Tunnel initial vault settlement monitoring method and device based on machine vision calibration

Abstract

The invention provides a tunnel initial vault settlement monitoring method and device based on machine vision calibration, and relates to the technical field of tunnel engineering monitoring, and the method comprises the steps: obtaining the settlement amount of a tunnel vault target in an excavated area behind a tunnel face in real time through a self-adaptive ambient light compensation algorithm and an infrared auxiliary calibration device; the settlement amount is used as a reference point correction amount and is input into a displacement rope data correction model; the displacement rope system is arranged in the advance drill hole to realize continuous monitoring of tunnel vault settlement; and the multi-sensor data space-time registration module ensures accurate fusion of data of the visual displacement system and the displacement rope system, so that a corrected whole-process settlement measurement result of the excavation section in front of the tunnel face is output. The method not only improves the measurement precision and efficiency, but also eliminates the drift error of the reference point of the displacement rope system due to stratum disturbance through a reference point correction algorithm, and enhances the adaptability and reliability of the monitoring system.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel engineering monitoring, and particularly to a method and device for monitoring the initial vault settlement of a tunnel based on machine vision calibration. Background Art

[0002] Currently, during the tunnel construction process, the monitoring of vault settlement is crucial, which is directly related to construction safety and engineering quality. However, there are many deficiencies in the existing monitoring technologies; the traditional total station monitoring method relies on manual operation, with low efficiency, and the most critical point is that monitoring points can only be arranged after the tunnel excavation, and generally, it takes 1 to 3 days after the initial support is formed to complete the arrangement of monitoring points. Therefore, the settlement changes from the initial state of the tunnel to the excavation stage cannot be captured, and it is difficult to meet the requirements of the dynamic construction environment. Although the monitoring scheme based on a single machine vision has certain automation advantages, it is also limited by the fact that the target points can only be arranged after the excavation, and the recognition accuracy drops significantly in complex environments such as construction dust, making it difficult to ensure the accuracy of the monitoring data. To solve the measurement of the vault settlement from the initial state of the tunnel to the whole excavation process, Chinese Patent with the application number 201910257595.1 discloses a device and method for monitoring the vault settlement during tunnel construction. By pre-burying an inclinometer tube through an advanced borehole above the tunnel face and arranging inclinometer sensors in the tube to calculate the total displacement of the vault settlement. Although the scheme of pre-burying displacement meters through advanced boreholes can monitor the whole process of the vault settlement before and after the excavation of the tunnel face in real time, this scheme needs to use the fixed points in the stratum as the starting reference points, and the disturbance of the stratum within the influence range of the tunnel face excavation will cause the drift of the reference points, and the displacement of the reference points in the stratum cannot be calibrated and corrected through measurement, thus affecting the reliability of the measurement results of this scheme.

[0003] More critically, in the existing technology, there is no integration of the machine vision displacement system and the physical sensor system for vault settlement monitoring, using machine vision dynamic calibration as the basis for correcting the reference points of the physical sensors for vault settlement monitoring, and effectively solving the time and space reference synchronization problems between the vision displacement system and the physical sensors, and then accurately and dynamically measuring the vault settlement during the whole process of tunnel excavation through the effective integration of multi-source data.

[0004] Therefore, developing a new technology that can achieve accurate and dynamic measurement of the vault settlement from the initial unexcavated state of the tunnel to the whole process of excavation construction has important practical significance for improving the level of tunnel engineering monitoring.

[0005] In view of this, this application is proposed. Summary of the Invention

[0006] The present invention provides a method and device for monitoring the initial vault settlement of a tunnel based on machine vision calibration, which can at least partially improve the above problems.

[0007] To achieve the above object, the present invention adopts the following technical solutions: A method for monitoring the initial vault settlement of a tunnel based on machine vision calibration, comprising: Obtain the real-time dynamic visual displacement data collected by a preset visual displacement system, and obtain the tunnel vault settlement amount by collecting the displacement rope system data through the displacement rope system pre-embedded in the tunnel in advance, and preprocess the visual displacement data and the displacement rope system data to obtain the corrected visual displacement data and the vault settlement amount; Perform data fusion spatio-temporal registration processing according to the corrected visual displacement data and the vault settlement amount, so that the visual displacement data and the displacement rope system data are aligned in space and synchronized in time; Input the visual displacement data as the reference point correction amount into the displacement rope system data dynamic correction model, and use the displacement rope system data correction model to perform dynamic correction processing on the aligned displacement rope system data to obtain the settlement measurement result of the excavation section in front of the tunnel face.

[0008] The present invention also provides a device for monitoring the initial vault settlement of a tunnel based on machine vision calibration, comprising: A preprocessing unit for obtaining the visual displacement data collected by a preset visual displacement system and the displacement rope system data collected by the displacement rope system, and preprocessing the visual displacement data and the displacement rope system data to obtain the corrected visual displacement data and the vault settlement amount; An alignment unit for performing data fusion spatio-temporal registration processing according to the corrected visual displacement data and the vault settlement amount, so that the visual displacement data and the displacement rope system data are aligned in space and synchronized in time; A correction unit for inputting the visual displacement data as the reference point correction amount into the displacement rope data correction model, and using the displacement rope data correction model to correct the aligned displacement rope system data to obtain the settlement measurement result of the excavation section in front of the tunnel face.

[0009] In summary, the initial vault settlement monitoring method of the tunnel based on machine vision calibration solves the problem of drift of the pre-buried displacement meter benchmark due to the stratum disturbance of tunnel excavation by integrating machine vision and displacement meter data correction technology with multi-source monitoring data spatiotemporal registration technology, and realizes high-precision dynamic monitoring of the entire process from the initial state of the tunnel to the excavation construction. Specifically, the method adopts machine vision dynamic calibration as the core, combined with the extended monitoring of the displacement meter, to construct a new double-layer monitoring architecture. The machine vision system obtains the settlement data of the tunnel vault in real time through ambient light compensation and infrared auxiliary calibration, and uses it as the benchmark correction amount to correct the displacement meter data. Through the spatiotemporal registration technology of multi-source data, the time and space benchmark synchronization problem between the visual system and the displacement meter is solved, ensuring the accuracy and consistency of the monitoring data. In addition, the method also introduces a benchmark correction algorithm, which evaluates the reliability of the visual data in real time through a dynamic adjustment mechanism, and dynamically adjusts and corrects the displacement meter data, thereby effectively eliminating the influence of stratum disturbance on the benchmark. The method for monitoring initial tunnel vault settlement based on machine vision calibration not only improves the monitoring accuracy, but also enhances the adaptability and reliability. It is suitable for monitoring tunnel vault settlement in complex construction environments and provides a strong technical guarantee for the safe construction of tunnel projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 It is a flow chart of a method for monitoring initial vault settlement of a tunnel based on machine vision calibration provided by the first embodiment of the present invention; Figure 2 It is an overall flow chart of a method for monitoring initial vault settlement of a tunnel based on machine vision calibration provided by the first embodiment of the present invention; Figure 3 It is a schematic diagram of the structure of the visual displacement system and the displacement rope system provided by the embodiment of the present invention; Figure 4 It is a module schematic diagram of a tunnel initial vault settlement monitoring device based on machine vision calibration provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0011] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0012] refer to Figures 1 to 3 As shown, the first embodiment of the present invention discloses a method for monitoring initial vault settlement of a tunnel based on machine vision calibration, which can be performed by a monitoring device for initial vault settlement of a tunnel based on machine vision calibration (hereinafter referred to as monitoring device), and in particular, by one or more processors in the monitoring device to implement the following method: S1. Obtain the real-time dynamic visual displacement data collected by a preset visual displacement system, and obtain the vault settlement of the tunnel by acquiring the displacement rope system data collected by a displacement rope system pre-buried in advance in the tunnel, and preprocess the visual displacement data and the displacement rope system data to obtain the corrected visual displacement data and the vault settlement. Preferably, the visual displacement system is a visual displacement camera, which includes an infrared anti-interference module. The visual displacement camera is configured at a stable area where the tunnel support has been formed and does not displace within a preset length range behind the tunnel face to be monitored, and its corresponding target is arranged at the vault position within the excavated area behind the tunnel face to be monitored. Among them, the preset length range is 20 - 50m.

[0013] The displacement rope system is a displacement rope fixed on a steel pipe. The displacement rope is pre-buried into the formation above the tunnel by means of advanced drilling. The displacement rope is composed of node sensors with equal or unequal spacing distributed in a gradient manner. Among them, the position of the target coincides with the position of the drilling orifice of the displacement rope system.

[0014] Specifically, step S1 further includes: judging whether the current ambient light intensity is less than a preset value; If so, activate the infrared anti-interference module, perform infrared light filling, and perform adaptive environment compensation processing on the collected visual displacement data to obtain the corrected visual data; If not, directly perform adaptive environment compensation processing on the collected visual displacement data to obtain the corrected visual data.

[0015] Based on the non-linear compensation model, calculate the corrected visual displacement data. The formula is: , where is the gray value of the camera, is the ambient light intensity, is the dark current reference value, and are both fitting parameters.

[0016] Obtain the inclination change data at the position collected by the node sensor, and take a preset reference point as the starting point, perform trapezoidal integration processing, and calculate the vault settlement at any position of the tunnel to be monitored. The calculation formula is: , where is the vault settlement at the i-th point, is the i-th original inclination change data, is the (i - 1)-th original inclination change data, is the arrangement spacing of the node sensors.

[0017] In this embodiment, first, it is necessary to reasonably arrange the monitoring equipment. Refer toFigure 3 It can be seen that the visual displacement camera is installed in the formed area of the tunnel support at a distance of 20 to 50 meters behind the tunnel face to be monitored. The selection of this position comprehensively considers the monitoring range and data accuracy. The target of the camera is precisely arranged at the crown position of the excavated area behind the tunnel face, coinciding with the borehole opening position of the displacement rope system, ensuring the spatial consistency of the data of the two. The displacement rope system consists of displacement ropes fixed on steel pipes and is pre-buried into the strata above the tunnel through advanced drilling. The node sensors on the displacement ropes are distributed in an equal-spacing or unequal-spacing gradient, and this distribution method can be flexibly adjusted according to the specific geological conditions and monitoring requirements of the tunnel to achieve more accurate settlement monitoring. Among them, the spacing of the node sensors with equal spacing can be 0.5 m.

[0018] During the monitoring process, the visual displacement camera first collects visual displacement data, and then immediately judges whether the current ambient light intensity is lower than the preset value (the preset value can be 50 lux). If the ambient light intensity is insufficient, the infrared anti-interference module will be activated for infrared supplementary lighting to ensure the clarity of the image and the accuracy of the data. Subsequently, the collected visual displacement data is subjected to adaptive environmental compensation processing. This processing process is based on a non-linear compensation model, and by calculating the corrected visual data, the influence of ambient light changes on the monitoring results is effectively eliminated, improving the reliability of the data. Through this compensation processing, even in complex construction environments such as dust and water mist interference, the visual displacement camera can stably output high-quality monitoring data.

[0019] At the same time, the displacement rope system is also working synchronously; the node sensors collect the inclination change data at the position in real time, and taking the preset reference point as the starting point, the system adopts the trapezoidal integral processing method to calculate the crown settlement amount at any position of the tunnel to be monitored. To accurately reflect the settlement of the tunnel crown at different positions and provide real-time data support for construction safety.

[0020] S2. Perform data fusion spatio-temporal registration processing according to the corrected visual displacement data and the crown settlement amount, so that the visual displacement data and the displacement rope system data are aligned in space and synchronized in time; Specifically, step S2 further includes: performing Euler rotation matrix transformation processing on the corrected visual displacement data to unify the coordinates of the corrected visual data with the coordinates of the crown settlement amount; Adjust the data sampling frequency of the displacement rope system according to the change of the crown settlement amount. Among them, when the settlement change of the crown settlement amount is within the preset normal state, the data sampling frequency of the displacement rope system is the initial set value. When the settlement change of the crown settlement amount exceeds the preset warning value, the acquisition frequency will be automatically dynamically adjusted to encrypt the acquisition frequency, and the displacement rope system will, according to the real-time dynamic acquisition frequency, process the displacement rope system data Perform cubic spline interpolation to match the timestamps of the vision displacement system ; Set the time axis node sequence to , and define the recurrence formula for the j-th cubic B-spline basis function as: , , where k = 3 represents cubic spline, and the final basis function is obtained, where is the 0th-order (constant) B-spline basis function, serving as the starting point for recurrence, defining the basic time unit for data sampling, and being the basis for constructing all higher-order basis functions; is the j-th k-th order B-spline basis function, used to construct the cubic spline interpolation curve, is the j-th k-1-th order B-spline basis function, is the j+1-th k-1-th order B-spline basis function; here, to construct the cubic spline function, k = 3 represents cubic B-spline, and the final basis function is obtained. The cubic B-spline basis function is composed of the weighted combination of two adjacent quadratic basis functions, and higher-order smooth basis functions are gradually constructed by recursively combining lower-order basis functions, finally generating the cubic B-spline curve; Determine the time non-uniformity point allocation rule suitable for the excavation process, dynamically adjust the data acquisition time interval, and the allocation rule is: , where is the dynamic acquisition time interval of the displacement rope system data; Based on the final basis function and the allocation rule, according to the data point sequence of the displacement rope system, construct the difference function: , where m is the number of original data points of the displacement rope system, is the interpolation coefficient to be solved, and 2 control points are extended to meet the boundary conditions; Perform coefficient solution processing according to the difference function, and the formula is: , and mark it as Ac = S, where B m+2 (t m ) is the value of the (m+2)-th cubic B-spline basis function at the time node t m , is the interpolation coefficient of the (m+2)-th basis function to be solved, is the settlement data actually measured by the displacement rope system at the timestamp t m , t m is the time label of the m-th data point collected by the displacement rope system; A is the coefficient matrix composed of the values B1(t1), B2(t1)...B m+2 (t m ) at the time nodes, and c is composed of c1, c2...cm+2 The coefficient vector to be solved, and S is the settlement data actually collected by the displacement rope system ... The vector formed; According to the constraint conditions , the constrained least-squares solution is obtained , , where the constraint matrix C corresponds to the second derivative condition and is solved using the Lagrange multiplier method; Based on the solved constrained least-squares solution, high-frequency data synchronization processing is performed for the timestamps of the vision displacement system , and the corresponding synchronized displacement rope system data is: , where is the interpolation coefficient of the j-th basis function to be solved.

[0021] In this embodiment, the purpose of data fusion spatio-temporal registration processing is to ensure that the vision displacement data and the displacement rope system data are aligned in space and synchronized in time, thereby providing an accurate and reliable data basis for subsequent settlement analysis. First, for the corrected vision data, Euler rotation matrix transformation processing is performed. This processing process unifies the coordinate systems of the vision data and the coordinate system of the crown settlement amount through mathematical transformation, thereby solving the possible problem of inconsistent spatial references between the vision system and the displacement meter system. This spatial alignment method not only improves the accuracy of data fusion but also provides a unified spatial reference framework for subsequent settlement analysis, enabling effective comparison and analysis of data from different sources in the same spatial dimension.

[0022] Secondly, the data sampling frequency of the displacement rope system is dynamically adjusted according to the crown settlement amount. When the settlement change of the crown settlement amount is within the preset normal state, the data sampling frequency of the displacement rope system remains the initial set value. This initial set value is usually determined in advance according to the general situation of tunnel construction and monitoring requirements and can meet the requirements of conventional monitoring. However, when the settlement change of the crown settlement amount exceeds the preset warning value, this indicates that there may be an abnormal situation in the tunnel crown settlement. At this time, it is necessary to sample the displacement rope system data more frequently to capture the details of the settlement change in a timely manner. To achieve this goal, cubic spline interpolation processing is performed on the displacement rope system data to match the timestamps of the vision displacement system. Cubic spline interpolation is a mathematical interpolation method that can generate a smooth curve based on existing data points, thereby encrypting the displacement rope system data in time and synchronizing it with the high-frequency data of the vision displacement system in time.

[0023] When performing cubic spline interpolation processing, first set the time axis node sequence to a specific distribution form. Define the recursive formula of the jth cubic B-spline basis function, where k=3 represents cubic spline. Through the recursive formula, the final basis function can be obtained. The determination of this basis function is the basis of interpolation processing, which determines the shape and properties of the interpolation curve. Next, according to the point allocation rule that adapts to the time non-uniformity of the excavation process, the data collection time interval is dynamically adjusted. This dynamic adjustment rule can flexibly adjust the data collection time interval according to the actual situation during the tunnel excavation process, so as to better adapt to the time non-uniformity of the excavation process. Through this dynamic adjustment, the data collection frequency can be increased when the settlement changes greatly, and the collection frequency can be kept low when the settlement changes are small, thereby improving the monitoring efficiency while ensuring data accuracy.

[0024] Based on the final basis function and the allocation rule, the difference function is constructed according to the data point sequence of the displacement rope system. Through the difference function, the data points of the displacement rope system can be linked to the nodes on the time axis, thereby realizing the interpolation processing of the data. Next, the coefficients are solved according to the difference function; by solving the equation group, the coefficients to be solved can be obtained, thereby determining the specific form of the interpolation function.

[0025] In addition, in order to ensure the smoothness of the interpolation curve, constraints are introduced and solved by the Lagrange multiplier method. The constraints correspond to the second-order derivative conditions. Through the Lagrange multiplier method, a constrained least squares solution can be obtained. This constrained least squares solution method can not only ensure the smoothness of the interpolation curve, but also suppress the overfitting phenomenon in the interpolation process to a certain extent, thereby improving the reliability and stability of the interpolation result. Based on the constrained least squares solution after solution, high-frequency data synchronization processing is performed. This synchronization processing realizes the precise alignment of the visual displacement system and the displacement rope system data in time, thereby providing high-quality synchronized data for subsequent settlement analysis.

[0026] S3, inputting the visual displacement data as a reference point correction amount into a displacement rope system data dynamic correction model, and using the displacement rope system data correction model to dynamically correct the aligned displacement rope system data to obtain a settlement measurement result of the excavation section in front of the tunnel face.

[0027] Specifically, step S3 further includes: the visual displacement system detects the current measured visual displacement data and the visual displacement data at the previous moment in real time, and when the visual displacement system measures data that suddenly changes, it automatically triggers continuous data collection, and determines whether the current sudden change data is a measurement error or sudden settlement through a standard deviation evaluation method based on the continuously measured data set; When a measurement error occurs, the erroneous data value is eliminated and the stable data is updated using continuous measurement Alternative processing; When sudden settlement occurs, the vault settlement amount is taken as the reference point correction amount ; When the lens of the visual displacement system is blocked and the system fails, data is dynamically generated through an interpolation algorithm , to smoothly correct the data curve of the displacement rope system. The formula for dynamically generating reference point data by the interpolation algorithm is: , where is the displacement measurement at the current moment and the displacement measurement at the previous moment is the time interval between them, is the displacement measurement at the next moment and the displacement measurement at the previous moment is the time interval between them; According to the reference point correction amount correct the vault settlement. The formula for the displacement rope data correction model is: , where is the settlement amount of the i-th point.

[0028] In this embodiment, by inputting the visual displacement data as the reference point correction amount into the displacement rope data correction model, the data of the displacement rope system is corrected, so as to obtain the settlement measurement result of the excavation section in front of the tunnel face.

[0029] Specifically, the visual displacement data at the current moment is monitored in real time and compared with the visual displacement data at the previous moment. Through the standard deviation evaluation method, it is judged whether the current visual displacement data has measurement errors or sudden settlements. This real-time monitoring and analysis mechanism can quickly identify data anomalies and ensure the reliability of the monitoring data. If the system detects measurement errors, such as abnormal visual displacement data caused by dust, water mist or other interference factors, these incorrect data values will be automatically excluded. Subsequently, the stable data of continuous measurement is used for update and alternative processing. This process not only avoids the influence of incorrect data on the monitoring results, but also ensures the continuity and stability of the data, and improves the robustness of the monitoring system.

[0030] When sudden settlement is detected, the current crown settlement amount is used as the reference point correction amount and input into the displacement rope data correction model. According to this correction method, this method can dynamically adjust the data of the displacement rope system, eliminate the reference point drift error caused by formation disturbance or other factors, and thus improve the accuracy of the monitoring results. During the correction process, this method also dynamically generates data based on the corrected crown settlement amount and the interpolation algorithm to smooth the data curve of the displacement rope system. This dynamic interpolation method enables the system to generate a smooth corrected data curve in the case of the failure of the visual displacement system or discontinuous data, ensuring the integrity and continuity of the monitoring data. It can not only effectively eliminate the reference point drift error, but also generate reliable corrected data through the dynamic interpolation algorithm when the visual displacement system fails.

[0031] In summary, the tunnel initial crown settlement monitoring method based on machine vision calibration constructs an innovative double-layer monitoring architecture by integrating machine vision dynamic calibration technology and displacement meter data correction, realizing continuous and high-precision monitoring from before tunnel construction to the construction process. It aims to solve the problem in the prior art that the crown settlement of the tunnel cannot be accurately measured throughout the whole process from the initial unexcavated state to the excavation construction.

[0032] Specifically, this method first collects the visual displacement data of the tunnel crown through a visual displacement camera, and uses an adaptive ambient light compensation algorithm and an infrared auxiliary calibration device to ensure that high-quality monitoring data can be obtained even in a complex construction environment (such as interference from dust, water mist, etc.). The visual displacement camera is installed in the supported area 20 to 50 meters behind the tunnel face, and its target is collinear with the borehole orifice position of the displacement rope system, ensuring the consistency of the spatial reference. At the same time, the displacement rope system is pre-buried into the formation above the tunnel through advanced drilling, and the node sensors are distributed in a gradient with equal or unequal intervals, realizing continuous settlement monitoring of the excavation section in front of the tunnel face.

[0033] Secondly, through the change of the Euler rotation matrix, the coordinates of the visual displacement data are unified with the coordinates of the displacement rope system data, solving the problem of possible inconsistent spatial reference between the two. In addition, the data sampling frequency of the displacement rope system is dynamically adjusted according to the crown settlement amount. When the settlement change exceeds the warning value, cubic spline interpolation is used to match the time stamp of the visual displacement system, ensuring the time synchronization. This spatio-temporal registration method not only improves the accuracy of data fusion, but also provides a unified spatio-temporal reference for subsequent settlement analysis.

[0034] Finally, in terms of data correction, the visual displacement data is input into the displacement rope data correction model as the reference point correction amount. By real-time monitoring the changes in the visual displacement data, measurement errors or sudden settlements can be quickly identified, and corresponding correction measures can be taken. When a measurement error is detected, the error data is eliminated, and the stable data obtained from continuous measurements is used for update and replacement processing; when a sudden settlement is detected, the data of the displacement rope system is corrected using the reference point correction amount, thereby eliminating the reference point drift error caused by formation disturbance. In addition, through a dynamic interpolation algorithm, a smooth correction data curve is generated when the visual displacement system fails, ensuring the integrity and continuity of the monitoring data.

[0035] Briefly speaking, the tunnel initial crown settlement monitoring method based on machine vision calibration can not only achieve continuous monitoring from the initial state of the tunnel to the whole process of excavation construction, but also significantly improve the monitoring accuracy and the self-adaptability of the system through the dynamic reference establishment and transfer mechanism. Compared with the existing technologies, the tunnel initial crown settlement monitoring method based on machine vision calibration solves the problems of low monitoring efficiency of traditional total station instruments, insufficient accuracy of single machine vision monitoring in complex environments, and reference point drift of displacement gauges. It also further enhances the reliability and stability of the monitoring system through multi-source data cross-verification and spatio-temporal reference synchronization. This high-precision and high-reliability monitoring system provides strong technical support for the safety and quality of tunnel construction, and has significant practical value and broad application prospects.

[0036] Please refer to Figure 4 , the second embodiment of the present invention provides a tunnel initial crown settlement monitoring device based on machine vision calibration, which includes: A preprocessing unit 201, configured to obtain the visual displacement data collected by a preset visual displacement system and the displacement rope system data collected by a displacement rope system, and preprocess the visual displacement data and the displacement rope system data to obtain the corrected visual displacement data and the crown settlement amount; An alignment unit 202, configured to perform data fusion spatio-temporal registration processing according to the corrected visual displacement data and the crown settlement amount, so that the visual displacement data and the displacement rope system data are aligned in space and synchronized in time; A correction unit 203, configured to input the visual displacement data into a displacement rope data correction model as a reference point correction amount, and use the displacement rope data correction model to correct the aligned displacement rope system data to obtain the settlement measurement result of the excavation section in front of the tunnel face.

[0037] The above are the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements are also regarded as the protection scope of the present invention.

Claims

1. A method for monitoring the initial vault settlement of a tunnel based on machine vision calibration, characterized in that, Including: Obtain the real-time dynamic visual displacement data collected by a preset visual displacement system, and obtain the vault settlement of the tunnel by acquiring the displacement rope system data collected by the displacement rope system pre-embedded in the tunnel in advance, and preprocess the visual displacement data and the displacement rope system data to obtain the corrected visual displacement data and the vault settlement; Perform data fusion spatio-temporal registration processing based on the corrected visual displacement data and the vault settlement, so that the visual displacement data and the displacement rope system data are aligned in space and synchronized in time; Input the visual displacement data as the reference point correction amount into the displacement rope system data dynamic correction model, and use the displacement rope system data correction model to perform dynamic correction processing on the aligned displacement rope system data to obtain the settlement measurement result of the excavation section in front of the heading face.

2. The tunnel initial vault settlement monitoring method based on machine vision calibration according to claim 1, wherein The visual displacement system is a visual displacement camera, which includes an infrared anti-interference module. The visual displacement camera is configured in a stable area where the tunnel support has been formed and does not displace at a preset length range behind the heading face of the tunnel to be monitored, and its corresponding target is arranged at the vault position within the excavated area behind the heading face of the tunnel to be monitored. Among them, the preset length range is 20 - 50m.

3. The method for monitoring the initial vault settlement of a tunnel based on machine vision calibration according to claim 2, wherein The displacement rope system is a displacement rope fixed on a steel pipe. The displacement rope is pre-embedded into the strata above the tunnel by means of advance drilling. The displacement rope is composed of node sensors with equal or unequal spacing distributed in a gradient manner. Among them, the position of the target coincides with the borehole orifice position of the displacement rope system.

4. The method for monitoring the initial vault settlement of a tunnel based on machine vision calibration according to claim 2, characterized in that, Preprocess the visual displacement data to obtain the corrected visual data, specifically: Judge whether the current ambient light intensity is less than a preset value; If so, activate the infrared anti-interference module, perform infrared supplementary lighting, and perform adaptive environment compensation processing on the collected visual displacement data to obtain the corrected visual data; If not, directly perform adaptive environment compensation processing on the collected visual displacement data to obtain the corrected visual data.

5. The tunnel initial vault settlement monitoring method based on machine vision calibration according to claim 4, characterized in that The adaptive environment compensation processing is specifically: Based on the non - linear compensation model, calculate the corrected visual displacement data, and the formula is: , where is the gray value of the camera, is the ambient light intensity, is the dark current reference value, and are both fitting parameters.

6. The tunnel initial vault settlement monitoring method based on machine vision calibration according to claim 3, characterized in that Preprocess the displacement rope system data to obtain the vault settlement, specifically: Obtain the inclination angle change data at the position collected by the node sensor, and take the preset reference point as the starting point for trapezoidal integration processing to calculate the crown settlement amount at any position of the tunnel to be monitored. The calculation formula is as follows: , where is the crown settlement amount at the i-th point, is the i-th original inclination angle change data, is the (i - 1)-th original inclination angle change data, is the layout spacing of the node sensors.

7. The method for monitoring the initial vault settlement of a tunnel based on machine vision calibration according to claim 6, wherein, Perform data fusion spatio-temporal registration processing based on the corrected visual displacement data and the vault settlement, specifically: Perform Euler rotation matrix transformation processing on the corrected visual displacement data so that the coordinates of the corrected visual data are unified with the coordinates of the vault settlement; Adjust the data sampling frequency of the displacement rope system according to the change in the vault settlement. Among them, when the settlement change of the vault settlement is within the preset normal state, the data sampling frequency of the displacement rope system is the initially set value. When the settlement change of the vault settlement exceeds the preset warning value, the acquisition frequency will be automatically adjusted dynamically to encrypt the acquisition frequency. The displacement rope system will perform cubic spline interpolation processing on the displacement rope system data according to the real-time dynamic acquisition frequency to match the time stamp of the visual displacement system for cubic spline interpolation to match the time stamp of the visual displacement system ; Set the time-axis node sequence as , and define the recurrence formula for the j-th cubic B-spline basis function as follows: , , where k = 3 represents a cubic spline, is the 0-th order B-spline basis function and serves as the starting point for recurrence, is the j-th k-th order B-spline basis function, is the j-th k - 1-th order B-spline basis function, is the j + 1-th k - 1-th order B-spline basis function. Construct a cubic spline interpolation curve with k = 3 to obtain the final basis function ; Determine the time non-uniformity point allocation rule adapted to the excavation process, dynamically adjust the data acquisition time interval, and the allocation rule is: , where is the dynamic acquisition time interval of the displacement rope system data; Based on the final basis function and the assignment rule, according to the data point sequence of the displacement rope system , construct the difference function: , where m is the number of original data points of the displacement rope system, is the interpolation coefficient to be solved, and 2 control points are extended to meet the boundary conditions; Coefficient solving processing is carried out according to the difference function, and the formula is: , and it is marked as Ac = S, where is the value of the (m + 2)-th cubic B-spline basis function at the time node ; is the value of the (m + 2)-th cubic B-spline basis function at the time node ; is the value of the (m + 2)-th cubic B-spline basis function at the time node ; is the interpolation coefficient of the first basis function to be solved; is the interpolation coefficient of the second basis function to be solved; is the interpolation coefficient of the (m + 2)-th basis function to be solved; is the settlement data actually measured by the displacement rope system at the time node ; is the settlement data actually measured by the displacement rope system at the time node ; is the settlement data actually measured by the displacement rope system at the time node ; is the time tag of the m-th data point collected by the displacement rope system. A is the coefficient matrix composed of the values of the basis functions at each time node, , c is the coefficient vector to be solved, , S is the vector composed of the settlement data actually collected by the displacement rope system, ; According to the constraint conditions , the least squares solution with constraints is obtained , , where the constraint matrix C corresponds to the second derivative condition and the Lagrange multiplier method is used for solution; Based on the solved least squares solution with constraints, high-frequency data synchronization processing is performed for the timestamps of the vision displacement system , and the corresponding synchronized displacement rope system data is as follows: , where is the interpolation coefficient of the j-th basis function to be solved.

8. The method for monitoring the initial vault settlement of a tunnel based on machine vision calibration according to claim 1, wherein, Input the visual displacement data as the reference point correction amount into the displacement rope data correction model, and use the displacement rope data correction model to correct the aligned displacement rope system data to eliminate the drift error caused by formation disturbance at the reference point of the displacement rope system, and obtain the vault settlement measurement result of the excavation section in front of the heading face, specifically: The visual displacement system detects the current visual displacement data and the visual displacement data of the previous moment in real time. When the visual displacement system measures data that suddenly changes, it automatically triggers continuous data collection. Based on the continuously measured data set, the standard deviation evaluation method is used to determine whether the current sudden change data is a measurement error or sudden settlement. When a measurement error occurs, the erroneous data value is eliminated and the continuous measurement stable data is updated. Alternative treatment; when sudden settlement occurs, the vault settlement is used as the reference point correction amount When the visual displacement system lens is blocked and the system fails, data is dynamically generated through an interpolation algorithm , to smoothly correct the data curve of the displacement rope system. The formula for the interpolation algorithm to dynamically generate reference point data is: , where is the displacement measurement at the current moment and the displacement measurement at the previous moment is the time interval between them, is the displacement measurement at the next moment and the displacement measurement at the previous moment is the time interval between them; Correction amount based on reference point To correct the crown settlement, the formula for the displacement rope data correction model is: , where is the settlement amount of the i-th point.

9. A tunnel initial vault settlement monitoring device based on machine vision calibration, characterized in that, Including: A preprocessing unit, which is used to obtain the visual displacement data collected by a preset visual displacement system and the displacement rope system data collected by the displacement rope system, and preprocess the visual displacement data and the displacement rope system data to obtain the corrected visual displacement data and the vault settlement; An alignment unit for performing data fusion spatio-temporal registration processing according to the corrected visual displacement data and the vault settlement amount, so that the visual displacement data and the displacement rope system data are spatially aligned and temporally synchronized; A correction unit for inputting the visual displacement data as a reference point correction amount into a displacement rope data correction model, and using the displacement rope data correction model to correct the aligned displacement rope system data to obtain the settlement measurement result of the excavation section in front of the tunnel face.

Images