Track monitoring data processing method, device and storage medium based on three-dimensional structure
Through the three-dimensional structure data processing method, the weighted fusion of time and space-time dimensions is used to solve the problem of false alarms in rail transit tunnel monitoring, improve the reliability and system efficiency of monitoring results, and ensure safety.
Patent Information
- Application Number
- CN202411102615.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-13
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-08-13
AI Technical Summary
In the monitoring of rail transit tunnel structure, due to the complex environment, the angle and distance observation of measuring robots are affected by atmospheric refraction, atmospheric turbulence and occlusion of running trains, resulting in false alarms, resulting in unnecessary emergency response and waste of resources, affecting the efficiency and safety of the monitoring system. sex.
The orbital monitoring data processing method based on three-dimensional structure is adopted, and the weighted fusion processing of time dimensions and spatiotemporal dimensions is used to calculate the weight value using the historical information of the monitoring data and the correlation coefficient of neighboring points to improve the reliability and accuracy of the monitoring results.
It improves the reliability of the deformation monitoring data of rail transit tunnel structure, reduces false alarms, improves the efficiency and safety of the monitoring system, and ensures the smooth progress of monitoring data decision processing.
Smart Images

Figure CN118627016B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of rail transit tunnel structure deformation monitoring, and in particular relates to a rail monitoring data processing method, device and storage medium based on a three-dimensional structure. Background Art
[0002] With the continuous advancement of urbanization, rail transit tunnel projects have received more and more attention. Rail transit tunnel construction is a time-consuming and labor-intensive project with high costs and large passenger flow. In recent years, rail transit tunnel safety accidents have occurred from time to time. If an accident occurs, it will cause significant economic losses and casualties. Therefore, it is of great significance to carry out real-time continuous deformation monitoring of rail transit.
[0003] At present, the commonly used means of monitoring deformation of rail transit tunnel structures is: using a measuring robot to measure the angle and distance values of the monitoring points on the tunnel structure in real time, and calculate the three-dimensional coordinate deformation value of the monitoring point; the three-dimensional deformation value of the monitoring point calculated in each measurement is compared with the pre-determined deformation value threshold, and when the deformation value exceeds the threshold, an alarm is issued in time to avoid the occurrence of safety accidents.
[0004] However, due to the complex environment in rail transit tunnels, the angle and distance observation of the measuring robot, as an optical instrument, may be abnormal due to various influences such as atmospheric refraction, atmospheric turbulence, and obstruction by running trains. If the above anomalies are regarded as deformations and false alarms are issued, it will lead to unnecessary emergency responses, waste of resources, and may even cause public panic. Therefore, it is necessary to make full use of relevant information when processing rail transit tunnel structure monitoring data, improve the reliability of monitoring results, minimize the occurrence of false alarms, and thus improve the efficiency and safety of rail transit monitoring systems. Summary of the invention
[0005] Based on the above problems, the present invention provides a rail monitoring data processing method, device and storage medium based on a three-dimensional structure, so as to improve the reliability of monitoring results in the processing of rail transit tunnel structure deformation monitoring data, improve the efficiency and safety of the rail transit monitoring system, and facilitate the smooth progress of rail transit tunnel monitoring data decision-making processing.
[0006] On the one hand, the present invention provides a method for processing track monitoring data based on a three-dimensional structure, the method comprising the following steps:
[0007] A plurality of monitoring points are set in the rail transit tunnel structure to be monitored, and a monitoring system is used to monitor the deformation of the monitoring points at a preset monitoring frequency during the operation time;
[0008] Obtain historical monitoring data of monitoring points during the monitoring process;
[0009] Perform weighted fusion processing of the time dimension and the space-time dimension on the historical monitoring data;
[0010] The weighted fusion processing of the time dimension is performed on the historical monitoring data, wherein the time dimension is divided into one period according to the preset time point, and multiple time dimensions are multiple periods, including the following steps:
[0011] Obtain the corresponding coordinate values of at least one monitoring point in multiple periods, and calculate the coordinate deformation values of multiple directions corresponding to the i-th period of the monitoring point according to the coordinate values of the first period and the i-th period, where the first period is the first time point and i is a positive integer;
[0012] Obtain the corresponding angle monitoring values of the monitoring point in multiple periods. Obtain the angle monitoring values of multiple rounds for each period. Calculate the field observation value corresponding to the period based on the angle monitoring values of multiple rounds.
[0013] The first weight value is calculated based on the difference of multiple period field observation values;
[0014] According to the coordinate deformation value of the monitoring point in the previous i periods and the first weight value, the time dimension weighted fusion result corresponding to the monitoring point is calculated;
[0015] The weighted fusion processing of historical monitoring data in time and space dimensions includes the following steps:
[0016] According to the monitoring point layout map and the monitoring point numbering rules, multiple neighborhood points corresponding to the monitoring point are found, and the multiple field points include longitudinal neighborhood points and transverse neighborhood points. The type and number of each neighborhood point are extracted according to the number of the monitoring point, and the relative position relationship between each neighborhood point and the monitoring point is obtained, and finally multiple relative position relationships are obtained;
[0017] Obtain the historical monitoring data corresponding to the monitoring point and each neighboring point, and calculate the correlation coefficient of the historical monitoring data corresponding to the neighboring point based on the historical monitoring data of the monitoring point and the historical monitoring data of a certain neighboring point, and finally obtain multiple historical monitoring data correlation coefficients;
[0018] A second weight is calculated based on the correlation coefficients of the multiple relative position relationships and the multiple historical monitoring data;
[0019] Obtain the time dimension weighted fusion result of each neighborhood point in the same time dimension as the monitoring point;
[0020] According to the weighted fusion result of the time dimension corresponding to the monitoring point and its multiple neighboring points and the second weight, the weighted fusion result of the space-time dimension corresponding to the monitoring point is calculated.
[0021] Furthermore, the plurality of monitoring points are distributed in a plurality of monitoring sections of the rail transit tunnel structure to be monitored, and are located at least at the tunnel top, the side walls on both sides of the tunnel, and the tunnel bottom of the monitoring section.
[0022] Furthermore, a total station is used to perform multiple rounds of edge and angle measurements, and the first-period coordinate values and the i-th-period coordinate values of the monitoring points are calculated;
[0023] use Identifies the i-th period coordinate value of the monitoring point, The first-period coordinate value of the monitoring point is identified. The coordinate deformation value corresponding to the i-th period of the monitoring point is calculated based on the first-period coordinate value and the i-th period coordinate value. The expression is as follows:
[0024] ,
[0025] in It represents the coordinate deformation values of the monitoring point in the X, Y, and Z directions at the i-th period.
[0026] Furthermore, the angle monitoring value includes the horizontal angle monitoring value of the left side of the plate , horizontal angle monitoring value on the right side of the plane , Left plate vertical angle monitoring value , plane right vertical angle monitoring value ;
[0027] Field observation values include 2C value deviation, horizontal angle mean error value, vertical plate index difference deviation, and vertical angle mean error value;
[0028] The 2C value is calculated from the horizontal angle monitoring value of the historical monitoring data, and the expression is:
[0029] ;
[0030] The 2C value deviation is the difference between the mean 2C value of the i-th period and the mean 2C value of the previous N periods, denoted as ;
[0031] The horizontal angle is the projection of the angle between the monitoring point and the starting reference point on the horizontal plane. The horizontal angle of each period is calculated by the horizontal angle monitoring value of each measurement round. The expression is:
[0032]
[0033] in, is the horizontal angle of the monitoring point at the i-th period and the j-th measurement, is the average value of the horizontal angle monitoring value on the left side of the disk and the horizontal angle monitoring value on the right side of the disk during the i-th period and the j-th measurement of the monitoring point, is the average value of the horizontal angle monitoring value on the left side of the disk and the horizontal angle monitoring value on the right side of the disk during the i-th period and the j-th measurement of the starting reference point, where j is a positive integer;
[0034] The mean error value of the horizontal angle is the mean error value calculated from the horizontal angles of the j measured rounds obtained in each monitoring period, denoted as ;
[0035] The vertical index difference is calculated from the vertical angle monitoring value of the historical monitoring data, and the expression is:
[0036] ;
[0037] The vertical index difference deviation is the difference between the mean of the vertical index difference in the i-th period and the mean of the vertical index difference in the previous N periods, denoted as ;
[0038] The vertical angle mean error value is the mean error value of the average value of the horizontal angle monitoring value on the left side of the disk and the horizontal angle monitoring value on the right side of the disk in each monitoring period, recorded as ;
[0039] The expression of the first weight is:
[0040] ;
[0041] ;
[0042] Where A is the difference between the first weighted start calculation period and the i-th period; are the weight of the X-direction coordinate deformation value, the Y-direction coordinate deformation value, and the Z-direction coordinate deformation value of the monitoring point in the i-th period, respectively, and i is a positive integer.
[0043] Furthermore, the weighted fusion result of the time dimension is calculated by a priori judgment of the deformation trend of the rail transit tunnel structure, and the deformation value of the monitoring point in the previous N periods and the deformation value of the i-th period are weighted and fused. The calculation method is as follows:
[0044] ;
[0045] in They are respectively represented as the time dimension fusion processing results in the X direction, Y direction, and Z direction. is the weight of the X-direction coordinate deformation value of the monitoring point in the i-th period and its previous N periods; are the weights of the Y-direction coordinate deformation values of the monitoring point in the i-th period and its previous N periods respectively; are the weights of the Z-direction coordinate deformation values of the monitoring point in the i-th period and its previous N periods respectively; are the coordinate deformation values of the monitoring point in the i-th period and the previous N periods in the X direction; are the coordinate deformation values of the monitoring point in the i-th period and the N periods before it in the Y direction; are the coordinate deformation values of the monitoring point in the i-th period and the previous N periods in the Z direction, and i is a positive integer.
[0046] Furthermore, the monitoring point numbering rule is that the monitoring point numbering includes at least a section number and a monitoring point number, wherein the monitoring point number represents the position of the monitoring point on the section;
[0047] According to the number of the monitoring point, the number of each neighboring point is extracted, including:
[0048] Find out the section number and monitoring point number of the monitoring point by comparing the historical monitoring data and the monitoring point map;
[0049] Add or subtract the ordinal number of the section number to obtain the number of the neighboring point of the same longitudinal section of the monitoring point;
[0050] The fixed section number remains unchanged, and the monitoring point number is added or subtracted to obtain the number of the neighboring points in the same cross section of the monitoring point.
[0051] Furthermore, the relative position relationship between a certain monitoring point and the corresponding multiple neighboring points includes: the distance between the monitoring point and the multiple neighboring points in the same cross section, and the distance between the monitoring point and the multiple neighboring points in the same longitudinal section, expressed as:
[0052] ,
[0053] in, Respectively represent the coordinate values of monitoring point a and neighborhood point b, Represents the distance between monitoring point a and neighboring point b;
[0054] The correlation coefficient expression of the historical monitoring data of monitoring point a and neighboring point b is:
[0055] ;
[0056] in is the correlation coefficient of the historical monitoring data of the neighborhood point b and the monitoring point a in the X, Y, and Z directions respectively, are the coordinate deformation values of the monitoring point a in the X, Y, and Z directions at the i-th period, are the mean values of the historical coordinate deformation values of monitoring point a in the X, Y, and Z directions from the 1st to the Mth period, are the coordinate deformation values of the neighborhood point b in the X, Y, and Z directions in the i-th period, are the means of the historical coordinate deformation values of the neighborhood point b in the X, Y, and Z directions from the 1st to the Mth period, respectively, and M is a positive integer.
[0057] The weight expression of the coordinate deformation value of the neighborhood point in the X, Y, and Z directions is:
[0058] ;
[0059] in is the initial weight value of the neighborhood point b, which is determined by the type of the neighborhood point; is the distance from the neighborhood point b to the monitoring point a, are the correlation coefficients of the historical monitoring data of the neighborhood point b and the monitoring point a in the X, Y, and Z directions respectively.
[0060] Furthermore, the expression of weighted fusion processing in the spatiotemporal dimension is:
[0061] ;
[0062] in is the weighted fusion result of the spatiotemporal dimension of monitoring point a in the i-th period; , is the weight of the coordinate deformation value of the monitoring point a in the X, Y, and Z directions; are the weights of the coordinate deformation values of the m neighboring points b in the X direction; are the weights of the coordinate deformation values of m neighboring points b in the Y direction; are the weights of the coordinate deformation values of the m neighboring points b in the Z direction; They are the time dimension weighted fusion results of the X-direction coordinate deformation values of m neighborhood points b in the i-th period; They are the time dimension weighted fusion results of the Y-direction coordinate deformation values of m neighborhood points b in the i-th period; They are the time dimension weighted fusion results of the deformation values of the coordinates of m neighborhood points b in the i-th period in the Z direction.
[0063] In a second aspect, an electronic device is provided, the electronic device comprising:
[0064] at least one processor; and,
[0065] a memory communicatively connected to at least one processor; wherein,
[0066] The memory stores a computer program that can be executed by at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute a track monitoring data processing method based on a three-dimensional structure.
[0067] In a third aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to execute a track monitoring data processing method based on a three-dimensional structure.
[0068] Compared with the prior art, the present invention has the following beneficial effects:
[0069] The present invention fully mines the time and space-time related information of the deformation monitoring data of the rail transit tunnel structure according to the space-time correlation of the occurrence and development of deformation; determines the weight according to the time span of the monitoring information and the quality of the monitoring data, and realizes the fusion processing of the time dimension of the monitoring data; determines the weight according to the space-time distribution, structural correlation and historical deformation correlation coefficient between the monitoring points, and realizes the fusion processing of the space-time dimension of the monitoring data; finally, the processing result of the rail transit tunnel structure monitoring data taking into account the space-time correlation is obtained.
[0070] The method of the present invention can improve the reliability of monitoring results in the processing of rail transit tunnel structure deformation monitoring data, thereby improving the efficiency and safety of the rail transit monitoring system, and is conducive to the smooth advancement of rail transit tunnel monitoring data decision-making processing work. BRIEF DESCRIPTION OF THE DRAWINGS
[0071] Figure 1 A specific flow chart of a method for processing track structure monitoring data provided by an embodiment of the present invention;
[0072] Figure 2 A specific flow chart of a track structure monitoring data processing method provided by another embodiment of the present invention;
[0073] Figure 3 A schematic diagram of monitoring longitudinal section points provided by another embodiment of the present invention;
[0074] Figure 4 A schematic diagram of monitoring cross-section points provided for another embodiment of 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] Embodiment 1
[0077] Figure 1 This is a specific flow chart of a method for processing track structure monitoring data provided by an embodiment of the present invention. The embodiment of the present invention provides a method for processing track monitoring data based on a three-dimensional structure. The specific method is as follows:
[0078] A plurality of monitoring points are set in the rail transit tunnel structure to be monitored, and a monitoring system is used to monitor the deformation of the monitoring points at a preset monitoring frequency during the operation time;
[0079] Obtain historical monitoring data of monitoring points during the monitoring process;
[0080] Perform weighted fusion processing of the time dimension and the space-time dimension on the historical monitoring data;
[0081] The weighted fusion processing of the time dimension is performed on the historical monitoring data, wherein the time dimension is divided into one period according to the preset time point, and multiple time dimensions are multiple periods, including the following steps:
[0082] Obtain the corresponding coordinate values of at least one monitoring point in multiple periods, and calculate the coordinate deformation values of multiple directions corresponding to the i-th period of the monitoring point according to the coordinate values of the first period and the i-th period, where the first period is the first time point, i is a positive integer, and the i-th period is the current period;
[0083] Obtain the corresponding angle monitoring values of the monitoring point in multiple periods. Obtain the angle monitoring values of multiple rounds for each period. Calculate the field observation value corresponding to the period based on the angle monitoring values of multiple rounds.
[0084] The first weight value is calculated based on the difference of multiple period field observation values;
[0085] According to the coordinate deformation value of the monitoring point in the previous i periods and the first weight value, the time dimension weighted fusion result corresponding to the monitoring point is calculated;
[0086] The weighted fusion processing of historical monitoring data in time and space dimensions includes the following steps:
[0087] According to the monitoring point layout map and the monitoring point numbering rules, multiple neighborhood points corresponding to the monitoring point are found, and the multiple field points include longitudinal neighborhood points and transverse neighborhood points. The type and number of each neighborhood point are extracted according to the number of the monitoring point, and the relative position relationship between each neighborhood point and the monitoring point is obtained, and finally multiple relative position relationships are obtained;
[0088] Obtain the historical monitoring data corresponding to the monitoring point and each neighboring point, and calculate the correlation coefficient of the historical monitoring data corresponding to the neighboring point based on the historical monitoring data of the monitoring point and the historical monitoring data of a certain neighboring point, and finally obtain multiple historical monitoring data correlation coefficients;
[0089] A second weight is calculated based on the correlation coefficients of the multiple relative position relationships and the multiple historical monitoring data;
[0090] Obtain the time dimension weighted fusion result of each neighborhood point in the same time dimension as the monitoring point;
[0091] According to the weighted fusion result of the time dimension corresponding to the monitoring point and its multiple neighboring points and the second weight, the weighted fusion result of the space-time dimension corresponding to the monitoring point is calculated.
[0092] In this embodiment, the plurality of monitoring points are distributed in a plurality of monitoring sections of the rail transit tunnel structure to be monitored, and are located at least at the tunnel top, the side walls on both sides of the tunnel, and the tunnel bottom of the monitoring section.
[0093] In this embodiment, a total station is used to perform multiple rounds of edge and angle measurement, and the first-period coordinate value and the i-th-period coordinate value of the monitoring point are calculated;
[0094] use Identifies the i-th period coordinate value of the monitoring point, The first-period coordinate value of the monitoring point is identified. The coordinate deformation value corresponding to the i-th period of the monitoring point is calculated based on the first-period coordinate value and the i-th period coordinate value. The expression is as follows:
[0095] ,
[0096] in It represents the coordinate deformation values of the monitoring point in the X, Y, and Z directions at the i-th period.
[0097] In this embodiment, the angle monitoring value includes the horizontal angle monitoring value of the left side of the plate , horizontal angle monitoring value on the right side of the plane , Left plate vertical angle monitoring value , plane right vertical angle monitoring value ;
[0098] Field observation values include 2C value deviation, horizontal angle mean error value, vertical plate index difference deviation, and vertical angle mean error value;
[0099] The 2C value is calculated from the horizontal angle monitoring value of the historical monitoring data, and the expression is:
[0100] ;
[0101] The 2C value deviation is the difference between the mean 2C value of the i-th period and the mean 2C value of the previous N periods, denoted as ;
[0102] The horizontal angle is the projection of the angle between the monitoring point and the starting reference point on the horizontal plane. The horizontal angle of each period is calculated by the horizontal angle monitoring value of each measurement round. The expression is:
[0103]
[0104] in, is the horizontal angle of the monitoring point at the i-th period and the j-th measurement, is the average value of the horizontal angle monitoring value on the left side of the disk and the horizontal angle monitoring value on the right side of the disk during the i-th period and the j-th measurement of the monitoring point, is the average value of the horizontal angle monitoring value on the left side of the disk and the horizontal angle monitoring value on the right side of the disk during the i-th period and the j-th measurement of the starting reference point, where j is a positive integer;
[0105] The mean error value of the horizontal angle is the mean error value calculated from the horizontal angles of the j measured rounds obtained in each monitoring period, denoted as ;
[0106] The vertical index difference is calculated from the vertical angle monitoring value of the historical monitoring data, and the expression is:
[0107] ,
[0108] The vertical index difference deviation is the difference between the mean of the vertical index difference in the i-th period and the mean of the vertical index difference in the previous N periods, denoted as ;
[0109] The vertical angle mean error value is the mean error value of the average value of the horizontal angle monitoring value on the left side of the disk and the horizontal angle monitoring value on the right side of the disk in each monitoring period, recorded as ;
[0110] The expression of the first weight is:
[0111] ;
[0112] ;
[0113] Where A is the difference between the first weighted start calculation period and the i-th period; are the weight of the X-direction coordinate deformation value, the Y-direction coordinate deformation value, and the Z-direction coordinate deformation value of the monitoring point in the i-th period respectively.
[0114] In this embodiment, the weighted fusion result of the time dimension is calculated by a priori judgment of the deformation trend of the rail transit tunnel structure, and the deformation value of the monitoring point in the previous N periods and the deformation value of the i-th period are weighted and fused. The calculation method is as follows:
[0115] ;
[0116] in They are respectively represented as the time dimension fusion processing results in the X direction, Y direction, and Z direction. is the weight of the X-direction coordinate deformation value of the monitoring point in the i-th period and its previous N periods; are the weights of the Y-direction coordinate deformation values of the monitoring point in the i-th period and its previous N periods respectively; are the weights of the Z-direction coordinate deformation values of the monitoring point in the i-th period and its previous N periods respectively; are the coordinate deformation values of the monitoring point in the i-th period and the previous N periods in the X direction; are the coordinate deformation values of the monitoring point in the i-th period and the N periods before it in the Y direction; They are the coordinate deformation values of the monitoring point in the i-th period and the previous N periods in the Z direction.
[0117] In this embodiment, the monitoring point numbering rule is that the monitoring point numbering includes at least a section number and a monitoring point number, wherein the monitoring point number represents the position of the monitoring point on the section;
[0118] According to the number of the monitoring point, the number of each neighboring point is extracted, including:
[0119] Find out the section number and monitoring point number of the monitoring point by comparing the historical monitoring data and the monitoring point map;
[0120] Add or subtract the ordinal number of the section number to obtain the number of the neighboring point of the same longitudinal section of the monitoring point;
[0121] The fixed section number remains unchanged, and the monitoring point number is added or subtracted to obtain the number of the neighboring points in the same cross section of the monitoring point.
[0122] The specific monitoring point numbering rule is: line + line direction code + interval number + P + section number + monitoring point number. The track monitoring data method of this embodiment is applied to the same line monitoring, and the line, line direction code and interval code are the same.
[0123] In this embodiment, the relative position relationship between a monitoring point and the corresponding multiple neighboring points includes: the distance between the monitoring point and the multiple neighboring points in the same cross section, and the distance between the monitoring point and the multiple neighboring points in the same longitudinal section, expressed as:
[0124] ,
[0125] in, Respectively represent the coordinate values of monitoring point a and neighborhood point b, Represents the distance between monitoring point a and neighboring point b;
[0126] The correlation coefficient expression of the historical monitoring data of monitoring point a and neighboring point b is:
[0127] ;
[0128] in is the correlation coefficient of the historical monitoring data of the neighborhood point b and the monitoring point a in the X, Y, and Z directions respectively, are the coordinate deformation values of the monitoring point a in the X, Y, and Z directions at the i-th period, are the mean values of the historical coordinate deformation values of monitoring point a in the X, Y, and Z directions from the 1st to the Mth period, are the coordinate deformation values of the neighborhood point b in the X, Y, and Z directions in the i-th period, are the means of the historical coordinate deformation values of the neighborhood point b in the X, Y, and Z directions from the 1st to the Mth period, respectively, and M is a positive integer.
[0129] The weight expression of the coordinate deformation value of the neighborhood point in the X, Y, and Z directions is:
[0130] ;
[0131] in is the initial weight value of the neighborhood point b, which is determined by the type of the neighborhood point; is the distance from the neighborhood point b to the monitoring point a, are the correlation coefficients of the historical monitoring data of the neighborhood point b and the monitoring point a in the X, Y, and Z directions respectively.
[0132] In this embodiment, the expression of weighted fusion processing in the spatiotemporal dimension is:
[0133] ;
[0134] in is the weighted fusion result of the spatiotemporal dimension of monitoring point a in the i-th period; , is the weight of the coordinate deformation value of the monitoring point a in the X, Y, and Z directions; are the weights of the coordinate deformation values of the m neighboring points b in the X direction; are the weights of the coordinate deformation values of m neighboring points b in the Y direction; are the weights of the coordinate deformation values of the m neighboring points b in the Z direction; They are the time dimension weighted fusion results of the X-direction coordinate deformation values of m neighborhood points b in the i-th period; They are the time dimension weighted fusion results of the Y-direction coordinate deformation values of m neighborhood points b in the i-th period; They are the time dimension weighted fusion results of the deformation values of the coordinates of m neighborhood points b in the i-th period in the Z direction.
[0135] Secondly, the present invention also provides an electronic device, the electronic device comprising:
[0136] At least one processor; and a memory in communication with the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned track monitoring data processing method.
[0137] The present invention also provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to implement the above-mentioned track monitoring data processing method when executed by a processor.
[0138] Embodiment 2
[0139] Combination Figure 1, Figure 2 The flowchart of the track structure monitoring data processing method provided in the second embodiment of the present invention is based on the above-mentioned first embodiment. The present invention specifically takes a certain rail transit tunnel structure deformation monitoring project as an example. A measuring robot is used to monitor the deformation of 100 monitoring points in 20 sections. The monitoring frequency is 3 times / day, that is, 3 periods / day. The monitoring system has been operating normally for 100 days, with a total of 300 periods. The historical monitoring data collected by the monitoring system operating for 100 days is obtained, and the data is processed. The i-th period of monitoring data collected is first calculated according to the polar coordinate method. , and the difference between it and the first period coordinates stored in the database is obtained , where i=300.
[0140] Calculate the mean 2C value and the mean vertical index difference of the current historical monitoring data, and update the mean 2C value and the mean vertical index difference of the current period with the historical 2C mean and the mean vertical index difference in the database to obtain the 2C mean and the mean vertical index difference of 300 periods of data. The current period is the 300th period; calculate the difference between the mean 2C value and the mean vertical index difference of the current period and the 2C mean and the mean vertical index difference of 300 periods of data to obtain the current 2C value deviation , vertical index difference deviation , where i=300; calculate the horizontal angle mean error of the original historical monitoring data of the current period and vertical angle error .
[0141] According to deformation analysis, the time fusion dimension is determined to be 3 days, and the monitoring results of the first 9 periods are extracted from the database. , that is, N=9, that is, extract the monitoring results from the 291st to the 299th period, and the horizontal angle error of the original data of the first 9 periods of monitoring , vertical angle error , 2C value average , vertical index difference mean ; The average of 2C values , vertical index difference mean The 2C value deviation of the previous 9 periods is obtained by calculating the difference between the 2C mean and the vertical index difference mean of the i-period data. , vertical index difference deviation .
[0142] The weights of the coordinate deformation values in the three directions of X, Y, and Z are calculated according to the following formula:
[0143] ;
[0144] ;
[0145] Among them, A is the difference between the first weight calculation period and the i-th period, A=300-291=9.
[0146] Then the monitoring results are subjected to the following weighted fusion processing in the time dimension to obtain the processing results of the monitoring points:
[0147] ;
[0148] Perform weighted fusion processing of the time dimension on all monitoring points in turn.
[0149] Taking monitoring point 02Y23P311 No. 1 on section 31 as an example, data fusion processing in the time and space dimensions is then performed. Figure 2 A schematic diagram of monitoring longitudinal section points provided by an embodiment of the present invention, such as Figure 3 As shown, first determine the points 02Y23P291, 02Y23P301, 02Y23P321, 02Y23P331, i.e., the four No. 1 points on sections 29, 30, 32, and 33 as neighboring points on the same longitudinal section, and record them as b1, b2, b3, and b4 respectively.
[0150] Figure 3 A schematic diagram of monitoring cross-section points provided by an embodiment of the present invention, such as Figure 4 As shown, points 02Y23P312, 02Y23P313, 02Y23P314, 02Y23P315, i.e. the other four points on section 31, are neighboring points on the same cross section, denoted as b5, b6, b7, b8 respectively. The distances between the neighboring points on the same longitudinal section and 02Y23P311 are calculated respectively. , the distance between the neighboring point of the same cross section and the monitoring point 02Y23P311 .
[0151] The correlation coefficients of the historical monitoring data of each neighborhood point and the monitoring point 02Y23P311 are calculated in turn according to the following formula:
[0152] ;
[0153] Given the initial weight values of the neighborhood points in the longitudinal and cross-sectional views, the weights of the deformation values of each neighborhood point in different directions are determined by combining the distance between the neighborhood point and the monitoring point 02Y23P311 and the correlation coefficient of the historical monitoring data.
[0154] Finally, weighted fusion in the time and space dimensions is performed according to the following formula. The weight of the monitoring point 02Y23P311 is 1, and the final processing result is obtained.
[0155] .
[0156] The above specific embodiments further illustrate the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above are only specific embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A track monitoring data processing method based on three-dimensional structure, characterized in that: The method comprises the following steps: A plurality of monitoring points are set in the rail transit tunnel structure to be monitored, and a monitoring system is used to perform deformation monitoring on the monitoring points at a preset monitoring frequency during operation time; Acquiring historical monitoring data of the monitoring point during the monitoring process; Performing weighted fusion processing of the time dimension and weighted fusion processing of the space-time dimension on the historical monitoring data; The weighted fusion processing of the time dimension is performed on the historical monitoring data, wherein the time dimension is divided into one period according to a preset time point, and multiple time dimensions are multiple periods, including the following steps: Obtain the corresponding coordinate values of at least one monitoring point in multiple periods, and calculate the coordinate deformation values of multiple directions corresponding to the i-th period of the monitoring point according to the coordinate value of the first period and the coordinate value of the i-th period, where the first period is the first time point and i is a positive integer; Obtain the angle monitoring values corresponding to the monitoring point in multiple periods, obtain the angle monitoring values of multiple rounds for each period, and calculate the field observation value corresponding to the period based on the angle monitoring values of the multiple rounds; The first weight value is calculated based on the difference of multiple period field observation values; The time dimension weighted fusion result corresponding to the monitoring point is calculated based on the coordinate deformation value of the monitoring point in the previous N periods and the first weight value, where N is a positive integer; The weighted fusion processing of the historical monitoring data in the time and space dimensions includes the following steps: According to the monitoring point layout map and the monitoring point numbering rules, multiple neighborhood points corresponding to the monitoring point are found, wherein the multiple neighborhood points include longitudinal neighborhood points and transverse neighborhood points, and the type and number of each neighborhood point are extracted according to the number of the monitoring point, and the relative position relationship between each neighborhood point and the monitoring point is obtained, and finally multiple relative position relationships are obtained; Obtain the historical monitoring data corresponding to the monitoring point and each neighboring point, and calculate the correlation coefficient of the historical monitoring data corresponding to the neighboring point based on the historical monitoring data of the monitoring point and the historical monitoring data of a certain neighboring point, and finally obtain multiple historical monitoring data correlation coefficients; Calculating a second weight according to the plurality of relative position relationships and the plurality of correlation coefficients of the historical monitoring data; Obtain the time dimension weighted fusion result of each neighborhood point in the same time dimension as the monitoring point; The weighted fusion result of the spatiotemporal dimension corresponding to the monitoring point is calculated according to the weighted fusion result of the time dimension corresponding to the monitoring point and its multiple neighboring points and the second weight; The total station is used to perform multiple rounds of edge and angle measurement, and the first period coordinate value and the i-th period coordinate value of the monitoring point are calculated; use Identifies the i-th period coordinate value of the monitoring point, The first period coordinate value of the monitoring point is identified, and the coordinate deformation value corresponding to the i-th period of the monitoring point is calculated according to the first period coordinate value and the i-th period coordinate value. The expression is as follows: , in It represents the coordinate deformation values of the monitoring point in the X, Y and Z directions at the i-th period.
2. A track monitoring data processing method based on three-dimensional structure according to claim 1, characterized in that: The multiple monitoring points are distributed in multiple monitoring sections of the rail transit tunnel structure to be monitored, and are at least located at the tunnel top, the side walls on both sides of the tunnel, and the tunnel bottom of the monitoring sections.
3. The method for processing track monitoring data based on three-dimensional structure according to claim 1, characterized in that: The angle monitoring value includes the horizontal angle monitoring value of the left side of the plate , horizontal angle monitoring value on the right side of the plane , Left plate vertical angle monitoring value , plane right vertical angle monitoring value ; The field observation values include 2C value deviation, horizontal angle mean error value, vertical plate index difference deviation, and vertical angle mean error value; The 2C value is calculated from the horizontal angle monitoring value of the historical monitoring data, and the expression is: ; The 2C value deviation is the difference between the mean 2C value of the i-th period and the mean 2C value of the previous N periods, denoted as ; The horizontal angle is the projection of the angle between the monitoring point and the starting reference point on the horizontal plane. The horizontal angle of each period is calculated by the horizontal angle monitoring value of each measurement round. The expression is: in, is the horizontal angle of the monitoring point at the i-th period and the j-th measurement, is the average value of the horizontal angle monitoring value on the left side of the disk and the horizontal angle monitoring value on the right side of the disk during the i-th period and the j-th measurement of the monitoring point, is the average value of the horizontal angle monitoring value on the left side of the disk and the horizontal angle monitoring value on the right side of the disk during the i-th period and the j-th measurement of the starting reference point, where j is a positive integer; The mean error value of the horizontal angle is the mean error value calculated from the horizontal angles of the j measured rounds obtained in each monitoring period, denoted as ; The vertical index difference is calculated from the vertical angle monitoring value of the historical monitoring data, and the expression is: The vertical index difference deviation is the difference between the mean of the vertical index difference in the i-th period and the mean of the vertical index difference in the previous N periods, denoted as ; The vertical angle mean error value is the mean error value of the average value of the horizontal angle monitoring value on the left side of the disk and the horizontal angle monitoring value on the right side of the disk in each monitoring period, recorded as ; The expression of the first weight is: ; ; Where A is the difference between the first weighted start calculation period and the i-th period; are respectively the weight of the X-direction coordinate deformation value, the Y-direction coordinate deformation value, and the Z-direction coordinate deformation value of the monitoring point in the i-th period.
4. The method for processing track monitoring data based on three-dimensional structure according to claim 1, characterized in that: The time dimension weighted fusion result is obtained by prior judgment of the deformation trend of the rail transit tunnel structure, selecting the deformation value of the monitoring point N periods before and the deformation value of the i-th period for weighted fusion, and the calculation method is as follows: ; in They are respectively represented as the time dimension fusion processing results in the X direction, Y direction, and Z direction. is the weight of the X-direction coordinate deformation value of the monitoring point in the i-th period and its previous N periods; are the weights of the Y-direction coordinate deformation values of the monitoring point in the i-th period and its previous N periods respectively; are the weights of the Z-direction coordinate deformation values of the monitoring point in the i-th period and its previous N periods respectively; are the coordinate deformation values of the monitoring point in the i-th period and the previous N periods in the X direction; are the coordinate deformation values of the monitoring point in the i-th period and the N periods before it in the Y direction; They are the coordinate deformation values of the monitoring point in the i-th period and the previous N periods in the Z direction.
5. The method for processing track monitoring data based on three-dimensional structure according to claim 1, characterized in that: The monitoring point numbering rule is that the monitoring point numbering includes at least a section number and a monitoring point number, wherein the monitoring point number represents the position of the monitoring point on the section; According to the number of the monitoring point, the number of each neighboring point is extracted, including: Find out the section number and monitoring point number of the monitoring point by comparing the historical monitoring data with the monitoring point layout map; Add or subtract the ordinal number of the section number to obtain the number of the neighboring point of the same longitudinal section of the monitoring point; The fixed section number remains unchanged, and the monitoring point number is added or subtracted to obtain the number of the neighboring points in the same cross section of the monitoring point.
6. The method for processing track monitoring data based on three-dimensional structure according to claim 1, characterized in that: The relative position relationship between a monitoring point and the corresponding multiple neighboring points includes: the distance between the monitoring point and multiple neighboring points in the same cross section, and the distance between the monitoring point and multiple neighboring points in the same longitudinal section, expressed as: , in , Respectively represent the coordinate values of monitoring point a and neighborhood point b, Represents the distance between monitoring point a and neighboring point b; The correlation coefficient expression of the historical monitoring data of monitoring point a and neighboring point b is: in is the correlation coefficient of the historical monitoring data of the neighborhood point b and the monitoring point a in the X, Y, and Z directions respectively, are the coordinate deformation values of the monitoring point a in the X, Y, and Z directions at the i-th period, are the mean values of the historical coordinate deformation values of monitoring point a in the X, Y, and Z directions from the 1st to the Mth period, are the coordinate deformation values of the neighborhood point b in the X, Y, and Z directions in the i-th period, are the means of the historical coordinate deformation values of the neighborhood point b in the X, Y, and Z directions from the 1st to the Mth period, respectively, and M is a positive integer; The weight expression of the coordinate deformation value of the neighborhood point in the X, Y, and Z directions is: ; in is the initial weight value of the neighborhood point b, which is determined by the type of the neighborhood point; is the distance from the neighborhood point b to the monitoring point a, are the correlation coefficients of the historical monitoring data of the neighborhood point b and the monitoring point a in the X, Y, and Z directions respectively.
7. The method for processing track monitoring data based on three-dimensional structure according to claim 1, characterized in that: The expression of weighted fusion processing in the time and space dimensions is: ; in is the weighted fusion result of the spatiotemporal dimension of monitoring point a in the i-th period; , , PX is the weight of the coordinate deformation value of the monitoring point a in the X, Y, and Z directions; b1 , PX b2 , ...PX bm are the weights of the coordinate deformation values of the m neighboring points b in the X direction; are the weights of the coordinate deformation values of m neighboring points b in the Y direction; are the weights of the coordinate deformation values of the m neighboring points b in the Z direction; They are the time dimension weighted fusion results of the X-direction coordinate deformation values of m neighborhood points b in the i-th period; They are the time dimension weighted fusion results of the Y-direction coordinate deformation values of m neighborhood points b in the i-th period; They are the time dimension weighted fusion results of the deformation values of the coordinates of m neighborhood points b in the i-th period in the Z direction.
8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the three-dimensional structure-based track monitoring data processing method described in any one of claims 1 to 7.
9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the three-dimensional structure-based track monitoring data processing method according to any one of claims 1 to 7 when executed.
Citation Information
Patent Citations
Tunnel monitoring method and device for data fusion, computer equipment and storage medium
CN117272232A
Similar ensemble forecast optimization method and device, equipment and medium
CN118245822A
