Track deformation monitoring method and system based on total station

Abstract

The invention relates to the technical field of track deformation monitoring, and discloses a track deformation monitoring method and system based on a total station, and the method comprises the steps: obtaining the measurement data of a horizontal angle, a vertical angle, a distance and the like of a track observation point through the total station; temperature compensation is carried out on track deformation measurement data of the total station based on monitoring data of the temperature sensor, adjustment calculation of the track deformation measurement data is achieved through the total station controller, and the three-dimensional deformation quantity of an observation point is accurately obtained in real time. Error correction is carried out on the geometric parameter data of the track through a Kalman filtering algorithm and a machine learning algorithm to obtain more accurate track geometric parameters, so that the accuracy of a track deformation analysis result is improved, and the safety of track transportation is further ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of track deformation monitoring, and in particular to a track deformation monitoring method and system based on a total station. Background Art

[0002] The total station is a high-precision measuring instrument that integrates optical measurement and electronic measurement. It can measure parameters such as the horizontal angle, vertical angle and slope distance of the target point through an integrated electronic rangefinder, electronic goniometer and data processing system.

[0003] Due to the high precision and automated measurement capabilities of the total station, it has become an important tool for track deformation monitoring. Track deformation monitoring is an important part of ensuring the safe operation of railways and subway lines. Track deformation will directly affect the smooth operation of trains, and in severe cases may lead to safety accidents such as derailment. At present, in the process of track deformation analysis of the measurement data obtained by total station monitoring, coordinate measurement is usually used, and the background service system is required for secondary data processing and processing. Therefore, there are problems such as large data errors and poor real-time and accuracy when calculating and processing the total station measurement data. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a track deformation monitoring method and system based on a total station, so as to solve the problems of large data errors, poor real-time performance and accuracy in the current process of track deformation analysis and processing based on the measurement data obtained by total station monitoring.

[0005] The first aspect of the present invention discloses a track deformation monitoring method based on a total station, the method comprising the following steps:

[0006] Step S1, install the total station intelligent monitoring embedded control software on the client, create a new target project in the software interface, set up the server, establish a connection between the client and the total station controller, and perform access operations on the total station controller through the client;

[0007] Step S2: creating a track deformation monitoring task in the target project, and setting measurement task parameters based on the track deformation monitoring task;

[0008] Step S3, issuing a measurement instruction to the total station based on the measurement task parameters through the total station controller, and measuring the observation point according to the measurement instruction through the total station to obtain first measurement data;

[0009] Step S4, monitoring the temperature of the environment through a temperature sensor to obtain second measurement data;

[0010] Step S5, performing an acquisition operation and a data processing operation on the first measurement data and the second measurement data through a total station controller to obtain first processed data, and performing a three-dimensional adjustment calculation on the first processed data to obtain a three-dimensional deformation amount of the observation point;

[0011] Step S6, calculating the geometric parameters of the track according to the three-dimensional deformation variables of the observation points, and generating a track deformation analysis report in the client based on the geometric parameters of the track;

[0012] Among them, the geometric parameters of the track include track gauge, track height, track direction, triangular pits, and track deviation.

[0013] Furthermore, the measurement task parameter settings in step S2 include basic settings, tolerance settings, task plan settings, data processing settings, instrument temperature settings, observation point settings and station establishment settings; wherein the basic settings include TS serial number, station point name settings, measurement round number settings, whether to return to zero observation, measurement round observation mode, maximum number of single target observation attempts, maximum number of single task measurement attempts, and instrument connection method.

[0014] Furthermore, the first measurement data includes a horizontal angle, a vertical angle and a distance of an observation point, and the measurement method of the first measurement data is remote multi-round full-circle observation and monitoring; wherein the horizontal angle is the angle between the total station and the observation point in the horizontal direction, the vertical angle is the angle between the total station and the observation point in the vertical direction, and the distance is the slope distance and the horizontal distance from the instrument to the observation point.

[0015] Furthermore, the data processing operation in step S5 includes:

[0016] A linear regression algorithm is used to perform temperature compensation on the first measurement data based on the second measurement data to obtain first processed data.

[0017] Furthermore, in step S5, performing three-dimensional adjustment calculation on the first processed data to obtain the three-dimensional deformation amount of the observation point specifically includes:

[0018] Some observation points are taken as quasi-stable points, and the quasi-stable adjustment method is used to make preliminary adjustments to obtain the initial values ​​of the observation points;

[0019] After obtaining the initial value of the observation point, the three-dimensional deformation of the observation point is obtained by adjusting the calculation through the classical adjustment method.

[0020] Furthermore, before generating the track deformation analysis report in the client based on the track geometric parameters, the method further includes using a Kalman filter algorithm to perform optimization processing on the track geometric parameters, specifically including:

[0021] Predicted status;

[0022] Forecast error covariance;

[0023] Calculate measurement residuals;

[0024] Correction of measurement residuals;

[0025] Calculate Kalman gain;

[0026] Update the state estimate using the corrected measurement residual and the Kalman gain;

[0027] Update the error covariance matrix.

[0028] Furthermore, the training process of the machine learning model M includes:

[0029] Collect the orbital geometric parameters z obtained from actual measurements and calculations k , and forecast data in Specifically, the orbit geometry parameters obtained through the Kalman filter prediction step are calculated based on the measurement residual calculation formula. k As the eigenvector X, measure the residual v k as the target vector Y;

[0030] The machine learning model M is constructed by the random forest regression algorithm, and the machine learning model M is trained based on the feature vector X and the target vector Y to obtain M(v k ) correction value to predict the measurement residual v k Systematic errors in .

[0031] Furthermore, the generating of the track deformation analysis report in the client based on the track geometric parameters specifically includes:

[0032] Get the geometric parameters of the orbit of the current cycle and the previous cycle, calculate the difference in orbital geometric parameters between the current cycle and the previous cycle, get the deformation of each parameter, and get the orbit deformation analysis report based on the deformation analysis of each parameter; the orbit deformation analysis report includes the orbital geometric dimension deviation status, the orbital change this time, the orbital cumulative change, the orbital geometric dimension measured value, the orbital geometric correction number, the orbital initial value setting, and the orbital dimension change curve.

[0033] Furthermore, the number of newly created track deformation monitoring tasks is greater than or equal to one. When the number of newly created track deformation monitoring tasks is greater than one, each task corresponds to a total station, and a joint adjustment calculation is performed on the measurement data obtained by each total station.

[0034] The second aspect of the present invention discloses a track deformation monitoring system based on a total station, which is implemented based on the method disclosed in the first aspect, and includes a client, a total station, a total station controller, a temperature sensor, and a solar controller;

[0035] The client is used to install the total station intelligent monitoring embedded control software, allowing the user to create a new target project through the software interface, and perform server settings to establish a connection between the client and the total station controller; and create a new track deformation monitoring task in the target project through the software interface, and set measurement task parameters based on the track deformation monitoring task;

[0036] The total station controller is provided with a transmission unit for receiving measurement task parameters sent by the client, and issuing measurement instructions to the total station based on the measurement task parameters;

[0037] The total station is used to measure the observation point according to the measurement instruction to obtain first measurement data;

[0038] The temperature sensor is used to monitor the temperature of the environment to obtain second measurement data;

[0039] The transmission unit of the total station controller is also used to perform an acquisition operation on the first measurement data and the second measurement data. The total station controller is also provided with a data processing unit, which is used to perform a data processing operation on the first measurement data and the second measurement data to obtain first processed data, and perform a three-dimensional adjustment calculation on the first processed data to obtain a three-dimensional deformation amount of the observation point;

[0040] The client is also used to calculate the geometric parameters of the track according to the three-dimensional deformation variables of the observation points, and generate a track deformation analysis report in the client based on the geometric parameters of the track; wherein the geometric parameters of the track include track gauge, track height, track direction, triangular pits, and track positive and negative deviation;

[0041] The solar controller is used to perform power supply control on the total station, the total station controller and the temperature sensor.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] The present invention obtains measurement data such as the horizontal angle, vertical angle, distance, etc. of the track observation point through a total station, and sets a temperature sensor. Based on the monitoring data of the temperature sensor, temperature compensation is performed on the track deformation measurement data of the total station. The adjustment calculation of the track deformation measurement data is realized through the total station controller, and the three-dimensional deformation variable of the observation point is obtained in real time and accurately. The geometric parameter data of the track is corrected for errors through a Kalman filter algorithm and a machine learning algorithm to obtain more accurate track geometric parameters, thereby improving the accuracy of the track deformation analysis results and further ensuring the safety of track transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of the economic application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0045] Figure 1 A schematic flow chart of a track deformation monitoring method based on a total station disclosed in an embodiment of the present invention;

[0046] Figure 2 The present invention is a schematic structural diagram of a track deformation monitoring system based on a total station disclosed in yet another embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments.

[0048] Embodiment 1

[0049] The first aspect of the present invention discloses a track deformation monitoring method based on a total station. Figure 1 , Figure 1 1 is a flow chart of a track deformation monitoring method based on a total station disclosed in an embodiment of the present invention, the method comprising the following steps:

[0050] Step S1, install the total station intelligent monitoring embedded control software on the client, create a new target project in the software interface, set up the server, establish a connection between the client and the total station controller, and perform access operations on the total station controller through the client;

[0051] Step S2: creating a track deformation monitoring task in the target project, and setting measurement task parameters based on the track deformation monitoring task;

[0052] Step S3, issuing a measurement instruction to the total station based on the measurement task parameters through the total station controller, and measuring the observation point according to the measurement instruction through the total station to obtain first measurement data;

[0053] Step S4, monitoring the temperature of the environment through a temperature sensor to obtain second measurement data;

[0054] Step S5, performing an acquisition operation and a data processing operation on the first measurement data and the second measurement data through a total station controller to obtain first processed data, and performing a three-dimensional adjustment calculation on the first processed data to obtain a three-dimensional deformation amount of the observation point;

[0055] Step S6: Calculate the geometric parameters of the track according to the three-dimensional deformation variables of the observation points, and generate a track deformation analysis report in the client based on the geometric parameters of the track.

[0056] Among them, the geometric parameters of the track include track gauge, track height, track direction, triangular pits, and track deviation.

[0057] Specifically, in an embodiment of the present invention, there is no limit on the number of newly created projects, nor is there a limit on the number of newly created tasks in the project. The total station is connected to the total station controller by wire, including connection via a USB cable and a serial port cable; the total station controller is also connected to the temperature sensor by wire, and the total station and the temperature sensor transmit the measured first measurement data and the second measurement data to the total station controller. Among them, the first measurement data includes the horizontal angle, vertical angle and distance of the observation point, the horizontal angle is the angle between the total station and the observation point in the horizontal direction, the vertical angle is the angle between the total station and the observation point in the vertical direction, and the distance is the slant distance and horizontal distance from the instrument to the observation point. The second measurement data is the temperature data of the track environment.

[0058] The measurement method of the first measurement data is remote multi-round full-circle observation monitoring. Multi-round refers to the measurement of the same observation point for multiple times. Full-circle observation refers to measuring the same observation point from different azimuth angles to ensure that the measurement covers a full circle range of 360 degrees. In the embodiment of the present invention, the round observation mode includes four modes: reading only the left disk in each direction, reading the left disk and the right disk in each direction before turning to the next observation point, measuring the left disk in sequence from point 1 to point n, and then reading the right disk in sequence, and reading the left disk in sequence from point 1 to point n, and then reading the right disk in sequence from point n to point 1. The embodiment of the present invention does not specifically limit the round observation mode.

[0059] In addition, the total station controller is provided with a transmission unit, which includes but is not limited to being realized by setting a SIM card slot and a wired network port. When creating a new target project, it is necessary to configure the total station controller as a server. Each total station controller is provided with a unique service address. By entering the service address, port number, user name and password of the total station controller, it is suggested that the client connect to the total station controller.

[0060] In the embodiment of the present invention, each target project is provided with a point set, the point set includes known points and unknown points, and the observation results are presented based on three-dimensional coordinates, wherein the three-dimensional coordinates include north coordinate X, east coordinate Y, and elevation H. The current coordinates are automatically updated after each task is completed, and the coordinates can also be set manually. When updating the initial value of the coordinates, the quasi-stable adjustment method is used, two or more measurement results are selected, and the current measurement value is updated through post-processing adjustment, and then the initial value is updated. In addition, the adjustment report needs to be browsed before updating the initial value to prevent gross errors in individual observation points.

[0061] Furthermore, the measurement task parameter settings in step S2 include but are not limited to basic settings, tolerance settings, task plan settings, data processing settings, instrument temperature settings, observation point settings and station establishment settings; wherein the basic settings include but are not limited to TS serial number, station point name settings, measurement round number settings, whether to return to zero observation, measurement round observation mode, maximum number of single target observation attempts, maximum number of single task measurement attempts, and instrument connection method.

[0062] Among them, the observation point setting includes equipment control. Specifically, the equipment control includes: connecting and disconnecting the total station and the total station controller; turning on the total station laser pointer; making the total station measure and aim at the target, and measure and obtain the horizontal angle, zenith distance, slant distance and horizontal distance; inputting the horizontal angle and zenith distance of the known target, and turning the total station eyepiece to this position; locking the prism center with one click after aiming at the target; displaying the horizontal angle, vertical angle, slant distance and horizontal distance of the measured target.

[0063] In an embodiment of the present invention, the learning process of the observation point includes selecting the point to be learned in the "selected observation points" and aiming at the target, "setting the target" to lock the prism center, selecting the appropriate "prism target type", "measuring", waiting for the measurement result, "reading" and finally "saving the configuration to the total station controller"; repeating the operation until all selected observation points have been learned and "saved the configuration to the total station controller".

[0064] Specifically, the station establishment setting includes selecting "Selected station establishment points" from the point set. When the coordinates of all candidate observation points are known, the measurement points selected in "Selected station establishment points" will be measured twice on the left and right sides of the face. After all four data are measured successfully, click "Complete station establishment" and back-calculate based on the existing coordinates to back-calculate the horizontal and vertical angles of all selected observation points.

[0065] Furthermore, the data processing operation in step S5 includes:

[0066] A linear regression algorithm is used to perform temperature compensation on the first measurement data based on the second measurement data to obtain first processed data.

[0067] Specifically, the measurement data of horizontal angle, vertical angle and distance at different temperatures in the past period of time, as well as the corresponding temperature data, are collected. Using these historical data, a linear regression model is trained to obtain a linear relationship between temperature and measurement data. The current measurement data is temperature compensated through the trained linear regression model, and the current temperature data is input into the trained linear regression model to predict the impact of temperature on each measurement data. According to the prediction results of the model, the amount of compensation required for each measurement data is calculated, and the calculated compensation amount is applied to the current measurement data to obtain the measurement data after temperature compensation.

[0068] Through the above steps, the compensated first measurement data, that is, the first processed data, can be obtained, including the horizontal angle, vertical angle and distance after temperature compensation, so as to reduce the influence of temperature change on the measurement result and ensure the accuracy and reliability of the measurement data.

[0069] Furthermore, in step S5, the three-dimensional adjustment calculation is performed on the first processed data to obtain the three-dimensional deformation amount of the observation point, which specifically includes:

[0070] Some observation points are taken as quasi-stable points, and the quasi-stable adjustment method is used to make preliminary adjustments to obtain the initial values ​​of the observation points;

[0071] After obtaining the initial value of the observation point, the three-dimensional deformation of the observation point is obtained by adjusting the calculation through the classical adjustment method.

[0072] Specifically, for example, assume that there are n observation points, among which m points are selected as quasi-stable points. For each quasi-stable point, the minimum weighted error in the adjustment process is calculated, and the preliminary adjustment results of the quasi-stable points are used to calculate the preliminary positions of other observation points. After obtaining the initial values ​​of the observation points, further optimization and adjustment are performed through the classical adjustment method to obtain accurate three-dimensional deformation. The classical adjustment uses the measurement data of all observation points for global optimization to ensure the accuracy of the results.

[0073] Furthermore, before generating the track deformation analysis report in the client based on the track geometric parameters, the Kalman filter algorithm is used to perform optimization processing on the track geometric parameters, specifically including:

[0074] Prediction status:

[0075]

[0076] in, is the predicted state vector of orbital geometry parameters at time k, A is the state transfer matrix, is the state estimation vector at time k-1;

[0077] Forecast error covariance:

[0078] P k|k-1 =AP k-1|k-1 A T +Q

[0079] Among them, P k|k-1 is the prediction error covariance matrix at time k, Q is the process noise covariance matrix, P k-1|k-1 is the error covariance matrix at time k-1;

[0080] Calculate the measurement residuals:

[0081]

[0082] Among them, v k is the measurement residual at time k, z k is the orbital geometric parameter actually measured and calculated at time k, and H is the measurement matrix;

[0083] Correction of measurement residuals:

[0084]

[0085] in, is the corrected measurement residual, M(v k ) is the error correction value predicted by the machine learning model;

[0086] Calculate the Kalman gain:

[0087] K k =P k|k-1 H T (HP k|k-1 H T +R) -1

[0088] Among them, K k is the Kalman gain at time k, R is the measurement noise covariance matrix;

[0089] Update the state estimate using the corrected measurement residuals and the Kalman gain:

[0090]

[0091] in, is the state estimation vector at time k;

[0092] Update the error covariance matrix:

[0093] P k|k =(IK k H)P k|k-1

[0094] Among them, P k|k is the error covariance matrix at time k, and I is the identity matrix.

[0095] Furthermore, the training process of the machine learning model M includes:

[0096] Collect the orbital geometric parameters z obtained from actual measurements and calculations k , and forecast data in Specifically, the orbit geometry parameters obtained through the Kalman filter prediction step are calculated based on the measurement residual calculation formula. k As the eigenvector X, measure the residual v k as the target vector Y;

[0097] The machine learning model M is constructed by the random forest regression algorithm, and the machine learning model M is trained based on the feature vector X and the target vector Y to obtain M(v k ) correction value to predict the measurement residual v k Systematic errors in .

[0098] Furthermore, the track deformation analysis report generated in the client based on the track geometric parameters specifically includes:

[0099] The geometric parameters of the orbits of the current cycle and the previous cycle are obtained, the differences in the geometric parameters of the orbits between the current cycle and the previous cycle are calculated, the deformation of each parameter is obtained, and the orbit deformation analysis report is obtained based on the deformation analysis of each parameter.

[0100] Among them, the track deformation analysis report includes adjustment results and task results. The adjustment results are the relevant output data after adjustment and the deformation report (initial value, current measurement value, current change, cumulative change); the task results are all measurement results within the selected time range, including the original observation files used for data analysis and post-processing adjustments.

[0101] The deformation report may include the track geometry deviation status, the track change this time, the track cumulative change, the track geometry measured value, the track geometry correction number, the track initial value setting, and the track dimension change curve.

[0102] Furthermore, as a preferred implementation mode of Example 1 of the present invention, an early warning function is also provided, and a deviation status early warning value, a current early warning value and a cumulative early warning value are set. If the monitoring value exceeds the limit, an early warning is generated. The early warning levels are divided into primary early warning, intermediate early warning and advanced early warning.

[0103] Furthermore, when the number of newly created track deformation monitoring tasks is greater than one, each task corresponds to a total station, and the measurement data obtained by each total station is jointly adjusted. Joint adjustment means that the observation data of multiple tasks are adjusted according to relevant settings, which mainly solves the problem that there is no backsight point in some tasks on long lines.

[0104] Embodiment 2

[0105] The second aspect of the present invention discloses a track deformation monitoring system based on a total station, see Figure 2 , Figure 2 It is a structural schematic diagram of a track deformation monitoring system based on a total station disclosed in another embodiment of the present invention, the system includes a client, a total station, a total station controller, a temperature sensor, and a solar controller;

[0106] The client is used to install the total station intelligent monitoring embedded control software, allowing users to create a new target project through the software interface, perform server settings, and establish a connection between the client and the total station controller; and create a new track deformation monitoring task in the target project through the software interface, and set measurement task parameters based on the track deformation monitoring task;

[0107] The total station controller is provided with a transmission unit for receiving the measurement task parameters sent by the client, and sending measurement instructions to the total station based on the measurement task parameters;

[0108] The total station is used to measure the observation point according to the measurement instruction to obtain the first measurement data;

[0109] The temperature sensor is used to monitor the temperature of the environment and obtain second measurement data;

[0110] The transmission unit of the total station controller is also used to perform an acquisition operation on the first measurement data and the second measurement data. The total station controller is also provided with a data processing unit, which is used to perform a data processing operation on the first measurement data and the second measurement data to obtain first processed data, and perform a three-dimensional adjustment calculation on the first processed data to obtain a three-dimensional deformation amount of the observation point;

[0111] The client is also used to calculate the geometric parameters of the track according to the three-dimensional deformation variables of the observation points, and generate a track deformation analysis report in the client based on the geometric parameters of the track; among which, the geometric parameters of the track include track gauge, track height, track direction, triangular pits, and track positive and negative deviations.

[0112] The solar controller is used to control the power supply of the total station, the total station controller and the temperature sensor.

[0113] Furthermore, the measurement task parameter settings include basic settings, tolerance settings, task plan settings, data processing settings, instrument temperature settings, observation point settings and station establishment settings; among them, the basic settings include TS serial number, station point name settings, measurement round number settings, whether to return to zero observation, measurement round observation mode, maximum number of single target observation attempts, maximum number of single task measurement attempts, and instrument connection method.

[0114] Furthermore, the first measurement data includes the horizontal angle, vertical angle and distance of the observation point, and the measurement method of the first measurement data is remote multi-round full-circle observation and monitoring; wherein, the horizontal angle is the angle between the total station and the observation point in the horizontal direction, the vertical angle is the angle between the total station and the observation point in the vertical direction, and the distance is the slope distance and horizontal distance from the instrument to the observation point.

[0115] Furthermore, the data processing operations include:

[0116] A linear regression algorithm is used to perform temperature compensation on the first measurement data based on the second measurement data to obtain first processed data.

[0117] Furthermore, the three-dimensional adjustment calculation is performed on the first processed data to obtain the three-dimensional deformation variables of the observation points, which specifically include:

[0118] Some observation points are taken as quasi-stable points, and the quasi-stable adjustment method is used to make preliminary adjustments to obtain the initial values ​​of the observation points;

[0119] After obtaining the initial value of the observation point, the three-dimensional deformation of the observation point is obtained by adjusting the calculation through the classical adjustment method.

[0120] Furthermore, before generating the track deformation analysis report in the client based on the track geometric parameters, the Kalman filter algorithm is used to perform optimization processing on the track geometric parameters, specifically including:

[0121] Prediction status:

[0122]

[0123] in, is the predicted state vector of orbital geometry parameters at time k, A is the state transfer matrix, is the state estimation vector at time k-1;

[0124] Forecast error covariance:

[0125] P k|k-1 =AP k-1|k-1 A T +Q

[0126] Among them, P k|k-1 is the prediction error covariance matrix at time k, Q is the process noise covariance matrix, P k-1|k-1 is the error covariance matrix at time k-1;

[0127] Calculate the measurement residuals:

[0128]

[0129] Among them, v k is the measurement residual at time k, z k is the orbital geometric parameter actually measured and calculated at time k, and H is the measurement matrix;

[0130] Correction of measurement residuals:

[0131]

[0132] in, is the corrected measurement residual, M(v k) is the error correction value predicted by the machine learning model;

[0133] Calculate the Kalman gain:

[0134] K k =P k|k-1 H T (HP k|k-1 H T +R) -1

[0135] Among them, K k is the Kalman gain at time k, R is the measurement noise covariance matrix;

[0136] Update the state estimate using the corrected measurement residuals and the Kalman gain:

[0137]

[0138] in, is the state estimation vector at time k;

[0139] Update the error covariance matrix:

[0140] P k|k =(IK k H)P k|k-1

[0141] Among them, P k|k is the error covariance matrix at time k, and I is the identity matrix.

[0142] Furthermore, the training process of the machine learning model M includes:

[0143] Collect the orbital geometric parameters z obtained from actual measurements and calculations k , and forecast data in

[0144] is the orbit geometry parameter obtained by the Kalman filter prediction step. Based on the measurement residual calculation formula, z k As the eigenvector X, measure the residual v k as the target vector Y;

[0145] The machine learning model M is constructed by the random forest regression algorithm, and the machine learning model M is trained based on the feature vector X and the target vector Y to obtain M(v k ) correction value to predict the measurement residual v k Systematic errors in .

[0146] Furthermore, the track deformation analysis report generated in the client based on the track geometric parameters specifically includes:

[0147] Get the geometric parameters of the orbit of the current cycle and the previous cycle, calculate the difference in orbital geometric parameters between the current cycle and the previous cycle, get the deformation of each parameter, and get the orbit deformation analysis report based on the deformation analysis of each parameter; the orbit deformation analysis report includes the orbital geometric dimension deviation status, the orbital change this time, the orbital cumulative change, the orbital geometric dimension measured value, the orbital geometric correction number, the orbital initial value setting, and the orbital dimension change curve.

[0148] Furthermore, the number of newly created track deformation monitoring tasks is greater than or equal to one. When the number of newly created track deformation monitoring tasks is greater than one, each task corresponds to a total station. All total stations except the total station directly connected to the total station controller are equipped with a TCU, and the observed data is transmitted to the total station controller through the TCU; and the measurement data monitored by each total station are jointly adjusted.

[0149] It should be noted that the specific implementation process of the second embodiment is similar to that of the first embodiment and will not be repeated in the second embodiment.

[0150] Finally, it should be noted that the track deformation monitoring method and system based on the total station disclosed in the embodiment of the present invention only discloses the preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A track deformation monitoring method based on a total station, characterized in that: The method comprises the following steps: Step S1, install the total station intelligent monitoring embedded control software on the client, create a new target project in the software interface, set up the server, establish a connection between the client and the total station controller, and perform access operations on the total station controller through the client; Step S2: creating a track deformation monitoring task in the target project, and setting measurement task parameters based on the track deformation monitoring task; Step S3, issuing a measurement instruction to the total station based on the measurement task parameters through the total station controller, and measuring the observation point through the total station according to the measurement instruction to obtain first measurement data; Step S4, monitoring the temperature of the environment through a temperature sensor to obtain second measurement data; Step S5, performing an acquisition operation and a data processing operation on the first measurement data and the second measurement data through a total station controller to obtain first processed data, and performing a three-dimensional adjustment calculation on the first processed data to obtain a three-dimensional deformation amount of the observation point; Step S6, calculating the geometric parameters of the track according to the three-dimensional deformation variables of the observation points, and generating a track deformation analysis report in the client based on the geometric parameters of the track; Among them, the geometric parameters of the track include track gauge, track height, track direction, triangular pits, and track deviation.

2. The track deformation monitoring method based on total station according to claim 1, characterized in that: The measurement task parameter settings in step S2 include basic settings, tolerance settings, task plan settings, data processing settings, instrument temperature settings, observation point settings and station establishment settings; wherein the basic settings include TS sequence number, station point name settings, measurement round number settings, whether to return to zero observation, measurement round observation mode, maximum number of single target observation attempts, maximum number of single task measurement attempts, and instrument connection method.

3. The track deformation monitoring method based on total station according to claim 1, characterized in that: The first measurement data includes the horizontal angle, vertical angle and distance of the observation point, and the measurement method of the first measurement data is remote multi-round full-circle observation and monitoring; wherein the horizontal angle is the angle between the total station and the observation point in the horizontal direction, the vertical angle is the angle between the total station and the observation point in the vertical direction, and the distance is the slope distance and horizontal distance from the instrument to the observation point.

4. The track deformation monitoring method based on total station according to claim 3 is characterized in that: The data processing operation in step S5 includes: A linear regression algorithm is used to perform temperature compensation on the first measurement data based on the second measurement data to obtain first processed data.

5. The track deformation monitoring method based on total station according to claim 4, characterized in that: In step S5, the three-dimensional adjustment calculation is performed on the first processed data to obtain the three-dimensional deformation amount of the observation point, which specifically includes: Some observation points are taken as quasi-stable points, and the quasi-stable adjustment method is used for preliminary adjustment to obtain the initial values ​​of the observation points; After obtaining the initial value of the observation point, the three-dimensional deformation of the observation point is obtained by adjusting the calculation through the classical adjustment method.

6. The track deformation monitoring method based on total station according to claim 5, characterized in that: Before generating a track deformation analysis report in the client based on the track's geometric parameters, the method further includes performing optimization processing on the track's geometric parameters using a Kalman filter algorithm, specifically including: Prediction status; Forecast error covariance; Calculate measurement residuals; Correction of measurement residuals; Calculate Kalman gain; Update the state estimate using the corrected measurement residual and the Kalman gain; Update the error covariance matrix.

7. The track deformation monitoring method based on total station according to claim 6, characterized in that: The training process of the machine learning model M includes: Collect the orbital geometric parameters z obtained from actual measurements and calculations k , and forecast data in Specifically, the orbit geometry parameters obtained through the Kalman filter prediction step are calculated based on the measurement residual calculation formula. k As the eigenvector X, measure the residual v k as the target vector Y; The machine learning model M is constructed by the random forest regression algorithm, and the machine learning model M is trained based on the feature vector X and the target vector Y to obtain M(v k ) correction value to predict the measurement residual v k Systematic errors in .

8. The track deformation monitoring method based on total station according to claim 7, characterized in that: Generating a track deformation analysis report in the client based on the track geometric parameters specifically includes: Get the geometric parameters of the orbit of the current cycle and the previous cycle, calculate the difference in orbital geometric parameters between the current cycle and the previous cycle, get the deformation of each parameter, and get the orbit deformation analysis report based on the deformation analysis of each parameter; the orbit deformation analysis report includes the orbital geometric dimension deviation status, the orbital change this time, the orbital cumulative change, the orbital geometric dimension measured value, the orbital geometric correction number, the orbital initial value setting, and the orbital dimension change curve.

9. The track deformation monitoring method based on total station according to claim 8, characterized in that: The number of newly established track deformation monitoring tasks is greater than or equal to one. When the number of newly established track deformation monitoring tasks is greater than one, each task corresponds to a total station, and a joint adjustment calculation is performed on the measurement data obtained by each total station.

10. A track deformation monitoring system based on a total station, the system being implemented based on the method according to any one of claims 1 to 9, characterized in that: The system includes a client, a total station, a total station controller, a temperature sensor, and a solar controller; The client is used to install the total station intelligent monitoring embedded control software, allowing the user to create a new target project through the software interface, and perform server settings to establish a connection between the client and the total station controller; and create a new track deformation monitoring task in the target project through the software interface, and set measurement task parameters based on the track deformation monitoring task; The total station controller is provided with a transmission unit for receiving measurement task parameters sent by the client, and issuing measurement instructions to the total station based on the measurement task parameters; The total station is used to measure the observation point according to the measurement instruction to obtain first measurement data; The temperature sensor is used to monitor the temperature of the environment to obtain second measurement data; The transmission unit of the total station controller is also used to perform an acquisition operation on the first measurement data and the second measurement data. The total station controller is also provided with a data processing unit, which is used to perform a data processing operation on the first measurement data and the second measurement data to obtain first processed data, and perform a three-dimensional adjustment calculation on the first processed data to obtain a three-dimensional deformation amount of the observation point; The client is also used to calculate the geometric parameters of the track according to the three-dimensional deformation variables of the observation points, and generate a track deformation analysis report in the client based on the geometric parameters of the track; wherein the geometric parameters of the track include track gauge, track height, track direction, triangular pits, and track positive and negative deviation; The solar controller is used to perform power supply control on the total station, the total station controller and the temperature sensor.

Images