Multi-monitoring-point abnormal data intelligent processing system and method for iron-related project
By combining measurement robot monitoring and deformation detection models, the railway state matrix is generated, which solves the problem of data analysis and real-time accuracy balance in iron-related projects, and realizes automated monitoring and efficient data processing to ensure the safety of railway structure.
Patent Information
- Application Number
- CN202411076658.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-07
- Publication Date
- 2024-11-22
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In iron-related engineering, measuring robots can collect a large amount of data, but how to extract useful information from it and conduct efficient and accurate analysis is a challenge, and how to achieve a balance between high precision and real-time at complex construction sites is also a difficult point.
Through the measurement robot, it monitors the railway structure, collects data and generates a railway state matrix, uses the deformation detection model to calculate the deformation degree of the railway structure, issues an alarm when it exceeds the safety range, activates emergency plans, and realizes automated monitoring and data processing.
It realizes automated monitoring, reduces human error, improves data accuracy, promptly detects slight deformation of railway structure, ensures safe operation of railways, and provides reliable technical support through intelligent evaluation.
Smart Images

Figure CN119005901A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of railway engineering monitoring, and in particular to a system and method for intelligently processing abnormal data at multiple monitoring points for railway engineering. Background Art
[0002] In recent years, with the development of social economy and the increase of railway operation, a large number of subway tunnels, urban roads, large-scale water conservancy projects under construction have intersected with the railway lines that have been put into operation. During their construction, they will affect the railway structures that have been put into operation, and even directly cause deformation of the existing railway structures. Railway tracks, especially high-speed railway ballastless tracks, have very high requirements for foundation stability. In order to ensure the safe operation of railways, it is very necessary to monitor the railway structures within the scope of their construction.
[0003] As automated monitoring methods have significant advantages over traditional monitoring methods, more and more domestic railway monitoring projects are currently adopting automated monitoring technologies. The measuring robot is an intelligent instrument that emits infrared beams through the self-collimation principle and image processing function. It can automatically distinguish, find and measure the measurement target, and automatically store the measurement information to achieve 24-hour all-weather monitoring. As an all-weather real-time monitoring method, the measuring robot has unique advantages in capturing gradual or sudden displacement changes, and can provide solid data support for railway operation safety.
[0004] However, although measurement robots can collect a large amount of data, it is still a challenge to extract useful information from these data and conduct efficient and accurate analysis. At the same time, in railway-related projects such as high-speed railways, there are high requirements for the accuracy and real-time performance of monitoring data. How to find a balance between high accuracy and real-time performance in complex construction sites is also a problem that measurement robots currently need to solve. Summary of the invention
[0005] The purpose of the present invention is to provide a system and method for intelligently processing abnormal data at multiple monitoring points in railway-related projects, so as to solve the problems raised in the above-mentioned background technology.
[0006] In order to solve the above technical problems, the present invention provides the following technical solution: an intelligent processing method for abnormal data of multiple monitoring points in railway engineering, the method comprising the following steps:
[0007] Step S1: monitoring railway-related projects based on a measuring robot; the measuring robot collects railway status data through a monitoring device; the monitoring device is installed at a monitoring point, and the monitoring point is set according to the railway structure;
[0008] Step S2: processing the railway state data collected by the measuring robot according to the measuring sequence of the measuring robot, integrating the railway state data collected when the n monitoring points are sequentially used as reference points to generate a railway state matrix;
[0009] Step S3: Detecting the railway state matrix based on the deformation detection model, obtaining the railway structure deformation degree according to the deformation detection model, and judging whether the impact of the railway-related project on the railway structure exceeds the safety range through the railway structure deformation degree;
[0010] Step S4: When the impact of the railway project on the railway structure exceeds the safety range, an alarm is issued to relevant personnel and an on-site emergency plan is initiated.
[0011] Furthermore, the step S1 includes:
[0012] S11: obtaining a construction plan for a railway-related project, marking a railway range affected by the construction based on the construction plan, and extracting railway structures within the marked railway range, wherein the railway structures include roadbeds, bridges, tunnels, tracks, and overhead wire pillars;
[0013] According to the preset monitoring point setting scheme in the railway structure acquisition database, n monitoring points are set within the marked railway range;
[0014] A standard reference point is set, each monitoring point is measured based on the standard reference point, and railway status data corresponding to the standard reference point is collected; the railway status data is timestamped and includes coordinates of n monitoring points relative to the reference point;
[0015] The standard reference point is a fixed point within the railway structure, which is used to calibrate other measurements;
[0016] S12: Select the i-th monitoring point as the i-th reference point, i∈[1,n], measure each monitoring point at the i-th reference point, and collect the railway status data corresponding to the i-th reference point;
[0017] When the measuring robot cannot measure the position of the monitoring point based on the reference point position, the coordinates of the monitoring point relative to the reference point are marked as empty;
[0018] This allows the measuring robot to automatically identify the data from the monitoring device and measure changes around the railway structure.
[0019] Furthermore, the step S2 comprises:
[0020] S21: According to the measurement sequence of the measurement robot, the railway state data collected when the n monitoring points are sequentially used as reference points are integrated to generate a railway state matrix, wherein the railway state matrix includes n rows and n columns; wherein the matrix element corresponding to the i-th row and the j-th column in the railway state matrix is denoted as Aij , represents the coordinates of the jth monitoring point relative to the reference point when the i-th monitoring point is used as the i-th reference point, j∈[1,n];
[0021] S22: extracting any set of control elements in the railway state matrix, wherein the set of control elements is symmetrical about the main diagonal in the railway state matrix, and any item in the set of control elements is not empty, and representing the set of control elements as (A ij →A ji ), calculate the relative offset P(A) of any set of control elements according to the following formula ij →A ji ):
[0022]
[0023] in, represents the coordinates of the jth monitoring point collected based on the i-th reference point, represents the coordinates of the i-th reference point; represents the coordinates of the i-th monitoring point collected based on the j-th reference point, represents the coordinates of the jth reference point;
[0024] According to the above method, the relative offset between two monitoring points in a control relationship within the railway range can be calculated. By taking the two monitoring points as reference points in turn to measure the coordinates of other monitoring points, and then analyzing the coordinates of the monitoring points generated by the two measurements, the relative change between the two monitoring points in a control relationship is verified, further reflecting the degree of deformation of some structures within the railway range.
[0025] Process the large amount of data collected by the measuring robot, organize the monitoring data, reduce false alarms, and improve the accuracy of data analysis.
[0026] Furthermore, the step S3 includes:
[0027] S31: Calculate the non-empty element A in the railway state matrix according to the following formula ij The displacement component F(A ij ):
[0028]
[0029]
[0030] Among them, L j Indicates the distance between the jth monitoring point collected by the measuring robot and the standard reference point; L j+vrepresents the distance between the j+vth monitoring point collected by the measuring robot and the standard reference point; j+v represents the number of the monitoring point closest to the jth monitoring point that is not empty; σ j→i+v represents the angle between the line connecting the jth monitoring point collected by the measuring robot and the standard reference point and the line connecting the j+vth monitoring point and the standard reference point; C(A ij ) represents the distance between the jth monitoring point and the j+vth monitoring point collected based on the i-th reference point; represents the coordinates of the j+vth monitoring point collected based on the i-th reference point;
[0031] According to the above method, the railway status data corresponding to the ith reference point is analyzed based on the railway status data measured by the standard reference point. By comparing the connection line between the jth monitoring point collected based on the ith reference point and the j+vth monitoring point collected based on the ith reference point with the standard quantity obtained from the railway status data measured based on the standard reference point through the above formula, the difference between the jth monitoring point and the standard quantity in the railway status data corresponding to the ith reference point can be obtained, and then the difference between the jth monitoring point and the standard quantity can be obtained through the element A. ij The displacement component of represents the deformation degree of the jth monitoring point in the railway structure.
[0032] S32: Calculate the displacement component R of the railway state matrix according to the following formula [Aij] :
[0033]
[0034]
[0035] Among them, L j+1 represents the distance between the j+1th monitoring point collected by the measuring robot and the standard reference point; σ j→j+1 represents the angle between the line between the jth monitoring point collected by the measuring robot and the standard reference point and the line between the j+1th monitoring point and the standard reference point; g represents the relative measurement mean of the railway state matrix, N j represents the number of matrix elements that are not empty in the jth column of the railway state matrix;
[0036] According to the above method, the railway state matrix is analyzed based on the railway state data measured at the standard reference point. The railway state data measured based on the standard reference point is used as a reference value. Through the above formula, the overall gap of the railway state matrix relative to the reference value can be obtained, and then the overall deformation degree of the railway structure is expressed through the displacement component of the railway state matrix.
[0037] S33: Calculate the railway structure deformation △ according to the following formula:
[0038]
[0039] Among them, ω1, ω2, and ω3 represent preset influence coefficients.
[0040] In the above method, the displacement component R of the railway state matrix [Aij] It shows the overall deformation degree of the railway structure. The accumulated displacement component of each element in the railway state matrix reflects the accumulated deformation degree of each element in the railway state matrix. The relative offset P(A ij →A ji ) reflects the deformation degree of some structures within the railway. By combining the influence of the above three deformation degrees, the deformation degree of the current railway structure is obtained based on the abnormal data of multiple monitoring points.
[0041] Furthermore, the deformation detection model detects the railway state matrix through steps S31-S33, and calculates the railway structure deformation degree according to the deformation detection model. When the railway structure deformation degree exceeds the preset risk range, it is determined that the impact of the current railway-related project on the railway structure exceeds the safety range;
[0042] The risk range of railway structure deformation is generated according to the following steps:
[0043] S41: The time required for the measuring robot to generate a railway state matrix is regarded as a detection cycle; each detection cycle corresponds to a railway structure deformation Δ(t);
[0044] S42: Calculate the risk range according to the following formula:
[0045] Risk upper limit H1 = μ + σ;
[0046] The lower limit of risk H2 = μ-σ;
[0047] Risk range: [H2, H1];
[0048] in, t∈[1,T], where T represents the total number of deformations of the railway structure.
[0049] An intelligent processing system for abnormal data from multiple monitoring points for railway projects, the system comprising: a data monitoring module, a railway status data processing module, a railway structure deformation detection module and a safety early warning module;
[0050] The data monitoring module monitors railway-related projects based on the measurement robot and collects railway status data;
[0051] The railway state data processing module is used to process the railway state data collected by the measurement robot to generate a railway state matrix;
[0052] The railway structure deformation detection module is used to detect the railway state matrix and calculate the deformation degree of the railway structure;
[0053] The safety warning module is used to determine whether the impact of the railway project on the railway structure exceeds the safety range based on the output of the railway structure deformation detection module, and to issue a warning for events that exceed the safety range.
[0054] Further, the data monitoring module includes a monitoring point setting unit and a monitoring data collection unit;
[0055] The monitoring point setting unit marks the railway range affected by the construction based on the construction plan, extracts the railway structure within the marked railway range, obtains the monitoring point setting plan preset in the database according to the railway structure, and sets a number of monitoring points within the marked railway range;
[0056] The monitoring data collection unit sets reference points, measures all monitoring points based on the reference points, and collects railway status data corresponding to the reference points.
[0057] Further, the railway status data processing module includes a matrix generation unit and a data transmission unit;
[0058] The matrix generation unit integrates the railway state data collected when each monitoring point is used as a reference point in turn according to the measurement sequence of the measurement robot to generate a railway state matrix;
[0059] The data transmission unit is used to transmit the generated railway state matrix.
[0060] Further, the railway structure deformation detection module includes a partial structure detection unit, a monitoring point detection unit and an overall deformation detection unit;
[0061] The partial structure detection unit outputs the degree of partial structure deformation within the railway range by calculating the relative offset between any set of reference elements within the railway range; the set of reference elements are symmetrical about the main diagonal in the railway state matrix;
[0062] The monitoring point detection unit analyzes the railway state data with the monitoring point as the reference point based on the railway state data measured by the standard reference point, and outputs the deformation degree of each monitoring point in the railway structure by calculating the displacement component of each element in the railway state matrix;
[0063] The overall deformation detection unit analyzes the railway state matrix based on the railway state data measured at the standard reference point, and outputs the overall deformation degree of the railway structure through the displacement component of the railway state matrix.
[0064] Furthermore, the safety warning module includes a risk identification unit and a warning feedback unit;
[0065] The risk identification unit is used to calculate the railway structure deformation degree according to the deformation detection model, generate the risk range of the railway structure deformation degree, and when the railway structure deformation degree exceeds the risk range, determine that the impact of the current railway-related project on the railway structure exceeds the safety range;
[0066] The early warning feedback unit is used to send out an alarm to relevant personnel and initiate an on-site emergency plan when the impact of the railway project on the railway structure exceeds the safety range.
[0067] Compared with the prior art, the beneficial effects achieved by the present invention are:
[0068] The present invention can realize automatic monitoring through the measuring robot, reduce human errors, and improve the accuracy of monitoring data. By collecting railway status data at multiple monitoring points, it is possible to timely discover slight deformations of railway structures, thereby making quick responses.
[0069] The present invention generates a railway state matrix by integrating monitoring data from multiple monitoring points, making the data more structured, extracting key data from massive data, and facilitating efficient data processing and analysis. Based on the deformation detection model, the deformation degree of the railway structure can be intelligently evaluated, providing reliable technical support for safe railway operation.
[0070] The present invention can achieve a balance between high precision and real-time performance at complex construction sites. When the deformation of the railway structure exceeds the safety range, it can promptly issue an alarm and initiate an emergency plan to effectively prevent the occurrence of safety accidents. By accurately assessing the deformation of the railway structure, it helps engineering and technical personnel make more reasonable maintenance and repair decisions. In order to ensure the structural safety of the railway, it is necessary to monitor the railway structure within the scope of its construction.
[0071] The present invention can be flexibly adjusted according to different railway structures and monitoring requirements, has strong adaptability and universality, and can serve railway-related monitoring projects to improve operation quality and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0072] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:
[0073] Figure 1 It is a structural schematic diagram of the intelligent processing system for abnormal data of multiple monitoring points used in railway projects according to the present invention;
[0074] Figure 2 It is a flow chart of the method for intelligently processing abnormal data from multiple monitoring points in railway-related projects according to the present invention. DETAILED DESCRIPTION
[0075] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0076] See also Figure 1 , in the first embodiment: a multi-monitoring point abnormal data intelligent processing system for railway-related projects is provided, including: a data monitoring module, a railway status data processing module, a railway structure deformation detection module and a safety warning module;
[0077] The data monitoring module monitors railway-related projects based on the measurement robot and collects railway status data; it includes a monitoring point setting unit and a monitoring data collection unit;
[0078] The monitoring point setting unit marks the railway range affected by the construction based on the construction plan, extracts the railway structure within the marked railway range, obtains the monitoring point setting plan preset in the database according to the railway structure, and sets a number of monitoring points within the marked railway range;
[0079] The monitoring data collection unit sets reference points, measures all monitoring points based on each reference point, and collects the railway status data corresponding to each reference point.
[0080] The railway state data processing module is used to process the railway state data collected by the measurement robot to generate a railway state matrix; it includes a matrix generation unit and a data transmission unit;
[0081] The matrix generation unit integrates the railway state data collected when each monitoring point is used as a reference point in turn according to the measurement sequence of the measurement robot to generate a railway state matrix;
[0082] The data transmission unit is used to transmit the generated railway state matrix.
[0083] The railway structure deformation detection module is used to detect the railway state matrix and calculate the deformation degree of the railway structure; it includes a partial structure detection unit, a monitoring point detection unit and an overall deformation detection unit;
[0084] The partial structure detection unit outputs the partial structure deformation degree within the railway range by calculating the relative offset between any set of reference elements within the railway range; a set of reference elements is symmetrical about the main diagonal in the railway state matrix;
[0085] The monitoring point detection unit analyzes the railway state data with the monitoring point as the reference point based on the railway state data measured at the standard reference point, and outputs the deformation degree of each monitoring point in the railway structure by calculating the displacement component of each element in the railway state matrix;
[0086] The overall deformation detection unit analyzes the railway state matrix based on the railway state data measured at the standard reference point, and outputs the overall deformation degree of the railway structure through the displacement component of the railway state matrix.
[0087] The safety warning module is used to judge whether the impact of the railway project on the railway structure exceeds the safety range according to the output of the railway structure deformation detection module, and to issue a warning for events that exceed the safety range; it includes a risk identification unit and a warning feedback unit;
[0088] The risk identification unit is used to calculate the railway structure deformation according to the deformation detection model and generate the risk range of the railway structure deformation. When the railway structure deformation exceeds the risk range, it is determined that the impact of the current railway-related project on the railway structure exceeds the safety range.
[0089] The early warning feedback unit is used to issue an alarm to relevant personnel and activate the on-site emergency plan when the impact of railway-related projects on railway structures exceeds the safety range.
[0090] See also Figure 2 In the second embodiment, a method for intelligently processing abnormal data of multiple monitoring points for railway projects is provided, comprising the following steps:
[0091] Step S1: monitoring railway-related projects based on a measurement robot;
[0092] S11: Obtain the construction plan of the railway project, mark the railway range affected by the construction based on the construction plan, and extract the railway structure within the marked railway range, which includes the roadbed, bridges, tunnels, tracks and overhead wire pillars;
[0093] According to the preset monitoring point setting scheme in the railway structure acquisition database, n monitoring points are set within the marked railway range;
[0094] Set a standard reference point, measure each monitoring point based on the standard reference point, and collect the railway status data corresponding to the standard reference point; the railway status data is time-stamped and includes the coordinates of n monitoring points relative to the reference point;
[0095] A standard datum point is a fixed point within the railway structure that is used to calibrate other measurements;
[0096] In one embodiment, the monitoring device may be a prism;
[0097] For example, when monitoring a railway track, the preset monitoring point setting scheme in the database is to set a monitoring point every 10 meters along the track direction, set monitoring points at track joints and switch positions, and increase the density of monitoring points in the track curve section; number the monitoring points starting from the starting position, and set a number of monitoring points for the railway track within the range according to the marked railway range;
[0098] S12: Select the i-th monitoring point as the i-th reference point, i∈[1,n], measure each monitoring point at the i-th reference point, and collect the railway status data corresponding to the i-th reference point;
[0099] When the measuring robot cannot measure the position of the monitoring point based on the reference point position, the coordinates of the monitoring point relative to the reference point are marked as empty;
[0100] This allows the measuring robot to automatically identify the data from the monitoring device and measure changes around the railway structure.
[0101] Step S2: processing the railway state data collected by the measuring robot according to the measuring sequence of the measuring robot, integrating the railway state data collected when the n monitoring points are sequentially used as reference points to generate a railway state matrix;
[0102] S21: According to the measurement sequence of the measuring robot, the railway state data collected when the n monitoring points are used as reference points in turn are integrated to generate a railway state matrix, and the railway state matrix includes n rows and n columns; wherein the matrix element corresponding to the i-th row and j-th column in the railway state matrix is recorded as A ij , represents the coordinates of the jth monitoring point relative to the reference point when the i-th monitoring point is used as the i-th reference point, j∈[1,n];
[0103] S22: extract any group of control elements in the railway state matrix, where the group of control elements is symmetrical about the main diagonal in the railway state matrix, and any item in the group of control elements is not empty, and represent any group of control elements as (A ij →A ji ), calculate the relative offset P(A) of any set of control elements according to the following formula ij →A ji ):
[0104]
[0105] in, represents the coordinates of the jth monitoring point collected based on the i-th reference point, represents the coordinates of the i-th reference point; represents the coordinates of the i-th monitoring point collected based on the j-th reference point, represents the coordinates of the jth reference point;
[0106] According to the above method, the relative offset between two monitoring points in a control relationship within the railway range can be calculated. By taking the two monitoring points as reference points in turn to measure the coordinates of other monitoring points, and then analyzing the coordinates of the monitoring points generated by the two measurements, the relative change between the two monitoring points in a control relationship is verified, further reflecting the degree of deformation of some structures within the railway range.
[0107] Step S3: Detect the railway state matrix based on the deformation detection model, obtain the railway structure deformation degree according to the deformation detection model, and judge whether the impact of the railway-related project on the railway structure exceeds the safety range through the railway structure deformation degree;
[0108] S31: Calculate the non-empty element A in the railway state matrix according to the following formula ij The displacement component F(A ij ):
[0109]
[0110]
[0111] Among them, L j Indicates the distance between the jth monitoring point collected by the measuring robot and the standard reference point; L j+v represents the distance between the j+vth monitoring point collected by the measuring robot and the standard reference point; j+v represents the number of the monitoring point closest to the jth monitoring point that is not empty; σ j→j+v represents the angle between the line connecting the jth monitoring point collected by the measuring robot and the standard reference point and the line connecting the j+vth monitoring point and the standard reference point; C(A ij ) represents the distance between the jth monitoring point and the j+vth monitoring point collected based on the i-th reference point; represents the coordinates of the j+vth monitoring point collected based on the i-th reference point;
[0112] According to the above method, the railway status data corresponding to the ith reference point is analyzed based on the railway status data measured by the standard reference point. By comparing the connection line between the jth monitoring point collected based on the ith reference point and the j+vth monitoring point collected based on the ith reference point with the standard quantity obtained from the railway status data measured based on the standard reference point through the above formula, the difference between the jth monitoring point and the standard quantity in the railway status data corresponding to the ith reference point can be obtained, and then the difference between the jth monitoring point and the standard quantity can be obtained through the element A. ij The displacement component of represents the deformation degree of the jth monitoring point in the railway structure.
[0113] S32: Calculate the displacement component R of the railway state matrix according to the following formula [Aij] :
[0114]
[0115]
[0116] Among them, L j+1 represents the distance between the j+1th monitoring point collected by the measuring robot and the standard reference point; σ j→j+1 represents the angle between the line between the jth monitoring point collected by the measuring robot and the standard reference point and the line between the j+1th monitoring point and the standard reference point; g represents the relative measurement mean of the railway state matrix, N j represents the number of matrix elements that are not empty in the jth column of the railway state matrix;
[0117] According to the above method, the railway state matrix is analyzed based on the railway state data measured at the standard reference point. The railway state data measured based on the standard reference point is used as a reference value. Through the above formula, the overall gap of the railway state matrix relative to the reference value can be obtained, and then the overall deformation degree of the railway structure is expressed through the displacement component of the railway state matrix.
[0118] S33: Calculate the railway structure deformation △ according to the following formula:
[0119]
[0120] Among them, ω1, ω2, and ω3 represent preset influence coefficients.
[0121] In the above method, the displacement component R of the railway state matrix [Aij] It shows the overall deformation degree of the railway structure. The accumulated displacement component of each element in the railway state matrix reflects the accumulated deformation degree of each element in the railway state matrix. The relative offset P(A ij →A ji ) reflects the deformation degree of some structures within the railway. By combining the influence of the above three deformation degrees, the deformation degree of the current railway structure is obtained based on the abnormal data of multiple monitoring points.
[0122] S34: The deformation detection model detects the railway state matrix through steps S31-S33, and calculates the railway structure deformation according to the deformation detection model. When the railway structure deformation exceeds the preset risk range, it is determined that the impact of the current railway-related project on the railway structure exceeds the safety range;
[0123] The risk range of railway structure deformation is generated according to the following steps:
[0124] S341: The time required for the measuring robot to generate a railway state matrix is regarded as a detection cycle; each detection cycle corresponds to a railway structure deformation Δ(t);
[0125] S342: Calculate the risk range according to the following formula:
[0126] Risk upper limit H1 = μ + σ;
[0127] The lower limit of risk H2 = μ-σ;
[0128] Risk range: [H2, H1];
[0129] in, t∈[1,T], where T represents the total number of deformations of the railway structure.
[0130] Step S4: When the impact of the railway project on the railway structure exceeds the safety range, an alarm is issued to relevant personnel and an on-site emergency plan is initiated.
[0131] Among them, the on-site emergency plan includes the isolation of dangerous areas, and the dangerous areas are located according to the railway status data corresponding to each benchmark point; the data perception results of multiple monitoring points are integrated, and monitoring reports are generated regularly to record the deformation of the railway structure.
[0132] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0133] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. An intelligent processing method for abnormal data from multiple monitoring points in railway projects, characterized in that: The method comprises the following steps: Step S1: monitoring railway-related projects based on a measuring robot; the measuring robot collects railway status data through a monitoring device; the monitoring device is installed at a monitoring point, and the monitoring point is set according to the railway structure; Step S2: processing the railway state data collected by the measuring robot according to the measuring sequence of the measuring robot, integrating the railway state data collected when the n monitoring points are sequentially used as reference points to generate a railway state matrix; Step S3: Detecting the railway state matrix based on the deformation detection model, obtaining the railway structure deformation degree according to the deformation detection model, and judging whether the impact of the railway-related project on the railway structure exceeds the safety range through the railway structure deformation degree; Step S4: When the impact of the railway project on the railway structure exceeds the safety range, an alarm is issued to relevant personnel and an on-site emergency plan is initiated.
2. The method for intelligently processing abnormal data at multiple monitoring points for railway projects according to claim 1 is characterized in that: The step S1 comprises: S11: Obtain a construction plan for the railway project, mark the railway range affected by the construction based on the construction plan, and extract the railway structure within the marked railway range; obtain a preset monitoring point setting plan in the database according to the railway structure, and set n monitoring points within the marked railway range; A standard reference point is set, each monitoring point is measured based on the standard reference point, and railway status data corresponding to the standard reference point is collected; the railway status data is timestamped and includes coordinates of n monitoring points relative to the reference point; S12: Select the i-th monitoring point as the i-th reference point, i∈[1,n], measure each monitoring point at the i-th reference point, and collect the railway status data corresponding to the i-th reference point; When the measuring robot cannot measure the position of the monitoring point based on the reference point position, the coordinates of the monitoring point relative to the reference point are marked as empty.
3. The intelligent processing method for abnormal data of multiple monitoring points for railway projects according to claim 1 is characterized in that: The step S2 comprises: S21: According to the measurement sequence of the measurement robot, the railway state data collected when the n monitoring points are sequentially used as reference points are integrated to generate a railway state matrix, wherein the railway state matrix includes n rows and n columns; wherein the matrix element corresponding to the i-th row and the j-th column in the railway state matrix is denoted as A ij , represents the coordinates of the jth monitoring point relative to the reference point when the i-th monitoring point is used as the i-th reference point, j∈[1,n]; S22: extracting any set of control elements in the railway state matrix, wherein the set of control elements is symmetrical about the main diagonal in the railway state matrix, and any item in the set of control elements is not empty, and representing the set of control elements as (A ij →A ji ), calculate the relative offset P(A) of any set of control elements according to the following formula ij →A ji ): in, represents the coordinates of the jth monitoring point collected based on the i-th reference point, represents the coordinates of the i-th reference point; represents the coordinates of the i-th monitoring point collected based on the j-th reference point, Represents the coordinates of the jth reference point.
4. The method for intelligently processing abnormal data at multiple monitoring points for railway projects according to claim 1 is characterized in that: The step S3 comprises: S31: Calculate the non-empty element A in the railway state matrix according to the following formula ij The displacement component F(A ij ): Among them, L j Indicates the distance between the jth monitoring point collected by the measuring robot and the standard reference point; L j+v represents the distance between the j+vth monitoring point collected by the measuring robot and the standard reference point; j+v represents the number of the monitoring point closest to the jth monitoring point that is not empty; σ j→j+v represents the angle between the line connecting the jth monitoring point collected by the measuring robot and the standard reference point and the line connecting the j+vth monitoring point and the standard reference point; C(A ij ) represents the distance between the jth monitoring point and the j+vth monitoring point collected based on the i-th reference point; represents the coordinates of the j+vth monitoring point collected based on the i-th reference point; S32: Calculate the displacement component R of the railway state matrix according to the following formula [Aij] : Among them, L j+1 represents the distance between the j+1th monitoring point collected by the measuring robot and the standard reference point; σ j→j+1 represents the angle between the line between the jth monitoring point collected by the measuring robot and the standard reference point and the line between the j+1th monitoring point and the standard reference point; g represents the relative measurement mean of the railway state matrix, N j represents the number of matrix elements that are not empty in the jth column of the railway state matrix; S33: Calculate the railway structure deformation △ according to the following formula: Among them, ω1, ω2, and ω3 represent preset influence coefficients.
5. The method for intelligently processing abnormal data at multiple monitoring points for railway projects according to claim 4 is characterized in that: The deformation detection model detects the railway state matrix through steps S31-S33, and calculates the railway structure deformation degree according to the deformation detection model. When the railway structure deformation degree exceeds the preset risk range, it is determined that the impact of the current railway-related project on the railway structure exceeds the safety range; The risk range of railway structure deformation is generated according to the following steps: S41: The time required for the measuring robot to generate a railway state matrix is regarded as a detection cycle; each detection cycle corresponds to a railway structure deformation Δ(t); S42: Calculate the risk range according to the following formula: Risk upper limit H1 = μ + σ; The lower limit of risk H2 = μ-σ; Risk range: [H2, H1]; in, t∈[1,T], where T represents the total number of deformations of the railway structure.
6. A system for intelligently processing abnormal data from multiple monitoring points for railway projects, which executes the method for intelligently processing abnormal data from multiple monitoring points for railway projects as claimed in any one of claims 1 to 5, characterized in that: The system includes: a data monitoring module, a railway status data processing module, a railway structure deformation detection module and a safety early warning module; The data monitoring module monitors railway-related projects based on the measurement robot and collects railway status data; The railway state data processing module is used to process the railway state data collected by the measurement robot to generate a railway state matrix; The railway structure deformation detection module is used to detect the railway state matrix and calculate the deformation degree of the railway structure; The safety warning module is used to determine whether the impact of the railway project on the railway structure exceeds the safety range based on the output of the railway structure deformation detection module, and to issue a warning for events that exceed the safety range.
7. The intelligent processing system for abnormal data at multiple monitoring points for railway projects according to claim 6 is characterized by: The data monitoring module includes a monitoring point setting unit and a monitoring data acquisition unit; The monitoring point setting unit marks the railway range affected by the construction based on the construction plan, extracts the railway structure within the marked railway range, obtains the monitoring point setting plan preset in the database according to the railway structure, and sets a number of monitoring points within the marked railway range; The monitoring data collection unit sets reference points, measures all monitoring points based on the reference points, and collects railway status data corresponding to the reference points.
8. The intelligent processing system for abnormal data at multiple monitoring points for railway projects according to claim 6 is characterized by: The railway status data processing module includes a matrix generation unit and a data transmission unit; The matrix generation unit integrates the railway state data collected when each monitoring point is used as a reference point in turn according to the measurement sequence of the measurement robot to generate a railway state matrix; The data transmission unit is used to transmit the generated railway state matrix.
9. The intelligent processing system for abnormal data at multiple monitoring points for railway projects according to claim 6 is characterized by: The railway structure deformation detection module includes a partial structure detection unit, a monitoring point detection unit and an overall deformation detection unit; The partial structure detection unit outputs the degree of partial structure deformation within the railway range by calculating the relative offset between any set of reference elements within the railway range; the set of reference elements are symmetrical about the main diagonal in the railway state matrix; The monitoring point detection unit analyzes the railway state data with the monitoring point as the reference point based on the railway state data measured by the standard reference point, and outputs the deformation degree of each monitoring point in the railway structure by calculating the displacement component of each element in the railway state matrix; The overall deformation detection unit analyzes the railway state matrix based on the railway state data measured at the standard reference point, and outputs the overall deformation degree of the railway structure through the displacement component of the railway state matrix.
10. The intelligent processing system for abnormal data at multiple monitoring points for railway projects according to claim 6 is characterized in that: The safety warning module includes a risk identification unit and a warning feedback unit; The risk identification unit is used to calculate the railway structure deformation degree according to the deformation detection model, generate the risk range of the railway structure deformation degree, and when the railway structure deformation degree exceeds the risk range, determine that the impact of the current railway-related project on the railway structure exceeds the safety range; The early warning feedback unit is used to send out an alarm to relevant personnel and initiate an on-site emergency plan when the impact of the railway project on the railway structure exceeds the safety range.
Citation Information
Patent Citations
Railway construction site positioning management system based on BIM and GIS
CN112597578A
Dam break process safety monitoring, early warning and influence evaluation method
CN113108764A
Method for obtaining mapping deformation of CRTS-I type slab ballastless track caused by roadbed deformation
CN114139253A
Subway tunnel structure safety monitoring method based on measuring robot
CN116518945A
Overlying strata movement deformation monitoring system after highway goaf filling
CN116878432A
Cited By
Railway line monitoring alarm method and system
CN119840689A
