocity of the running train at time t; h(t) represents the vibration displacement of the running train.

[0064] S203: Calculate the time sequence corresponding to the equal travel distance of the running train according to the gear wheel tooth time data and the number of gear teeth.

[0065] Specifically, the process of calculating the time sequence corresponding to the equal travel distance of the running train includes Sb1 to Sb6:

[0066] Sb1: Calculate the time between each tooth based on the gear wheel tooth timing data.

[0067] Specifically, the gear wheel tooth time data t i , (i=0,1,2,…,N-1), calculate the time Δt between each tooth i =t i -t i-1 .

[0068] Sb2: Calculate the wheel rotation distance between two adjacent teeth based on the wheel diameter and the number of teeth on the sprocket of the running train.

[0069] Specifically, according to the wheel diameter D of the running train and the number of teeth N of the sprocket, the formula for calculating the wheel rotation distance p between two adjacent teeth is: p=πD / N.

[0070] Sb3: Calculate the instantaneous speed between each tooth based on the wheel rotation distance between two adjacent teeth and the time between each tooth.

[0071] Specifically, the wheel rotation distance p between two adjacent teeth and the time Δt between each tooth i , calculate the instantaneous velocity V between each tooth i The formula is: V i =p / Δt i ,(i=1,2,...,N-1).

[0072] Sb4: Continuously process the instantaneous speed between each tooth to determine the travel distance of the running train at each moment.

[0073] Specifically, the instantaneous speed between each tooth is processed continuously, and the calculation formula of the running speed V(t) of the running train at each moment is obtained as follows:

[0074]

[0075] Specifically, the running speed of the running train is integrated to obtain the running distance L(t) of the running train at each time:

[0076]

[0077] Sb5: Set the distance interval to generate a sequence of equidistant positions.

[0078] Specifically, based on the mapping relationship f:t->L between time t and the travel distance L(t) of the running train, the inverse mapping relationship f is obtained: -1 :L->t. Set the distance interval ΔL=L q -L q-1 , generate an equidistant position sequence L q ,(q=0,1,2,...,J).

[0079] Sb6: Determine the time sequence corresponding to the equal travel distance according to the travel distance of the running train at each time and the equal distance position sequence.

[0080] Specifically, the equidistant position sequence L q Substitute the inverse mapping relation f -1 , determine the time sequence corresponding to equal driving distance

[0081] S204: resample the vibration displacement according to the time sequence corresponding to the equal travel distance to obtain the equal distance resampled data of the running train.

[0082] Specifically, the time series corresponding to equal travel distances Substitute into the vibration displacement continuous data h(t) to obtain the equidistant resampled data The formula is:

[0083]

[0084] In the formula, represents the equidistant resampled data of the running train, h(0) represents the initial vibration displacement of the running train, v(t) represents the vibration velocity of the axle box of the running train at time t, a(t) represents the acceleration of the axle box of the running train at time t after continuous processing, and B1~B2 represent the effective signal analysis frequency band.

[0085] S205: Perform median filtering on the equidistant resampled data based on a preset window length to obtain processed smoothed vibration displacement data.

[0086] Specifically, the preset window length is set to 2k+1, and the equidistant resampled data is performed based on the preset window length. Perform median filtering to obtain the processed smooth vibration displacement data:

[0087]

[0088] In the formula, Med(·) means to find the median value of the data.

[0089] S206: Determine consistent vibration displacement characterization data based on a plurality of smoothed vibration displacement data obtained by a running train on a track of the same position and length.

[0090] Specifically, the track distance between two stations is divided into intervals of length d. Assume that a moving train is at the same position and the same length d. The vibration displacement H of the zth data collection is z (q), analyze the data collected Z times and extract the consistent vibration displacement characterization data O c (q).

[0091] S207: Calculate the first wavelength and the first wave depth of track irregularity in the consistent vibration displacement characterization data.

[0092] Specifically, in the consistency vibration displacement characterization data O c In (q), firstly, the consistent vibration displacement characterization data O is calculated. c (q) average value d, obtain the consistent vibration displacement characterization data O cThe set of subsequences Λ in (q) that are less than d d [q].

[0093] The formula for calculating the first wavelength and first wave depth of track irregularity is:

[0094]

[0095] In the formula, λ[Λ j di ] indicates that the consistent vibration displacement characterization data on the i-th track with a length of d is less than d i The wavelength of the jth subsequence of j di ; ΔL is the equidistant resampling resolution. ζ[Λ j di ] represents the sequence Λ j di The wave depth of jw di Represents the sequence Λ j di The w-th value of .

[0096] S208: Acquire the first wavelengths and first wave depths of multiple running trains on the track to obtain a first wavelength set and a first wave depth set, and perform standardization on the first wavelength set and the first wave depth set to obtain a high-confidence roughness detection result.

[0097] Among them, the high-confidence roughness detection results include wavelength range and wave depth range.

[0098] Specifically, multiple running trains collect data on the same track. After data processing and analysis, the first wavelength set {λ i |i=1,2,3,...,I} and the first wave deep set {ζ i |i=1,2,3,…,I}.

[0099] Specifically, the process of obtaining a high-confidence roughness detection result includes Sc1 to Sc4:

[0100] Sc1: From the first wavelength depth set and the first wavelength set, a second wavelength depth set and a second wavelength set whose wavelength exceeds a preset wavelength depth threshold are screened out.

[0101] Specifically, a wavelength depth threshold δ is set, and a second wavelength set {λ i δ |i=1,2,3,...,I δ} and the second wave deep set {ζ iδ |i=1,2,3,...,I δ}, where I δ Indicates the size of the filtered data.

[0102] Sc2: Calculate the wavelength mean and wavelength variance of the second wavelength set, and perform standard normalization on the second wavelength set.

[0103] Specifically, calculate the second wavelength set {λ i δ |i=1,2,3,...,I δ The mean μ λ and variance σ λ , standardize the second wavelength set and get

[0104] Sc3: Calculate the wave depth mean and wave depth variance of the second wave depth set, and perform standard normalization on the second wave depth set.

[0105] Specifically, calculate the second wave deep set {ζ i δ |i=1,2,3,...,I δ The mean μ ζ and variance σ ζ , standardize the second wave deep set, and get

[0106] Sc4: Based on the preset signal level, get the wavelength range and wavelength depth range.

[0107] Specifically, given a preset confidence level θ, the roughness wavelength is within the confidence interval satisfy The roughness depth is within the confidence interval satisfy

[0108] S209: Outputting the roughness detection result.

[0109] Specifically, the actual detection wavelength range of the irregularity is and wave depth range The output is sent to the display screen so that the staff can accurately polish the track according to the actual detection wavelength range and actual detection wave depth range of the unevenness.

[0110] In summary, by processing the collected gear wheel tooth moment data and vibration acceleration discrete data, and using computer equipment to calculate the wave depth and wavelength of track irregularity, it is possible to reduce labor costs and improve detection efficiency. In addition, by continuously processing the discrete data of axle box vibration acceleration, it is possible to reduce the integral error caused by the conversion of vibration acceleration into vibration displacement. By obtaining consistent vibration displacement characterization data and standardizing the first wavelength set and the first wave depth set, a high-confidence irregularity detection result is obtained, which can reduce errors to a certain extent and more accurately detect the wave depth and wavelength of track irregularity.

[0111] In another embodiment of the present application, the step of determining consistent vibration displacement characterization data may include S301 to S305 based on a plurality of smoothed vibration displacement data obtained by a running train on a track of the same position and length:

[0112] S301: Randomly select a preset number of smoothed vibration displacement data from a plurality of smoothed vibration displacement data and determine them as an initial cluster center sequence.

[0113] Specifically, from Z smoothed vibration displacement data H z (q) Randomly select C sequences from the sequence as the initial cluster center sequence O c (q), where c = 1, 2, 3, ..., C; q = 1, 2, 3, ..., J. FIG2 (2) is an initial cluster center sequence O provided in an embodiment of the present application. c (q) and smoothed vibration displacement data H z (q) Schematic diagram of the relationship between sequences.

[0114] S302: For any smoothed vibration displacement data, calculate the cross-correlation value between any smoothed vibration displacement data and each sequence in the initial cluster center sequence to obtain the maximum correlation peak value.

[0115] Specifically, calculate the zth H z (q) sequence and the cth O c (q) The cross-correlation value of the sequence determines the maximum correlation peak CP zc The formula is:

[0116]

[0117] S303: Divide any smoothed vibration displacement data into a cluster center sequence corresponding to the maximum correlation peak value.

[0118] Specifically, for each H z (q), (z=1,2,3,…,Z), find the maximum correlation peak CP zc The corresponding c, and the H z (q) is divided into the center sequence of cluster c.

[0119] S304: Repeat the steps of "for any smooth vibration displacement data, calculating the cross-correlation value between any smooth vibration displacement data and each sequence in the initial cluster center sequence to obtain the maximum correlation peak; dividing any smooth vibration displacement data into the cluster center sequence corresponding to the maximum correlation peak" until all cluster center sequences remain unchanged.

[0120] Specifically, let the vibration displacement sequence in each cluster be H g (q),(g=1,2,3,…,G c ), G c Represents the size of the cth cluster, and the cluster center sequence is updated using the following formula:

[0121]

[0122] Specifically, the step of dividing any smoothed vibration displacement data into a cluster center sequence corresponding to the maximum correlation peak is repeatedly performed until the cluster center no longer changes significantly.

[0123] S305: Determine the cluster center sequence of the largest cluster among all cluster center sequences as consistent vibration displacement characterization data.

[0124] Specifically, the largest cluster O C (q) is the consistent vibration displacement characterization data.

[0125] In summary, among all the smooth vibration displacement data, there are changes in the data collected multiple times by multiple trains. Finding consistent characterization data that truly reflects the changes in track irregularities in these difference data can reduce errors and more accurately detect the wave depth and wavelength of track irregularities.

[0126] Figure 3 A schematic diagram of the structure of a track irregularity detection device based on relevant statistical representation and continuous perception provided in an embodiment of the present application. Figure 3 As shown, the device includes: a data acquisition module 301, a vibration displacement determination module 302, a time series calculation module 303, a resampling module 304, a median filtering module 305, a characterization data determination module 306, a wavelength depth calculation module 307, a standardization processing module 308 and a detection result output module 309.

[0127] The data acquisition module 301 is used to acquire the gear tooth moment data and vibration acceleration discrete data of the axle box of the running train.

[0128] The vibration displacement determination module 302 is used to perform continuous processing on the discrete data of vibration acceleration to determine the vibration displacement of the running train.

[0129] The time sequence calculation module 303 is used to calculate the time sequence corresponding to the same travel distance of the running train according to the gear plate gear time data and the number of gear plate teeth.

[0130] The resampling module 304 is used to resample the vibration displacement according to the time sequence corresponding to the equal travel distance to obtain the equal distance resampling data of the running train.

[0131] The median filter module 305 is used to perform median filtering on the equidistant resampled data based on a preset window length to obtain processed smoothed vibration displacement data.

[0132] The characterization data determination module 306 is used to determine consistent vibration displacement characterization data based on a plurality of smoothed vibration displacement data obtained by a running train on a track of the same position and length.

[0133] The wavelength-wave-depth calculation module 307 is used to calculate the first wavelength and the first wave depth of the track irregularity in the consistent vibration displacement characterization data.

[0134] The standardization processing module 308 is used to obtain the first wavelength and the first wave depth of multiple running trains on the track, obtain the first wavelength set and the first wave depth set, and perform standardization processing on the first wavelength set and the first wave depth set to obtain a high-confidence roughness detection result.

[0135] The detection result output module 309 is used to output the roughness detection result.

[0136] In a possible implementation, the time series calculation module 303 is specifically used to calculate the time between each tooth based on the tooth time data of the sprocket; calculate the wheel rotation distance between two adjacent teeth based on the wheel diameter of the running train and the number of teeth of the sprocket; calculate the instantaneous speed between each tooth based on the wheel rotation distance between two adjacent teeth and the time between each tooth; continuously process the instantaneous speed between each tooth to determine the travel distance of the running train at each moment; set the distance interval to generate an equidistant position sequence; determine the time series corresponding to the equal travel distance based on the travel distance of the running train at each moment and the equidistant position sequence.

[0137] In a possible implementation, the sampling formula for the equidistant resampled data of the running train in the resampling module 304 is:

[0138]

[0139]

[0140] In the formula, represents the equidistant resampled data of the running train, h(0) represents the initial vibration displacement of the running train, v(t) represents the vibration velocity of the axle box of the running train at time t, a(t) represents the acceleration of the axle box of the running train at time t after continuous processing, and B1~B2 represent the effective signal analysis frequency band.

[0141] In a possible implementation, the characterization data determination module 306 is specifically used to randomly select a preset number of smooth vibration displacement data from multiple smooth vibration displacement data to determine them as an initial cluster center sequence; for any smooth vibration displacement data, calculate the cross-correlation value between any smooth vibration displacement data and each sequence in the initial cluster center sequence to obtain a maximum correlation peak; divide any smooth vibration displacement data into a cluster center sequence corresponding to the maximum correlation peak; repeat the steps of "for any smooth vibration displacement data, calculate the cross-correlation value between any smooth vibration displacement data and each sequence in the initial cluster center sequence to obtain a maximum correlation peak; divide any smooth vibration displacement data into a cluster center sequence corresponding to the maximum correlation peak" until all cluster center sequences remain unchanged; among all cluster center sequences, the cluster center sequence of the largest cluster is determined as the consistent vibration displacement characterization data.

[0142] In a possible implementation, the calculation formula for the first wavelength and the first wavelength depth in the wavelength wavelength depth calculation module 307 is:

[0143]

[0144] In the formula, λ[Λ j di ] represents the sequence Λ j di The wavelength, ζ[Λ j di ] represents the sequence Λ j di The wave depth, P represents the sequence Λ j di The number of points, ΔL is the equidistant resampling resolution, Λ jw di Represents the sequence Λ j di The w-th value of , Λ j di Indicates less than d i The jth sequence of i It is the i-th consistent vibration displacement characterization data of the running train on the track of the same length at the same position.

[0145] In a possible implementation, the standardization processing module 308 is specifically configured to select a second wavelength set and a second wavelength set whose wavelength exceeds a preset wavelength threshold from the first wavelength set and the first wavelength set; calculate the wavelength mean and wavelength variance of the second wavelength set, and

[0146] The long set is normalized; the wavelength mean and wavelength variance of the second wavelength set are calculated and normalized; based on the preset confidence level, the wavelength range and wavelength depth range are obtained.

[0147] The track irregularity detection device based on relevant statistical representation and perception continuity provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effects are similar, and this embodiment will not be described in detail here.

[0148] Figure 4 This is a schematic diagram of the structure of the computer device provided in this application. Figure 4 As shown, the computer device provided in this embodiment includes: at least one processor 401 and a memory 402. Optionally, the computer device also includes a communication component 403. The processor 401, the memory 402 and the communication component 403 are connected via a bus 404.

[0149] In a specific implementation process, at least one processor 401 executes the computer-executable instructions stored in the memory 402, so that at least one processor 401 executes the above method.

[0150] The specific implementation process of the processor 401 can be found in the above method embodiment, and its implementation principle and technical effect are similar, so this embodiment will not be repeated here.

[0151] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be executed by a combination of hardware and software modules in the processor.

[0152] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-volatile Memory, NVM), such as at least one disk memory.

[0153] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0154] An embodiment of the present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0155] An embodiment of the present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0156] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general or special-purpose computer.

[0157] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (Application Specific Integrated Circuits, referred to as: ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0158] The division of units is only a logical function division, and there may be other divisions in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0159] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0160] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0161] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0162] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0163] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention, which follow the general principles of the present invention and include common knowledge or customary technical means in the art not disclosed by the present invention, are not limited to the precise structure described above and shown in the drawings, and may be modified and changed in various ways without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A track irregularity detection method based on relevant statistical representation and perception continuity, characterized in that: Applicable to computer equipment, including: Obtain the gear wheel tooth moment data and vibration acceleration discrete data of the axle box of the running train; Continuously processing the discrete data of vibration acceleration to determine the vibration displacement of the running train; According to the toothed disc gear timing data and the number of teeth on the toothed disc, a timing sequence corresponding to equal travel distances of the running train is calculated; resampling the vibration displacement according to the time sequence corresponding to the equal travel distance to obtain equal distance resampling data of the running train; Performing median filtering on the equidistant resampled data based on a preset window length to obtain processed smoothed vibration displacement data; Determining consistent vibration displacement characterization data based on a plurality of smoothed vibration displacement data obtained by the running train on a track of the same position and length; In the consistent vibration displacement characterization data, calculating a first wavelength and a first wave depth of track irregularity; Acquire a first wavelength and a first wave depth of a plurality of running trains on the track to obtain a first wavelength set and a first wave depth set, and perform standardization processing on the first wavelength set and the first wave depth set to obtain a high-confidence roughness detection result; The roughness detection result is outputted.

2. The method according to claim 1, characterized in that The step of calculating the time sequence corresponding to the equal travel distance of the running train according to the toothed disc gear time data and the number of teeth of the toothed disc comprises: Calculating the time between each tooth according to the gear wheel tooth timing data; Calculating the wheel rotation distance between two adjacent teeth according to the wheel diameter of the running train and the number of teeth of the sprocket; Calculating the instantaneous speed between each tooth according to the wheel rotation distance between the two adjacent teeth and the time between each tooth; Continuously processing the instantaneous speeds between the teeth to determine the travel distance of the running train at each moment; Set the distance interval to generate a sequence of equidistant positions; According to the travel distance of the running train at each time and the equal distance position sequence, the time sequence corresponding to the equal travel distance is determined.

3. The method according to claim 1, characterized in that The sampling formula of the equidistant resampling data of the running train is: In the formula, represents the equidistant resampled data of the running train, h(0) represents the initial vibration displacement of the running train, v(t) represents the vibration velocity of the axle box of the running train at time t, a(t) represents the acceleration of the axle box of the running train at time t after continuous processing, and B1~B2 represent the effective signal analysis frequency band.

4. The method according to claim 1, characterized in that: The step of determining consistent vibration displacement characterization data based on a plurality of smoothed vibration displacement data obtained by the running train on a track of the same position and length comprises: Randomly selecting a preset number of smoothed vibration displacement data from the plurality of smoothed vibration displacement data to determine as an initial cluster center sequence; For any smoothed vibration displacement data, calculate the cross-correlation value between the any smoothed vibration displacement data and each sequence in the initial cluster center sequence to obtain the maximum correlation peak value; Dividing any of the smoothed vibration displacement data into a cluster center sequence corresponding to the maximum correlation peak; Repeat the steps of "for any smooth vibration displacement data, calculating the cross-correlation value between any smooth vibration displacement data and each sequence in the initial cluster center sequence to obtain the maximum correlation peak value; and dividing any smooth vibration displacement data into the cluster center sequence corresponding to the maximum correlation peak value" until all cluster center sequences remain unchanged; The cluster center sequence of the largest cluster among all the cluster center sequences is determined as the consistent vibration displacement characterization data.

5. The method according to claim 1, characterized in that The calculation formula of the first wavelength and the first wave depth of the track irregularity is: In the formula, λ[Λ j di ] represents the sequence Λ j di The wavelength, ζ[Λ j di ] represents the sequence Λ j di The wave depth, P represents the sequence Λ j di The number of points, ΔL is the equidistant resampling resolution, Λ jw di Represents the sequence Λ j di The w-th value of , Λ j di Indicates less than d i The jth sequence of i It is the i-th consistent vibration displacement characterization data of the running train on the track of the same length at the same position.

6. The method according to claim 1, characterized in that The high confidence roughness detection result includes a wavelength range and a wave depth range; Accordingly, the first wavelength set and the first wavelength depth set are normalized to obtain a high-confidence roughness detection result, including: Screening out a second wavelength set and a second wavelength set whose wavelength exceeds a preset wavelength threshold value from the first wavelength set and the first wavelength set; Calculating the wavelength mean and wavelength variance of the second wavelength set, and performing standard normalization on the second wavelength set; Calculating the wave depth mean and wave depth variance of the second wave depth set, and performing standard normalization on the second wave depth set; Based on a preset signal level, the wavelength range and the wavelength depth range are obtained.

7. A track irregularity detection device based on relevant statistical representation and perception continuity, characterized in that: Applicable to computer equipment, including: A data acquisition module, used to acquire the gear wheel tooth moment data and vibration acceleration discrete data of the axle box of the running train; A vibration displacement determination module, used for performing continuous processing on the discrete vibration acceleration data to determine the vibration displacement of the running train; A time sequence calculation module, used for calculating the time sequence corresponding to the equal travel distance of the running train according to the toothed disc gear time data and the number of teeth of the toothed disc; A resampling module, used for resampling the vibration displacement according to the time sequence corresponding to the equal travel distance to obtain the equal distance resampling data of the running train; A median filtering module, used for performing median filtering on the equidistant resampled data based on a preset window length to obtain processed smoothed vibration displacement data; A characterization data determination module, used to determine consistent vibration displacement characterization data based on a plurality of smoothed vibration displacement data obtained by the running train on a track of the same position and length; A wavelength-wave-depth calculation module, used to calculate a first wavelength and a first wave depth of track irregularity in the consistent vibration displacement characterization data; A standardization processing module, used for acquiring a first wavelength and a first wave depth of a plurality of running trains on the track, obtaining a first wavelength set and a first wave depth set, and performing standardization processing on the first wavelength set and the first wave depth set to obtain a high-confidence roughness detection result; The detection result output module is used to output the roughness detection result.

8. A computer device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 6 when executed by a processor.

10. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 6 when being executed by a processor.

Images