CN115339484A - Long-distance passive sensing rail transit health monitoring system and method - Google Patents

Long-distance passive sensing rail transit health monitoring system and method Download PDF

Info

Publication number
CN115339484A
CN115339484A CN202210976856.7A CN202210976856A CN115339484A CN 115339484 A CN115339484 A CN 115339484A CN 202210976856 A CN202210976856 A CN 202210976856A CN 115339484 A CN115339484 A CN 115339484A
Authority
CN
China
Prior art keywords
track
deformation
value
sensor
time
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.)
Pending
Application number
CN202210976856.7A
Other languages
Chinese (zh)
Inventor
芮易
陈建荣
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Yaguan Smart Rail Transit Technology Co ltd
Original Assignee
Shanghai Yaguan Smart Rail Transit Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Yaguan Smart Rail Transit Technology Co ltd filed Critical Shanghai Yaguan Smart Rail Transit Technology Co ltd
Priority to CN202210976856.7A priority Critical patent/CN115339484A/en
Publication of CN115339484A publication Critical patent/CN115339484A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B61—RAILWAYS
    • B61K—AUXILIARY EQUIPMENT SPECIALLY ADAPTED FOR RAILWAYS, NOT OTHERWISE PROVIDED FOR
    • B61K9/00—Railway vehicle profile gauges; Detecting or indicating overheating of components; Apparatus on locomotives or cars to indicate bad track sections; General design of track recording vehicles
    • B61K9/08—Measuring installations for surveying permanent way
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B61—RAILWAYS
    • B61K—AUXILIARY EQUIPMENT SPECIALLY ADAPTED FOR RAILWAYS, NOT OTHERWISE PROVIDED FOR
    • B61K9/00—Railway vehicle profile gauges; Detecting or indicating overheating of components; Apparatus on locomotives or cars to indicate bad track sections; General design of track recording vehicles
    • B61K9/08—Measuring installations for surveying permanent way
    • B61K9/10—Measuring installations for surveying permanent way for detecting cracks in rails or welds thereof
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
    • G01B21/32—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring the deformation in a solid
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Mechanical Engineering (AREA)
  • Theoretical Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Evolutionary Biology (AREA)
  • Algebra (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Operations Research (AREA)
  • Probability & Statistics with Applications (AREA)
  • Emergency Management (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Machines For Laying And Maintaining Railways (AREA)

Abstract

The invention discloses a long-distance passive sensing rail transit health monitoring system and a long-distance passive sensing rail transit health monitoring method. The invention relates to the technical field of rail transit, which comprehensively considers the aspects of static deformation quantity, dynamic deformation quantity, running time length and fault probability of a rail, quantifies the relationship between the running time lengths corresponding to different sensors and the fault probability of the rail, accurately predicts the maintenance time of the rail to be detected, and gives early warning to a rail supervisor to be detected in advance, thereby realizing the effective supervision of the health state of the rail transit.

Description

Long-distance passive sensing rail transit health monitoring system and method
Technical Field
The invention relates to the technical field of rail transit, in particular to a long-distance passive sensing rail transit health monitoring system and a long-distance passive sensing rail transit health monitoring method.
Background
In the background of urban rail transit peak-to-peak in the whole country, rail transit informatization has become a considerable research direction. The track can receive external factors' influence at the in-process of using, and then can produce deformation, and track deformation volume directly concerns the probability that the track broke down in the use, and the track deformation volume is bigger then the probability that the track broke down in the use is bigger, and then seriously influences the healthy state of track traffic, influences the trip of train, therefore people need monitor track deformation volume.
Passive sensing is a way of sensing that uses energy captured from the environment to perform sensing tasks in place of the power supply on the basis of conventional sensing techniques.
In the existing track traffic health monitoring system based on passive perception, evaluation standards of local peak values and section mean values of multiple track geometric irregularity parameters are combined with vehicle body vibration acceleration, and then track irregularity states are analyzed, but abnormal data intervals corresponding to the track irregularity states are only screened out according to the existing track data according to monitoring results, and the health states of track traffic cannot be predicted in advance and early warning can be carried out on overhaul time.
Disclosure of Invention
The invention aims to provide a long-distance passive sensing rail transit health monitoring system and a long-distance passive sensing rail transit health monitoring method, so as to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme: a long-distance passive sensing rail transit health monitoring method, the method comprising the steps of:
s1, acquiring different monitoring points of a track to be detected respectively corresponding to track deformation quantities in real time through a sensor in passive sensing equipment, recording the track deformation quantity when no train passes as a static deformation quantity, recording the difference value of the track deformation quantity when the train passes and the latest static deformation quantity in the monitoring results of the sensor with the same number in historical data as a track dynamic deformation quantity,
constructing an array of the track static deformation quantity and the track dynamic deformation quantity monitored by the sensor with the number i at the time t, and recording the array as [ i, t, ait and Dit ], wherein the Ait represents the track static deformation quantity monitored by the sensor with the number i at the time t, the Dit represents the track dynamic deformation quantity monitored by the sensor with the number i at the time t,
when the train passes the monitoring point corresponding to the sensor with the number i at the time t, the track deformation quantity when no train passes before the time t and nearest to the time t in the monitoring result of the sensor with the number i of the Ait is judged, the track deformation quantity corresponding to the time t and the Ait in the monitoring result of the sensor with the number i of the Dit are different,
when the train does not pass through the monitoring point corresponding to the sensor with the number i at the time t, judging that the track deformation quantity corresponding to the time t and the Dit value are 0 in the monitoring result of the sensor with the number i at the time t;
s2, obtaining an array corresponding to monitoring data of each sensor in historical data, and analyzing a relation G1i between a recovery deviation value of dynamic deformation of a track in the track to be detected and a dynamic deformation value of the track, wherein the static deformation value of the track is equal to the sum of a static deformation value of a track environment and a comprehensive recovery deviation value of the dynamic deformation of the track, and the comprehensive recovery deviation value of the dynamic deformation of the track is the sum of recovery deviation values of dynamic deformation of the track generated in the recovery process of the dynamic deformation value of each track in the track to be detected;
s3, predicting a relation function G2i of the static deformation quantity of the track to be detected and the track running time according to the analysis result in the S2;
s4, acquiring a comprehensive deformation quantity of the corresponding track when the track in the historical database fails, wherein the comprehensive deformation quantity of the track to be detected is equal to the sum of the static deformation value and the dynamic deformation value of the track to be detected, and analyzing the relation H = G3i (U1) between the fault probability of the track and the comprehensive deformation quantity of the track;
and S5, combining a relation function of the comprehensive deformation quantity of the track to be detected and the track operation time and a relation between the track fault probability and the comprehensive deformation quantity of the track to obtain the relation between the track operation time and the track fault probability, calculating the corresponding track operation time when the track fault probability to be detected is a first threshold value, and presenting the track operation time to a track supervisor to be detected so as to overhaul the track to be detected in advance, wherein the first threshold value is a constant prefabricated in the database.
Further, the method for analyzing the relationship between the restoration deviation value of the dynamic deformation of the track in the track to be tested and the dynamic deformation value of the track in the S2 includes the following steps:
s2.1, acquiring each array [ i, t, ait, dit ] corresponding to the sensor with the number of i, dividing each array with the fourth value different from 0 and continuous t values in the arrays into a cluster, numbering each cluster according to the time sequence,
acquiring each array corresponding to a reference group sensor, wherein the reference group sensor is a sensor of which the fourth value in each acquired array is always 0;
s2.2, constructing a first type data pair (a 1, a 2), wherein the sensor with the number of i acquired in the S2.1 corresponds to each cluster except the last cluster in each cluster, the a1 represents the maximum value of the fourth value in each array in the corresponding cluster of the sensor with the number of i,
calculating the average value of the third values in each array in the next cluster of the corresponding cluster of a1, and recording the average value as a3, obtaining the minimum time b1 and the maximum time b2 corresponding to each array in the next cluster of the corresponding cluster of a1, obtaining time intervals [ b1, b2], calculating the average value of the third values in each array with the corresponding time intervals [ b1, b2], and recording the average value as a4, wherein a2 is equal to the difference value between a3 and a4 in the monitoring result of the sensor of the reference group,
calculating the average value of third values in each array in the corresponding cluster of a1, which is recorded as a5, obtaining the minimum time b3 and the maximum time b4 corresponding to each array in the corresponding cluster of a1, obtaining a time interval [ b3, b4], calculating the average value of the third values in each array, which corresponds to the time interval [ b3, b4], in the monitoring result of the sensor of the reference group, which is recorded as a6, and wherein a2 is equal to (a 3-a 4) - (a 5-a 6);
s2.3, constructing a first plane rectangular coordinate system by taking the o1 as an original point, taking the track dynamic deformation value as an x1 axis and taking the recovery deviation value of the track dynamic deformation as a y1 axis, and marking corresponding coordinate points of each first type of data acquired in the S2.2 in the first plane rectangular coordinate system;
s2.4, performing linear fitting on coordinate points marked in the first plane rectangular coordinate system according to a first function model prefabricated in a database to obtain a relation G1i between a recovery deviation value of the dynamic deformation of the corresponding track of the sensor with the number i in the track to be detected and a dynamic deformation value of the track,
the first function model is a piecewise function,
when x1 is not more than xQ1, the first function model is y1=0;
when x1 is not more than xQ1, the first function model is a linear regression equation formula, and the xQ1 is a preset constant in the database.
In the process of analyzing the relationship between the recovery deviation value of the dynamic deformation of the track in the track to be detected and the dynamic deformation value of the track in the S2, each array corresponding to the reference group sensor is obtained, the fourth value in each array in the reference group is always 0 (namely the dynamic deformation of the track is always 0, the comprehensive recovery deviation value of the dynamic deformation of the track in the static deformation value of the track in the corresponding reference group is 0, and the static deformation value of the track in the reference group is equal to the static deformation value of the track environment), when x1 is not more than xQ1, the first function model is y1=0, the track is considered to be elastic, the default dynamic deformation value of the track is within a certain degree (xQ 1), and the dynamic deformation value of the track can be completely recovered to 0.
Further, the method for predicting the relation function between the static deformation quantity of the track to be measured and the track running time in the S3 includes the following steps:
s3.1, obtaining each array corresponding to the reference group sensor, and enabling a second value and a third value in each array corresponding to the reference group sensor to form a second type data pair (e 1, e 2), wherein e1 in the second type data pair is a second value in the corresponding array, and e2 in the second type data pair is a third value in the corresponding array;
s3.2, constructing a second plane rectangular coordinate system by taking o2 as an origin, taking the track running time t as a horizontal axis and taking the track environment static deformation value as a vertical axis, marking corresponding coordinate points of each second type of data acquired in S3.1 in the second plane rectangular coordinate system, and performing linear fitting on the marked coordinate points in the second plane rectangular coordinate system according to a second function model prefabricated in a database to obtain a relation F1i (t) between the track environment static deformation value corresponding to the sensor with the number i in the track to be measured and the track running time,
the second function model is y = p1 tan h (p 2 x), p1 is a first coefficient, p2 is a second coefficient, and in the linear fitting process, a fitting curve with the minimum sum of distances between the second function model and the marked coordinate points is selected as a final fitting result;
s3.3, acquiring a time interval corresponding to each cluster corresponding to a sensor with the number of i, respectively acquiring a union of the time intervals corresponding to each cluster in the same period by taking one day as a period, obtaining a track dynamic deformation time interval in the corresponding period, converting the track dynamic deformation time interval in each period into a track dynamic deformation time interval in a first period, recording the track dynamic deformation time interval in a jth period as [ b5, b6], converting [ b5, b6] into a track dynamic deformation time interval in the first period as [ b5-24 (j-1), b6-24 (j-1) ],
calculating the intersection of the track dynamic deformation time intervals in each period after the track dynamic deformation time intervals in the first period are converted into the track dynamic deformation time intervals in the first period, and obtaining a track dynamic deformation time interval B in the first period after the sensor with the number of i processes, wherein the B is a union of a plurality of unconnected time intervals;
s3.4, calculating a recovery deviation value PCk of the dynamic deformation of the track corresponding to the kth unconnected time interval in the B,
acquiring the average value of the fourth values in the corresponding arrays in each cluster which contains the kth unconnected time interval in B in the dynamic deformation time interval of the track in the first period, substituting the obtained average value into G1i as the dynamic deformation value of the track, taking the calculated result after substitution as PCk, and recording the maximum value in the kth unconnected time interval in B as t k And further obtain the track dynamic shape corresponding to the sensor with the number iThe function ZPi = F2i (t) between the variable integrated recovery bias value ZPi and the length t of the track run,
let t be equal to [0, t ∈ 1 ) A function between a comprehensive restoration deviation value ZPi of the dynamic deformation of the track corresponding to the sensor with the number of i in the first period and the track running time t is recorded as ZPi =0,
let k1 be more than or equal to 1 and t epsilon [ t ∈ k1 ，t k1+1 ) The function between the comprehensive recovery deviation value ZPi of the dynamic deformation of the track corresponding to the sensor with the number i in the first period and the track running time t is recorded as
Figure BDA0003798641300000041
Let t be an element of [ t ∈ ] k2 And 24) recording the function between the comprehensive recovery deviation value ZPi of the dynamic deformation of the track corresponding to the sensor with the number i in the first period and the track running time t as the function
Figure BDA0003798641300000042
K2 is the number of unconnected time intervals in B,
let t epsilon [24 (j-1), 24 (j-1) + t 1 ) The function between the comprehensive recovery deviation value ZPi of the dynamic deformation of the track corresponding to the sensor with the number i in the jth period and the track running time t is recorded as
Figure BDA0003798641300000051
Let k1 be more than or equal to 1 and t epsilon [24 (j-1) + t k1 ，24*(j-1)+t k1+1 ) And recording a function between the comprehensive recovery deviation value ZPi of the dynamic deformation of the track corresponding to the sensor with the number of i in the jth period and the track running time t as
Figure BDA0003798641300000052
Let t be [24 (j-1) + t ∈ k2 And a function between the comprehensive recovery deviation value ZPi of the dynamic deformation of the track corresponding to the sensor numbered i in the j cycle and the track running time t at 24 × (j-1) + 24) is recorded as
Figure BDA0003798641300000053
The k2 is the number of unconnected time intervals in the B;
s3.5, predicting a relation function G2i of the static deformation quantity of the track to be measured and the track running time,
the G2i = F1i (t) + F2i (t).
In the process of predicting the relation function between the static deformation amount of the track to be measured and the track running time in the S3, considering that the static deformation value of the track is equal to the sum of the static deformation value of the track environment and the comprehensive recovery deviation value of the dynamic deformation of the track, obtaining a relation F1i (t) between the static deformation value of the track environment corresponding to the sensor with the number i in the track to be measured and the track running time, obtaining a function ZPi = F2i (t) between the comprehensive recovery deviation value ZPi of the dynamic deformation of the track corresponding to the sensor with the number i and the track running time t, and predicting a relation function G2i between the static deformation amount of the track to be measured and the track running time; in the process of acquiring the ZPi = F2i (t), the track dynamic deformation time intervals in different periods are acquired by considering that the travel time table of the actual train has periodicity.
Further, the method for analyzing the relationship between the fault probability of the track and the comprehensive deformation quantity of the track in S4 includes the following steps:
s4.1, acquiring a corresponding comprehensive deformation amount of the track in the database when the track fails every time, and recording the total times of the track faults in the database as M;
s4.2, counting the number M1 of track faults when the comprehensive deformation of the track is less than or equal to U to obtain corresponding track fault probability M1/M and constructing a third type data pair (U, M1/M);
s4.3, constructing a third plane rectangular coordinate system by taking o3 as an origin, taking the track comprehensive deformation quantity as a horizontal axis and taking the track fault probability as a longitudinal axis, marking corresponding coordinate points of each third type of data acquired in S4.2 in the third plane rectangular coordinate system, and performing linear fitting on the coordinate points marked in the third plane rectangular coordinate system according to a third function model prefabricated in a database to obtain a relation H = G3i (U1) between the track fault probability H corresponding to the sensor with the number i in the track to be measured and the track comprehensive deformation quantity U1,
the second functional model is y = p3 (x + p 4) 2 And + p5, p3 is a third coefficient, p4 is a fourth coefficient, p5 is a fifth coefficient, and in the linear fitting process, a fitting curve with the minimum sum of distances between the fitting curve and each marked coordinate point is selected as a final fitting result.
Further, the method for obtaining the relationship between the operation time length of the rail to be detected and the rail fault probability in the step S5 includes the following steps:
s5.1, acquiring a dynamic deformation value of the track corresponding to the kth unconnected time interval in the B,
obtaining the average value DBk of the fourth values in the corresponding arrays in each cluster which is converted into the k-th unconnected time interval in the dynamic deformation time interval of the track in the first period and contains the k-th unconnected time interval in B, and marking the minimum value in the k-th unconnected time interval in B as tx k Further, a function Dit = F3i (t) between the dynamic deformation value Dit of the track corresponding to the sensor with the number i and the track running time t is obtained,
when k2 is more than or equal to k1 and more than or equal to 1 and t epsilon [24 (j-1) + tx k1 ，24*(j-1)+t k1 ]Then F3i (t) = DBK,
when k 2. Gtoreq.k 1. Gtoreq.1 and
Figure BDA0003798641300000061
if so, then F3i (t) =0;
s5.2, obtaining a relation F3i (t) + G2i between the relation between the comprehensive deformation quantities of the tracks and the operation duration;
and S5.3, substituting the comprehensive track deformation F3i (t) + G2i corresponding to the track running time t as U1 into H = G3i (U1) to obtain the relation H = G3i [ F3i (t) + G2i ] between the track fault probabilities corresponding to the running time corresponding to the sensor numbered i in the track to be detected.
In the process of acquiring the relationship between the operation time length and the track fault probability of the track to be detected in the S5, the comprehensive track deformation F3i (t) + G2i corresponding to the operation time length t of the track is substituted into H = G3i (U1) as U1, so that the functional relationship between the track fault probabilities corresponding to the operation time length corresponding to the sensor numbered i in the track to be detected can be accurately calculated, the operation time length corresponding to the sensor numbered i and the track fault probability can be quantized, the time for overhauling the track to be detected can be conveniently calculated, and the early warning can be performed on a supervisor of the track to be detected in advance.
Furthermore, the monitoring data of the sensor is updated in real time, the relationship between the recovery deviation value of the dynamic deformation of the rail in the corresponding rail to be detected and the dynamic deformation value of the rail, the relationship function between the comprehensive deformation quantity of the rail to be detected and the rail operation time length, the relationship between the rail fault probability and the comprehensive deformation quantity of the rail and the relationship between the rail fault probabilities corresponding to the rail operation time length to be detected are also updated and changed in real time, and the corresponding rail operation time length is also updated in real time when the rail fault probability to be detected presented to the rail supervisor to be detected is the first threshold value.
A long-range passive sensing rail transit health monitoring system, the system comprising the following modules:
the system comprises a track deformation quantity acquisition module, a passive sensing device and a control module, wherein the track deformation quantity acquisition module acquires different monitoring points of a track to be detected in real time through a sensor in the passive sensing device, the track deformation quantity when no train passes is recorded as a static deformation quantity, the difference value between the track deformation quantity when the train passes and the latest static deformation quantity in the monitoring result of the sensor with the same number in historical data is recorded as a track dynamic deformation quantity, the track static deformation quantity and the track dynamic deformation quantity monitored by the sensor with the number i at the time t are constructed into an array, and are recorded as [ i, t, ait and Dit ], the Ait represents the track static deformation quantity monitored by the sensor with the number i at the time t, and the Dit represents the track dynamic deformation quantity monitored by the sensor with the number i at the time t;
a data analysis module comprising a first analysis module, a second analysis module and a third analysis module,
the first analysis module is used for acquiring an array corresponding to monitoring data of each sensor in historical data and analyzing the relationship between a recovery deviation value of the dynamic deformation of the track in the track to be tested and a dynamic deformation value of the track;
the second analysis module is used for predicting a relation function between the static deformation quantity of the track to be detected and the track running time according to an analysis result in the first analysis module;
the third analysis module is used for acquiring a comprehensive deformation quantity of the rail corresponding to the failure of the rail in the historical database, wherein the comprehensive deformation quantity of the rail to be detected is equal to the sum of a static deformation value and a dynamic deformation value of the rail to be detected, and analyzing the relationship between the failure probability of the rail and the comprehensive deformation quantity of the rail;
the early warning maintenance module is used for combining a relation function of the comprehensive deformation quantity of the track to be detected and the track operation time and a relation between the track fault probability and the comprehensive deformation quantity of the track, acquiring the relation between the track operation time and the track fault probability to be detected, calculating the track operation time corresponding to the track fault probability to be detected when the track fault probability to be detected is a first threshold value, presenting the track operation time to a track supervisor to be detected, and further maintaining the track to be detected in advance, wherein the first threshold value is a constant prefabricated in a database.
Further, in the process of analyzing the relationship between the probability of the track fault and the comprehensive deformation quantity of the track in the third analysis module, the third analysis module obtains the comprehensive deformation quantity of the track corresponding to each track fault in the database, and records the total times of the track faults in the database as M; the third analysis module counts the times M1 of the track faults when the comprehensive deformation quantity of the track is less than or equal to U, obtains the corresponding track fault probability M1/M, and constructs a third type data pair (U, M1/M);
the third analysis module takes o3 as an origin, takes the track comprehensive deformation quantity as a horizontal axis and takes the track fault probability as a longitudinal axis to construct a third plane rectangular coordinate system, marks corresponding coordinate points of each acquired third type data in the third plane rectangular coordinate system, and performs linear fitting on the coordinate points marked in the third plane rectangular coordinate system according to a third function model prefabricated in a database to obtain a relation H = G3i (U1) between the track fault probability H corresponding to the sensor with the number i in the track to be measured and the track comprehensive deformation quantity U1,
the second function model is y = p3 (x + p 4) 2 + p5, p3 is the third coefficient, p4 is the fourth coefficient, and p5 is the fifth coefficient.
Furthermore, the monitoring data of the sensor is updated in real time, and the corresponding track operation duration is also updated in real time when the fault probability of the track to be detected presented to the track to be detected supervisor is the first threshold value.
Compared with the prior art, the invention has the following beneficial effects: the method comprehensively considers the aspects of the static deformation quantity of the rail, the dynamic deformation quantity of the rail, the operation time of the rail and the rail fault probability, quantifies the relationship between the operation time corresponding to different sensors and the rail fault probability, accurately predicts the maintenance time of the rail to be detected, and warns a rail supervisor to be detected in advance, thereby realizing the effective supervision of the rail transit health state.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic structural diagram of a long-distance passive sensing rail transit health monitoring system according to the present invention;
fig. 2 is a schematic flow chart of a long-distance passive sensing rail transit health monitoring method according to the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-2, the present invention provides a technical solution: a long-distance passive sensing rail transit health monitoring method, the method comprising the steps of:
s1, acquiring different monitoring points of a track to be detected respectively corresponding to track deformation quantities in real time through a sensor in passive sensing equipment, recording the track deformation quantity when no train passes as a static deformation quantity, recording the difference value of the track deformation quantity when the train passes and the latest static deformation quantity in the monitoring results of the sensor with the same number in historical data as a track dynamic deformation quantity,
the passive sensing device in the embodiment converts wind energy and solar energy in the environment into electric energy to support the operation of the sensor.
Constructing an array of the track static deformation quantity and the track dynamic deformation quantity monitored by the sensor with the number i at the time t, and recording the array as [ i, t, ait and Dit ], wherein the Ait represents the track static deformation quantity monitored by the sensor with the number i at the time t, the Dit represents the track dynamic deformation quantity monitored by the sensor with the number i at the time t,
when the train passes through the monitoring point corresponding to the sensor with the number i at the time t, the track deformation quantity when no train passes before the time t and closest to the time t in the monitoring result of the sensor with the number i with the value of Ait is judged, the difference value between the track deformation quantity corresponding to the time t and the Ait in the monitoring result of the sensor with the number i with the value of Dit,
in this embodiment, if the train passes the monitoring point corresponding to the sensor numbered 01 at the time Tt,
if the train-free passing time before the time Tt and closest to the time Tt is Tt1 in the monitoring result of the sensor numbered 01, the track deformation amount corresponding to the time Tt1 is XBtt1 in the monitoring result of the sensor numbered 01 01 Then the value of AiTt is equal to XBtt1 01 ，
In the monitoring result of the sensor numbered 01, the amount of the track deformation corresponding to the time Tt is XBtt 01 Then the value of DiTt is equal to XBtt 01 -XBTt1 01 ，
The sensor number 01 at time Tt corresponds to the array
[01，Tt，XBTt1 01 ，XBTt 01 -XBTt1 01 ]。
When the train does not pass through the monitoring point corresponding to the sensor with the number i at the time t, judging that the track deformation quantity corresponding to the time t and the Dit value are 0 in the monitoring result of the sensor with the number i at the time t;
s2, obtaining an array corresponding to monitoring data of each sensor in historical data, and analyzing a relation G1i between a recovery deviation value of dynamic deformation of a track in the track to be detected and a dynamic deformation value of the track, wherein the static deformation value of the track is equal to the sum of a static deformation value of a track environment and a comprehensive recovery deviation value of the dynamic deformation of the track, and the comprehensive recovery deviation value of the dynamic deformation of the track is the sum of recovery deviation values of dynamic deformation of the track generated in the recovery process of the dynamic deformation value of each track in the track to be detected;
s3, predicting a relation function G2i of the static deformation quantity of the track to be detected and the track running time according to the analysis result in the S2;
s4, acquiring a comprehensive deformation quantity of the track corresponding to the fault of the track in the historical database, wherein the comprehensive deformation quantity of the track to be detected is equal to the sum of the static deformation value and the dynamic deformation value of the track to be detected, and analyzing the relation H = G3i (U1) between the fault probability of the track and the comprehensive deformation quantity of the track;
and S5, combining a relation function of the comprehensive deformation quantity of the track to be detected and the track operation time and a relation between the track fault probability and the comprehensive deformation quantity of the track to obtain the relation between the track operation time and the track fault probability, calculating the corresponding track operation time when the track fault probability to be detected is a first threshold value, and presenting the track operation time to a track supervisor to be detected so as to overhaul the track to be detected in advance, wherein the first threshold value is a constant prefabricated in the database.
The first threshold value in this embodiment is 0.8.
The method for analyzing the relationship between the recovery deviation value of the dynamic deformation of the track in the track to be tested and the dynamic deformation value of the track in the S2 comprises the following steps:
s2.1, acquiring each array [ i, t, ait, dit ] corresponding to the sensor with the number of i, dividing each array with the fourth value different from 0 and continuous t values in the arrays into a cluster, numbering each cluster according to the time sequence,
acquiring each array corresponding to a reference group sensor, wherein the reference group sensor is a sensor of which the fourth value in each acquired array is always 0;
s2.2, constructing a first type data pair (a 1, a 2), wherein the sensor with the number of i acquired in the S2.1 corresponds to each cluster except the last cluster in each cluster, the a1 represents the maximum value of the fourth value in each array in the corresponding cluster of the sensor with the number of i,
calculating the average value of the third values in each array in the next cluster of the corresponding cluster of a1, and recording the average value as a3, obtaining the minimum time b1 and the maximum time b2 corresponding to each array in the next cluster of the corresponding cluster of a1, obtaining time intervals [ b1, b2], calculating the average value of the third values in each array with the corresponding time intervals [ b1, b2], and recording the average value as a4, wherein a2 is equal to the difference value between a3 and a4 in the monitoring result of the sensor of the reference group,
calculating the average value of third values in each array in the corresponding cluster of a1, which is recorded as a5, obtaining the minimum time b3 and the maximum time b4 corresponding to each array in the corresponding cluster of a1, obtaining a time interval [ b3, b4], calculating the average value of the third values in each array, which corresponds to the time interval [ b3, b4], in the monitoring result of the sensor of the reference group, which is recorded as a6, and wherein a2 is equal to (a 3-a 4) - (a 5-a 6);
s2.3, constructing a first plane rectangular coordinate system by taking the o1 as an origin, taking the track dynamic deformation value as an x1 axis and taking the recovery deviation value of the track dynamic deformation as a y1 axis, and marking corresponding coordinate points of each first type of data acquired in the S2.2 in the first plane rectangular coordinate system;
s2.4, performing linear fitting on coordinate points marked in the first plane rectangular coordinate system according to a first function model prefabricated in the database to obtain a relation G1i between a recovery deviation value of the dynamic deformation of the corresponding track of the sensor with the number i in the track to be detected and the dynamic deformation value of the track,
the first function model is a piecewise function,
when x1 is less than or equal to xQ1, the first function model is y1=0;
when x1 is not more than xQ1, the first function model is a linear regression equation formula, and the xQ1 is a preset constant in the database.
In the embodiment, when the dynamic deformation of the track occurs, the elastic deformation of the track which can be recovered to the initial state is only 2mm; theoretically, a rail elastic deformation exceeding 2mm cannot be completely recovered after the passage of the train, some residual deformation remains, and the value of xQ1 in this embodiment is equal to 2 mm.
The method for predicting the relation function between the static deformation quantity of the track to be measured and the track running time in the S3 comprises the following steps:
s3.1, obtaining each array corresponding to the reference group sensor, and enabling a second value and a third value in each array corresponding to the reference group sensor to form a second type data pair (e 1, e 2), wherein e1 in the second type data pair is a second value in the corresponding array, and e2 in the second type data pair is a third value in the corresponding array;
s3.2, constructing a second plane rectangular coordinate system by taking o2 as an origin, taking the track running time t as a horizontal axis and taking the track environment static deformation value as a longitudinal axis, marking corresponding coordinate points of each second type of data acquired in the S3.1 in the second plane rectangular coordinate system, and performing linear fitting on the coordinate points marked in the second plane rectangular coordinate system according to a second function model prefabricated in a database to obtain a relation F1i (t) between the track environment static deformation value corresponding to the sensor numbered i in the track to be measured and the track running time,
the second function model is y = p1 × tanh (p 2 × x), p1 is a first coefficient, p2 is a second coefficient, and in the linear fitting process, a fitting curve with the minimum sum of distances between the fitting curve and each marked coordinate point is selected as a final fitting result;
s3.3, acquiring a time interval corresponding to each cluster corresponding to a sensor with the number of i, respectively acquiring a union of the time intervals corresponding to each cluster in the same period by taking one day as a period, obtaining a track dynamic deformation time interval in the corresponding period, converting the track dynamic deformation time interval in each period into a track dynamic deformation time interval in a first period, recording the track dynamic deformation time interval in a jth period as [ b5, b6], converting [ b5, b6] into a track dynamic deformation time interval in the first period as [ b5-24 (j-1), b6-24 (j-1) ],
calculating the intersection of the track dynamic deformation time intervals in each period after the track dynamic deformation time intervals in the first period are converted into the track dynamic deformation time intervals in the first period, and obtaining a track dynamic deformation time interval B in the first period after the sensor with the number of i processes, wherein the B is a union of a plurality of unconnected time intervals;
s3.4, calculating a recovery deviation value PCk of the dynamic deformation of the track corresponding to the kth unconnected time interval in the B,
acquiring the average value of the fourth values in the corresponding arrays in each cluster which contains the kth unconnected time interval in B in the dynamic deformation time interval of the track in the first period, substituting the obtained average value into G1i as the dynamic deformation value of the track, taking the calculated result after substitution as PCk, and recording the maximum value in the kth unconnected time interval in B as t k Further obtaining a function ZPi = F2i (t) between the comprehensive recovery deviation value ZPi of the dynamic deformation of the track corresponding to the sensor with the number i and the track running time t,
let t be equal to [0, t ∈ ] 1 ) The function between the comprehensive restoration deviation value ZPi of the dynamic deformation of the track corresponding to the sensor with the number i in the first period and the track running time t is recorded as ZPi =0,
making k1 be greater than or equal to 1 and t epsilon [ t ∈ ] k1 ，t k1+1 ) Recording a function between the comprehensive restoration deviation value ZPi of the dynamic deformation of the track corresponding to the sensor with the number of i in the first period and the track running time t as
Figure BDA0003798641300000111
Let t be an element of [ t ∈ ] k2 And 24) recording the function between the comprehensive recovery deviation value ZPi of the dynamic deformation of the track corresponding to the sensor with the number i in the first period and the track running time t as the function
Figure BDA0003798641300000121
K2 is the number of unconnected time intervals in B,
let t epsilon [24 (j-1), 24 (j-1) + t 1 ) The function between the comprehensive recovery deviation value ZPi of the dynamic deformation of the track corresponding to the sensor with the number i in the jth period and the track running time t is recorded as
Figure BDA0003798641300000122
Making k1 be greater than or equal to 1 and t epsilon [24 x (j-1) + t k1 ，24*(j-1)+t k1+1 ) The function between the comprehensive recovery deviation value ZPi of the dynamic deformation of the track corresponding to the sensor with the number i in the jth period and the track running time t is recorded as
Figure BDA0003798641300000123
Let t be [24 (j-1) + t ∈ k2 And a function between the comprehensive recovery deviation value ZPi of the dynamic deformation of the track corresponding to the sensor numbered i in the j cycle and the track running time t at 24 × (j-1) + 24) is recorded as
Figure BDA0003798641300000124
The k2 is the number of unconnected time intervals in the B;
s3.5, predicting a relation function G2i of the static deformation quantity of the track to be measured and the track running time,
the G2i = F1i (t) + F2i (t).
The method for analyzing the relationship between the fault probability of the track and the comprehensive deformation quantity of the track in the S4 comprises the following steps of:
s4.1, acquiring a corresponding comprehensive deformation amount of the track in the database when the track fails every time, and recording the total times of the track faults in the database as M;
s4.2, counting the number M1 of the track faults when the comprehensive deformation of the track is less than or equal to U to obtain corresponding track fault probability M1/M, and constructing a third type data pair (U, M1/M);
s4.3, constructing a third plane rectangular coordinate system by taking o3 as an origin, taking the track comprehensive deformation as a horizontal axis and taking the track fault probability as a longitudinal axis, marking corresponding coordinate points of each third type of data acquired in S4.2 in the third plane rectangular coordinate system, and performing linear fitting on the coordinate points marked in the third plane rectangular coordinate system according to a third function model prefabricated in a database to obtain a relation H = G3i (U1) between the track fault probability H corresponding to the sensor with the number i in the track to be measured and the track comprehensive deformation U1,
the second function model is y = p3 (x + p 4) 2 And + p5, p3 is a third coefficient, p4 is a fourth coefficient, p5 is a fifth coefficient, and in the linear fitting process, a fitting curve with the minimum sum of distances between the fitting curve and each marked coordinate point is selected as a final fitting result.
The method for acquiring the relation between the running time of the track to be tested and the track fault probability in the S5 comprises the following steps:
s5.1, acquiring a dynamic track deformation value corresponding to the kth unconnected time interval in the B,
obtaining the average value DBk of the fourth values in the corresponding arrays in each cluster which contains the kth unconnected time interval in B in the dynamic deformation time interval of the track in the first period, and recording the minimum value in the kth unconnected time interval in B as tx k Further, a function Dit = F3i (t) between the dynamic deformation value Dit of the track corresponding to the sensor with the number i and the track running time t is obtained,
when k2 is more than or equal to k1 and more than or equal to 1 and t epsilon [24 (j-1) + tx k1 ，24*(j-1)+t k1 ]F3i (t) = DBK,
when k2 is not less than k1 not less than 1
Figure BDA0003798641300000131
F3i (t) =0;
s5.2, obtaining a relation F3i (t) + G2i between the relation between the comprehensive deformation quantities of the tracks and the operation duration;
and S5.3, substituting the comprehensive track deformation F3i (t) + G2i corresponding to the track running time t as U1 into H = G3i (U1) to obtain the relation H = G3i [ F3i (t) + G2i ] between the track fault probabilities corresponding to the running time corresponding to the sensor numbered i in the track to be detected.
The monitoring data of the sensor is updated in real time, the relation between the recovery deviation value of the dynamic deformation of the rail in the corresponding rail to be detected and the dynamic deformation value of the rail, the relation function between the comprehensive deformation quantity of the rail to be detected and the rail operation time length, the relation between the rail fault probability and the comprehensive deformation quantity of the rail and the relation between the rail fault probability corresponding to the rail operation time length of the rail to be detected are also updated and changed in real time, and the corresponding rail operation time length is also updated in real time when the rail fault probability of the rail to be detected presented to a rail to be detected supervisor is a first threshold value.
A long-range passive sensing rail transit health monitoring system, the system comprising the following modules:
the system comprises a track deformation quantity acquisition module, a passive sensing device and a control module, wherein the track deformation quantity acquisition module acquires different monitoring points of a track to be detected in real time through a sensor in the passive sensing device, the track deformation quantity when no train passes is recorded as a static deformation quantity, the difference value between the track deformation quantity when the train passes and the latest static deformation quantity in the monitoring result of the sensor with the same number in historical data is recorded as a track dynamic deformation quantity, the track static deformation quantity and the track dynamic deformation quantity monitored by the sensor with the number i at the time t are constructed into an array, and are recorded as [ i, t, ait and Dit ], the Ait represents the track static deformation quantity monitored by the sensor with the number i at the time t, and the Dit represents the track dynamic deformation quantity monitored by the sensor with the number i at the time t;
a data analysis module comprising a first analysis module, a second analysis module and a third analysis module,
the first analysis module is used for acquiring an array corresponding to monitoring data of each sensor in historical data and analyzing the relationship between a recovery deviation value of the dynamic deformation of the track in the track to be tested and a dynamic deformation value of the track;
the second analysis module is used for predicting a relation function between the static deformation quantity of the track to be detected and the track running time according to an analysis result in the first analysis module;
the third analysis module is used for acquiring a comprehensive deformation quantity of the rail corresponding to the failure of the rail in the historical database, wherein the comprehensive deformation quantity of the rail to be detected is equal to the sum of a static deformation value and a dynamic deformation value of the rail to be detected, and analyzing the relationship between the failure probability of the rail and the comprehensive deformation quantity of the rail;
the early warning maintenance module is used for combining a relation function of the comprehensive deformation quantity of the track to be detected and the track operation time and a relation between the track fault probability and the comprehensive deformation quantity of the track, acquiring the relation between the track operation time and the track fault probability to be detected, calculating the track operation time corresponding to the track fault probability to be detected when the track fault probability to be detected is a first threshold value, presenting the track operation time to a track supervisor to be detected, and further maintaining the track to be detected in advance, wherein the first threshold value is a constant prefabricated in a database.
In the process of analyzing the relation between the track fault probability and the track comprehensive deformation quantity in the third analysis module, the third analysis module acquires the corresponding track comprehensive deformation quantity at each track fault in the database, and records the total times of the track faults in the database as M; the third analysis module counts the track fault times M1 when the comprehensive deformation quantity of the track is less than or equal to U, obtains the corresponding track fault probability M1/M, and constructs a third type data pair (U, M1/M);
the third analysis module takes o3 as an origin, takes the track comprehensive deformation quantity as a horizontal axis and takes the track fault probability as a longitudinal axis to construct a third plane rectangular coordinate system, marks corresponding coordinate points of each acquired third type data in the third plane rectangular coordinate system, and performs linear fitting on the coordinate points marked in the third plane rectangular coordinate system according to a third function model prefabricated in a database to obtain a relation H = G3i (U1) between the track fault probability H corresponding to the sensor with the number i in the track to be measured and the track comprehensive deformation quantity U1,
the second function model is y = p3 (x + p 4) 2 + p5, p3 is the third coefficient, p4 is the fourth coefficient, and p5 is the fifth coefficient.
The monitoring data of the sensor is updated in real time, and the corresponding track operation time length is also updated in real time when the fault probability of the track to be detected presented to the track to be detected supervisor is the first threshold value.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (9)

1. A long-distance passive sensing rail transit health monitoring method is characterized by comprising the following steps:
s1, acquiring different monitoring points of a track to be detected respectively corresponding to track deformation quantities in real time through a sensor in passive sensing equipment, recording the track deformation quantity when no train passes as a static deformation quantity, recording the difference value of the track deformation quantity when the train passes and the latest static deformation quantity in the monitoring results of the sensor with the same number in historical data as a track dynamic deformation quantity,
constructing an array of the track static deformation and the track dynamic deformation monitored by the sensor with the number i at the time t, and recording the array as [ i, t, ait and Dit ], wherein the Ait represents the track static deformation monitored by the sensor with the number i at the time t, the Dit represents the track dynamic deformation monitored by the sensor with the number i at the time t,
when the train passes the monitoring point corresponding to the sensor with the number i at the time t, the track deformation quantity when no train passes before the time t and nearest to the time t in the monitoring result of the sensor with the number i of the Ait is judged, the track deformation quantity corresponding to the time t and the Ait in the monitoring result of the sensor with the number i of the Dit are different,
when the train does not pass through the monitoring point corresponding to the sensor with the number i at the time t, judging that the track deformation quantity corresponding to the time t and the Dit value are 0 in the monitoring result of the sensor with the number i at the time t;
s2, obtaining an array corresponding to monitoring data of each sensor in historical data, and analyzing a relation G1i between a recovery deviation value of dynamic deformation of a track in the track to be detected and a dynamic deformation value of the track, wherein the static deformation value of the track is equal to the sum of a static deformation value of a track environment and a comprehensive recovery deviation value of the dynamic deformation of the track, and the comprehensive recovery deviation value of the dynamic deformation of the track is the sum of recovery deviation values of dynamic deformation of the track generated in the recovery process of the dynamic deformation value of each track in the track to be detected;
s3, predicting a relation function G2i of the static deformation quantity of the track to be detected and the track running time according to the analysis result in the S2;
s4, acquiring a comprehensive deformation quantity of the track corresponding to the fault of the track in the historical database, wherein the comprehensive deformation quantity of the track to be detected is equal to the sum of the static deformation value and the dynamic deformation value of the track to be detected, and analyzing the relation H = G3i (U1) between the fault probability of the track and the comprehensive deformation quantity of the track;
s5, combining a relation function of the comprehensive deformation quantity of the track to be detected and the track running time and a relation between the track fault probability and the comprehensive deformation quantity of the track to obtain the relation between the running time of the track to be detected and the track fault probability, calculating the corresponding track running time when the track fault probability to be detected is a first threshold value, and presenting the track running time to a track supervisor to be detected so as to overhaul the track to be detected in advance, wherein the first threshold value is a constant prefabricated in a database.
2. The long-distance passive sensing rail transit health monitoring method according to claim 1, characterized in that: the method for analyzing the relationship between the recovery deviation value of the dynamic deformation of the track in the track to be tested and the dynamic deformation value of the track in the S2 comprises the following steps:
s2.1, acquiring each array [ i, t, ait, dit ] corresponding to the sensor with the number of i, dividing each array with the fourth value different from 0 and continuous t values in the arrays into a cluster, numbering each cluster according to the time sequence,
acquiring each array corresponding to a reference group sensor, wherein the reference group sensor is a sensor of which the fourth value in each acquired array is always 0;
s2.2, constructing a first type data pair (a 1, a 2), wherein the sensor with the number of i acquired in the S2.1 corresponds to each cluster except the last cluster in each cluster, the a1 represents the maximum value of the fourth value in each array in the corresponding cluster of the sensor with the number of i,
calculating the average value of the third values in each array in the next cluster of the corresponding cluster of a1, and recording the average value as a3, obtaining the minimum time b1 and the maximum time b2 corresponding to each array in the next cluster of the corresponding cluster of a1, obtaining time intervals [ b1, b2], calculating the average value of the third values in each array with the corresponding time intervals [ b1, b2], and recording the average value as a4, wherein a2 is equal to the difference value between a3 and a4 in the monitoring result of the sensor of the reference group,
calculating the average value of the third values in each array in the corresponding cluster of a1, recording the average value as a5, obtaining the minimum time b3 and the maximum time b4 corresponding to each array in the corresponding cluster of a1, obtaining a time interval [ b3, b4], calculating the average value of the third values in each array corresponding to the time interval [ b3, b4] in the monitoring result of the sensor of the reference group, recording the average value as a6, and enabling a2 to be equal to (a 3-a 4) - (a 5-a 6);
s2.3, constructing a first plane rectangular coordinate system by taking the o1 as an original point, taking the track dynamic deformation value as an x1 axis and taking the recovery deviation value of the track dynamic deformation as a y1 axis, and marking corresponding coordinate points of each first type of data acquired in the S2.2 in the first plane rectangular coordinate system;
s2.4, performing linear fitting on coordinate points marked in the first plane rectangular coordinate system according to a first function model prefabricated in the database to obtain a relation G1i between a recovery deviation value of the dynamic deformation of the corresponding track of the sensor with the number i in the track to be detected and the dynamic deformation value of the track,
the first function model is a piecewise function,
when x1 is less than or equal to xQ1, the first function model is y1=0;
when x1 is not more than xQ1, the first function model is a linear regression equation formula, and the xQ1 is a preset constant in the database.
3. The long-distance passive sensing rail transit health monitoring method according to claim 1, characterized in that: the method for predicting the relation function between the static deformation quantity of the track to be measured and the track running time in the S3 comprises the following steps:
s3.1, obtaining each array corresponding to the reference group sensor, and enabling a second value and a third value in each array corresponding to the reference group sensor to form a second type data pair (e 1, e 2), wherein e1 in the second type data pair is a second value in the corresponding array, and e2 in the second type data pair is a third value in the corresponding array;
s3.2, constructing a second plane rectangular coordinate system by taking o2 as an origin, taking the track running time t as a horizontal axis and taking the track environment static deformation value as a longitudinal axis, marking corresponding coordinate points of each second type of data acquired in the S3.1 in the second plane rectangular coordinate system, and performing linear fitting on the coordinate points marked in the second plane rectangular coordinate system according to a second function model prefabricated in a database to obtain a relation F1i (t) between the track environment static deformation value corresponding to the sensor numbered i in the track to be measured and the track running time,
the second function model is y = p1 × tanh (p 2 × x), p1 is a first coefficient, p2 is a second coefficient, and in the linear fitting process, a fitting curve with the minimum sum of distances between the fitting curve and each marked coordinate point is selected as a final fitting result;
s3.3, acquiring time intervals corresponding to clusters of the sensor with the number i, respectively acquiring a union of the time intervals corresponding to the clusters in the same period by taking one day as a period, obtaining track dynamic deformation time intervals in corresponding periods, converting the track dynamic deformation time interval in each period into a track dynamic deformation time interval in a first period, recording the track dynamic deformation time interval in a jth period as [ b5, b6], converting [ b5, b6] into the track dynamic deformation time interval in the first period as [ b5-24 (j-1), b6-24 (j-1) ],
calculating the intersection of the track dynamic deformation time intervals in each period after the track dynamic deformation time intervals in the first period are converted into the track dynamic deformation time intervals in the first period, and obtaining a track dynamic deformation time interval B in the first period after the sensor with the number of i processes, wherein the B is a union of a plurality of unconnected time intervals;
s3.4, calculating a recovery deviation value PCk of the dynamic deformation of the track corresponding to the kth unconnected time interval in the B,
acquiring the average value of the fourth values in the corresponding arrays in each cluster which contains the kth unconnected time interval in B in the dynamic deformation time interval of the track in the first period, substituting the obtained average value into G1i as the dynamic deformation value of the track, taking the calculated result after substitution as PCk, and recording the maximum value in the kth unconnected time interval in B as t k Further obtaining a function ZPi = F2i (t) between the comprehensive recovery deviation value ZPi of the dynamic deformation of the track corresponding to the sensor with the number i and the track running time t,
let t be equal to [0, t ∈ ] 1 ) A function between a comprehensive restoration deviation value ZPi of the dynamic deformation of the track corresponding to the sensor with the number of i in the first period and the track running time t is recorded as ZPi =0,
making k1 be greater than or equal to 1 and t epsilon [ t ∈ ] k1 ，t k1+1 ) The function between the comprehensive recovery deviation value ZPi of the dynamic deformation of the track corresponding to the sensor with the number i in the first period and the track running time t is recorded as
Figure FDA0003798641290000041
Let t be e [ t ∈ ] k2 And 24) recording the function between the comprehensive recovery deviation value ZPi of the dynamic deformation of the track corresponding to the sensor with the number i in the first period and the track running time t as the function
Figure FDA0003798641290000042
K2 is the number of unconnected time intervals in B,
the t epsilon [24 (j-1), 24 (j-1) + t is added 1 ) And recording a function between the comprehensive recovery deviation value ZPi of the dynamic deformation of the track corresponding to the sensor with the number of i in the jth period and the track running time t as
Figure FDA0003798641290000043
Figure FDA0003798641290000044
Let k1 be more than or equal to 1 and t epsilon [24 (j-1) + t k1 ，24*(j-1)+t k1+1 ) The function between the comprehensive recovery deviation value ZPi of the dynamic deformation of the track corresponding to the sensor with the number i in the jth period and the track running time t is recorded as
Figure FDA0003798641290000045
Let t be [24 (j-1) + t ∈ k2 And a function between the comprehensive recovery deviation value ZPi of the dynamic deformation of the track corresponding to the sensor numbered i in the j cycle and the track running time t at 24 × (j-1) + 24) is recorded as
Figure FDA0003798641290000046
The k2 is the number of unconnected time intervals in the B;
s3.5, predicting a relation function G2i of the static deformation quantity of the track to be measured and the track running time,
the G2i = F1i (t) + F2i (t).
4. The long-distance passive sensing rail transit health monitoring method according to claim 1, characterized in that: the method for analyzing the relationship between the fault probability of the track and the comprehensive deformation quantity of the track in the S4 comprises the following steps:
s4.1, acquiring a corresponding comprehensive deformation amount of the track in the database when the track fails every time, and recording the total times of the track faults in the database as M;
s4.2, counting the number M1 of the track faults when the comprehensive deformation of the track is less than or equal to U to obtain corresponding track fault probability M1/M, and constructing a third type data pair (U, M1/M);
s4.3, constructing a third plane rectangular coordinate system by taking o3 as an origin, taking the track comprehensive deformation quantity as a horizontal axis and taking the track fault probability as a longitudinal axis, marking corresponding coordinate points of each third type of data acquired in S4.2 in the third plane rectangular coordinate system, and performing linear fitting on the coordinate points marked in the third plane rectangular coordinate system according to a third function model prefabricated in a database to obtain a relation H = G3i (U1) between the track fault probability H corresponding to the sensor with the number i in the track to be measured and the track comprehensive deformation quantity U1,
the second functional model is y = p3 (x + p 4) 2 And + p5, p3 is a third coefficient, p4 is a fourth coefficient, p5 is a fifth coefficient, and in the linear fitting process, a fitting curve with the minimum sum of distances between the fitting curve and each marked coordinate point is selected as a final fitting result.
5. The long-distance passive sensing rail transit health monitoring method according to claim 3, wherein: the method for acquiring the relation between the running time of the track to be tested and the track fault probability in the S5 comprises the following steps:
s5.1, acquiring a dynamic deformation value of the track corresponding to the kth unconnected time interval in the B,
acquiring corresponding arrays in each cluster which contains the kth unconnected time interval in B in the dynamic deformation time interval of the track converted into the first periodThe average value DBk of the fourth value in B, and the minimum value in the kth unconnected time interval in B is recorded as tx k Then obtaining a function Dit = F3i (t) between the dynamic deformation value Dit of the track corresponding to the sensor with the number i and the track running time t,
when k2 is more than or equal to k1 and more than or equal to 1 and t epsilon [24 (j-1) + tx k1 ，24*(j-1)+t k1 ]Then F3i (t) = DBK,
when k2 is not less than k1 not less than 1
Figure FDA0003798641290000051
24*(j-1)+t k1 ]If so, then F3i (t) =0;
s5.2, obtaining a relation F3i (t) + G2i between the relation between the comprehensive deformation quantities of the tracks and the operation duration;
and S5.3, substituting the comprehensive track deformation F3i (t) + G2i corresponding to the track running time t as U1 into H = G3i (U1) to obtain the relation H = G3i [ F3i (t) + G2i ] between the track fault probabilities corresponding to the running time corresponding to the sensor numbered i in the track to be detected.
6. The long-distance passive sensing rail transit health monitoring method according to claim 1, characterized in that: the monitoring data of the sensor is updated in real time, the relation between the recovery deviation value of the dynamic deformation of the rail in the corresponding rail to be detected and the dynamic deformation value of the rail, the relation function between the comprehensive deformation quantity of the rail to be detected and the rail operation time length, the relation between the rail fault probability and the comprehensive deformation quantity of the rail and the relation between the rail fault probability corresponding to the rail operation time length of the rail to be detected are also updated and changed in real time, and the corresponding rail operation time length is also updated in real time when the rail fault probability of the rail to be detected presented to a rail to be detected supervisor is a first threshold value.
7. A long-distance passive sensing rail transit health monitoring system is characterized by comprising the following modules:
the system comprises a track deformation quantity acquisition module, a passive sensing device and a dynamic deformation quantity acquisition module, wherein the track deformation quantity acquisition module acquires different monitoring points of a track to be detected in real time through a sensor in the passive sensing device, the track deformation quantity when no train passes is recorded as a static deformation quantity, the difference value between the track deformation quantity when the train passes and the latest static deformation quantity in the monitoring result of a sensor with the same number in historical data is recorded as a track dynamic deformation quantity, the track static deformation quantity and the track dynamic deformation quantity monitored by the sensor with the number i at the time t are constructed into an array and recorded as [ i, t, ait and Dit ], the Ait represents the track static deformation quantity monitored by the sensor with the number i at the time t, and the Dit represents the track dynamic deformation quantity monitored by the sensor with the number i at the time t;
a data analysis module comprising a first analysis module, a second analysis module and a third analysis module,
the first analysis module is used for acquiring an array corresponding to monitoring data of each sensor in historical data and analyzing the relationship between a recovery deviation value of dynamic deformation of a track in the track to be detected and a dynamic deformation value of the track;
the second analysis module is used for predicting a relation function between the static deformation quantity of the track to be detected and the track running time according to an analysis result in the first analysis module;
the third analysis module is used for acquiring a comprehensive deformation quantity of the rail corresponding to the failure of the rail in the historical database, wherein the comprehensive deformation quantity of the rail to be detected is equal to the sum of a static deformation value and a dynamic deformation value of the rail to be detected, and analyzing the relationship between the failure probability of the rail and the comprehensive deformation quantity of the rail;
the early warning maintenance module is used for combining a relation function of the comprehensive deformation quantity of the track to be detected and the track operation time and a relation between the track fault probability and the comprehensive deformation quantity of the track, acquiring the relation between the track operation time and the track fault probability to be detected, calculating the track operation time corresponding to the track fault probability to be detected when the track fault probability to be detected is a first threshold value, presenting the track operation time to a track supervisor to be detected, and further maintaining the track to be detected in advance, wherein the first threshold value is a constant prefabricated in a database.
8. The long-distance passive sensing rail transit health monitoring system of claim 7, wherein: in the process of analyzing the relation between the track fault probability and the track comprehensive deformation quantity in the third analysis module, the third analysis module acquires the corresponding track comprehensive deformation quantity when the track in the database fails every time, and the total frequency of the track in the database is recorded as M; the third analysis module counts the track fault times M1 when the comprehensive deformation quantity of the track is less than or equal to U, obtains the corresponding track fault probability M1/M, and constructs a third type data pair (U, M1/M);
the third analysis module constructs a third plane rectangular coordinate system by taking o3 as an origin, taking the track comprehensive deformation as a transverse axis and taking the track fault probability as a longitudinal axis, marks corresponding coordinate points of each acquired third type of data in the third plane rectangular coordinate system, and performs linear fitting on the coordinate points marked in the third plane rectangular coordinate system according to a third function model prefabricated in a database to obtain a relation H = G3i (U1) between the track fault probability H corresponding to the sensor with the number i in the track to be measured and the track comprehensive deformation U1,
the second function model is y = p3 (x + p 4) 2 + p5, p3 is the third coefficient, p4 is the fourth coefficient, and p5 is the fifth coefficient.
9. The long-distance passive sensing rail transit health monitoring system of claim 7, wherein: the monitoring data of the sensor is updated in real time, and the corresponding track operation time length is also updated in real time when the fault probability of the track to be detected presented to the track to be detected supervisor is the first threshold value.
CN202210976856.7A 2022-08-15 2022-08-15 Long-distance passive sensing rail transit health monitoring system and method Pending CN115339484A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210976856.7A CN115339484A (en) 2022-08-15 2022-08-15 Long-distance passive sensing rail transit health monitoring system and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210976856.7A CN115339484A (en) 2022-08-15 2022-08-15 Long-distance passive sensing rail transit health monitoring system and method

Publications (1)

Publication Number Publication Date
CN115339484A true CN115339484A (en) 2022-11-15

Family

ID=83953005

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210976856.7A Pending CN115339484A (en) 2022-08-15 2022-08-15 Long-distance passive sensing rail transit health monitoring system and method

Country Status (1)

Country Link
CN (1) CN115339484A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116245362A (en) * 2023-03-07 2023-06-09 北京磁浮有限公司 Urban rail contact network risk assessment method and related device

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116245362A (en) * 2023-03-07 2023-06-09 北京磁浮有限公司 Urban rail contact network risk assessment method and related device
CN116245362B (en) * 2023-03-07 2023-12-12 北京磁浮有限公司 Urban rail contact network risk assessment method and related device

Similar Documents

Publication Publication Date Title
CN106712713B (en) The monitoring system and monitoring and abnormal localization method of a kind of photovoltaic plant
CN111474299B (en) Industrial environment real-time monitoring system based on big data
CN104134349B (en) A kind of public transport road conditions disposal system based on traffic multisource data fusion and method
CN106651100B (en) Air quality evaluation system and method based on vehicle-mounted monitoring points optimized through Internet of vehicles
CN106017551A (en) Intelligent transmission line integrated monitoring analysis and early warning method
CN114371260A (en) Gridding monitoring, diffusion early warning and tracing method for non-organized VOCs of industrial enterprise
CN108021732B (en) Online damage early warning method for modular expansion joint of cable-supported bridge
CN116227752B (en) Park facility management system based on Internet of things
CN105003453A (en) Online monitoring and fault diagnosis system of mine fan
CN104571079A (en) Wireless long-distance fault diagnosis system based on multiple-sensor information fusion
CN104615122B (en) A kind of industry control signal detection system and detection method
CN204113701U (en) A kind of mine fan on-line monitoring and fault diagnosis system
CN115979349B (en) Power station space environment monitoring method and system
CN107134978A (en) A kind of method that generated energy curve differentiates photovoltaic module failure
CN115339484A (en) Long-distance passive sensing rail transit health monitoring system and method
CN117220441A (en) Information monitoring intelligent early warning method based on panoramic monitoring
CN113657041A (en) Intelligent sensing and forecasting system for physical and mechanical states of roadbed in alpine region
CN108921305B (en) Component life period monitoring method
CN116840732A (en) Distributed power supply device monitoring system for wind power plant
CN104425046A (en) Method and system for quantizing operation security indexes of nuclear power station
CN115577860B (en) Intelligent maintenance method and system for rail transit based on adaptive control
CN111259539B (en) Simulation method, system and computer storage medium for road PM2.5 refined pollution distribution
KR20120125741A (en) Methods and Systems which can classify vehicles class through the magnetic characteristic analysis of vehicles
CN110956330A (en) Method and system for predicting line loss of power transmission line based on multidimensional influence quantity
CN113569491B (en) Wheel set size detection data analysis and correction method and 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