Detection Method, System, Readable Storage Medium and Computer Device for Track Inspection Data

Abstract

The present invention provides a method, a system, a readable storage medium and a computer device for detecting track inspection data. The method includes: obtaining historical static track inspection data related to a track to be measured, and using a track inspection device to pass through the track to be measured to obtain static track inspection data; matching the static track inspection data with the historical static track inspection data, and using an interpolation algorithm to align the static track inspection data with the historical static track inspection data; comparing the aligned historical static track inspection data with the static track inspection data, and determining whether the comparison result is greater than a preset alarm threshold; if the comparison result is greater than the preset alarm threshold, generating an alarm signal so that the staff can perform corresponding processing operations according to the alarm signal. The present invention effectively realizes accurate judgment of the track inspection data by comparing the static track inspection data after data alignment with the historical static track inspection data, so as to effectively guide the maintenance and repair operations of railway field workers.

Description

Technical Field

[0001] The present invention relates to the technical field of railway track detection, and particularly relates to a detection method, system, readable storage medium and computer device for track inspection data. Background Art

[0002] Since the basic structure of railway tracks requires high stability and smoothness to ensure the safety and smoothness of trains during high-speed operation. With the increasingly wide coverage of railway tracks, the analysis of track detection data has become particularly important.

[0003] Currently, for the analysis of track detection data, due to technical limitations, there is no good detection method at present, and it still mainly relies on manual on-site detection and observation. It is necessary for manual workers to collect track detection data on site. When there are only slight differences in the track, it is impossible to accurately measure them solely through manual on-site detection; moreover, the measured track inspection data cannot be calculated immediately, resulting in the inability to accurately ensure the safety of the track. At the same time, when the track data measured manually is abnormal, it is impossible to determine whether it is due to track deviation, interference during the measurement process, or a malfunction of the track inspection instrument. Therefore, in view of the current technical limitations, there is an urgent need for a detection method for track inspection data to effectively guide the maintenance and repair operations of railway workers on site. Summary of the Invention

[0004] Based on this, the purpose of the present invention is to provide a detection method, system, readable storage medium and computer device for track inspection data to at least solve the deficiencies in the above related technologies.

[0005] The present invention proposes a detection method for track inspection data, and the method includes:

[0006] Step 1: Obtain historical static track inspection data related to the track to be measured, and use a track inspection device to travel through the track to be measured to obtain the static track inspection data of the track to be measured;

[0007] Step 2: Match the static track inspection data with the historical static track inspection data, and use an interpolation algorithm to process the static track inspection data and the historical static track inspection data to align the data of the static track inspection data and the historical static track inspection data;

[0008] Step 3: Compare the historical static track inspection data and the static track inspection data after data alignment, and determine whether the comparison result is greater than a preset alarm threshold;

[0009] Step 4: If the comparison result is greater than the preset alarm threshold, generate an alarm signal so that the staff can perform corresponding processing operations according to the alarm signal.

[0010] Further, the second step includes:

[0011] Obtain the static data sequence constructed from the static track inspection data and the historical static data sequence constructed from the historical static track inspection data;

[0012] Based on the dynamic time warping algorithm, find the path with the minimum total cumulative distance between the static data sequence and the historical static data sequence, so as to align the mileage of the static track inspection data and the historical static track inspection data.

[0013] Further, the steps of calculating the path with the minimum total cumulative distance between the static data sequence and the historical static data sequence based on the dynamic time warping algorithm include:

[0014] Calculate the distance between any two points between the static data sequence and the historical static data sequence, and obtain the corresponding distance matrix according to the distance;

[0015] Use the dynamic programming algorithm to calculate the optimal planning path of the distance matrix to find the path with the minimum total cumulative distance between the static data sequence and the historical static data sequence.

[0016] Further, the expression of the static data sequence is:

[0017] S = {s1, s2,..., s m};

[0018] Wherein, S represents the static data sequence, s i represents any point in the static data sequence, i = 1, 2,..., m;

[0019] The expression of the historical static data sequence is:

[0020] M = {m1, m2,..., m n};

[0021] Wherein, M represents the historical static data sequence, m j represents any point in the historical static data sequence, j = 1, 2,..., n;

[0022] The expression of the distance between any two points between the static data sequence and the historical static data sequence is:

[0023] d(i, j) = ||s i - m j || w ;

[0024] Where i = 1, 2, ..., m, j = 1, 2, ..., n, when w = 1, d(i, j) is the Manhattan distance; when w = 2, d(i, j) is the Euclidean distance;

[0025] The expression of the distance matrix is:

[0026]

[0027] Where D represents the distance matrix.

[0028] Furthermore, the step three specifically includes:

[0029] Respectively acquiring the amplitude sequence of the aligned historical static track inspection data and the aligned static track inspection data, and calculating the difference between the two amplitude sequences;

[0030] The preset alarm threshold is calculated according to the amplitude sequence of the aligned historical static track inspection data, and it is determined whether the difference is greater than the preset alarm threshold.

[0031] Furthermore, the step of generating an alarm signal so that the staff can perform corresponding processing operations according to the alarm signal includes:

[0032] The track inspection device re-passes the local position of the track to be inspected corresponding to the alarm signal, so that the staff can rule out whether there is an abnormality in the track inspection process or confirm whether the track to be inspected is deformed, and refresh the static track inspection data of the local position of the track to be inspected corresponding to the alarm signal;

[0033] Using the track inspection device to travel over the track to be inspected to obtain complete static track inspection data of the track to be inspected;

[0034] If the difference between the amplitude sequence of the complete static track inspection data and the amplitude sequence of the aligned historical static track inspection data is not greater than the preset alarm threshold, the complete static track inspection data is uploaded as the historical static track inspection data for the next measurement.

[0035] Furthermore, the step of generating an alarm signal so that a staff member performs a corresponding processing operation according to the alarm signal includes:

[0036] The track inspection device re-passes the track to be inspected a preset number of times to obtain multiple sets of re-measured static track inspection data of the track to be inspected;

[0037] Comparing the multiple groups of re-measured static track inspection data with the aligned historical static track inspection data, so as to respectively calculate the difference between the amplitude sequence of each group of the re-measured static track inspection data and the amplitude sequence of the aligned historical static track inspection data;

[0038] Determine whether the difference between the amplitude sequences of the retested static track inspection data of each group and the amplitude sequences of the aligned historical static track inspection data is continuously greater than the preset alarm threshold;

[0039] If the difference between the amplitude sequences of the retested static track inspection data of each group and the amplitude sequences of the aligned historical static track inspection data is continuously greater than the preset alarm threshold, an abnormal signal of the track inspection device is generated, so that the staff can check the track inspection device according to the abnormal signal of the track inspection device.

[0040] The present invention also proposes a detection system for track inspection data, and the system includes:

[0041] A static track inspection data acquisition module, configured to acquire historical static track inspection data related to the to-be-detected track, and use a track inspection device to travel through the to-be-detected track to obtain the static track inspection data of the to-be-detected track;

[0042] A static inspection data alignment module, configured to match the static track inspection data and the historical static track inspection data, and process the static track inspection data and the historical static track inspection data by using an interpolation algorithm, so as to align the static track inspection data and the historical static track inspection data;

[0043] A data comparison module, configured to compare the aligned historical static track inspection data and the static track inspection data, and determine whether the comparison result is greater than a preset alarm threshold;

[0044] A processing module, configured to generate an alarm signal if the comparison result is greater than a preset alarm threshold, so that the staff can perform corresponding processing operations according to the alarm signal.

[0045] Further, the static inspection data alignment module includes:

[0046] A first acquisition unit, configured to acquire a static data sequence constructed by the static track inspection data and a historical static data sequence constructed by the historical static track inspection data;

[0047] A data alignment unit, configured to find the path with the smallest total cumulative distance between the static data sequence and the historical static data sequence based on the dynamic time warping algorithm, so as to align the mileage of the static track inspection data and the historical static track inspection data.

[0048] Further, the data alignment unit is further configured to:

[0049] Calculate the distance between any two points between the static data sequence and the historical static data sequence, and obtain a corresponding distance matrix according to the distance;

[0050] The optimal planning path of the distance matrix is ​​calculated using a dynamic programming algorithm to find a path with the minimum total cumulative distance between the static data sequence and the historical static data sequence.

[0051] Furthermore, the data comparison module includes:

[0052] A second acquisition unit, used for respectively acquiring the amplitude sequence of the aligned historical static track inspection data and the aligned static track inspection data, and calculating the difference between the two amplitude sequences;

[0053] The first calculation unit is used to calculate the preset alarm threshold according to the amplitude sequence of the aligned historical static track inspection data, and determine whether the difference is greater than the preset alarm threshold.

[0054] Furthermore, the processing module includes:

[0055] A first data comparison unit is used to re-pass the local position of the track to be tested corresponding to the alarm signal through the track inspection device, so that the staff can rule out whether there is an abnormality in the track inspection process or confirm whether the track to be tested is deformed, and refresh the measured static track inspection data of the local position of the track to be tested corresponding to the alarm signal;

[0056] A third acquisition unit, configured to use the track inspection device to travel through the track to be inspected to obtain complete static track inspection data of the track to be inspected;

[0057] The first processing unit is used to upload the complete static track inspection data as the historical static track inspection data for next measurement if the difference between the amplitude sequence of the complete static track inspection data and the amplitude sequence of the aligned historical static track inspection data is not greater than the preset alarm threshold.

[0058] Furthermore, the processing module includes:

[0059] A fourth acquisition unit, configured to re-pass the track to be measured by the track inspection device a preset number of times to obtain multiple sets of re-measured static track inspection data of the track to be measured;

[0060] a second data comparison unit, configured to compare the plurality of groups of re-measured static track inspection data with the aligned historical static track inspection data, so as to respectively calculate the difference between the amplitude sequence of each group of the re-measured static track inspection data and the amplitude sequence of the aligned historical static track inspection data;

[0061] A first judgment unit is used to judge whether the difference between the amplitude sequence of each group of the re-measured static track inspection data and the amplitude sequence of the aligned historical static track inspection data is continuously greater than the preset alarm threshold;

[0062] A second processing unit, configured to generate an abnormal track inspection device signal if the difference between the amplitude sequences of the retested static track inspection data in each group and the amplitude sequences of the aligned historical static track inspection data is continuously greater than the preset alarm threshold, so that the staff can inspect the track inspection device according to the abnormal track inspection device signal.

[0063] The present invention also provides a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned track inspection data detection method is implemented.

[0064] The present invention also provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the above-mentioned track inspection data detection method is implemented.

[0065] Compared with the prior art, the beneficial effects of the present invention are as follows: By matching the historical static track inspection data and the currently detected static track inspection data, and using the interpolation algorithm to align the static track inspection data and the historical static track inspection data, and comparing the aligned static track inspection data and the historical static track inspection data, the situation of the track inspection data can be accurately judged effectively, so as to effectively guide the maintenance and repair operations of railway field workers. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 is a flowchart of the track inspection data detection method in the first embodiment of the present invention;

[0067] Figure 2 is Figure 1 a detailed flowchart of step S102 in

[0068] Figure 3 is Figure 1 a detailed flowchart of step S103 in

[0069] Figure 4 is Figure 1 a detailed flowchart of step S104 in

[0070] Figure 5 is a flowchart of the track inspection data detection method in the second embodiment of the present invention;

[0071] Figure 6 is a structural block diagram of the track inspection data detection system in the third embodiment of the present invention;

[0072] Figure 7 is a structural block diagram of the computer device in the fourth embodiment of the present invention.

[0073] MAIN ELEMENT SYMBOL DESCRIPTION:

[0074]

[0075]

[0076] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. Specific Embodiments

[0077] For ease of understanding of the present invention, the present invention will be described more fully hereinafter with reference to the relevant drawings. Several embodiments of the present invention are shown in the drawings. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided so that the disclosure of the present invention will be thorough and complete.

[0078] It should be noted that when an element is referred to as being "fixed to" another element, it can be directly on the other element or there can also be an intermediate element. When an element is considered to be "connected" to another element, it can be directly connected to the other element or there may be an intermediate element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0079] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs. The terms used herein in the description of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0080] The quality of the track geometric state not only affects the comfort of passengers when taking the train, but also a poor track geometric state will pose a hazard to the train operation safety and there are potential safety hazards. Therefore, the monitoring and management of the track geometric state play a crucial role in train safety. The track inspection instrument is also the main tool for monitoring the track geometric condition. Track static inspection, abbreviated as "static track inspection", refers to using an unloaded track inspection vehicle or a dynamic inspection vehicle to run on the track line to obtain static track inspection data to evaluate the track quality.

[0081] Embodiment 1

[0082] Please refer to Figure 1 , which shows the detection method of track inspection data in the first embodiment of the present invention. The method specifically includes steps S101 to S104:

[0083] S101. Obtain historical static track inspection data related to the to-be-tested track, and use a track inspection device to travel along the to-be-tested track to obtain the static track inspection data of the to-be-tested track;

[0084] In this embodiment, the historical static track inspection data related to the to-be-tested track is stored in the track inspection device and can be directly called; in other alternative embodiments, the historical static track inspection data can be transmitted to the track inspection device in real time by a data platform or downloaded to the track inspection device from the data platform in advance before detecting the to-be-tested track.

[0085] In specific implementation, use a track inspection device without load (in this application, it is a track detector, and in other alternative embodiments, the track inspection device can be other devices capable of obtaining track data) to sample the to-be-tested track at a first interval mileage to obtain corresponding static track inspection data. For example, generally sample data at an interval of 0.125 meters, which means that the distance between two adjacent sampling points is fixed at 0.125 meters to sample and obtain static track inspection data.

[0086] S102. Match the static track inspection data and the historical static track inspection data, and use an interpolation algorithm to process the static track inspection data and the historical static track inspection data to align the data of the static track inspection data and the historical static track inspection data;

[0087] Further, please refer to Figure 2 , the step S102 specifically includes steps S1021 to S1023:

[0088] S1021. Obtain a static data sequence constructed from the static track inspection data and a historical static data sequence constructed from the historical static track inspection data;

[0089] S1022. Calculate the distance between any two points between the static data sequence and the historical static data sequence, and obtain a corresponding distance matrix according to the distance;

[0090] S1023. Use a dynamic programming algorithm to calculate the optimal planning path of the distance matrix to find the path with the smallest total cumulative distance between the static data sequence and the historical static data sequence, so as to align the mileage of the static track inspection data and the historical static track inspection data.

[0091] In specific implementation, obtain a static data sequence S = {s1, s2,..., s m}(S represents the static data sequence, S i represents any point in the static data sequence, i = 1, 2,..., m) and a historical static data sequence M = {m1, m2,..., mn}(where \(M\) represents the historical static data sequence, \(m\) j represents any point in the historical static data sequence, \(j = 1, 2, \ldots, n\)), the static data sequence and the historical static data sequence are two identical feature sequences with equal time intervals, and the distance between any two points between them is calculated according to the following formula:

[0092] \(d(i,j)=\|s\) i - m j \| w ;

[0093] In the formula, \(i = 1, 2, \ldots, m\), \(j = 1, 2, \ldots, n\). When \(w = 1\), \(d(i,j)\) is the Manhattan distance; when \(w = 2\), \(d(i,j)\) is the Euclidean distance;

[0094] Based on the above formula, the corresponding distance matrix \(D\) is calculated as:

[0095]

[0096] Use the DP (dynamic programming) algorithm to find the optimal planning path of the distance matrix \(D\):

[0097] P best =\{p1, p2, \ldots, p k , \ldots, p K \};

[0098] In the formula, \(p k represents the path planning position, that is, \(p k =(i,j) k means that \(s m is aligned with \(m n where \(\max(m,n)\leq K\leq m + n - 1\), and the lengths of the static data sequence \(S\) and the historical static data sequence \(M\) are \(m\) and \(n\) respectively.

[0099] It should be noted that in this embodiment, to make all the searched paths meaningful, therefore, any searched path must meet the following constraint conditions:

[0100] (1) Boundary: The starting point and the ending point of the shortest path are fixed, as shown in the following formula:

[0101]

[0102] (2) Monotonicity: In the same measurement, after calculation, the features of the previous moment cannot appear after the features of the next moment, that is, when given \(p k =(s i , m j ) and \(p k+1 =(s i′ , mj′ ) When i ≤ i' and j ≤ j'.

[0103] (3) Continuity: To avoid losing information in the finally obtained shortest path, each feature information should be correspondingly matched. That is, when given p k =(s i , m j ) and p k+1 =(s i′ , m j′ ), then i' ≤ i + 1 and j' ≤ j + 1.

[0104] The warping path p between p1 and p K is determined by constructing a cost matrix. The matrix element γ(i, j) is defined as: k γ(i, j) = d(i, j) + min[γ(i - 1, j - 1), γ(i - 1, j), γ(i, j - 1)];

[0105] where i ∈ {1, 2,..., m}, j ∈ {1, 2,..., n}, γ(0, 0) = 0, γ(i, 0) = γ(0, j) = ∞.

[0106] The dynamic time warping distance DTW(S, M) of the obtained optimal warping path P

[0107] makes the cumulative distance value between the static data sequence S and the historical static data sequence M the smallest. The dynamic time warping distance is calculated as shown in the following formula: best

[0108]

[0109] Through the above DTW algorithm, the static data sequence S and the historical static data sequence M can be matched, and a certain point on the static data sequence S is corresponding to a certain point or several points on the historical static data sequence M with the shortest distance; or, a certain point on the historical static data sequence M is corresponding to a certain point or several points on the static data sequence S with the shortest distance, so as to form a corresponding relationship between the static data sequence S and the historical static data sequence M.

[0110] S103. Compare the historical static track inspection data and the static track inspection data after data alignment, and determine whether the comparison result is greater than a preset alarm threshold;

[0111] Further, please refer to Figure 3 , and the step S103 specifically includes steps S1031 to S1032:

[0112] S1031, respectively obtaining the amplitude sequence of the aligned historical static track inspection data and the aligned static track inspection data, and calculating the difference between the two amplitude sequences;

[0113] S1032: Calculate the preset alarm threshold according to the amplitude sequence of the aligned historical static track inspection data, and determine whether the difference is greater than the preset alarm threshold.

[0114] In this embodiment, the amplitude sequence of the aligned historical static track inspection data and the amplitude sequence of the aligned static track inspection data are respectively obtained (in this embodiment, the amplitude sequence is a waveform amplitude sequence of the data), and the difference between the two amplitude sequences is calculated by subtracting the two amplitude sequences;

[0115] The variance of the amplitude sequence of the aligned historical track inspection data is calculated, and the preset alarm threshold is set to ±10% of the variance, and it is determined whether the difference obtained is greater than the preset alarm threshold. If the difference obtained is greater than the preset alarm threshold, it means that there is a large difference between the static track inspection data and the historical static track inspection data; if the difference obtained is not greater than the preset alarm threshold, it means that there is no difference between the static track inspection data and the historical track inspection data or there is a difference within a qualified range.

[0116] S104: If the comparison result is greater than a preset alarm threshold, an alarm signal is generated so that the staff can perform corresponding processing operations according to the alarm signal.

[0117] For further information, see Figure 4 , the step S104 specifically includes steps S1041 to S1043:

[0118] S1041, the track inspection device re-passes the local position of the track to be inspected corresponding to the alarm signal, so that the staff can rule out whether there is an abnormality in the track inspection process or confirm whether the track to be inspected is deformed, and refresh the measured static track inspection data of the local position of the track to be inspected corresponding to the alarm signal;

[0119] S1042, using the track inspection device to travel through the track to be inspected to obtain complete static track inspection data of the track to be inspected;

[0120] S1043: If the difference between the amplitude sequence of the complete static track inspection data and the amplitude sequence of the aligned historical static track inspection data is not greater than the preset alarm threshold, the complete static track inspection data is uploaded as the historical static track inspection data for the next measurement.

[0121] In specific implementation, if the obtained difference is greater than a preset alarm threshold, an alarm signal will be sent. This alarm signal occurs at the site where the staff uses the track inspection equipment to pass through the to-be-tested track to obtain the static track inspection data of the to-be-tested track, prompting the staff to re-pass through the local to-be-tested track where the alarm occurs through the same track inspection equipment, so as to rule out that the data anomaly alarm is caused by an abnormal track inspection process, or to confirm that the data anomaly alarm is caused by the actual deformation of the to-be-tested track, and refresh the measured static track inspection data of the local position of the to-be-tested track corresponding to the alarm signal;

[0122] After the refresh is completed, use the same track inspection equipment to measure the to-be-tested track, that is, re-pass through the to-be-tested track with the above-mentioned track inspection equipment, so as to obtain the complete static track inspection data of the to-be-tested track;

[0123] Compare the data in the same way using the complete static track inspection data and the above-mentioned historical static track inspection data. If the difference between the amplitude sequences of the complete static track inspection data and the amplitude sequences of the aligned historical static track inspection data is not greater than the preset alarm threshold, it means that the previous measurement process was interfered, and the static track inspection data of this re-measurement meets the requirements. Then upload the complete static track inspection data as the historical static track inspection data for the next measurement.

[0124] It should be noted that in some alternative embodiments, the root mean square of the historical static track inspection data and the static track inspection data within a certain range is calculated. If the difference amplitude of the root mean square of the two static track inspection data is too large, it is determined as abnormal and re-measurement is required. If the values of the root mean square of the static track inspection data of the two measurements are both large, it means that there is an anomaly in the track.

[0125] In summary, the detection method of the track inspection data in the above embodiments of the present invention effectively realizes accurate judgment of the track inspection data by matching the historical static track inspection data and the currently detected static track inspection data, and using the interpolation algorithm to align the static track inspection data and the historical static track inspection data, so as to effectively guide the maintenance and repair operations of railway field workers.

[0126] Embodiment 2

[0127] Please refer to Figure 5 , which shows the detection method of the track inspection data in the second embodiment of the present invention. The method specifically includes steps S201 to S207:

[0128] S201, obtain the historical static track inspection data related to the to-be-tested track, and use the track inspection equipment to pass through the to-be-tested track to obtain the static track inspection data of the to-be-tested track;

[0129] In this embodiment, the historical static track inspection data related to the track to be measured is stored in the track inspection device and can be directly called; in other alternative embodiments, the historical static track inspection data can be transmitted to the track inspection device in real time by the data platform or downloaded to the track inspection device from the data platform in advance before detecting the track to be measured.

[0130] In specific implementation, a track inspection device without load (in this application, it is a track inspection instrument; in other alternative embodiments, the track inspection device can be other devices capable of acquiring track data) samples the track to be measured at a first interval mileage to obtain corresponding static track inspection data. For example, data sampling is generally performed at an interval of 0.125 meters, which means that the distance between two adjacent sampling points is fixed at 0.125 meters to sample and obtain static track inspection data.

[0131] S202. Match the static track inspection data with the historical static track inspection data, and process the static track inspection data and the historical static track inspection data by using an interpolation algorithm to align the data of the static track inspection data and the historical static track inspection data.

[0132] In specific implementation, obtain the static track inspection data to construct a static data sequence S = {s1, s2,..., s m}(S represents the static data sequence, s i represents any point in the static data sequence, i = 1, 2,..., m) and the historical static data to construct a historical static data sequence M = {m1, m2,..., m n}(M represents the historical static data sequence, m i represents any point in the historical static data sequence, j = 1, 2,..., n). The static data sequence and the historical static data sequence are two same feature sequences with equal time intervals. Calculate the distance between any two points between and according to the following formula:

[0133] d(i, j) = ||s i - m i || w ;

[0134] In the formula, i = 1, 2,..., m, j = 1.2,..., n. When w = 1, it is the Manhattan distance; when w = 2, it is the Euclidean distance.

[0135] Based on the above formula, calculate the corresponding distance matrix D as:

[0136]

[0137] Use the DP (dynamic programming) algorithm to obtain the optimal planning path of the distance matrix D:

[0138] P best = {p1, p2, …, p k , …, p K};

[0139] Wherein, p k represents the path planning position, that is, p k = (i, j) k means that s m is aligned with m n , where max(m, n) ≤ K ≤ m + n - 1, and the lengths of the static data sequence S and the historical static data sequence M are m and n respectively.

[0140] It should be noted that in this embodiment, in order to make all the searched paths meaningful, any searched path must meet the following constraint conditions:

[0141] (1) Boundary: The start and end points of the shortest path are fixed, as shown in the following formula:

[0142]

[0143] (2) Monotonicity: In the same measurement, after calculation, the features at the previous moment cannot appear after the features at the later moment, that is, when given p k = (s i , m j ) and p k+1 = (s i′ , m j′ ), then i ≤ i', j ≤ j'.

[0144] (3) Continuity: In order to avoid losing information in the finally obtained shortest path, each feature information must be correspondingly matched, that is, when given p k = (s i , m j ) and p k+1 = (s i′ , m j′ ), then i' ≤ i + 1, j' ≤ j + 1.

[0145] The regular path p K between p1 and p k is determined by constructing a cost matrix, and the matrix element γ(i, j) is defined as:

[0146] γ(i, j) = d(i, j) + min[γ(i - 1, j - 1), γ(i - 1, j), γ(i, j - 1)];

[0147] In the formula, i∈{1,2,…,m}, j∈{1,2,…,n}, γ(0,0)=0, γ(i,0)=γ(0,j)=∞.

[0148] The optimal regularized path P obtained above best The dynamic time warping distance DTW(S, M) minimizes the cumulative distance between the static data sequence S and the historical static data sequence M. The dynamic time warping distance is calculated as follows:

[0149]

[0150] Through the above-mentioned DTW algorithm, the static data sequence S and the historical static data sequence M can be matched, and a point on the static data sequence S can be corresponded with a point or points on the historical static data sequence M with the shortest distance; or, a point on the historical static data sequence M can be corresponded with a point or points on the static data sequence S with the shortest distance to form a corresponding relationship between the static data sequence S and the historical static data sequence M.

[0151] S203, comparing the historical static track inspection data after the data alignment with the static track inspection data, and determining whether the comparison result is greater than a preset alarm threshold;

[0152] In this embodiment, the amplitude sequence of the aligned historical static track inspection data and the amplitude sequence of the aligned static track inspection data are respectively obtained (in this embodiment, the amplitude sequence is a waveform amplitude sequence of the data), and the difference between the two amplitude sequences is calculated by subtracting the two amplitude sequences;

[0153] The variance of the amplitude sequence of the aligned historical track inspection data is calculated, and the preset alarm threshold is set to ±10% of the variance, and it is determined whether the difference obtained is greater than the preset alarm threshold. If the difference obtained is greater than the preset alarm threshold, it means that there is a large difference between the static track inspection data and the historical static track inspection data; if the difference obtained is not greater than the preset alarm threshold, it means that there is no difference between the static track inspection data and the historical track inspection data or there is a difference within a qualified range.

[0154] S204, if the comparison result is greater than a preset alarm threshold, the track inspection device re-travels the track to be inspected a preset number of times to obtain multiple sets of re-measured static track inspection data of the track to be inspected;

[0155] S205, comparing the multiple groups of re-measured static track inspection data with the aligned historical static track inspection data, so as to respectively calculate the difference between the amplitude sequence of each group of the re-measured static track inspection data and the amplitude sequence of the aligned historical static track inspection data;

[0156] S206, determine whether the difference between the amplitude sequences of the retested static track inspection data of each group and the amplitude sequences of the aligned historical static track inspection data is continuously greater than the preset alarm threshold;

[0157] S207, if the difference between the amplitude sequences of the retested static track inspection data of each group and the amplitude sequences of the aligned historical static track inspection data is continuously greater than the preset alarm threshold, generate an abnormal signal of the track inspection device, so that the staff can check the track inspection device according to the abnormal signal of the track inspection device.

[0158] In specific implementation, if the obtained difference is greater than the preset alarm threshold, at this time, the staff re-measure the track to be measured with the same track inspection device for a preset number of times (3 times in this embodiment), that is, use the above track inspection device to re-pass through the track to be measured, and then obtain multiple groups of retested static track inspection data;

[0159] Compare the above multiple groups of retested static track inspection data with the above historical static track inspection data in the same way as above. If the difference between the amplitude sequences of the multiple groups of retested track inspection data and the amplitude sequences of the aligned historical static track inspection data is continuously greater than the preset alarm threshold, it means that the track inspection device is abnormal.

[0160] In this embodiment, by comparing multiple groups of retested static track inspection data with historical static track inspection data, it is possible to detect whether the track inspection device is abnormal, further ensure the working condition of the track inspection device, and improve the accuracy of track detection.

[0161] Embodiment III

[0162] On the other hand, the present invention also proposes a detection system for track inspection data. Please refer to Figure 6 , which shows the detection system for track inspection data in the third embodiment of the present invention. The system includes:

[0163] A static track inspection data acquisition module 11, configured to acquire historical static track inspection data related to the track to be measured, and use a track inspection device to pass through the track to be measured to obtain static track inspection data of the track to be measured;

[0164] A static inspection data alignment module 12, configured to match the static track inspection data and the historical static track inspection data, and process the static track inspection data and the historical static track inspection data using an interpolation algorithm to align the static track inspection data and the historical static track inspection data;

[0165] Further, the static inspection data alignment module 12 includes:

[0166] A first acquisition unit, configured to acquire a static data sequence constructed by the static track inspection data and a historical static data sequence constructed by the historical static track inspection data;

[0167] The data alignment unit is used to find the path with the minimum total cumulative distance between the static data sequence and the historical static data sequence based on a dynamic time warping algorithm, so as to align the mileage of the static track inspection data with the historical static track inspection data.

[0168] Furthermore, the data alignment unit is also used for:

[0169] Calculate the distance between any two points of the static data sequence and the historical static data sequence, and obtain a corresponding distance matrix according to the distance;

[0170] The optimal planning path of the distance matrix is ​​calculated using a dynamic programming algorithm to find a path with the minimum total cumulative distance between the static data sequence and the historical static data sequence.

[0171] The data comparison module 13 is used to compare the historical static track inspection data and the static track inspection data after the data alignment, and determine whether the comparison result is greater than a preset alarm threshold;

[0172] Furthermore, the data comparison module 13 includes:

[0173] A second acquisition unit, used for respectively acquiring the amplitude sequence of the aligned historical static track inspection data and the aligned static track inspection data, and calculating the difference between the two amplitude sequences;

[0174] The first calculation unit is used to calculate the preset alarm threshold according to the amplitude sequence of the aligned historical static track inspection data, and determine whether the difference is greater than the preset alarm threshold.

[0175] The processing module 14 is used to generate an alarm signal if the comparison result is greater than a preset alarm threshold, so that the staff can perform corresponding processing operations according to the alarm signal.

[0176] Furthermore, the processing module 14 includes:

[0177] A first data comparison unit is used to re-pass the local position of the track to be tested corresponding to the alarm signal through the track inspection device, so that the staff can rule out whether there is an abnormality in the track inspection process or confirm whether the track to be tested is deformed, and refresh the measured static track inspection data of the local position of the track to be tested corresponding to the alarm signal;

[0178] A third acquisition unit, configured to use the track inspection device to travel through the track to be inspected to obtain complete static track inspection data of the track to be inspected;

[0179] The first processing unit is configured to upload the complete static track inspection data as the historical static track inspection data for the next measurement if the differences between the amplitude sequences of the complete static track inspection data and the aligned historical static track inspection data are not greater than the preset alarm threshold.

[0180] In other alternative embodiments, the processing module 14 includes:

[0181] The fourth acquisition unit is configured to re - traverse the track to be measured by the track inspection device a preset number of times to obtain multiple groups of retested static track inspection data of the track to be measured;

[0182] The second data comparison unit is configured to compare the multiple groups of retested static track inspection data with the aligned historical static track inspection data, and respectively calculate the differences between the amplitude sequences of each group of the retested static track inspection data and the amplitude sequence of the aligned historical static track inspection data;

[0183] The first judgment unit is configured to judge whether the differences between the amplitude sequences of each group of the retested static track inspection data and the amplitude sequence of the aligned historical static track inspection data are continuously greater than the preset alarm threshold;

[0184] The second processing unit is configured to generate an abnormal signal of the track inspection device if the differences between the amplitude sequences of each group of the retested static track inspection data and the amplitude sequence of the aligned historical static track inspection data are continuously greater than the preset alarm threshold, so that the staff can check the track inspection device according to the abnormal signal of the track inspection device.

[0185] The functions or operation steps realized when the above - mentioned modules and units are executed are substantially the same as those in the above - mentioned method embodiments, and will not be elaborated here.

[0186] The detection system of track inspection data provided by the embodiments of the present invention has the same implementation principle and technical effects as those in the foregoing method embodiments. For the sake of brief description, for the parts not mentioned in the device embodiments, reference can be made to the corresponding content in the foregoing method embodiments.

[0187] Embodiment 4

[0188] The present invention also provides a computer device. Please refer to Figure 7 , which shows the computer device in the fourth embodiment of the present invention, including a memory 10, a processor 20, and a computer program 30 stored on the memory 10 and executable on the processor 20. When the processor 20 executes the computer program 30, the above - mentioned method for detecting track inspection data is realized.

[0189] Among them, the memory 10 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, magnetic disk, optical disc, etc. The memory 10 can be an internal storage unit of a computer device in some embodiments, such as the hard disk of the computer device. The memory 10 can also be an external storage device in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 10 can also include both the internal storage unit of the computer device and the external storage device. The memory 10 can be used not only to store application software installed in the computer device and various types of data, but also to temporarily store data that has been output or will be output.

[0190] Among them, the processor 20 can be an Electronic Control Unit (ECU, also known as a vehicle computer), a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments, and is used to run the program code stored in the memory 10 or process data, such as executing an access restriction program, etc.

[0191] It should be noted that Figure 7 The structure shown does not constitute a limitation on the computer device. In other embodiments, the computer device may include fewer or more components than shown in the figure, or combine certain components, or have a different component layout.

[0192] An embodiment of the present invention also provides a readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the detection method of track inspection data as described above is implemented.

[0193] Those skilled in the art can understand that the logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0194] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then stored in a computer memory.

[0195] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0196] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0197] The above-described embodiments merely represent several implementation manners of the present application. Their descriptions are relatively specific and detailed, but should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for detecting track inspection data, characterized in that The method includes: Step 1: Obtain historical static track inspection data related to the track to be measured, and use a track inspection device to travel along the track to be measured to obtain the static track inspection data of the track to be measured; Step 2: Match the static track inspection data and the historical static track inspection data, and use an interpolation algorithm to process the static track inspection data and the historical static track inspection data to align the data of the static track inspection data and the historical static track inspection data; Step 3: Compare the historical static track inspection data and the static track inspection data after data alignment, and determine whether the comparison result is greater than a preset alarm threshold; Step 4: If the comparison result is greater than the preset alarm threshold, generate an alarm signal to enable the staff to perform corresponding processing operations according to the alarm signal. Among them, the step of generating an alarm signal to enable the staff to perform corresponding processing operations according to the alarm signal includes: The track inspection device travels along the local position of the track to be measured corresponding to the alarm signal again to enable the staff to rule out whether there is an abnormality in the track inspection process or confirm whether the track to be measured is deformed, and refresh the measured static track inspection data of the local position of the track to be measured corresponding to the alarm signal; Use the track inspection device to travel along the track to be measured to obtain the complete static track inspection data of the track to be measured; If the difference between the amplitude sequences of the complete static track inspection data and the amplitude sequences of the historical static track inspection data after alignment is not greater than the preset alarm threshold, upload the complete static track inspection data as the historical static track inspection data for the next measurement; Among them, the step of generating an alarm signal to enable the staff to perform corresponding processing operations according to the alarm signal further includes: The track inspection device travels along the track to be measured a preset number of times to obtain multiple sets of re-measured static track inspection data of the track to be measured; Compare the multiple sets of re-measured static track inspection data with the historical static track inspection data after alignment to calculate the differences between the amplitude sequences of each set of re-measured static track inspection data and the amplitude sequences of the historical static track inspection data after alignment respectively; Judge whether the differences between the amplitude sequences of each set of re-measured static track inspection data and the amplitude sequences of the historical static track inspection data after alignment are continuously greater than the preset alarm threshold; If the differences between the amplitude sequences of each set of re-measured static track inspection data and the amplitude sequences of the historical static track inspection data after alignment are continuously greater than the preset alarm threshold, generate a track inspection device abnormality signal to enable the staff to check the track inspection device according to the track inspection device abnormality signal.

2. The detection method of track inspection data according to claim 1, characterized in that, The said Step 2 includes: Obtain the static data sequence constructed by the static track inspection data and the historical static data sequence constructed by the historical static track inspection data; Based on the dynamic time warping algorithm, find the path with the minimum total cumulative distance between the static data sequence and the historical static data sequence, so as to align the mileage of the static track inspection data and the historical static track inspection data.

3. The detection method of track inspection data according to claim 2, characterized in that, The steps of calculating the minimum total cumulative distance path between the static data sequence and the historical static data sequence based on the dynamic time warping algorithm include: Calculate the distance between any two points of the static data sequence and the historical static data sequence, and obtain the corresponding distance matrix according to the distance; Use the dynamic programming algorithm to calculate the optimal planning path of the distance matrix to find the minimum total cumulative distance path between the static data sequence and the historical static data sequence.

4. The detection method of track inspection data according to claim 3, characterized in that The expression of the static data sequence is: ； In the formula, represents a static data sequence, represents any point in the static data sequence, ; The expression of the historical static data sequence is: ； In the formula, represents the historical static data sequence, represents any point in the historical static data sequence, ; The expression of the distance between any two points of the static data sequence and the historical static data sequence is: ； Wherein, , When , is the Manhattan distance; when , is the Euclidean distance; The expression of the distance matrix is: ； In the formula, represents the distance matrix.

5. The detection method of track inspection data according to claim 1, characterized in that The specific content of step three includes: Obtain the amplitude sequences of the aligned historical static track inspection data and the aligned static track inspection data respectively, and calculate the difference between the two amplitude sequences; Calculate the preset alarm threshold according to the amplitude sequence of the aligned historical static track inspection data, and judge whether the difference is greater than the preset alarm threshold.

6. A detection system for track inspection data, characterized in that, The system includes: A static track inspection data acquisition module, which is used to acquire historical static track inspection data related to the track to be measured, and use the track inspection equipment to travel through the track to be measured to obtain the static track inspection data of the track to be measured; A static track inspection data alignment module, which is used to match the static track inspection data and the historical static track inspection data, and use the interpolation algorithm to process the static track inspection data and the historical static track inspection data to align the static track inspection data and the historical static track inspection data; A data comparison module, which is used to compare the aligned historical static track inspection data and static track inspection data, and judge whether the comparison result is greater than the preset alarm threshold; A processing module, which is used to generate an alarm signal if the comparison result is greater than the preset alarm threshold, so that the staff can perform corresponding processing operations according to the alarm signal; Among them, the processing module includes: A first data comparison unit, which is used to make the track inspection equipment travel through the local position of the track to be measured corresponding to the alarm signal again, so that the staff can rule out whether there is any abnormality in the track inspection process or confirm whether the track to be measured is deformed, and refresh the measured static track inspection data of the local position of the track to be measured corresponding to the alarm signal; A third acquisition unit, which is used to make the track inspection equipment travel through the track to be measured to obtain the complete static track inspection data of the track to be measured; A first processing unit, which is used to upload the complete static track inspection data as the historical static track inspection data for the next measurement if the difference between the amplitude sequence of the complete static track inspection data and the amplitude sequence of the aligned historical static track inspection data is not greater than the preset alarm threshold; Among them, the processing module further includes: A fourth acquisition unit, which is used to make the track inspection equipment travel through the track to be measured a preset number of times to obtain multiple groups of retested static track inspection data of the track to be measured; A second data comparison unit, configured to compare the multiple groups of retested static track inspection data with the aligned historical static track inspection data, so as to calculate the differences between the amplitude sequences of the retested static track inspection data of each group and the amplitude sequences of the aligned historical static track inspection data respectively; A first judgment unit, configured to judge whether the differences between the amplitude sequences of the retested static track inspection data of each group and the amplitude sequences of the aligned historical static track inspection data are continuously greater than the preset alarm threshold; A second processing unit, configured to generate a track inspection equipment abnormal signal if the differences between the amplitude sequences of the retested static track inspection data of each group and the amplitude sequences of the aligned historical static track inspection data are continuously greater than the preset alarm threshold, so that the staff can inspect the track inspection equipment according to the track inspection equipment abnormal signal.

7. A readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the track inspection data detection method according to any one of claims 1 to 5.

8. A computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the track inspection data detection method according to any one of claims 1 to 5.

Images