CN114417921B - Method, device, equipment and storage medium for identifying geometric anomaly data of track - Google Patents
Method, device, equipment and storage medium for identifying geometric anomaly data of track Download PDFInfo
- Publication number
- CN114417921B CN114417921B CN202210009844.7A CN202210009844A CN114417921B CN 114417921 B CN114417921 B CN 114417921B CN 202210009844 A CN202210009844 A CN 202210009844A CN 114417921 B CN114417921 B CN 114417921B
- Authority
- CN
- China
- Prior art keywords
- data
- data segment
- abnormal
- sequence
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 97
- 230000002159 abnormal effect Effects 0.000 claims abstract description 176
- 238000001514 detection method Methods 0.000 claims abstract description 67
- 238000012545 processing Methods 0.000 claims abstract description 48
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 17
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 15
- 238000012937 correction Methods 0.000 claims description 46
- 238000000605 extraction Methods 0.000 claims description 16
- 230000015654 memory Effects 0.000 claims description 15
- 238000012216 screening Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 9
- 125000004122 cyclic group Chemical group 0.000 claims description 8
- 238000012952 Resampling Methods 0.000 claims description 6
- 230000006641 stabilisation Effects 0.000 claims description 5
- 238000011105 stabilization Methods 0.000 claims description 5
- 238000010845 search algorithm Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 description 17
- 230000008569 process Effects 0.000 description 10
- 230000005856 abnormality Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 5
- 230000002547 anomalous effect Effects 0.000 description 4
- 230000035772 mutation Effects 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000002688 persistence Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000006073 displacement reaction Methods 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000227 grinding Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
- G06F18/256—Fusion techniques of classification results, e.g. of results related to same input data of results relating to different input data, e.g. multimodal recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Machines For Laying And Maintaining Railways (AREA)
Abstract
Provided herein are a method, apparatus, device and storage medium for identifying geometric anomaly data of a track, wherein the method comprises: acquiring original detection data of track geometry; processing the original detection data by combining an empirical mode decomposition method with a data segment sliding standard deviation, and identifying to obtain a first abnormal data segment; processing the original detection data by combining a local peak value searching algorithm with a data segment sliding root mean square, and identifying to obtain a second abnormal data segment; processing the original detection data through the data segment sliding standard deviation, and identifying to obtain a third abnormal data segment; processing the original detection data by combining a data threshold value through a difference method, and identifying to obtain a fourth abnormal data segment; and merging the first abnormal data segment, the second abnormal data segment, the third abnormal data segment and the fourth abnormal data segment to obtain an abnormal data segment. The efficiency and accuracy of anomaly data identification can be improved.
Description
Technical Field
The present invention relates to the field of rail traffic, and in particular, to a method, apparatus, device, and storage medium for identifying geometric anomaly data of a rail.
Background
At present, the evaluation of the track irregularity state is obtained based on the combination of the local peak value and the section mean value of a plurality of track geometric irregularity parameters and the evaluation standard of the vibration acceleration of the vehicle body, and in addition, the track maintenance scheme is mainly formulated based on the track geometric irregularity data, and the track geometric irregularity parameters mainly comprise the height, the track direction, the track gauge, the level, the triangular pit and the like of the track.
In the actual detection process of the geometric irregularity data of the track, the detection device comprises a laser component, an acceleration sensor, a string displacement sensor, a gyroscope and the like, and the detection device can be influenced by various external conditions, so that abnormal detection data of partial and continuous sections can be inevitably generated.
For abnormal data of continuous sections, usually, abnormal values in the data are identified and removed manually, or the outlier judgment is directly carried out on the calculation index by directly using the amplitude value of track irregularity data or the standard deviation of the sections and using a specific threshold range (such as 3 sigma principle). However, the manual identification has the problems of low efficiency and insufficient accuracy of abnormal data identification. For example, when a large number of track geometry detection data calculations are required for research purposes, the identification and elimination of abnormal sections by hand at this time requires a large amount of labor and is inefficient. In addition, for the line with long mileage and complex equipment working condition, misjudgment or missed judgment still exists when a specific threshold (such as 3 sigma principle) is used for judging the abnormal section.
Therefore, there is a need for a method for identifying geometric anomaly data of a track, which can improve the efficiency and accuracy of anomaly data identification.
Disclosure of Invention
An object of embodiments herein is to provide a method, apparatus, device and storage medium for identifying geometric anomaly data of a track, so as to improve efficiency and accuracy of anomaly data identification.
To achieve the above object, in one aspect, an embodiment herein provides a method for identifying geometric anomaly data of a track, including:
Acquiring original detection data of track geometry;
processing the original detection data by combining an empirical mode decomposition method with a data segment sliding standard deviation, and identifying to obtain a first abnormal data segment;
Processing the original detection data by combining a local peak value searching algorithm with a data segment sliding root mean square, and identifying to obtain a second abnormal data segment;
processing the original detection data through the data segment sliding standard deviation, and identifying to obtain a third abnormal data segment;
processing the original detection data by combining a data threshold value through a difference method, and identifying to obtain a fourth abnormal data segment;
And merging the first abnormal data segment, the second abnormal data segment, the third abnormal data segment and the fourth abnormal data segment to obtain an abnormal data segment.
Preferably, the raw detection data further includes:
laser signal data, string signal data, gyro assembly signal data, and accelerometer signal data.
Preferably, the processing the original detection data by combining an empirical mode decomposition method with a data segment sliding standard deviation, and identifying to obtain the first abnormal data segment further includes:
Performing stabilization treatment on the laser signal data through an empirical mode decomposition method to obtain N intrinsic mode components;
extracting the sum of the first M eigenvalue components in the N eigenvalue components;
Performing sliding extraction on the sum of the first M eigenvalue components according to a set time window length and a set step length to obtain a plurality of laser signal data segments;
calculating the standard deviation of each laser signal data segment to obtain a standard deviation sequence;
And screening the standard deviation sequence according to the standard deviation upper limit value and the standard deviation lower limit value, and determining a first abnormal data segment.
Preferably, the processing the original detection data by combining a local peak value searching algorithm with a data segment sliding root mean square, and identifying to obtain the second abnormal data segment further includes:
sliding extraction is carried out on the string pulling signal data according to the set time window length and the set step length, so that a plurality of string pulling signal data segments are obtained;
calculating the root mean square of each pull string signal data segment to obtain a root mean square sequence;
Judging whether an abnormal root mean square exists in the root mean square sequence;
If yes, carrying out cyclic correction on the pull string signal data to obtain a correction sequence;
Performing sliding extraction on the correction sequence according to the set time window length and the set step length to obtain a plurality of correction data segments;
calculating the root mean square of each correction data segment to obtain a correction root mean square sequence;
and screening the corrected root mean square sequence according to a correction threshold value to determine a second abnormal data segment.
Preferably, the performing the cyclic correction on the pull string signal data to obtain a correction sequence further includes:
The method comprises the following steps of circularly executing for a plurality of times, and taking new string pulling signal data obtained after the plurality of times of circulation as a correction sequence:
calculating the pull string signal data according to a local peak value searching algorithm to obtain a local extremum sequence;
Carrying out interpolation resampling processing on the local extremum sequence to obtain a capacity expansion sequence; wherein the data volume of the expansion sequence is the same as the data volume of the pull string signal data;
and correspondingly subtracting the data in the string pulling signal data from the data in the capacity expansion sequence to obtain new string pulling signal data.
Preferably, the determining whether the abnormal root mean square exists in the root mean square sequence further includes:
Any root mean square value in the root mean square sequence is calculated by the following formula:
|rms(r)-|G00||＜|αG00|；
wherein rms (r) is the r-th root mean square value in the root mean square sequence, G 00 is the initial signal value of the pull string signal data, and alpha is the fluctuation coefficient of the pull string signal;
If any root mean square value satisfies the above formula, the root mean square value is an abnormal root mean square.
Preferably, the processing the original detection data by the sliding standard deviation of the data segment, and identifying to obtain the third abnormal data segment further includes:
calculating the standard deviation of each string pulling signal data segment to obtain a string pulling standard deviation sequence;
and screening the string standard deviation sequence according to a string pulling threshold value, and determining a third abnormal data segment.
Preferably, the processing the original detection data by a difference method in combination with a data threshold value, and identifying to obtain the fourth abnormal data segment further includes:
calculating selected data by a difference method to obtain a difference value sequence, wherein the selected data is laser signal data, gyro component signal data or accelerometer signal data;
judging whether an abnormal value exists in the selected data, wherein the abnormal value is smaller than the data threshold value, and the differential value corresponding to the abnormal value in the differential value sequence is smaller than the data threshold value;
if yes, a fourth abnormal data segment is obtained according to the abnormal value set.
In another aspect, embodiments herein provide an apparatus for identifying geometric anomaly data of a track, the apparatus comprising:
The acquisition module is used for acquiring original detection data of the track geometry;
the first determining module is used for processing the original detection data by combining a data segment sliding standard deviation through an empirical mode decomposition method, and identifying to obtain a first abnormal data segment;
the second determining module is used for processing the original detection data by combining a local peak value searching algorithm with the sliding root mean square of the data segment, and identifying to obtain a second abnormal data segment;
The third determining module is used for processing the original detection data through the sliding standard deviation of the data segment, and identifying to obtain a third abnormal data segment;
The fourth determining module is used for processing the original detection data by combining a data threshold value through a difference method and identifying to obtain a fourth abnormal data segment;
and the merging module is used for merging the first abnormal data segment, the second abnormal data segment, the third abnormal data segment and the fourth abnormal data segment to obtain an abnormal data segment.
In yet another aspect, embodiments herein also provide a computer device including a memory, a processor, and a computer program stored on the memory, which when executed by the processor, performs instructions of any of the methods described above.
In yet another aspect, embodiments herein also provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor of a computer device, performs instructions of a method according to any of the above.
As can be seen from the technical solutions provided in the embodiments herein, the first abnormal data segment is obtained by processing the original detection data with an empirical mode decomposition method in combination with a data segment sliding standard deviation, the second abnormal data segment is obtained by processing the original detection data with a local peak value searching algorithm in combination with a data segment sliding root mean square, the third abnormal data segment is obtained by processing the original detection data with a data segment sliding standard deviation, the fourth abnormal data segment is obtained by processing the original detection data with a difference method in combination with a data threshold, and the first abnormal data segment, the second abnormal data segment, the third abnormal data segment and the fourth abnormal data segment are combined, so that the abnormal data segment is obtained with high efficiency and high accuracy.
The foregoing and other objects, features and advantages will be apparent from the following more particular description of preferred embodiments, as illustrated in the accompanying drawings.
Drawings
In order to more clearly illustrate the embodiments herein or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments herein and that other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.
Fig. 1 is a schematic flow chart of a method for identifying geometric anomaly data of a track according to an embodiment of the present disclosure;
FIG. 2 illustrates a flow diagram provided by embodiments herein for identifying a first anomalous data segment;
FIG. 3 illustrates a flow diagram provided by embodiments herein for identifying a second anomalous data segment;
FIG. 4 illustrates a flow diagram for loop correction provided by embodiments herein;
FIG. 5 illustrates a flow diagram provided by embodiments herein for identifying a third anomalous data segment;
FIG. 6 illustrates a flow diagram provided by embodiments herein for identifying a fourth anomalous data segment;
fig. 7 is a schematic block diagram of an apparatus for identifying geometric anomaly data of a track according to an embodiment of the present disclosure;
fig. 8 shows a schematic structural diagram of a computer device provided in embodiments herein.
Description of the drawings:
100. an acquisition module;
200. A first determination module;
300. A second determination module;
400. a third determination module;
500. A fourth determination module;
600. a merging module;
802. A computer device;
804. a processor;
806. A memory;
808. a driving mechanism;
810. An input/output module;
812. an input device;
814. An output device;
816. a presentation device;
818. A graphical user interface;
820. a network interface;
822. A communication link;
824. a communication bus.
Detailed Description
The following description of the embodiments of the present disclosure will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the disclosure. All other embodiments, based on the embodiments herein, which a person of ordinary skill in the art would obtain without undue burden, are within the scope of protection herein.
In the actual detection process of the geometric irregularity data of the track, the detection device comprises a laser component, an acceleration sensor, a string displacement sensor, a gyroscope and the like, and the detection device can be influenced by various external conditions, so that abnormal detection data of partial and continuous sections can be inevitably generated.
For abnormal data of continuous sections, usually, abnormal values in the data are identified and removed manually, or the outlier judgment is directly carried out on the calculation index by directly using the amplitude value of the track irregularity data or the standard deviation of the sections and using a specific threshold range (such as 3 sigma principle). However, the manual identification has the problems of low efficiency and insufficient accuracy of abnormal data identification. For example, when a large number of track geometry detection data calculations are required for research purposes, the identification and elimination of abnormal sections by hand at this time requires a large amount of labor and is inefficient. In addition, for the line with long mileage and complex equipment working condition, misjudgment or missed judgment still exists when the abnormal section is judged by utilizing a specific threshold range (such as 3 sigma principle).
To solve the above-mentioned problems, embodiments herein provide a method for identifying geometric anomaly data of a track. Fig. 1 is a schematic step diagram of a method for identifying geometric anomaly data of a track, provided in embodiments herein, the present disclosure provides method operational steps as described in the examples or flowcharts, but may include more or fewer operational steps based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one way of performing the order of steps and does not represent a unique order of execution. When a system or apparatus product in practice is executed, it may be executed sequentially or in parallel according to the method shown in the embodiments or the drawings.
Referring to fig. 1, a method for identifying geometric anomaly data of a track includes:
s101: acquiring original detection data of track geometry;
S102: processing the original detection data by combining an empirical mode decomposition method with a data segment sliding standard deviation, and identifying to obtain a first abnormal data segment;
s103: processing the original detection data by combining a local peak value searching algorithm with a data segment sliding root mean square, and identifying to obtain a second abnormal data segment;
s104: processing the original detection data through the data segment sliding standard deviation, and identifying to obtain a third abnormal data segment;
S105: processing the original detection data by combining a data threshold value through a difference method, and identifying to obtain a fourth abnormal data segment;
S106: and merging the first abnormal data segment, the second abnormal data segment, the third abnormal data segment and the fourth abnormal data segment to obtain an abnormal data segment.
Raw detection data of track geometry includes, but is not limited to: laser signal data, string signal data, gyro assembly signal data, and accelerometer signal data. The laser signal data comprise left laser signal data, right laser signal data and string pulling signal data, the string pulling signal data comprise left string pulling signal data and right string pulling signal data, the gyro component signal data comprise three data channels of rolling, shaking and dip angle, and the accelerometer signal data comprise vertical and horizontal two data channels. The identification method described herein is applicable to any of the left/right laser signal data, left/right pull string signal data described above, as well as gyro assembly signal data for any of the data channels and accelerometer signal data for any of the data channels.
The original detection data of the track geometry are used for detecting track geometry irregularity indexes such as track height, track direction, track gauge, horizontal pits, triangular pits and the like.
It should be distinguished that the anomalies generated by the influence of external environmental conditions such as sunlight, rainwater, rail grinding and the like on the laser signals include various conditions: the laser signal is abnormally and rapidly increased to generate a high-frequency signal, the intermittent no-signal, the accompanying signal after the step mutation of the laser signal is free from fluctuation, and the accompanying signal after the step mutation of the laser signal is weakly fluctuated, and according to the situations, the laser signal can be divided into a high-frequency abnormality and a low-frequency abnormality, wherein the high-frequency abnormality is the laser signal which is abnormally and rapidly increased to generate the high-frequency signal, the low-frequency abnormality is the intermittent no-signal, the accompanying signal after the step mutation of the laser signal is free from fluctuation or weak fluctuation, and the first abnormal data segment comprises a first high-frequency abnormal data segment and a first low-frequency abnormal data segment in laser signal data.
Anomalies in the pull string signal data include a number of situations: the first condition can be determined as the abnormal condition of string breakage, the second and third conditions can be determined as other abnormal conditions of string breakage, the second abnormal data section is the data section with the abnormal condition of string breakage, and the third abnormal data section is the data section with the abnormal condition of string breakage.
The anomalies of the gyro assembly signal data and the accelerometer signal data only comprise a condition that the signal persistence is approximately 0, and besides the gyro assembly signal data and the accelerometer signal data, the laser signal data also comprise a condition that the persistence is approximately 0, and the fourth anomaly data segment comprises the gyro assembly signal data, the accelerometer signal data and the laser signal data.
Compared with the method for identifying the abnormal section by directly carrying out the standard deviation of the track irregularity parameter and the direct 3 sigma principle, the method has the advantage that the specific single track irregularity is obtained by processing a plurality of sensor signals by using a specific algorithm. When an individual sensor fails, the standard deviation of the corresponding track irregularity data may still satisfy the 3 sigma principle, and an abnormal section cannot be identified; in addition, for the lines with long mileage and complex equipment working conditions, when the distribution characteristics of the unsmooth track deviate from Gaussian distribution, misjudgment or missed judgment can occur. The abnormal value analysis is directly carried out from the original signals of each sensor by the method, and the accuracy and the applicability of the abnormal section identification can be improved compared with the abnormal section judgment method based on the 3 sigma principle or the specific threshold.
Referring to fig. 2, in the embodiment herein, the processing the raw detection data by the empirical mode decomposition method in combination with the sliding standard deviation of the data segment, identifying the first abnormal data segment further includes:
S201: performing stabilization treatment on the laser signal data through an empirical mode decomposition method to obtain N intrinsic mode components;
s202: extracting the sum of the first M eigenvalue components in the N eigenvalue components;
S203: performing sliding extraction on the sum of the first M eigenvalue components according to a set time window length and a set step length to obtain a plurality of laser signal data segments;
s204: calculating the standard deviation of each laser signal data segment to obtain a standard deviation sequence;
S205: and screening the standard deviation sequence according to the standard deviation upper limit value and the standard deviation lower limit value, and determining a first abnormal data segment.
Specifically, the EMD may perform a stabilization process on the laser signal data, where the laser signal data includes sampling mileage data set when the laser signal data is collected along a track by the track detection vehicle, and there are a plurality of sampling points along the set sampling mileage, each sampling point has laser signal data corresponding to the sampling point, and the laser signal data obtained by the plurality of sampling points are: y= { Y (i) }, i=1, 2,...
The residual quantity of N intrinsic mode components and signals can be obtained after the stabilization treatment by an empirical mode decomposition method, wherein the number N of the intrinsic mode components is determined by a cyclic judgment criterion of the empirical mode decomposition method, N is a positive integer greater than 0, and the empirical mode decomposition method obtains N intrinsic mode components IMF (j) with main frequency components ranging from high to low, j=1, 2. Computing the sum of the first M eigenmode componentsM herein may take on the value 1 or 2.
And when the sum of the first M eigenvalue components is subjected to sliding extraction according to a set time window length and a set step length, wherein the set time window length refers to the length of any one of a plurality of laser signal data segments obtained through sliding extraction, one laser signal data segment is extracted, then the set step length is slid, and the next laser signal data segment is extracted. It should be noted that the number of the laser signal data segments is an integer, and if the data amount of the end of the I is smaller than the set time window length when the data amount of the end is slid to the end of the I according to the set step length, the data amount of the end is not extracted as one laser signal data segment. The set time window length and the set step length can be determined according to actual working conditions.
For example, the data sequence of the first M eigenmode components includes 10000 data points with sampling mileage, the time window length is set to 800 data, the step length is set to 100 data, a first laser signal data segment is obtained according to the 1 st to 800 th data during sliding extraction, a second laser signal data segment is obtained by extracting the 101 st to 900 th data after sliding 100 data, and a plurality of laser signal data segments are sequentially obtained.
Further calculating the standard deviation of each laser signal data segment to obtain a standard deviation sequence: std (r), r=0, 1,2, … s; where s is the number of laser signal data segments.
The standard deviation upper limit value and the standard deviation lower limit value are determined before screening the standard deviation sequence according to the standard deviation upper limit value and the standard deviation lower limit value. The upper limit value of the standard deviation is W u1＝max{Su,P99 }, that is, the maximum value in S u and P 99 is taken as the upper limit value of the standard deviation, S u is the maximum standard deviation of the standard deviations corresponding to the historical laser signal data segments without abnormality, and P 99 is the fractional value corresponding to 99% of the cumulative percentage of the laser signal standard deviation sequence std (r) in the abnormal state to be determined. The lower limit value of the standard deviation is W l1＝min{Sl,P01 }, that is, the minimum value in S l and P 01 is taken as the lower limit value of the standard deviation, S l is the minimum standard deviation in the standard deviations corresponding to the historical laser signal data segments without abnormality, and P 01 is the fractional value corresponding to the cumulative percentage of the laser signal standard deviation sequence std (r) to be determined in the abnormal state being 1%.
And screening to obtain a standard deviation value which is larger than the standard deviation upper limit value or smaller than the standard deviation lower limit value in the standard deviation sequence std (r) according to the standard deviation upper limit value and the standard deviation lower limit value, and obtaining a laser signal data segment corresponding to the track mileage section as a first abnormal data segment according to the track mileage section corresponding to the standard deviation value, wherein specifically, if the standard deviation value is larger than the standard upper limit value, the corresponding laser signal data segment is a first high-frequency abnormal data segment, and if the standard deviation value is smaller than the standard lower limit value, the corresponding laser signal data segment is a first low-frequency abnormal data segment.
The laser sensor is interfered by factors such as sunlight, rainwater, foreign matter shielding and the like, abnormal conditions of increased abnormal fluctuation high-frequency components, approximate no fluctuation (weak fluctuation) of signals can occur, string pulling of different Yu Laxian sensors is broken, step-shaped fluctuation of the laser signals is continuous, no standby replacement is needed to solve the abnormality, the surge direction of corresponding signals is unknown, and the method for processing the abnormality of the string pulling sensor is not applicable.
Referring to fig. 3, in this embodiment, the processing the raw detection data by the local peak search algorithm in combination with the root mean square of the sliding of the data segment, and identifying the second abnormal data segment further includes:
s301: sliding extraction is carried out on the string pulling signal data according to the set time window length and the set step length, so that a plurality of string pulling signal data segments are obtained;
S302: calculating the root mean square of each pull string signal data segment to obtain a root mean square sequence;
S303: judging whether an abnormal root mean square exists in the root mean square sequence;
s304: if yes, carrying out cyclic correction on the pull string signal data to obtain a correction sequence;
s305: performing sliding extraction on the correction sequence according to the set time window length and the set step length to obtain a plurality of correction data segments;
s306: calculating the root mean square of each correction data segment to obtain a correction root mean square sequence;
s307: screening the corrected root mean square sequence according to a correction threshold value to determine a second abnormal data segment;
The string pulling signal data comprise sampling mileage data set when the track detection vehicle collects along the track, a plurality of sampling points are arranged along the set sampling mileage, each sampling point has corresponding string pulling signal data, and the string pulling signal data obtained by the sampling points are as follows: x= { X (i) }, i=1, 2,...
And carrying out sliding extraction on the string pulling signal data according to the set time window length and the set step length to obtain a plurality of string pulling signal data segments, wherein each string pulling signal data segment is provided with the data of the set time window length, and the step length is set at intervals between the starting points of any two adjacent string pulling signal data segments.
Further, the root mean square of each pull string signal data segment is calculated to obtain a root mean square sequence rms (r), r=0, 1,2, … s, wherein s is the number of pull string signal data segments.
And judging whether an abnormal root mean square exists in the root mean square sequence, if not, indicating that a second abnormal data segment does not exist in the pull string signal data.
If so, after the loop correction is carried out on the string pulling signal data, a correction sequence is further obtained: x k＝{xk (i) }, i=1, 2,..n, where k represents the cyclic correction k times. And performing sliding extraction on the correction sequence according to the set time window length and the set step length to obtain a plurality of correction data segments, and calculating the root mean square of each correction data segment to obtain a correction root mean square sequence rms' (r), wherein r=0, 1,2 and … s.
The correction threshold is determined before screening the correction root mean square sequence according to the correction threshold. Wherein the correction threshold is W u2＝|βG00, G 00 is an initial signal value, and beta can be determined to be 0.5-0.9 according to the actual working condition. Specifically, the method for determining the initial signal value of the string is as follows: the corresponding signal value after the string pulling sensor is installed on the track detection vehicle is an initial signal value, at the moment, a string pulling hook of the string pulling sensor is not installed, and the string pulling sensor does not work yet. The reason for the beta value is that: since the string pulling hook of the string pulling sensor is not installed when the initial signal value is obtained, the initial signal value can be regarded as the signal value corresponding to the string pulling fracture, and if the root mean square value in the corrected root mean square sequence approaches the signal value, the situation that the string pulling fracture is likely to occur corresponds.
According to the correction threshold, screening to obtain a root mean square value which is larger than the correction threshold in the correction root mean square sequence rms' (r), and according to the track mileage section corresponding to the root mean square value, obtaining that the string pulling signal data section corresponding to the track mileage section is a second abnormal data section, specifically, if the root mean square value is larger than the correction threshold, the corresponding string pulling signal data section is the second abnormal data section.
In this embodiment, the performing the cyclic correction on the pull string signal data to obtain the correction sequence further includes:
Referring to fig. 4, the following steps are circularly executed for several times, and new string pulling signal data obtained after several times of circulation is used as a correction sequence:
S401: calculating the pull string signal data according to a local peak value searching algorithm to obtain a local extremum sequence;
S402: carrying out interpolation resampling processing on the local extremum sequence to obtain a capacity expansion sequence; wherein the data volume of the expansion sequence is the same as the data volume of the pull string signal data;
s403: and correspondingly subtracting the data in the string pulling signal data from the data in the capacity expansion sequence to obtain new string pulling signal data.
It should be noted that the local extremum sequence is a local minimum value sequence or a local maximum value sequence, wherein if the initial signal value of the string is a positive sign, the local extremum sequence is taken as the local minimum value sequence, and the local minimum value sequence is subjected to interpolation resampling; if the initial signal value of the string is a negative sign, taking the local extremum sequence as a local maximum value sequence, and carrying out interpolation resampling on the local maximum value sequence;
Specifically, when the local peak value search algorithm is applied, differential calculation is performed on the pull string signal data x= { X (i) }, i=1, 2..n to obtain a differential sequence, if a certain differential value in the differential sequence is opposite to the sign of the previous adjacent differential value, the differential value is a local peak value point, and more specifically: the differential value of a certain point is negative, and the differential value of the previous adjacent point is positive, so that the point corresponds to a maximum value point and is the minimum value point; after all local peaks are screened out, the local peak sequence Z 1＝{z1 (i) }, i=1, 2,. The method for determining the local peak sequence can be as follows: selecting local peaks larger than the lower limit of the absolute value of the set peak value to form a local peak value sequence according to the set interval, wherein the set interval can be determined according to the actual working condition, the lower limit of the absolute value of the set peak value can be taken as an initial signal value of |beta G 00|,G00, beta can be determined to be 0.5-0.9 according to the actual working condition, starting from the initial position of the local peak value, judging whether the absolute value of the current local peak value is larger than the lower limit of the absolute value of the set peak value at intervals, if so, determining that the current local peak value belongs to the local peak value sequence, and further obtaining the local peak value sequence formed by a local peak values.
Through the above steps, a is smaller than n, so that interpolation resampling processing is needed to be performed on the local extremum sequence to obtain a capacity expansion sequence Z' 1＝{z′1 (i) }, i=1, 2. Because the volume expansion sequence is the same as the data volume of the adjusted string pulling signal data, the adjusted string pulling signal data can be correspondingly subtracted from the data in the volume expansion sequence, namely, x (i) -z' 1 (i); and (3) obtaining new adjusted string pulling signal data, carrying out the steps on the new adjusted string pulling signal data again, and repeating the steps for k times, wherein k can be 3 to 5, and finally obtaining X k＝{xk (i) }, i=1, 2, and n after repeating the steps for k times.
In embodiments herein, the determining whether an abnormal root mean square exists in the root mean square sequence further comprises:
Any root mean square value in the root mean square sequence is calculated by the following formula:
|rms(r)-|G00||＜|αG00|；
Wherein rms (r) is the r-th root mean square value in the root mean square sequence, G 00 is the initial signal value of the pull string signal data, and alpha is the fluctuation coefficient of the pull string signal, wherein alpha can be 0.1-0.2;
If any root mean square value meets the formula, the root mean square value is an abnormal root mean square, namely, if one root mean square value meets the formula, the root mean square value is the abnormal root mean square, and the second abnormal data segment exists in the string pulling signal data.
Referring to fig. 5, in this embodiment, the processing the raw detection data by the data segment sliding standard deviation, and identifying the third abnormal data segment further includes:
s501: sliding extraction is carried out on the string pulling signal data according to the set time window length and the set step length, so that a plurality of string pulling signal data segments are obtained;
S502: calculating the standard deviation of each string pulling signal data segment to obtain a string pulling standard deviation sequence;
S503: and screening the string standard deviation sequence according to a string pulling threshold value, and determining a third abnormal data segment.
The string pulling signal data comprise sampling mileage data set when the track detection vehicle collects along the track, a plurality of sampling points are arranged along the set sampling mileage, each sampling point has corresponding string pulling signal data, and the string pulling signal data obtained by the sampling points are as follows: x= { X (i) }, i=1, 2,...
And carrying out sliding extraction on the string pulling signal data according to the set time window length and the set step length to obtain a plurality of string pulling signal data segments, wherein each string pulling signal data segment is provided with the data of the set time window length, and the step length is set at intervals between the starting points of any two adjacent string pulling signal data segments.
Further, calculating the standard deviation of each string pulling signal data segment to obtain a string pulling standard deviation sequence std' (r), r=0, 1,2,..s; before screening the string standard deviation sequence according to the string pulling threshold value, the string pulling threshold value W l2＝min{S1′,P′01 is required to be determined, namely, the minimum value in S 1 ' and P ' 01 is taken as the string pulling threshold value, S 1 ' is the minimum standard deviation in the standard deviation of the data segments of the historical string pulling signal without abnormality, and P ' 01 is the bit division value corresponding to the accumulated percentage of the string pulling standard deviation sequence std ' (r) being 1%. If the standard deviation sequence does not have the standard deviation value smaller than the string pulling threshold value, the third abnormal data segment does not exist in the string pulling signal data, and if the standard deviation sequence has the standard deviation value smaller than the string pulling threshold value, the string pulling signal data segment corresponding to the track mileage section can be obtained to be the third abnormal data segment according to the track mileage section corresponding to the standard deviation value.
The common faults of the string pulling signal are signal surge caused by string pulling fracture, the corresponding signal shows step-shaped abrupt change and the signal is approximately kept stable, the string pulling signal can fall back in a step shape after a certain distance and is recovered to be normal at the moment of standby string pulling, besides the fracture, the string pulling signal can also show step-shaped surge caused by string pulling aging and the like and is approximately kept stable for a certain distance and then is recovered automatically. The local peak value searching algorithm and the judging method of the sliding root mean square of the data section can eliminate trend items of the pull string signal caused by the curve section, keep step mutation at the broken position of the pull string and recognize the abnormal section. The signal surge and the approximate position stability can be directly determined by means of the section sliding standard deviation. The two are combined to judge whether the use state of the pull string is broken or aged and needs to be replaced.
Referring to fig. 6, in the embodiment herein, the processing the raw detection data by the difference method in combination with the data threshold value, and identifying the fourth abnormal data segment further includes:
s601: calculating selected data by a difference method to obtain a difference value sequence, wherein the selected data is laser signal data, gyro component signal data or accelerometer signal data;
S602: judging whether an abnormal value exists in the selected data, wherein the abnormal value is smaller than the data threshold value, and the differential value corresponding to the abnormal value in the differential value sequence is smaller than the data threshold value;
S603: if yes, a fourth abnormal data segment is obtained according to the abnormal value set.
In particular, the selected data may be q= { Q (i) }, i=1, 2,.. the selected data is calculated by the difference method to obtain a differential value sequence Δq= { Δq (i) }, i=1, 2. Those skilled in the art will recognize that the difference value is obtained by subtracting the previous item of data from the next item of data.
The data threshold value needs to be determined before judging whether the abnormal value exists in the selected data, the data threshold value can be determined according to the actual working condition, and the fourth abnormal data segment is a value slightly larger than 0, for example, 0.01, 0.02 and the like because the signal persistence is approximately 0. If not, the fourth abnormal data segment does not exist.
If any data value exists in the selected data, the data value is smaller than the data threshold value, and the difference value corresponding to the data value is also smaller than the data threshold value, the data value is an abnormal value. Specifically, the differential value corresponding to the data value is a differential value obtained by the difference between the data value and the data value adjacent to the data value preamble.
And screening all abnormal values by the method to obtain a fourth abnormal data segment.
Finally, in step S106, the first abnormal data segment, the second abnormal data segment, the third abnormal data segment, and the fourth abnormal data segment are combined to obtain an abnormal data segment. Specifically, the abnormal data segment is a first abnormal data segment, a second abnormal data segment, a third abnormal data segment or a fourth abnormal data segment, and may include a plurality of abnormal data segments, when merging, if a data segment interval between any two adjacent abnormal data segments is smaller than a data segment interval threshold, the two adjacent abnormal data segments are considered to be relatively close, and the data segment between the two adjacent abnormal data segments is determined to be the abnormal data segment, wherein the size of the data segment interval threshold can be determined according to an actual working condition and a time window length in the document.
Based on the above-mentioned method for identifying the geometric anomaly data of the track, the embodiment of the invention further provides an apparatus for identifying the geometric anomaly data of the track. The described devices may include systems (including distributed systems), software (applications), modules, components, servers, clients, etc. that employ the methods described in embodiments herein in combination with the necessary devices to implement the hardware. Based on the same innovative concepts, the embodiments herein provide for devices in one or more embodiments as described in the following examples. Since the implementation of the device for solving the problem is similar to the method, the implementation of the device in the embodiment herein may refer to the implementation of the foregoing method, and the repetition is not repeated. As used below, the term "unit" or "module" may be a combination of software and/or hardware that implements the intended function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
Specifically, fig. 7 is a schematic block diagram of an embodiment of an apparatus for identifying geometric anomaly data of a track according to the embodiment of the present disclosure, and referring to fig. 7, the apparatus for identifying geometric anomaly data of a track according to the embodiment of the present disclosure includes: the system comprises an acquisition module 100, a first determination module 200, a second determination module 300, a third determination module 400, a fourth determination module 500 and a combination module 600.
An acquisition module 100, configured to acquire original detection data of the track geometry;
The first determining module 200 is configured to process the original detection data by using an empirical mode decomposition method in combination with a data segment sliding standard deviation, and identify a first abnormal data segment;
The second determining module 300 is configured to process the original detection data by combining a local peak value searching algorithm with a sliding root mean square of the data segment, and identify to obtain a second abnormal data segment;
A third determining module 400, configured to process the original detection data through a data segment sliding standard deviation, and identify a third abnormal data segment;
a fourth determining module 500, configured to process the original detection data by combining a difference method with a data threshold, and identify a fourth abnormal data segment;
And the merging module 600 is configured to merge the first abnormal data segment, the second abnormal data segment, the third abnormal data segment, and the fourth abnormal data segment to obtain an abnormal data segment.
Referring to fig. 8, a computer device 802 is further provided in an embodiment herein based on the above-described method for identifying geometric anomaly data of a track, wherein the above-described method is executed on the computer device 802. The computer device 802 may include one or more processors 804, such as one or more Central Processing Units (CPUs) or Graphics Processors (GPUs), each of which may implement one or more hardware threads. The computer device 802 may also comprise any memory 806 for storing any kind of information, such as code, settings, data, etc., and in a particular embodiment a computer program on the memory 806 and executable on the processor 804, which computer program, when executed by the processor 804, may execute instructions according to the methods described above. For example, and without limitation, memory 806 may include any one or more of the following combinations: any type of RAM, any type of ROM, flash memory devices, hard disks, optical disks, etc. More generally, any memory may store information using any technique. Further, any memory may provide volatile or non-volatile retention of information. Further, any memory may represent fixed or removable components of computer device 802. In one case, the computer device 802 may perform any of the operations of the associated instructions when the processor 804 executes the associated instructions stored in any memory or combination of memories. The computer device 802 also includes one or more drive mechanisms 808, such as a hard disk drive mechanism, an optical disk drive mechanism, and the like, for interacting with any memory.
The computer device 802 may also include an input/output module 810 (I/O) for receiving various inputs (via an input device 812) and for providing various outputs (via an output device 814). One particular output mechanism may include a presentation device 816 and an associated graphical user interface 818 (GUI). In other embodiments, input/output module 810 (I/O), input device 812, and output device 814 may not be included, but merely as a computer device in a network. The computer device 802 may also include one or more network interfaces 820 for exchanging data with other devices via one or more communication links 822. One or more communications buses 824 couple the above-described components together.
The communication link 822 may be implemented in any manner, such as, for example, through a local area network, a wide area network (e.g., the internet), a point-to-point connection, etc., or any combination thereof. Communication link 822 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc., governed by any protocol or combination of protocols.
Corresponding to the method in fig. 1-6, embodiments herein also provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the above method.
Embodiments herein also provide a computer readable instruction wherein the program therein causes the processor to perform the method as shown in fig. 1 to 6 when the processor executes the instruction.
It should be understood that, in the various embodiments herein, the sequence number of each process described above does not mean the sequence of execution, and the execution sequence of each process should be determined by its functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments herein.
It should also be understood that in embodiments herein, the term "and/or" is merely one relationship that describes an associated object, meaning that three relationships may exist. For example, a and/or B may represent: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided herein, it should be understood that the disclosed systems, devices, and methods may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. In addition, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices, or elements, or may be an electrical, mechanical, or other form of connection.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the elements may be selected according to actual needs to achieve the objectives of the embodiments herein.
In addition, each functional unit in the embodiments herein may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions herein are essentially or portions contributing to the prior art, or all or portions of the technical solutions may be embodied in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments herein. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Specific examples are set forth herein to illustrate the principles and embodiments herein and are merely illustrative of the methods herein and their core ideas; also, as will be apparent to those of ordinary skill in the art in light of the teachings herein, many variations are possible in the specific embodiments and in the scope of use, and nothing in this specification should be construed as a limitation on the invention.
Claims (11)
1. A method for identifying geometric anomaly data of a track, comprising:
Acquiring original detection data of track geometry;
processing the original detection data by combining an empirical mode decomposition method with a data segment sliding standard deviation, and identifying to obtain a first abnormal data segment;
Processing the original detection data by combining a local peak value searching algorithm with a data segment sliding root mean square, and identifying to obtain a second abnormal data segment;
processing the original detection data through the data segment sliding standard deviation, and identifying to obtain a third abnormal data segment;
processing the original detection data by combining a data threshold value through a difference method, and identifying to obtain a fourth abnormal data segment;
And merging the first abnormal data segment, the second abnormal data segment, the third abnormal data segment and the fourth abnormal data segment to obtain an abnormal data segment.
2. The method for identifying geometric anomaly data of a track according to claim 1, wherein the raw detection data further comprises:
laser signal data, string signal data, gyro assembly signal data, and accelerometer signal data.
3. The method for identifying geometric anomaly data of a track according to claim 2, wherein the processing the raw detection data by an empirical mode decomposition method in combination with a data segment sliding standard deviation, and identifying a first anomaly data segment further comprises:
Performing stabilization treatment on the laser signal data through an empirical mode decomposition method to obtain N intrinsic mode components;
extracting the sum of the first M eigenvalue components in the N eigenvalue components;
Performing sliding extraction on the sum of the first M eigenvalue components according to a set time window length and a set step length to obtain a plurality of laser signal data segments;
calculating the standard deviation of each laser signal data segment to obtain a standard deviation sequence;
And screening the standard deviation sequence according to the standard deviation upper limit value and the standard deviation lower limit value, and determining a first abnormal data segment.
4. The method for identifying geometric anomaly data of a track according to claim 2, wherein the processing the original detected data by a local peak search algorithm in combination with a root mean square of the sliding of the data segments, and identifying the second anomaly data segment further comprises:
sliding extraction is carried out on the string pulling signal data according to the set time window length and the set step length, so that a plurality of string pulling signal data segments are obtained;
calculating the root mean square of each pull string signal data segment to obtain a root mean square sequence;
Judging whether an abnormal root mean square exists in the root mean square sequence;
If yes, carrying out cyclic correction on the pull string signal data to obtain a correction sequence;
Performing sliding extraction on the correction sequence according to the set time window length and the set step length to obtain a plurality of correction data segments;
calculating the root mean square of each correction data segment to obtain a correction root mean square sequence;
and screening the corrected root mean square sequence according to a correction threshold value to determine a second abnormal data segment.
5. The method for identifying geometric anomaly data of a track according to claim 4, wherein the performing a cyclic correction on the pull-string signal data to obtain a correction sequence further comprises:
The method comprises the following steps of circularly executing for a plurality of times, and taking new string pulling signal data obtained after the plurality of times of circulation as a correction sequence:
calculating the pull string signal data according to a local peak value searching algorithm to obtain a local extremum sequence;
Carrying out interpolation resampling processing on the local extremum sequence to obtain a capacity expansion sequence; wherein the data volume of the expansion sequence is the same as the data volume of the pull string signal data;
and correspondingly subtracting the data in the string pulling signal data from the data in the capacity expansion sequence to obtain new string pulling signal data.
6. The method of claim 4, wherein determining whether an abnormal root mean square exists in the root mean square sequence further comprises:
Any root mean square value in the root mean square sequence is calculated by the following formula:
|rms(r)-|G00||＜|αG00|；
wherein rms (r) is the r-th root mean square value in the root mean square sequence, G 00 is the initial signal value of the pull string signal data, and alpha is the fluctuation coefficient of the pull string signal;
If any root mean square value satisfies the above formula, the root mean square value is an abnormal root mean square.
7. The method for identifying geometric anomaly data of a track according to claim 4, wherein the processing the raw detection data by the data segment sliding standard deviation, identifying to obtain a third anomaly data segment, further comprises:
calculating the standard deviation of each string pulling signal data segment to obtain a string pulling standard deviation sequence;
and screening the string standard deviation sequence according to a string pulling threshold value, and determining a third abnormal data segment.
8. The method for identifying geometric anomaly data of a track according to claim 2, wherein the processing the original detected data by a difference method in combination with a data threshold value, and identifying a fourth anomaly data segment further comprises:
calculating selected data by a difference method to obtain a difference value sequence, wherein the selected data is laser signal data, gyro component signal data or accelerometer signal data;
judging whether an abnormal value exists in the selected data, wherein the abnormal value is smaller than the data threshold value, and the differential value corresponding to the abnormal value in the differential value sequence is smaller than the data threshold value;
if yes, a fourth abnormal data segment is obtained according to the abnormal value set.
9. An apparatus for identifying geometric anomaly data of a track, the apparatus comprising:
The acquisition module is used for acquiring original detection data of the track geometry;
the first determining module is used for processing the original detection data by combining a data segment sliding standard deviation through an empirical mode decomposition method, and identifying to obtain a first abnormal data segment;
the second determining module is used for processing the original detection data by combining a local peak value searching algorithm with the sliding root mean square of the data segment, and identifying to obtain a second abnormal data segment;
The third determining module is used for processing the original detection data through the sliding standard deviation of the data segment, and identifying to obtain a third abnormal data segment;
The fourth determining module is used for processing the original detection data by combining a data threshold value through a difference method and identifying to obtain a fourth abnormal data segment;
and the merging module is used for merging the first abnormal data segment, the second abnormal data segment, the third abnormal data segment and the fourth abnormal data segment to obtain an abnormal data segment.
10. A computer device comprising a memory, a processor, and a computer program stored on the memory, characterized in that the computer program, when being executed by the processor, performs the instructions of the method according to any of claims 1-8.
11. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor of a computer device, executes instructions of the method according to any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210009844.7A CN114417921B (en) | 2022-01-05 | 2022-01-05 | Method, device, equipment and storage medium for identifying geometric anomaly data of track |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210009844.7A CN114417921B (en) | 2022-01-05 | 2022-01-05 | Method, device, equipment and storage medium for identifying geometric anomaly data of track |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114417921A CN114417921A (en) | 2022-04-29 |
| CN114417921B true CN114417921B (en) | 2024-04-30 |
Family
ID=81272127
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210009844.7A Active CN114417921B (en) | 2022-01-05 | 2022-01-05 | Method, device, equipment and storage medium for identifying geometric anomaly data of track |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114417921B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104794312A (en) * | 2015-05-15 | 2015-07-22 | 西南交通大学 | Method and device for evaluating track regularity |
| WO2017055838A1 (en) * | 2015-09-28 | 2017-04-06 | University Of Huddersfield | Method and system for predicting railway track quality |
| CN108592853A (en) * | 2018-04-09 | 2018-09-28 | 中国铁道科学研究院 | Track plates arch upward position identifying method, device, storage medium and equipment |
| CN108595374A (en) * | 2018-03-26 | 2018-09-28 | 中国铁道科学研究院 | High speed railway track geometry minor change recognition methods and device |
| CN109367569A (en) * | 2018-09-10 | 2019-02-22 | 广州大铁锐威科技有限公司 | Detection data synchronous and method for track geometric parameter measurement |
| CN110409234A (en) * | 2019-07-25 | 2019-11-05 | 北京三岭基业科技发展有限公司 | A kind of rail in high speed railway smooth degree dynamic testing method and device |
| KR102116890B1 (en) * | 2019-11-07 | 2020-05-29 | 주식회사 지에스지 | Mobile rail/track defect real-time analysis and monitoring system and method using wireless accelerometer |
| CN111655562A (en) * | 2017-11-30 | 2020-09-11 | 斯佩里铁路控股有限公司 | System and method for inspecting rails using machine learning |
| CN112308824A (en) * | 2020-10-21 | 2021-02-02 | 中国铁道科学研究院集团有限公司 | Curve radius classification identification method and device based on track geometric detection data |
| CN112380710A (en) * | 2020-11-18 | 2021-02-19 | 中国铁道科学研究院集团有限公司 | Method and device for determining state of track plate |
| CN113312715A (en) * | 2021-05-10 | 2021-08-27 | 暨南大学 | Tramcar groove rail distortion irregularity prediction method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190039633A1 (en) * | 2017-08-02 | 2019-02-07 | Panton, Inc. | Railroad track anomaly detection |
| FR3093493B1 (en) * | 2019-03-04 | 2021-04-09 | Commissariat Energie Atomique | Rolling stock anomaly detection method using a deformation signal of a rail support |
-
2022
- 2022-01-05 CN CN202210009844.7A patent/CN114417921B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104794312A (en) * | 2015-05-15 | 2015-07-22 | 西南交通大学 | Method and device for evaluating track regularity |
| WO2017055838A1 (en) * | 2015-09-28 | 2017-04-06 | University Of Huddersfield | Method and system for predicting railway track quality |
| CN111655562A (en) * | 2017-11-30 | 2020-09-11 | 斯佩里铁路控股有限公司 | System and method for inspecting rails using machine learning |
| CN108595374A (en) * | 2018-03-26 | 2018-09-28 | 中国铁道科学研究院 | High speed railway track geometry minor change recognition methods and device |
| CN108592853A (en) * | 2018-04-09 | 2018-09-28 | 中国铁道科学研究院 | Track plates arch upward position identifying method, device, storage medium and equipment |
| CN109367569A (en) * | 2018-09-10 | 2019-02-22 | 广州大铁锐威科技有限公司 | Detection data synchronous and method for track geometric parameter measurement |
| CN110409234A (en) * | 2019-07-25 | 2019-11-05 | 北京三岭基业科技发展有限公司 | A kind of rail in high speed railway smooth degree dynamic testing method and device |
| KR102116890B1 (en) * | 2019-11-07 | 2020-05-29 | 주식회사 지에스지 | Mobile rail/track defect real-time analysis and monitoring system and method using wireless accelerometer |
| CN112308824A (en) * | 2020-10-21 | 2021-02-02 | 中国铁道科学研究院集团有限公司 | Curve radius classification identification method and device based on track geometric detection data |
| CN112380710A (en) * | 2020-11-18 | 2021-02-19 | 中国铁道科学研究院集团有限公司 | Method and device for determining state of track plate |
| CN113312715A (en) * | 2021-05-10 | 2021-08-27 | 暨南大学 | Tramcar groove rail distortion irregularity prediction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114417921A (en) | 2022-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111832002A (en) | Detecting anomalous accounts using event logs | |
| CN103646167A (en) | Satellite abnormal condition detection system based on telemeasuring data | |
| CN104021601A (en) | Car collision detection method and device based on three-shaft acceleration sensor | |
| CN103606221B (en) | Fault automatic diagnostic method of counter and device | |
| CN106845447A (en) | A kind of face gas concentration prediction method for early warning | |
| CN108195396A (en) | A kind of detection method and system of the validity of new-energy automobile vehicle data | |
| CN110008247A (en) | Abnormal source determines method, apparatus, equipment and computer readable storage medium | |
| CN116308305B (en) | Bridge health monitoring data management system | |
| CN110867077B (en) | Road optimization method based on traffic video structured data quality control | |
| CN114417921B (en) | Method, device, equipment and storage medium for identifying geometric anomaly data of track | |
| WO2017055838A1 (en) | Method and system for predicting railway track quality | |
| CN113670616A (en) | Bearing performance degradation state detection method and system | |
| CN117191305B (en) | State evaluation method and system for highway bridge | |
| CN108346196B (en) | Method and device for judging heavy load and no load of vehicle | |
| CN113375775B (en) | Weight correction method and weight correction system for shared vehicle and electronic equipment | |
| CN112781556A (en) | Well lid transaction monitoring method and device based on multi-data fusion filtering | |
| CN102435209B (en) | Method for eliminating obliquity sensor signal baseline drift | |
| CN105785189A (en) | Portable transformer direct current magnetic bias monitor | |
| CN117271980B (en) | Drilling data processing method and device, electronic equipment and storage medium | |
| JP2021111034A (en) | Abnormality detection program, abnormality detection method, and information processing device | |
| CN106645776B (en) | The measuring wheel speed system and measuring wheel speed method of airplane brake system | |
| CN109655020A (en) | One tooth footpath of gear is to comprehensive deviation and tangential comprehensive deviation detection method | |
| CN109614966A (en) | It is a kind of based on information fusion Lidar sensor efficient road surface and curb detection method | |
| CN113947129B (en) | Method, equipment and medium for training and using AI model for intelligently identifying wheel out-of-roundness state | |
| CN108595386B (en) | Distributed optical fiber vibration measurement method and device based on high-order cumulant analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |