CN119152699B - Rail transit information data cleaning method and system - Google Patents
Rail transit information data cleaning method and system Download PDFInfo
- Publication number
- CN119152699B CN119152699B CN202411659151.8A CN202411659151A CN119152699B CN 119152699 B CN119152699 B CN 119152699B CN 202411659151 A CN202411659151 A CN 202411659151A CN 119152699 B CN119152699 B CN 119152699B
- Authority
- CN
- China
- Prior art keywords
- data
- vibration sensor
- difference
- amplitude
- track
- 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 51
- 238000004140 cleaning Methods 0.000 title claims abstract description 49
- 230000005856 abnormality Effects 0.000 claims abstract description 53
- 230000011218 segmentation Effects 0.000 claims abstract description 22
- 230000008859 change Effects 0.000 claims description 22
- 238000004458 analytical method Methods 0.000 claims description 16
- 238000007405 data analysis Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 abstract description 28
- 238000012544 monitoring process Methods 0.000 abstract description 8
- 238000012545 processing Methods 0.000 abstract description 8
- 230000003862 health status Effects 0.000 abstract 1
- 230000008569 process Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 9
- 238000003860 storage Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 7
- 238000005070 sampling Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 239000007787 solid Substances 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000002093 peripheral effect Effects 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 230000002238 attenuated effect Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
本发明涉及电数字数据处理技术领域，具体涉及一种轨道交通信息数据清洗方法及系统，所述方法包括：基于轨道振动传感器的预设切分周期数据，确定轨道振动传感器的局部数据异常程度和相邻局部数据之间的振幅差异；基于振幅差异，确定轨道振动传感器的整体规律性特征因子；利用多个相邻轨道振动传感器的整体规律性特征因子，确定轨道振动传感器的轨道节点故障影响可能性；利用局部数据异常程度和轨道节点故障影响可能性，确定局部数据是否为待清洗数据。通过本发明的轨道交通信息数据清洗方法，能够针对性排除或修正存在严重异常干扰的振动数据，确保系统仍然是对轨道节点自身的健康状态进行分析，提高对轨道节点的监测准确性。
The present invention relates to the field of electrical digital data processing technology, and specifically to a rail transit information data cleaning method and system, the method comprising: determining the degree of abnormality of local data of the rail vibration sensor and the amplitude difference between adjacent local data based on the preset segmentation period data of the rail vibration sensor; determining the overall regularity characteristic factor of the rail vibration sensor based on the amplitude difference; determining the possibility of influence of rail node failure of the rail vibration sensor using the overall regularity characteristic factor of multiple adjacent rail vibration sensors; determining whether the local data is data to be cleaned using the degree of abnormality of local data and the possibility of influence of rail node failure. Through the rail transit information data cleaning method of the present invention, vibration data with serious abnormal interference can be targetedly excluded or corrected, ensuring that the system still analyzes the health status of the rail node itself, and improving the monitoring accuracy of the rail node.
Description
Technical Field
The invention relates to the technical field of electric digital data processing, in particular to a method and a system for cleaning rail transit information data.
Background
The track traffic information data refers to various data related to the track traffic system, including train position, speed, delay situation, passenger flow, station operation situation, etc. Such data may be collected by various sensors, monitoring devices, computer systems, and other data sources.
The vehicle of the rail transit comprises subways, and relevant information of the vehicle comprises relevant data of states of rail equipment, such as running states and fault information of equipment (such as signal equipment, power equipment and communication equipment) of a recorded rail transit system, and vibration data of each node rail are contained, wherein the vibration data are collected by vibration sensors and can be used for equipment maintenance and fault investigation to ensure normal running of the rail transit system.
When the aging of the rail generates the abnormal condition of the rail node caused by cracks, looseness and the like, the abnormal frequency or the amplitude of the vibration can be suddenly increased or reduced, and the abnormal vibration data of the rail node needs to be separately identified for analysis. However, in the process of monitoring the track state, on one hand, due to the service life of the vibration sensor and the influence of external factors in the monitoring process, certain interference fluctuation exists in the acquired vibration data, on the other hand, due to the fact that a plurality of track trains sequentially run on the tracks and certain differences exist in speeds of different trains at corresponding detection positions, certain differences exist in generated interaction force, and certain interference fluctuation exists in the vibration data at the detection positions, so that the abnormal interference fluctuation in the two aspects can cause the final reduction of the monitoring accuracy of the abnormal track nodes, the abnormal interference data are required to be cleaned, and the abnormal vibration data of the track nodes are reserved for analysis.
Disclosure of Invention
In order to solve the technical problem of reduced monitoring accuracy of abnormal track nodes caused by abnormal interference fluctuation, the invention aims to provide a method and a system for cleaning track traffic information data, wherein the adopted technical scheme is as follows:
the invention provides a method for cleaning rail transit information data, which comprises the following steps:
determining the abnormality degree of local data of the track vibration sensor and the amplitude difference between adjacent local data based on preset segmentation period data of the track vibration sensor;
Determining an overall regularity feature factor of the orbital vibration sensor based on the amplitude differences;
Determining the possibility of influence of the fault of the track node of the track vibration sensor by utilizing the overall regularity characteristic factors of a plurality of adjacent track vibration sensors;
And determining whether the local data is to be cleaned or not by utilizing the abnormality degree of the local data and the influence possibility of the fault of the track node.
Further, the step of determining the degree of abnormality of the local data of the track vibration sensor based on the preset slicing cycle data of the track vibration sensor includes:
determining any target peak point and a peak group formed by a plurality of corresponding peak points adjacent to the target peak point based on preset segmentation period data of the track vibration sensor;
Determining a target amplitude difference value between the target peak point and other peak points in the peak group;
And determining the local data abnormality degree of the track vibration sensor by using the target amplitude difference value and the maximum amplitude difference value in the peak value group.
Further, the step of determining the degree of abnormality of the local data of the track vibration sensor using the target amplitude difference value and the maximum amplitude difference value in the peak group includes:
determining the local prominence degree of local data corresponding to the target peak point by utilizing the target amplitude difference value;
And calculating the local data abnormality degree of the track vibration sensor by using the local protrusion degree, the target amplitude corresponding to the target peak point and the maximum amplitude difference value in the peak group.
Further, the step of determining the amplitude difference between the adjacent local data based on the preset slicing period data of the track vibration sensor includes:
Determining a first amplitude difference between each set of adjacent maxima based on preset slicing cycle data of the track vibration sensor;
determining a second amplitude difference between each set of adjacent minima based on the preset segmentation period data;
wherein, two adjacent maxima or two adjacent minima are used as a group.
Further, the step of determining an overall regularity feature factor of the rail vibration sensor based on the amplitude difference, includes:
determining a first difference in the first amplitude differences between adjacent groups using the first amplitude differences;
Determining a second difference in a second amplitude difference between adjacent groups using the second amplitude difference;
Determining a first amplitude change regularity and a second amplitude change regularity corresponding to the first difference value and the second difference value respectively;
Determining the average value of the amplitude differences corresponding to all the first amplitude differences and the second amplitude differences;
and calculating to obtain the overall regularity characteristic factor of the track vibration sensor by using the amplitude difference average value, the first amplitude change regularity and the second amplitude change regularity.
Further, the step of determining a rail node fault impact probability of the rail vibration sensor using an overall regularity feature factor of a plurality of adjacent rail vibration sensors, includes:
determining a first difference in overall regularity characteristic factor between the rail vibration sensor and a preceding adjacent rail vibration sensor in a preceding direction;
Determining a second difference in overall regularity characteristic factor between a plurality of adjacent rail vibration sensors in a direction behind the rail vibration sensor;
Determining a third difference in overall regularity characteristic factor between a plurality of adjacent track vibration sensors in a front direction of the front adjacent track vibration sensor;
Calculating the track node fault influence possibility of the track vibration sensor by using the first difference, the second difference and the third difference;
wherein the fore and aft directions are based on the direction of travel along the train.
Further, the step of calculating the track node fault influence probability of the track vibration sensor by using the first difference, the second difference and the third difference includes:
And calculating the track node fault influence possibility of the track vibration sensor by using the accumulated values of the first difference, the second difference and the third difference.
Optionally, the step of determining whether the local data is data to be cleaned by using the abnormality degree of the local data and the possibility of influence of the fault of the track node includes:
determining a ratio between the degree of local data anomaly and the likelihood of track node failure impact;
and comparing the normalized ratio with a preset threshold value to determine whether the local data is the data to be cleaned.
Optionally, after the step of determining whether the local data is data to be cleaned using the degree of abnormality of the local data and the possibility of influence of the failure of the track node, the method further includes:
And correcting the data to be cleaned by using the normalized ratio to obtain cleaned data.
The invention also provides a system for cleaning the rail transit information data, which is used for realizing the rail transit information data cleaning method, and comprises the following steps:
the data analysis module is used for determining the abnormality degree of local data of the track vibration sensor and the amplitude difference between adjacent local data based on the preset segmentation period data of the track vibration sensor;
The amplitude analysis module is used for determining the overall regularity characteristic factor of the track vibration sensor based on the amplitude difference;
The track analysis module is used for determining the track node fault influence possibility of the track vibration sensor by utilizing the overall regularity characteristic factors of the plurality of adjacent track vibration sensors;
and the cleaning evaluation module is used for determining whether the local data is to-be-cleaned data or not by utilizing the abnormality degree of the local data and the influence possibility of the fault of the track node.
The invention has the following beneficial effects:
According to the method, each local data (local vibration data) of the track vibration sensor in the preset segmentation period data is analyzed, so that the local abnormality degree of each local vibration data is judged, interference to abnormal vibration data judgment of the track node due to saw-tooth change characteristics of the vibration data and factors of the vibration sensor is avoided, accuracy of data cleaning is improved, and the integral data change rule of the vibration data collected by the vibration sensor on a time sequence is analyzed, meanwhile, the rule difference between the vibration data and other peripheral vibration sensors is analyzed, and accordingly the integral data regularity of the vibration sensor and possibility of influence of faults of the track node are judged, and misjudgment of interference fluctuation generated in the train travelling process on the abnormal vibration data of the track node is avoided, so that accuracy of subsequent data cleaning is improved. The method combines the abnormality degree of local data and the influence possibility of the fault of the track node, balances the abnormality degree of the track node and the influence degree of the abnormality interference of other factors, comprehensively judges whether each local vibration data is the vibration data seriously influenced by the abnormality interference fluctuation, and can not normally identify and analyze the abnormality generated by the track node due to the vibration data, so that the vibration data seriously interfered by the track node can be specifically eliminated or corrected, the system is ensured to analyze the health state of the track node, and the monitoring accuracy of the track node is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of steps of a method for cleaning rail transit information data according to an embodiment of the present invention;
fig. 2 is a detailed flowchart of step S1 in a method for cleaning rail transit information data according to an embodiment of the present invention;
Fig. 3 is a detailed flowchart of step S1 in a method for cleaning rail transit information data according to another embodiment of the present invention;
Fig. 4 is a detailed flowchart of step S3 in a method for cleaning rail transit information data according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a hardware operation environment of a rail transit information data cleaning device according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a frame structure of a rail transit information data cleaning system according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description refers to specific implementation, structure, characteristics and effects of a method for cleaning rail transit information data according to the invention by combining the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the method for cleaning rail transit information data provided by the invention with reference to the accompanying drawings.
Embodiment one:
For a method for cleaning track traffic information data provided by the present invention, please refer to fig. 1, which shows a flowchart of steps of a method for cleaning track traffic information data provided by an embodiment of the present invention.
The method comprises the following steps:
Step S1, determining the abnormality degree of local data of a track vibration sensor and the amplitude difference between adjacent local data based on preset segmentation period data of the track vibration sensor;
Vibration sensors are usually arranged on the tracks along the subway according to fixed distances and used for monitoring vibration data of all nodes of the tracks in real time, and meanwhile, the vibration data can be combined with train number of a train, speed in the running process of the train and positions on the tracks, and the data are transmitted to a computer in the same way, so that follow-up analysis is facilitated.
In this embodiment, the preset segmentation period data refers to that all vibration data can be segmented according to a certain time period, and the abnormal condition of the track node in each segmentation period time can be judged by analyzing each segment of segmentation period data.
The preset slicing period can be set according to needs, for example, 10s, for a subway line track section to be detected, serial numbers can be marked on each vibration sensor according to the running direction of a train, vibration data (namely, preset slicing period data) in each vibration sensor 10s are continuously collected and analyzed, any vibration sensor is taken as an example for analysis in the embodiment, and the following embodiment will be referred to as a current sensor or the vibration sensor.
Because the abnormal interference data (abnormal interference fluctuation) generated by the vibration sensor is usually represented as local data fluctuation, irregular mutation of the vibration amplitude can occur, and the vibration data of the normal track node is usually represented as continuous sawtooth-shaped electric signals, the amplitude of the electric signals is relatively regular, namely the amplitudes among a plurality of adjacent wave crests or wave troughs are basically consistent, or the amplitudes are increased or reduced more smoothly;
Therefore, the degree of disturbance of the vibration sensor on the vibration data can be determined by determining the degree of abnormality of each local data (which can be regarded as one data point acquired by the vibration sensor) in the preset slicing period. The degree of abnormality of the local data may reflect the degree of irregularity or prominence of each local data compared to other local data in the vicinity.
For the obtained preset slicing period data, each local data has an amplitude and a peak point, so that the amplitude difference between the adjacent local data can be further obtained, and the peak point is a maximum value or a minimum value.
In a preferred embodiment, referring to fig. 2, the step S1 includes:
Step S10, determining any target peak point and a peak group formed by a plurality of corresponding peak points adjacent to the target peak point based on preset segmentation period data of the track vibration sensor;
Step S11, determining a target amplitude difference value between the target peak point and other peak points in the peak group;
And step S12, determining the local data abnormality degree of the track vibration sensor by using the target amplitude difference value and the maximum amplitude difference value in the peak value group.
Specifically, the step S12 includes:
determining the local prominence degree of local data corresponding to the target peak point by utilizing the target amplitude difference value;
And calculating the local data abnormality degree of the track vibration sensor by using the local protrusion degree, the target amplitude corresponding to the target peak point and the maximum amplitude difference value in the peak group.
According to the continuous change relation of the acquired preset segmentation period data on the time sequence, the adjacent vibration data generally have smaller difference, so that one peak point corresponding to any acquisition time t is taken as a target peak point (here, the peak point t can also be referred to as a peak point t, the peak point at the time t is unique), a plurality of corresponding peak points are taken to the left side or the right side or the left and right sides of the target peak point, for example, the number D=5 of the adjacent corresponding peak points is taken (if the peak point t is the maximum, other peak points are the maximum, otherwise, the peak points are all the minimum), and a window (peak group) is established;
acquiring target amplitude of data point corresponding to target peak point And obtaining the difference between the amplitude corresponding to the target peak point and the amplitudes corresponding to other peak points in the window, thereby obtaining:
;
where i represents the vibration sensor currently to be verified, k represents other peak points within the window, Representing amplitudes corresponding to other peak points; Reaction The greater the value of the local protrusion degree in the time series, the greater the local protrusion degree, and the greater the degree of abnormality corresponding to the t-th peak point (i.e., peak point t).
Meanwhile, the larger the value of the t-th peak point in the window is, the higher the possibility of abnormality exists, so that the abnormality degree of the local data at any moment is obtained:
;
;
In the formula, Represents the maximum value of the data difference (maximum amplitude difference, obtained by subtracting the minimum amplitude from the maximum amplitude in the window) in the window where the current exists,Representation ofThe greater the relative size within the window, the greater the value thereof, the greater the degree of anomaly of the nth data. Based on the aboveWeighting to obtain local data abnormality degree of any target peak point;
The degree of abnormality of the local dataTaking the maximum point of the peak point as an example, when the peak point is the minimum point, it is expressed asWhereinRepresenting the minimum value of the data difference (minimum amplitude difference value) within the window currently in existence,The greater the degree of abnormality of the t-th data, the greater.
In another preferred embodiment, referring to fig. 3, the step S1 includes:
Step S100, determining a first amplitude difference between each group of adjacent maxima based on preset segmentation period data of the track vibration sensor;
step S110, determining second amplitude differences between adjacent minima of each group based on the preset segmentation period data;
wherein, two adjacent maxima or two adjacent minima are used as a group.
According to priori knowledge, vibration data are transmitted to two sides along a track in a position where a train is located and gradually attenuated along with a distance increasing signal, when abnormal vibration is generated by a fault at a certain node of the track, the vibration data collected by a part of vibration sensors behind the node and the vibration data collected by the vibration sensors in front of the node in the vibration transmission direction are destroyed to the original vibration attenuation rule, so that the track node where the vibration sensor possibly has abnormal vibration can be judged according to the vibration data difference between adjacent vibration sensors;
It should be noted that, because the propagation time of the vibration data in the solid is required, and the transmission speed of the vibration in the solid medium is related to the property of the material, in order to avoid errors in the process of comparing the vibration sensor acquisition data caused by the influence of the propagation time, the propagation speed of the vibration and the distance between two adjacent vibration sensor nodes can be obtained according to the prior track design;
According to analysis, the train is in operation, and as the train approaches, vibration data collected by each vibration sensor is in the process of amplification, and the amplitude of the vibration data is in the process of gradual increase;
therefore, in the present embodiment, the amplitude differences between all adjacent maximum value points or adjacent minimum value points in the preset slicing period data corresponding to the vibration sensor i can be obtained Where t represents a sampling time corresponding to any one of the maximum value point and the minimum value point, and may also represent a peak point, where the explanation is the same as above;
At this time, according to the logic, the train is in the travelling process, so that for the vibration sensor, the closer the distance from the vibration sensor to the train is, the closer the sampling time is to the current acquisition time point, the amplitude difference between the adjacent sets of maximum values is in the process of continuously increasing;
Then, according to the updating direction of the sampling time, namely, the larger the t value is, the more new the representative sampling time is, the closer to the current acquisition time point is, thereby obtaining the amplitude difference between two adjacent sets of maximum value points And (3) withThe differences between the two adjacent maxima or each two adjacent minima are grouped, and taking maxima as an example, the first amplitude difference between each adjacent maxima refers to the difference of two corresponding amplitudes, namely the amplitude difference of each adjacent maxima, and the second amplitude difference refers to the difference of two adjacent amplitudesAnd (3) withThe difference between these means the difference obtained by subtracting the amplitude differences of the adjacent two groups, i.e., the first difference and the second difference mentioned in the next embodiment.
Step S2, determining the overall regularity characteristic factor of the track vibration sensor based on the amplitude difference;
In combination with the above embodiment, specifically, the step S2 includes:
determining a first difference in the first amplitude differences between adjacent groups using the first amplitude differences;
Determining a second difference in a second amplitude difference between adjacent groups using the second amplitude difference;
Determining a first amplitude change regularity and a second amplitude change regularity corresponding to the first difference value and the second difference value respectively;
Determining the average value of the amplitude differences corresponding to all the first amplitude differences and the second amplitude differences;
and calculating to obtain the overall regularity characteristic factor of the track vibration sensor by using the amplitude difference average value, the first amplitude change regularity and the second amplitude change regularity.
Immediately before the previous embodiment, all maximum point combinations are traversed, thereby representing a first amplitude variation regularity of the vibration data acquired by the vibration sensor:
;
wherein N represents the number of all adjacent groups, by obtaining the difference accumulated value of the amplitude differences between all adjacent maximum point combinations (adjacent groups), and the absolute value of the accumulated value, thereby representing by the partial formula I.e.The value range of the value is between [ -1,1], the closer the value is to 1, the more obvious the characteristic that the amplitude regularity of vibration data collected in the vibration sensor is increased due to the influence of train running is, and the higher the regularity of the vibration data is;
Similarly, the second amplitude change regularity corresponding to all minimum value point combinations is obtained according to the method ;
For the mean value of amplitude differenceThe amplitude difference corresponding to each group of maximum value points and each group of minimum value points is accumulated, so that the average value of the amplitude differences of the vibration sensor is obtainedThis value is used to characterize the amplitude of the current sensor during the detection process and thus to compare it with other vibration sensors.
Combining the calculated amplitude difference average values, thereby obtaining the integral regularity characteristic factor of the vibration sensor:
;
in the formula, a maximum value and a regular average value corresponding to the minimum value are obtained The greater the value and the closer to 1, the stronger the regularity, the lower the probability of track failure, and the average value of the amplitude difference by using the valueWeighting, thereby obtainingThe value represents the overall degree of regularity of the vibration data acquired by the vibration sensor;
at this time, according to analysis, when the track node is not abnormal, the vibration is attenuated along with the solid, and compared with the peripheral sensors, the vibration amplitude is reduced to a certain extent;
Therefore, the related vibration data corresponding to the vibration sensors of the same number before and after the ith vibration sensor along the train travelling direction are acquired, and the vibration data corresponding to each node when the same vibration wave arrives can be acquired according to the acquired propagation time, so that accidental errors can be avoided.
S3, determining the possibility of influence of the fault of the track node of the track vibration sensor by utilizing the overall regularity characteristic factors of a plurality of adjacent track vibration sensors;
through analyzing the overall regularity characteristic factors of a plurality of adjacent track vibration sensors including the vibration sensor, the fault influence possibility of the track node where the track vibration sensor is located can be more comprehensively analyzed, and the greater the fault influence possibility is, the greater the abnormal data is indicated to be caused by the fault of the track node.
In a preferred embodiment, referring to fig. 4, the step S3 includes:
Step S30, determining a first difference of overall regularity characteristic factors between the track vibration sensor and a front adjacent track vibration sensor in the previous direction;
Step S31, determining a second difference of overall regularity characteristic factors between a plurality of adjacent track vibration sensors in the rear direction of the track vibration sensor;
step S32, determining a third difference of overall regularity characteristic factors between a plurality of adjacent track vibration sensors in the front direction of the front adjacent track vibration sensor;
step S33, calculating the track node fault influence possibility of the track vibration sensor by using the first difference, the second difference and the third difference;
wherein the fore and aft directions are based on the direction of travel along the train.
Specifically, the step S33 includes:
And calculating the track node fault influence possibility of the track vibration sensor by using the accumulated values of the first difference, the second difference and the third difference.
According to the logic, the amplitude between adjacent vibration sensors is reduced regularly, and when a fault exists before a certain track node, the regularity is destroyed, and if the data of the adjacent sensors are subjected to differential operation directly, the data are easily affected by errors generated by small period increase when the vibration propagates in a medium;
According to analysis, when the existing fault track node is between the current ith sensor and the previous r sensor (the previous adjacent track vibration sensor), the integral rule characteristic factor difference is larger because the existing vibration data characteristic is destroyed, meanwhile, the vibration data after the ith sensor and before the r sensor are continued to the vibration characteristic of the previous vibration sensor because the vibration transmission characteristic of the solid medium is not changed, and the corresponding integral rule characteristic factor difference is smaller, so that the possibility of fault influence on the current vibration sensor i is larger;
The possibility that the vibration sensor i is affected by the rail node fault is obtained by the method that:
;
In the formula, The absolute value of the difference (first difference) of the overall rule characteristic factors between the current vibration sensor i and the adjacent vibration sensor r is represented, and the larger the absolute value is, the greater the possibility of node faults exists;
At this time, for the vibration sensor i, including i after the current vibration sensor i Each sensor obtains the characteristic factor difference between adjacent sensors(Accumulation of the second difference),Indicating thisAny vibration sensor in the individual sensors, and the same applies to the sensor r prior to acquisition of the sensor rIndividual sensors, differences in characteristic factors between adjacent sensors, thereby obtaining(Accumulation of the third difference),Indicating thisThe smaller the difference between the two (second and third differences) is, the higher the reality of the calculated fault influence probability is, the two are added and weighted with the calculated first difference, and the result isThe larger the value is, the greater the possibility that the current sensor i is affected by the fault is, and the larger the value is, the larger the abnormal amplitude of vibration data fluctuation caused by the node fault is, the lower the possibility that the monitored vibration data is abnormal due to other factors is, and the smaller the whole cleaning amplitude is.
And S4, determining whether the local data is to-be-cleaned data or not by utilizing the abnormality degree of the local data and the influence possibility of the fault of the track node.
Specifically, the step S4 includes:
determining a ratio between the degree of local data anomaly and the likelihood of track node failure impact;
and comparing the normalized ratio with a preset threshold value to determine whether the local data is the data to be cleaned.
The degree of abnormality of the local data of any one of the vibration sensors is calculated with reference to the above embodimentsAndAt the same time, based on the calculated possibility that the preset cutting period of the vibration sensor i is affected by faultsTherefore, the local abnormality degree can be corrected according to the possibility of being influenced by the faults, and the correction necessity and the correction amplitude of the data point (namely the local data) at any time can be obtained:
;
In which, the positive and negative ratio relation is used to makeThe abnormal degree of the local data is weighted by using the partial representation;
it should be noted that when the extreme point corresponding to t is the maximum value (i.e ) In the case ofWhen the extreme point corresponding to t is the minimum value (i.e) In the case ofThe two formulas are normalized by norm function to obtainThe larger the numerical value of the two parts is, the higher the abnormal degree of the local data is, the whole data of the sensor is not affected by the fault node, and the possibility that the generated vibration data fluctuation represents abnormal data is higher;
the threshold value can be set according to the requirement, for example, 0.7 when When the abnormal interference degree of the local data is higher, the local data needs to be cleaned, otherwise, the data is not changed.
In an embodiment, after the step S4, the method further includes:
And correcting the data to be cleaned by using the normalized ratio to obtain cleaned data.
According to the steps, cleaning the data to be cleaned (vibration data with higher abnormal interference degree), and using the cleaned and corrected data as new reference data for analyzing the track nodes, thereby obtaining local vibration data corresponding to any sampling time t of any vibration sensor after cleaning:
;
Here, the And (5) representing data to be cleaned corresponding to the sampling time t, traversing all vibration data acquired by all vibration sensors, and completing all data cleaning based on the steps.
According to the method, each local data (local vibration data) of the track vibration sensor in the preset segmentation period data is analyzed, so that the local abnormality degree of each local vibration data is judged, interference to abnormal vibration data judgment of the track node due to saw-tooth change characteristics of the vibration data and factors of the vibration sensor is avoided, accuracy of data cleaning is improved, and the integral data change rule of the vibration data collected by the vibration sensor on a time sequence is analyzed, meanwhile, the rule difference between the vibration data and other peripheral vibration sensors is analyzed, and accordingly the integral data regularity of the vibration sensor and possibility of influence of faults of the track node are judged, and misjudgment of interference fluctuation generated in the train travelling process on the abnormal vibration data of the track node is avoided, so that accuracy of subsequent data cleaning is improved. The method combines the abnormality degree of local data and the influence possibility of the fault of the track node, balances the abnormality degree of the track node and the influence degree of the abnormality interference of other factors, comprehensively judges whether each local vibration data is the vibration data seriously influenced by the abnormality interference fluctuation, and can not normally identify and analyze the abnormality generated by the track node due to the vibration data, so that the vibration data seriously interfered by the track node can be specifically eliminated or corrected, the system is ensured to analyze the health state of the track node, and the monitoring accuracy of the track node is improved.
Embodiment two:
The embodiment of the invention also provides a device for cleaning the rail transit information data. The rail transit information data cleaning equipment can be data computing processing equipment such as a computer and a server.
As shown in fig. 5, fig. 5 is a schematic structural diagram of a hardware operation environment of the rail transit information data cleaning apparatus according to the embodiment of the present invention.
As shown in fig. 5, the rail transit information data cleaning apparatus may include a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display (Display), an input unit such as a control panel, and the optional user interface 1003 may also include a standard wired interface, a wireless interface. Network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., a WIFI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above. A memory 1005, which is a kind of computer storage medium, may include therein a track traffic information data cleansing program.
Those skilled in the art will appreciate that the hardware configuration shown in fig. 5 is not limiting of the device and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
With continued reference to fig. 5, the memory 1005 in fig. 5, which is a computer readable storage medium, may include an operating system, a user interface module, a network communication module, and a rail traffic information data cleansing program.
In fig. 5, the network communication module is mainly used for connecting with a server and can perform data communication with the server, and the processor 1001 can call the track traffic information data cleaning program stored in the memory 1005 and perform the steps in the above embodiments.
The hardware structure of the rail transit information data cleaning device is used for realizing each embodiment of the rail transit information data cleaning method.
In addition, the present invention also provides a system for cleaning rail traffic information data, referring to fig. 6, the system for cleaning rail traffic information data includes:
the data analysis module A10 is used for determining the abnormality degree of local data of the track vibration sensor and the amplitude difference between adjacent local data based on the preset segmentation period data of the track vibration sensor;
an amplitude analysis module a20, configured to determine an overall regularity feature factor of the rail vibration sensor based on the amplitude difference;
The track analysis module A30 is used for determining the track node fault influence possibility of the track vibration sensor by utilizing the overall regularity characteristic factors of the plurality of adjacent track vibration sensors;
and the cleaning evaluation module A40 is used for determining whether the local data is data to be cleaned or not by utilizing the abnormality degree of the local data and the influence possibility of the fault of the track node.
Further, the data analysis module a10 is further configured to:
determining any target peak point and a peak group formed by a plurality of corresponding peak points adjacent to the target peak point based on preset segmentation period data of the track vibration sensor;
Determining a target amplitude difference value between the target peak point and other peak points in the peak group;
And determining the local data abnormality degree of the track vibration sensor by using the target amplitude difference value and the maximum amplitude difference value in the peak value group.
Further, the data analysis module a10 is further configured to:
determining the local prominence degree of local data corresponding to the target peak point by utilizing the target amplitude difference value;
And calculating the local data abnormality degree of the track vibration sensor by using the local protrusion degree, the target amplitude corresponding to the target peak point and the maximum amplitude difference value in the peak group.
Further, the data analysis module a10 is further configured to:
Determining a first amplitude difference between each set of adjacent maxima based on preset slicing cycle data of the track vibration sensor;
determining a second amplitude difference between each set of adjacent minima based on the preset segmentation period data;
wherein, two adjacent maxima or two adjacent minima are used as a group.
Further, the amplitude analysis module a20 is further configured to:
determining a first difference in the first amplitude differences between adjacent groups using the first amplitude differences;
Determining a second difference in a second amplitude difference between adjacent groups using the second amplitude difference;
Determining a first amplitude change regularity and a second amplitude change regularity corresponding to the first difference value and the second difference value respectively;
Determining the average value of the amplitude differences corresponding to all the first amplitude differences and the second amplitude differences;
and calculating to obtain the overall regularity characteristic factor of the track vibration sensor by using the amplitude difference average value, the first amplitude change regularity and the second amplitude change regularity.
Further, the track analysis module a30 is further configured to:
determining a first difference in overall regularity characteristic factor between the rail vibration sensor and a preceding adjacent rail vibration sensor in a preceding direction;
Determining a second difference in overall regularity characteristic factor between a plurality of adjacent rail vibration sensors in a direction behind the rail vibration sensor;
Determining a third difference in overall regularity characteristic factor between a plurality of adjacent track vibration sensors in a front direction of the front adjacent track vibration sensor;
Calculating the track node fault influence possibility of the track vibration sensor by using the first difference, the second difference and the third difference;
wherein the fore and aft directions are based on the direction of travel along the train.
Further, the track analysis module a30 is further configured to:
And calculating the track node fault influence possibility of the track vibration sensor by using the accumulated values of the first difference, the second difference and the third difference.
Further, the cleaning evaluation module a40 is further configured to:
determining a ratio between the degree of local data anomaly and the likelihood of track node failure impact;
and comparing the normalized ratio with a preset threshold value to determine whether the local data is the data to be cleaned.
Further, the cleaning evaluation module a40 is further configured to:
And correcting the data to be cleaned by using the normalized ratio to obtain cleaned data.
The specific implementation manner of the rail transit information data cleaning system is basically the same as that of each embodiment of the rail transit information data cleaning method, and is not repeated here.
Furthermore, the invention also provides a computer readable storage medium. The computer readable storage medium of the present invention stores a track traffic information data cleaning program, wherein the track traffic information data cleaning program, when executed by a processor, implements the steps of the track traffic information data cleaning method as described above.
The method implemented when the track traffic information data cleaning program is executed may refer to various embodiments of the track traffic information data cleaning method of the present invention, which are not described herein again.
It should be noted that the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, and all equivalent structural changes made by the description of the present invention and the accompanying drawings or direct/indirect application in other related technical fields are included in the scope of the present invention.
Claims (4)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411659151.8A CN119152699B (en) | 2024-11-20 | 2024-11-20 | Rail transit information data cleaning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411659151.8A CN119152699B (en) | 2024-11-20 | 2024-11-20 | Rail transit information data cleaning method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119152699A CN119152699A (en) | 2024-12-17 |
| CN119152699B true CN119152699B (en) | 2025-01-24 |
Family
ID=93810679
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411659151.8A Active CN119152699B (en) | 2024-11-20 | 2024-11-20 | Rail transit information data cleaning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119152699B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119827036A (en) * | 2025-03-17 | 2025-04-15 | 中交三航局第八工程(湖南)有限公司 | Hydraulic value measuring device and method for ecological floating island |
| CN119848614B (en) * | 2025-03-21 | 2025-07-04 | 深圳市嘉友锦磁科技有限公司 | Signal analysis method for electric control single-cylinder diesel engine |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111780809A (en) * | 2020-07-21 | 2020-10-16 | 重庆大学 | Method and system for monitoring and early warning of temperature and vibration of rail vehicle parts |
| CN115140132A (en) * | 2022-07-26 | 2022-10-04 | 北京唐智科技发展有限公司 | Track state monitoring method, system, equipment and medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5875420A (en) * | 1997-06-13 | 1999-02-23 | Csi Technology, Inc. | Determining machine operating conditioning based on severity of vibration spectra deviation from an acceptable state |
| US6289735B1 (en) * | 1998-09-29 | 2001-09-18 | Reliance Electric Technologies, Llc | Machine diagnostic system and method for vibration analysis |
| JP2004063040A (en) * | 2002-07-31 | 2004-02-26 | Toshiba Corp | Fault forecast system, disk device provided with fault forecasting function, fault forecasting method, and fault forecasting program |
| CA2976899C (en) * | 2015-01-16 | 2020-10-27 | International Electronic Machines Corp. | Abnormal vehicle dynamics detection |
| CN117436024B (en) * | 2023-12-19 | 2024-03-08 | 湖南翰文云机电设备有限公司 | Fault diagnosis method and system based on drilling machine operation data analysis |
| CN118094450B (en) * | 2024-04-26 | 2024-07-09 | 江苏中天互联科技有限公司 | Fault early warning method and related equipment |
| CN118565612A (en) * | 2024-06-04 | 2024-08-30 | 通号城市轨道交通技术有限公司 | Abnormal state detection device and method for railway track vibration |
-
2024
- 2024-11-20 CN CN202411659151.8A patent/CN119152699B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111780809A (en) * | 2020-07-21 | 2020-10-16 | 重庆大学 | Method and system for monitoring and early warning of temperature and vibration of rail vehicle parts |
| CN115140132A (en) * | 2022-07-26 | 2022-10-04 | 北京唐智科技发展有限公司 | Track state monitoring method, system, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119152699A (en) | 2024-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN119152699B (en) | Rail transit information data cleaning method and system | |
| JP5148457B2 (en) | Abnormality determination apparatus, method, and program | |
| JP6609050B2 (en) | Anomalous fusion in temporal causal graphs | |
| CN112416643A (en) | Unsupervised anomaly detection method and unsupervised anomaly detection device | |
| CA2931624A1 (en) | Systems and methods for event detection and diagnosis | |
| US10809695B2 (en) | Information processing apparatus, machine learning device and system | |
| Dehghan et al. | A novel concept drift detection method in data streams using ensemble classifiers | |
| CN108664603A (en) | A kind of method and device of abnormal polymerization value that repairing time series data | |
| US20170364401A1 (en) | Monitoring peripheral transactions | |
| JP2014232084A (en) | Abnormal sound detection device and program | |
| CN115407731A (en) | Production line working status monitoring and fault warning system and method | |
| US20220039716A1 (en) | Calibration method for critical point of mental fatigue based on self-organized criticality | |
| CN112320520B (en) | Elevator abnormal vibration detection method based on residual error analysis | |
| JP3305940B2 (en) | Traffic condition prediction device | |
| WO2018047805A1 (en) | Device for estimating speed of moving sound source, speed monitoring system, method for estimating speed of moving sound source, and storage medium in which program for estimating speed of moving sound source is stored | |
| CN104990717B (en) | A kind of magnetic-levitation train sensor signal processing method | |
| EP3502979A1 (en) | A probability-based detector and controller apparatus, method, computer program | |
| CN117360589B (en) | Positive line code monitoring system and detection method based on in-station track railway | |
| JP6898607B2 (en) | Abnormality sign detection system and abnormality sign detection method | |
| CN118776885A (en) | Rolling bearing degradation change point detection and failure threshold setting method and system | |
| CN118761598B (en) | Method and device for determining maintenance time of shielding door based on historical data analysis | |
| CN112711541B (en) | Unsupervised Software Aging Detection Method Based on Local Outlier Factor of Data Flow | |
| CN114931387B (en) | A method and device for correcting bad EEG segment data by segment weighting | |
| CN115979325B (en) | Suspension sensor gap fault detection method, device, equipment and storage medium | |
| JP2024121429A (en) | Learning model generation method and track abnormality judgment support device |
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 | ||
| GR01 | Patent grant |