A shield machine pose measurement system and measurement method

Abstract

The present invention relates to the technical field of tunnel construction. Specifically, it relates to a shield machine pose measurement system and a measurement method, including a shield machine data acquisition module, a pose parameter acquisition module, a pose deviation analysis module, a corrected pose parameter acquisition module, a pose instruction generation module, and a management database. In this system, by inputting three-dimensional point cloud data into a pose fusion model, initial pose parameters are obtained. By defining the range where the shield machine is located in the three-dimensional geological model and screening the points related to each axis for matching, the pose deviation parameters of the shield machine are evaluated by calculating the position deviation and the attitude deviation. By inputting the initial pose parameters and the pose deviation parameters into an adaptive filtering algorithm for iterative optimization, corrected pose parameters are obtained, and it is determined whether the corrected pose parameters exceed the dynamic threshold range, so as to timely generate pose adjustment instructions and prevent construction problems caused by excessive pose deviation.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel construction, and more specifically, to a shield machine pose measurement system and a measurement method. Background Art

[0002] In modern tunnel engineering construction, the shield tunneling method has become the mainstream construction method due to its advantages such as high efficiency, safety, and little impact on the surrounding environment. The shield machine operates in a complex underground environment, and the accurate measurement of its pose plays a decisive role in ensuring that the tunnel is accurately pushed forward along the designed route, guaranteeing construction quality and safety. Accurately mastering the position and attitude of the shield machine can effectively avoid tunnel deviation, reduce construction risks, and improve the overall efficiency of the project, which is a key technical link in the tunnel construction process.

[0003] Currently, although there are various technologies for measuring the pose of shield machines, they all have certain limitations. For example, the Chinese patent with the application number 202010649631.1 discloses an anti-vibration laser target, a shield machine pose measurement system and a measurement method. This solution collects the first angle data of the shield machine by an angle acquisition unit at a frequency greater than or equal to a first preset frequency, filters the first angle data based on a filtering algorithm to generate second angle data, and determines the pose of the shield machine based on the second angle data and the total station data collected by the total station, which can reduce the influence of the vibration of the shield machine during the pose measurement process on the measurement result and improve the measurement accuracy of the shield machine pose.

[0004] However, there are the following problems in the above patent: This solution directly measures three horizontal parameters of the shield machine through a total station, and determines the roll angle and pitch angle based on the second angle data and then determines the azimuth angle. This method relies on the reliability of angle and simple coordinate measurements. At the same time, when determining the roll angle and pitch angle, based on the angle relationship between the axis of the angle sensor coordinate system and the reference plane, it assumes the stability of the reference plane and the absolute accuracy of the sensor installation, which may lead to deviations in the determination of pose parameters in actual measurement.

[0005] For example, the Chinese patent with the application number 202211579395.6 discloses a shield tunneling attitude measurement method and system. This solution is based on a shield tunneling attitude measurement method that combines a gyroscope and an inclinometer. According to the high-precision data of the inclinometer, when the shield machine is operating stably, the offset angular rate of the gyroscope is accurately estimated and compensated in real time to improve the working accuracy of the gyroscope. When the inclinometer is subjected to severe vibration, the compensated gyroscope angle and the inclinometer data are fused to obtain the real-time attitude angle information of the shield machine.

[0006] However, there are the following problems in the above patents: This solution mainly relies on the data collected by gyroscopes and inclinometers. Measuring the attitude only from the information obtained by these two sensors cannot fully consider the complex spatial environment around the shield machine. There are deficiencies in the comprehensiveness and accuracy of obtaining the initial pose parameters, and the accuracy and reliability of pose determination are relatively low. At the same time, geological environment factors are not incorporated into the pose evaluation system. Under complex geological conditions, it may not be possible to accurately evaluate the true pose deviation of the shield machine, and the accuracy of the evaluation results is limited. Summary of the Invention

[0007] To overcome the shortcomings in the background technology, the embodiments of the present invention provide a shield machine pose measurement system and a measurement method, which can effectively solve the problems involved in the above background technology.

[0008] The object of the present invention can be achieved through the following technical solutions: The present invention provides a shield machine pose measurement system, including: a shield machine data acquisition module, configured to acquire three-dimensional point cloud data during the tunneling process of the shield machine, and the three-dimensional point cloud data includes the real-time three-dimensional coordinates of the shield machine and three-dimensional geological point cloud data.

[0009] A pose parameter acquisition module, configured to preprocess the three-dimensional point cloud data and input it into a pose fusion model to obtain initial pose parameters.

[0010] A pose deviation analysis module, configured to define the range where the shield machine is located in the three-dimensional geological model and screen the relevant points of each axis for matching, and evaluate the pose deviation parameters of the shield machine by calculating the position deviation and the attitude deviation.

[0011] A corrected pose parameter acquisition module, configured to iteratively optimize the initial pose parameters and the pose deviation parameters to obtain corrected pose parameters.

[0012] A pose instruction generation module, configured to determine whether the corrected pose parameters exceed the dynamic threshold range. If they exceed, a pose adjustment instruction is generated; otherwise, a trend analysis is performed on them together with the historical data, and a real-time pose warning message is output.

[0013] A management database, configured to store the three-dimensional point cloud data, initial pose parameters, pose deviation parameters, corrected pose parameters, and historical data of the shield machine body of the shield machine.

[0014] Preferably, the specific analysis method for preprocessing the three-dimensional point cloud data is: Collect the three-dimensional point cloud data of the shield machine according to the sampling frequency set by the corresponding sensor and record the corresponding timestamp information, and adjust the three-dimensional point cloud data of the shield machine to the same time point.

[0015] Preferably, the specific analysis method of the pose parameter acquisition module is as follows: Select the Kalman filter model as the pose fusion model, input the three-dimensional point cloud data of the shield machine to obtain the state estimation value of the shield machine, set the iteration termination condition of the Kalman filter model as the change amount of the pose parameter being less than the preset threshold, and enter iterative calculation according to the three-dimensional point cloud data of the shield machine and each state estimation value. After the iterative calculation is completed, extract the three-dimensional position coordinates and attitude angle information of the shield machine from the state estimation value finally output by the model as the initial pose parameter.

[0016] Preferably, the specific analysis method of constructing the three-dimensional geological model is as follows: Obtain the three-dimensional geological point cloud data of the shield machine, cluster the point cloud data belonging to the same tunnel area according to the regional division information of the surrounding tunnels, and extract the point cloud data corresponding to each cluster.

[0017] Fit each geometric surface according to the point cloud data corresponding to each cluster and combine them to obtain a complete three-dimensional geological model.

[0018] Preferably, the specific analysis method of the points related to each axis is as follows: Obtain the front-end point coordinates, rear-end point coordinates of the shield machine and the radius range of the shield machine from the real-time three-dimensional coordinates of the shield machine, and construct a cylinder with the axis of the shield machine as the center and in combination with the radius of the shield machine to define the range where the shield machine is located in the three-dimensional geological model.

[0019] Along the tunneling direction of the shield machine, divide the shield machine within the said range according to the equal-spacing principle to obtain each cross-section, and each cross-section is perpendicular to the tunneling direction of the shield machine.

[0020] For each cross-section, extract the points located within the cross-section from the three-dimensional geological point cloud data, and calculate their distances to the center of the cross-section respectively, where the center of the cross-section is the projection point of the designed axis of the shield machine on the cross-section.

[0021] Set a reasonable deviation value, sum it with the radius of the shield machine to determine the distance threshold, compare the distance of each point to the center of the cross-section with the said distance threshold, and screen out the points whose distances to the center of the cross-section are less than or equal to the distance threshold as the points related to each axis.

[0022] Perform linear fitting on the points related to each axis until the sum of the squares of the distances from the points related to each axis to the fitting line reaches the minimum, so as to determine the preliminary direction of the tunneling axis of the shield machine.

[0023] Preferably, the specific analysis method for the pose deviation parameter is as follows: Arbitrarily select two points on the tunneling axis, obtain the direction vector of the tunneling axis by calculating the vector difference formed by these two points, extract the relevant points of each axis on the tunneling axis of the shield machine, and at the same time obtain the points on the preset design axis. Find the point with the closest distance on the design axis for each relevant point of the axis, establish the corresponding relationship between the two, and form each pair of matching points.

[0024] Calculate the position differences of each pair of matching points in the three-dimensional space respectively, and obtain the position deviation by taking the average value. Calculate the included angle between the direction vectors of the design axis and the tunneling axis of the shield machine to obtain the attitude deviation.

[0025] Evaluate the pose deviation parameter of the shield machine based on the position deviation and the attitude deviation.

[0026] Preferably, the specific analysis method for the corrected pose parameter acquisition module is as follows: Set the state transition matrix and the measurement matrix. Use the initial pose parameter of the shield machine as the initial value of the state vector. Predict the state vector at the next moment by performing matrix multiplication on the initial value of the state vector and the state transition matrix.

[0027] Use the pose deviation parameter as the measurement value, and update the predicted state vector through the measurement matrix.

[0028] Determine the number of loop executions according to the accuracy requirement of the shield machine pose parameter. After the iterative operation of the set number of loop executions, record the obtained state vector as the corrected pose parameter of the shield machine.

[0029] Preferably, the specific analysis method for the pose command generation module is as follows: Set the dynamic threshold range, compare and judge the obtained corrected pose parameter with the dynamic threshold range. If the corrected pose parameter exceeds the dynamic threshold range, generate a pose adjustment command. The pose adjustment command takes the direction beyond the range as the positive direction, and the adjustment direction is to adjust in the negative direction. Determine the adjustment amplitude according to the exceeded range, and send the pose adjustment command to the system to perform the corresponding pose adjustment operation.

[0030] If the corrected pose parameter does not exceed the dynamic threshold range, perform a trend analysis on the corrected pose parameter and the historical data. The historical data is the attitude angle data accumulated during the previous operation of the shield machine.

[0031] Preferably, the pose command generation module further includes: Select the set number of time points as the time window size. Organize the historical data into a historical data sequence in the order of time points. Starting from the first data point of the historical data sequence, calculate the average value of the attitude angle data in each time window with the time window as the unit to obtain the moving average value sequence of the historical data sequence.

[0032] Perform a linear regression on the moving average sequence, calculate the slope of the regression line. If the slope of the regression line is positive, it indicates that the overall attitude angle of the shield machine shows an upward trend; if the slope of the regression line is negative, it indicates that the overall attitude angle of the shield machine shows a downward trend; if the slope of the regression line is within the set slope threshold range, it indicates that the stability degree of the attitude angle of the shield machine is qualified, and the change situation of the attitude angle of the shield machine is output to the system as real-time pose warning information.

[0033] Preferably, the present invention provides a method for measuring the pose of a shield machine. The specific steps of the measurement method are as follows: S1. Shield machine data acquisition: Obtain the three-dimensional point cloud data during the tunneling process of the shield machine. The three-dimensional point cloud data includes the real-time three-dimensional coordinates of the shield machine and the three-dimensional geological point cloud data.

[0034] S2. Pose parameter acquisition: Preprocess the three-dimensional point cloud data and input it into the pose fusion model to obtain the initial pose parameters.

[0035] S3. Pose deviation analysis: Define the range where the shield machine is located in the three-dimensional geological model and screen the relevant points of each axis for matching, and evaluate the pose deviation parameters of the shield machine by calculating the position deviation and the attitude deviation.

[0036] S4. Acquisition of corrected pose parameters: Iteratively optimize the initial pose parameters and the pose deviation parameters to obtain the corrected pose parameters.

[0037] S5. Generation of pose instructions: Determine whether the corrected pose parameters exceed the dynamic threshold range. If they exceed, generate pose adjustment instructions; otherwise, perform a trend analysis on them with historical data and output real-time pose warning information.

[0038] Compared with the prior art, the embodiments of the present invention at least have the following advantages or beneficial effects: First, by inputting the three-dimensional point cloud data into the pose fusion model to obtain the initial pose parameters, the present invention can make more comprehensive use of spatial information. The three-dimensional point cloud data can provide detailed geometric information about the environment around the shield machine, and the pose fusion model can comprehensively utilize this information for more accurate pose estimation, improving the accuracy and reliability of pose determination.

[0039] Second, by defining the range where the shield machine is located in the three-dimensional geological model and screening the relevant points of each axis for matching, and evaluating the pose deviation parameters of the shield machine by calculating the position deviation and the attitude deviation, the present invention can closely combine the geological environment of the actual construction of the shield machine to evaluate the pose, and can more accurately reflect the real pose situation of the shield machine under complex geological conditions, making the evaluation result more accurate.

[0040] III. The present invention inputs the initial pose parameters and pose deviation parameters into an adaptive filtering algorithm for iterative optimization to obtain corrected pose parameters, and determines whether the corrected pose parameters exceed the dynamic threshold range. If they exceed, a pose adjustment instruction is generated; otherwise, a trend analysis is performed on them together with historical data, and real-time pose warning information is output. Through dynamic threshold judgment, a pose adjustment instruction can be generated in a timely manner to prevent construction problems caused by excessive pose deviation, ensuring construction safety and accuracy. When the threshold is not exceeded, a trend analysis is performed with historical data to output real-time warning information, enabling the timely awareness of the pose change trend and preventing potential risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0042] Figure 1 It is a module connection diagram of a shield machine pose measurement system.

[0043] Figure 2 It is Figure 1 A flowchart of the relevant points of each axis in the pose deviation analysis module.

[0044] Figure 3 It is a flowchart of a shield machine pose measurement method. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, rather than all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0046] Please refer to Figure 1 As shown, a shield machine pose measurement system includes a shield machine data acquisition module, a pose parameter acquisition module, a pose deviation analysis module, a corrected pose parameter acquisition module, a pose instruction generation module, and a management database.

[0047] The management database is connected to the shield machine data acquisition module, the pose parameter acquisition module, the pose deviation analysis module, the corrected pose parameter acquisition module, and the pose instruction generation module. The corrected pose parameter acquisition module is connected to the pose parameter acquisition module, the pose deviation analysis module, and the pose instruction generation module. The pose parameter acquisition module is connected to the shield machine data acquisition module and the pose deviation analysis module.

[0048] The shield machine data acquisition module is used to acquire three-dimensional point cloud data during the tunneling process of the shield machine. The three-dimensional point cloud data includes the real-time three-dimensional coordinates of the shield machine and the three-dimensional geological point cloud data.

[0049] The pose parameter acquisition module is used to preprocess the three-dimensional point cloud data and input it into the pose fusion model to obtain the initial pose parameters.

[0050] The specific analysis method for preprocessing the three-dimensional point cloud data is as follows: The three-dimensional point cloud data of the shield machine is collected respectively according to the sampling frequency set by the corresponding sensor, and the corresponding timestamp information is recorded, and the three-dimensional point cloud data of the shield machine is adjusted to the same time point.

[0051] It should be noted that the specific analysis method for adjusting to the same time point is as follows: The three-dimensional point cloud data of the shield machine is arranged according to the acquisition order, and the target time point is selected ,and two time points adjacent to the target time point are found from the arranged three-dimensional point cloud data sequence, denoted as ,the corresponding original data values are obtained, and the linear interpolation formula is used to calculate the estimated data value corresponding to the target time point ,the linear interpolation formula is ,where respectively represent the data values corresponding to the two time points adjacent to the target time point.

[0052] The specific analysis method of the pose parameter acquisition module is as follows: The three-dimensional point cloud data of the shield machine is collected respectively according to the sampling frequency set by the corresponding sensor, and the corresponding timestamp information is recorded, and the three-dimensional point cloud data of the shield machine is adjusted to the same time point by using the linear interpolation algorithm; it can smooth the data to a certain extent, fill in the information missing or discontinuous caused by time differences, improve the overall quality of the data, and is conducive to more accurately analyzing the pose parameters of the shield machine, providing more reliable data support for the precise control of shield construction.

[0053] The Kalman filter model is selected as the pose fusion model, and the state estimation value of the shield machine is obtained by inputting the three-dimensional point cloud data of the shield machine. The iteration termination condition of the Kalman filter model is set as that the change amount of the pose parameters is less than the preset threshold. According to the three-dimensional point cloud data of the shield machine and each state estimation value, iterative calculation is carried out. After the iterative calculation is completed, the three-dimensional position coordinates and attitude angle information of the shield machine are extracted from the state estimation value finally output by the model as the initial pose parameters; during the construction process of the shield machine, its pose is constantly changing. The iterative calculation method can well adapt to this dynamic change. By continuously updating the data and iterative calculation, the model can timely capture the change of the shield machine's pose and accurately reflect its current real state.

[0054] It should be noted that the iterative calculation process of the Kalman filter includes two main steps: the prediction step and the update step. The three-dimensional point cloud data of the shield machine is converted into a linear form. In the prediction step, the control parameters of the shield machine and the time interval are combined to predict the state estimate value at the next moment, predict the state estimate value at the next moment, and at the same time predict the covariance matrix at the next moment. In the update step, the Kalman gain is calculated, the state estimate value is updated according to the observation value, and then the covariance matrix is updated. After each iterative calculation is completed, it is checked whether the change amount of the pose parameters is less than the preset threshold. If the termination condition is met, the iterative calculation is stopped; otherwise, the next iteration continues. After the iterative calculation is completed, the three-dimensional position coordinates and attitude angles of the shield machine are extracted from the finally output state estimate value as the initial pose parameters.

[0055] The pose deviation analysis module is used to define the range of the shield machine in the three-dimensional geological model and screen the relevant points of each axis for matching, and evaluate the pose deviation parameters of the shield machine by calculating the position deviation and the attitude deviation.

[0056] The specific analysis method for constructing the three-dimensional geological model is as follows: Obtain the three-dimensional geological point cloud data of the shield machine, cluster the point cloud data belonging to the same tunnel area according to the regional division information of the surrounding tunnels, and extract the point cloud data corresponding to each cluster; The geological conditions in the same tunnel area often have similarities. By clustering them into one category, it can more accurately reflect the geological characteristics of each tunnel area and provide a more reliable data basis for the subsequent construction of the geological model.

[0057] Fit each geometric surface according to the point cloud data corresponding to each cluster and combine them to obtain a complete three-dimensional geological model; Combining the geometric surfaces corresponding to each cluster into a complete model realizes the integration of geological data in different regions, enabling a comprehensive analysis of the geological conditions in the entire shield construction area and considering the mutual influence between different regions.

[0058] It should be noted that in a specific embodiment, after the previous hierarchical clustering step, three types of point cloud data are obtained, corresponding to different geological regions respectively: The first type of point cloud data is mainly concentrated in the top area of the tunnel, showing a relatively flat distribution characteristic. After analysis, a plane is selected for fitting: Using the least squares method to calculate these point cloud data, the equation of the plane is , where , that is, the plane equation is , indicating that the top of the tunnel is at an altitude of 10 meters.

[0059] The second type of point cloud data is distributed around the side wall of the tunnel and has certain cylindrical surface characteristics. The cylindrical surface fitting method is adopted. By establishing the mathematical model of the cylindrical surface and using the least squares method to solve, the axis equation of the cylinder is obtained (i.e., along the Z-axis direction) with a radius of 3 meters, then the equation of this cylindrical surface can be expressed as , which describes the shape of the tunnel sidewall.

[0060] The third type of point cloud data is located in the bottom area of the tunnel and also shows a relatively flat distribution. Plane fitting is selected, and after calculation, the plane equation is obtained as , indicating that the bottom of the tunnel is at an altitude of 5 meters.

[0061] When combining these three fitted geometric surfaces (the top plane, the sidewall cylindrical surface, and the bottom plane), make the top plane and the sidewall cylindrical surface smoothly connected at the top boundary, and the sidewall cylindrical surface and the bottom plane can also be smoothly transitioned at the bottom boundary, and finally obtain a three-dimensional geological model of the complete tunnel area.

[0062] Please refer to Figure 2 As shown, the specific analysis method for the points related to each axis is as follows: Obtain the front-end point coordinates, rear-end point coordinates of the shield machine, and the radius range of the shield machine from the real-time three-dimensional coordinates of the shield machine. Taking the axis of the shield machine as the center and combining the radius of the shield machine to construct a cylinder to define the range where the shield machine is located in the three-dimensional geological model; This provides a basis for subsequent analysis of the interaction between the shield machine and the surrounding geological environment and helps to detect potential geological risks in a timely manner.

[0063] Along the tunneling direction of the shield machine, divide the shield machine within the said range into cross-sections according to the equal-spacing principle to obtain each cross-section, and each cross-section is perpendicular to the tunneling direction of the shield machine; It can study the contact situation between the shield machine and the surrounding geology at different depths and positions in more detail and provide more detailed data for analyzing the force and tunneling stability of the shield machine.

[0064] For each of the said cross-sections, extract the points located within this cross-section from the three-dimensional geological point cloud data, and calculate their distances to the center of this cross-section respectively, where the center of the cross-section is the projection point of the design axis of the shield machine on this cross-section.

[0065] It should be noted that the center of the cross-section is the projection point of the design axis of the shield machine on this cross-section, and its coordinates are set as , for each point within the cross-section, use the Euclidean distance formula to calculate its distance to the center of the cross-section.

[0066] Set a reasonable deviation value, sum it with the radius of the shield machine to determine the distance threshold, compare the distance from each point to the center of the cross-section with the distance threshold, and select the points whose distance to the center of the cross-section is less than or equal to the distance threshold as the relevant points for each axis; by calculating the distance from the point to the center of the cross-section and comparing it with the distance threshold, the points closely related to the axis of the shield machine can be selected. These points reflect the actual situation of the geology around the shield machine, excluding some irrelevant points far from the shield machine, making the subsequent analysis more focused on the key data.

[0067] It should be noted that the reasonable deviation value is usually set between 5% and 10% of the radius of the shield machine.

[0068] Perform linear fitting on the relevant points of each axis until the sum of the squares of the distances from the relevant points of each axis to the fitting line reaches the minimum, so as to determine the preliminary direction of the tunneling axis of the shield machine; the minimization process of the sum of the squares of the distances will comprehensively consider the deviations of each point, making the fitting line as close as possible to the true trend of the tunneling axis, so as to obtain a more accurate and reliable preliminary direction of the axis.

[0069] It should be noted that let the relevant points of each axis be three-dimensional space points, and their coordinates are respectively , where represents the number of the th relevant point of the axis, , let the line pass through the point , and the direction vector is , then any point on the line can be expressed as , where , for a point in space and the line , the distance from the point to the line can be calculated by the method of vectors. Let the vector , then the square of the distance from the point to the line is: , for points, the sum of the squares of the distances is: , take the centroid of all relevant points of the axis as the initial point of the line, calculate the deviation vector of each point relative to the centroid, construct the covariance matrix , then, perform eigenvalue decomposition on the covariance matrix , obtain the eigenvalues and the corresponding eigenvectors , according to the least squares principle, the eigenvector corresponding to the largest eigenvalue It is the preliminary direction of the tunneling axis of the shield machine .

[0070] The specific analysis method of the pose deviation parameter is as follows: Arbitrarily select two points on the tunneling axis, calculate the vector difference formed by these two points to obtain the direction vector of the tunneling axis, extract the relevant points of each axis on the tunneling axis of the shield machine, and at the same time obtain the points on the preset design axis. Find the point with the shortest distance on the design axis for each relevant point of the axis, establish the corresponding relationship between the two, and form each pair of matching points; Using the method of determining the direction vector by two points is simple and direct, avoiding complex direction calculations for a large number of axis-related points. At the same time, establishing pairs of matching points enables each point in the actual tunneling process to be accurately associated with the corresponding position in the design state, thus providing an accurate data correspondence relationship for subsequent calculation of position deviation.

[0071] It should be noted that in a specific embodiment, 10 axis-related points are obtained, and the coordinates are respectively , and there are 20 points on the design axis . For the point on the tunneling axis, find the point with the shortest distance on the design axis through the multi-dimensional space search algorithm , then a pair of matching points is formed . In this way, corresponding matching points are found for all 10 axis-related points, forming 10 pairs of matching points.

[0072] Calculate the position differences of each pair of matching points in three-dimensional space respectively, and obtain the position deviation by taking the average value. Calculate the angle between the direction vectors of the design axis and the tunneling axis of the shield machine to obtain the attitude deviation; Calculating the angle between the direction vectors of the design axis and the tunneling axis of the shield machine to obtain the attitude deviation can clearly show the difference between the attitude of the shield machine and the design attitude.

[0073] It should be noted that the attitude deviation uses the vector dot product formula. By calculating the dot product of two direction vectors divided by the product of the moduli of the two vectors, the cosine value of the angle is obtained. Finally, through the inverse trigonometric function, the actual angle between the two axes is obtained, and this angle is the attitude deviation.

[0074] Based on the position deviation and attitude deviation, the pose deviation parameter of the shield machine is obtained; The pose deviation parameter provides a clear goal and direction for the real-time adjustment of the shield machine, and the tunneling parameters of the shield machine can be adjusted targeted.

[0075] It should be noted that the specific calculation method of the pose deviation parameter of the shield machine is as follows: Extract the position deviation and attitude deviation of the shield machine, and then perform a weighted summation calculation to obtain the pose deviation parameter of the shield machine.

[0076] Exemplarily, the weights corresponding to the position deviation and attitude deviation of the shield machine are .

[0077] A pose correction parameter acquisition module, which is used to iteratively optimize the initial pose parameters and pose deviation parameters to obtain the corrected pose parameters.

[0078] The specific analysis method of the pose correction parameter acquisition module is as follows: set the state transition matrix and the measurement matrix, use the initial pose parameters of the shield machine as the initial value of the state vector, and predict the state vector at the next moment by performing matrix multiplication on the initial value of the state vector and the state transition matrix.

[0079] It should be noted that the state vector of the shield machine contains 6 elements, namely three-dimensional position and three-dimensional attitude . Under the assumption of simple uniform linear motion and unchanged attitude, the state transition matrix , the attitude information measurement matrix . By performing matrix multiplication on the initial value of the state vector and the state transition matrix, the state vector at the next moment can be predicted.

[0080] Taking the pose deviation parameter as the measurement value, update the predicted state vector through the measurement matrix; using the pose deviation parameter to update the state vector in real time can enable the system to track these changes in a timely manner, ensure that the state vector always reflects the latest state of the shield machine, and enhance the dynamic adaptability of the system.

[0081] Determine the number of loop executions according to the accuracy requirements of the shield machine pose parameters. After the iterative operation of the set number of loop executions, record the obtained state vector as the corrected pose parameters of the shield machine; multiple iterative operations can make the state vector gradually stabilize during the continuous update process. Through repeated adjustment, the influence of accidental factors on state estimation is reduced, making the corrected pose parameters more reliable.

[0082] A pose instruction generation module, which is used to determine whether the corrected pose parameters exceed the dynamic threshold range. If they exceed, generate a pose adjustment instruction; otherwise, perform a trend analysis on them together with historical data and output real-time pose warning information.

[0083] The specific analysis method of the pose instruction generation module is as follows: Set a dynamic threshold range, compare the obtained corrected pose parameters with the dynamic threshold range. If the corrected pose parameters exceed the dynamic threshold range, generate a pose adjustment instruction. The positive direction of the pose adjustment instruction is the direction beyond the range, and the adjustment direction is the negative direction. Determine the adjustment amplitude according to the range exceeded, and send the pose adjustment instruction to the system to perform the corresponding pose adjustment operation; clarify that the adjustment direction is the opposite direction of the range exceeded, and determine the adjustment amplitude according to the range exceeded, so that the adjustment operation is targeted and effective, and avoid further expansion of the pose deviation of the shield machine.

[0084] If the corrected pose parameters do not exceed the dynamic threshold range, perform a trend analysis on the corrected pose parameters and historical data. The historical data is the attitude angle data accumulated by the shield machine during previous operations; it helps to deeply understand the pose change characteristics of the shield machine at different construction stages.

[0085] The pose instruction generation module further includes: Select the number of set time points as the time window size, form a historical data sequence with the historical data in the order of time points. Starting from the first data point of the historical data sequence, calculate the average value of the attitude angle data in each time window with the time window as the unit to obtain the moving average value sequence of the historical data sequence; The average value within each time window represents the overall level of the shield machine's attitude angle during that time period, and the moving average value sequence reflects the stage change of the shield machine's attitude angle over time, which helps to analyze the operating state of the shield machine in different time periods.

[0086] Perform linear regression on the moving average value sequence, calculate the slope of the regression line. If the slope of the regression line is positive, it means that the overall attitude angle of the shield machine shows an upward trend. If the slope of the regression line is negative, it means that the overall attitude angle of the shield machine shows a downward trend. If the slope of the regression line is within the set slope threshold range, it means that the stability degree of the shield machine's attitude angle is qualified, and output the change situation of the shield machine's attitude angle as real-time pose warning information to the system; When the slope is within the threshold range, it indicates that the change of the shield machine's attitude angle is relatively stable and the stability degree is qualified; otherwise, it indicates that there may be abnormal changes in the attitude, which requires further attention and adjustment, helps to timely discover potential problems during the operation of the shield machine, and ensures the construction safety and quality.

[0087] It should be noted that in a specific embodiment, the attitude angle data of the shield machine every 5 minutes in the past period of time, a total of 20 time point data are obtained, and the historical data sequence: , set the number of time points as 4 as the time window size, starting from the first data point of the historical data sequence, divide the time window, and the first time window is , and its average value is , the first time window is , and its average value is , and so on until the last time window. After calculation, the moving average value sequence obtained is: , perform a linear regression analysis on the moving average value sequence. Let the data point serial number in the moving average value sequence be the independent variable , , corresponding to 15 moving average value data points, and the moving average value is the dependent variable , the slope of the regression line obtained through linear regression calculation is -0.07, and the set slope threshold range is , because -0.07, that is, the slope of the regression line is negative and not within the set slope threshold range, so it indicates that the overall attitude angle of the shield machine shows a downward trend, and the change in the attitude angle exceeds the stable range.

[0088] The management database is used to store the three-dimensional point cloud data, initial pose parameters, pose deviation parameters, corrected pose parameters and historical data of the shield machine body.

[0089] Please refer to Figure 3 shown. In addition, the present invention provides a method for measuring the pose of a shield machine. The specific steps of the measurement method are as follows: S1. Shield machine data acquisition: Acquire the three-dimensional point cloud data during the tunneling process of the shield machine. The three-dimensional point cloud data includes the real-time three-dimensional coordinates of the shield machine and the three-dimensional geological point cloud data.

[0090] S2. Pose parameter acquisition: Preprocess the three-dimensional point cloud data and input it into the pose fusion model to obtain the initial pose parameters.

[0091] S3. Pose deviation analysis: Define the range where the shield machine is located in the three-dimensional geological model and screen the relevant points of each axis for matching, and evaluate the pose deviation parameters of the shield machine by calculating the position deviation and the attitude deviation.

[0092] S4. Corrected pose parameter acquisition: Iteratively optimize the initial pose parameters and the pose deviation parameters to obtain the corrected pose parameters.

[0093] S5. Pose instruction generation: Judge whether the corrected pose parameters exceed the dynamic threshold range. If they exceed, generate a pose adjustment instruction; otherwise, perform a trend analysis on them together with the historical data and output real-time pose warning information.

[0094] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention, and still be covered by the protection scope of the present invention.

Claims

1. A shield machine attitude measurement system, characterized in that, The system specifically includes the following modules: A shield machine data acquisition module, which is used to acquire three-dimensional point cloud data during the tunneling process of the shield machine. The three-dimensional point cloud data includes the real-time three-dimensional coordinates of the shield machine and three-dimensional geological point cloud data; A pose parameter acquisition module, which is used to preprocess the three-dimensional point cloud data and input it into a pose fusion model to obtain initial pose parameters; A pose deviation analysis module, which is used to define the range where the shield machine is located in the three-dimensional geological model and screen the relevant points of each axis for matching, and evaluate the pose deviation parameters of the shield machine by calculating the position deviation and attitude deviation; A corrected pose parameter acquisition module, which is used to iteratively optimize the initial pose parameters and the pose deviation parameters to obtain corrected pose parameters; A pose instruction generation module, which is used to judge whether the corrected pose parameters exceed the dynamic threshold range. If they exceed, a pose adjustment instruction is generated. Otherwise, a trend analysis is performed on the corrected pose parameters and historical data, and real-time pose warning information is output; A management database, which is used to store the three-dimensional point cloud data, initial pose parameters, pose deviation parameters, corrected pose parameters and historical data of the shield machine body; The pose instruction generation module further includes: Selecting the number of set time points as the time window size, forming a historical data sequence from the historical data in the order of time points. Starting from the first data point in the historical data sequence, taking the time window as the unit, calculating the average value of the attitude angle data in each time window to obtain a moving average value sequence of the historical data sequence; Performing linear regression on the moving average value sequence, calculating the slope of the regression line. If the slope of the regression line is positive, it means that the overall attitude angle of the shield machine shows an upward trend. If the slope of the regression line is negative, it means that the overall attitude angle of the shield machine shows a downward trend. If the slope of the regression line is within the set slope threshold range, it means that the stability degree of the attitude angle of the shield machine is qualified, and the change situation of the attitude angle of the shield machine is output as real-time pose warning information to the system.

2. The shield machine pose measurement system according to claim 1, wherein: The specific analysis method for preprocessing the three-dimensional point cloud data is: Collecting the three-dimensional point cloud data of the shield machine according to the sampling frequency set by the corresponding sensor and recording the corresponding timestamp information, and adjusting the three-dimensional point cloud data of the shield machine to the same time point.

3. The pose measurement system for a shield machine according to claim 2, characterized in that: The specific analysis method of the pose parameter acquisition module is: Selecting a Kalman filter model as the pose fusion model, inputting the three-dimensional point cloud data of the shield machine to obtain the state estimation value of the shield machine, setting the iteration termination condition of the Kalman filter model as the change amount of the pose parameters being less than the preset threshold, and entering iterative calculation according to the three-dimensional point cloud data of the shield machine and the state estimation value of each time. After the iterative calculation is completed, the three-dimensional position coordinates and attitude angle information of the shield machine are extracted from the state estimation value finally output by the model as the initial pose parameters.

4. A shield machine pose measurement system according to claim 2, characterized in that: The specific analysis method for constructing a three-dimensional geological model is: Obtaining the three-dimensional geological point cloud data of the shield machine, clustering the point cloud data belonging to the same tunnel area according to the regional division information of the surrounding tunnels, and extracting the point cloud data corresponding to each cluster; Fitting each geometric surface according to the point cloud data corresponding to each cluster and combining them to obtain a complete three-dimensional geological model.

5. A shield machine pose measurement system according to claim 4, characterized in that: The specific analysis method for each axis-related point is as follows: Obtain the coordinates of the front-end point, the rear-end point of the shield machine and the radius range of the shield machine from the real-time three-dimensional coordinates of the shield machine. Taking the axis of the shield machine as the center and combining the radius of the shield machine, construct a cylinder to define the location range of the shield machine in the three-dimensional geological model; Along the tunneling direction of the shield machine, divide the shield machine within the said location range according to the equal-spacing principle to obtain each cross-section, and each cross-section is perpendicular to the tunneling direction of the shield machine; For each of the said cross-sections, extract the points located within each cross-section from the three-dimensional geological point cloud data, and calculate the distances from the points within each cross-section to the center of the corresponding cross-section, where the center of the cross-section is the projection point of the designed axis of the shield machine on each cross-section; Set a reasonable deviation value, sum it with the radius of the shield machine to determine the distance threshold, compare the distances from the points within each cross-section to the center of the corresponding cross-section with the said distance threshold, and screen out the points whose distances from the points within each cross-section to the center of the corresponding cross-section are less than or equal to the distance threshold as each axis-related point; Perform linear fitting on each of the said axis-related points until the sum of the squares of the distances from each axis-related point to the fitting line reaches the minimum, thereby determining the preliminary direction of the tunneling axis of the shield machine.

6. The shield machine pose measurement system according to claim 5, wherein: The specific analysis method for the pose deviation parameter is as follows: Arbitrarily select two points on the said tunneling axis, obtain the direction vector of the tunneling axis by calculating the vector difference formed by these two points, extract each axis-related point on the tunneling axis of the shield machine, and at the same time obtain each point on the preset designed axis. Find the point with the shortest distance on the said designed axis for each axis-related point, establish the corresponding relationship between the two, and form each matching point pair; Calculate the position differences of each matching point pair in the three-dimensional space respectively, and obtain the position deviation by taking the average value. Calculate the included angle between the direction vectors of the designed axis and the tunneling axis of the shield machine to obtain the pose deviation; Evaluate the pose deviation parameter of the shield machine based on the position deviation and the pose deviation.

7. The shield machine pose measurement system according to claim 6, wherein: The specific analysis method for the modified pose parameter acquisition module is as follows: Set the state transition matrix and the measurement matrix. Taking the initial pose parameter of the shield machine as the initial value of the state vector, predict the state vector at the next moment by performing matrix multiplication on the initial value of the state vector and the state transition matrix; Taking the pose deviation parameter as the measurement value, update the predicted state vector through the measurement matrix; Determine the number of loop executions according to the accuracy requirement of the pose parameter of the shield machine. After the iterative operation of the set number of loop executions, record the obtained state vector as the modified pose parameter of the shield machine.

8. A shield machine pose measurement system according to claim 1, characterized in that: The specific analysis method for the pose instruction generation module is as follows: Set the dynamic threshold range, compare and judge the obtained modified pose parameter with the said dynamic threshold range. If the modified pose parameter exceeds the dynamic threshold range, generate a pose adjustment instruction. The pose adjustment instruction takes the direction beyond the range as the positive direction, and the adjustment direction is to adjust in the negative direction. Determine the adjustment amplitude according to the exceeded range, and send the said pose adjustment instruction to the system to perform the corresponding pose adjustment operation; If the corrected pose parameter does not exceed the dynamic threshold range, perform trend analysis on the corrected pose parameter and historical data, where the historical data is the attitude angle data accumulated during the previous operation of the shield machine.

9. A shield machine pose measurement method, characterized in that, It includes the following steps: S1. Shield machine data acquisition: Acquire the three-dimensional point cloud data during the tunneling process of the shield machine. The three-dimensional point cloud data includes the real-time three-dimensional coordinates of the shield machine and the three-dimensional geological point cloud data; S2. Pose parameter acquisition: Preprocess the three-dimensional point cloud data and input it into the pose fusion model to obtain the initial pose parameter; S3. Pose deviation analysis: Define the range where the shield machine is located in the three-dimensional geological model and screen the relevant points of each axis for matching. Evaluate the pose deviation parameter of the shield machine by calculating the position deviation and the attitude deviation; S4. Corrected pose parameter acquisition: Iteratively optimize the initial pose parameter and the pose deviation parameter to obtain the corrected pose parameter; S5. Pose instruction generation: Determine whether the corrected pose parameter exceeds the dynamic threshold range. If it exceeds, generate a pose adjustment instruction; otherwise, perform trend analysis on it and the historical data, and output real-time pose warning information.

Images