An intelligent monitoring system for tunnel construction deformation

Abstract

The present invention belongs to the technical field of tunnel construction deformation monitoring, and specifically relates to an intelligent monitoring system for tunnel construction deformation, comprising a multi-point deformation monitoring module, a spatiotemporal data fusion module, a spatial correlation analysis module and an intelligent early warning module. A dynamic spatial deformation database containing a time series is constructed by performing multi-point deformation monitoring on tunnel surrounding rocks, and the spatial deformation correlation between monitoring points is analyzed based on the database to construct a spatial deformation correlation network of the tunnel surrounding rocks. When the spatial deformation correlation network exceeds a preset safety threshold, an early warning display is performed, and abnormal deformation trends can be captured in time, the early warning lag time can be significantly shortened, and construction safety can be improved. At the same time, when an early warning is triggered based on tunnel surrounding rock deformation monitoring, local early warnings and global early warnings are distinguished, and early warning results are displayed in three dimensions, which is helpful for priority management, so that construction personnel can take targeted emergency measures according to the early warning level.

Description

Technical Field

[0001] The invention belongs to the technical field of tunnel construction deformation monitoring, and in particular relates to an intelligent monitoring system for tunnel construction deformation. Background Art

[0002] With the acceleration of urbanization, the demand for traffic efficiency in densely populated areas is increasing. Tunnel construction has become a key means to alleviate traffic congestion and optimize the transportation network. During the tunnel construction process, the surrounding rock, as the main geological medium supporting the tunnel structure, is prone to deformation due to changes in external loads (such as excavation unloading) due to its inherent heterogeneity and complexity. Surrounding rock deformation may further cause engineering disasters such as collapse, roof fall or water inrush, posing a serious threat to construction safety and engineering quality. Therefore, real-time monitoring of surrounding rock deformation is particularly necessary in tunnel construction.

[0003] In the prior art, there are already some technical solutions for monitoring tunnel surrounding rock deformation. For example, China Invention Patent Publication No. CN101458069B proposes a tunnel surrounding rock deformation monitoring method and monitoring system. By fixing the laser on the inner wall of the stable tunnel surrounding rock and installing a photosensitive displacement signal monitor on the initial support of the unstable surrounding rock, the surrounding rock deformation displacement data is collected in real time. After analysis by the signal processing terminal, an alarm is triggered when the dangerous deformation value is reached or exceeded. This solution helps to reduce the risk of collapse in tunnel construction and improve operational safety.

[0004] In addition, China's invention patent publication number CN108050952B provides a method for monitoring tunnel section deformation using a tunnel section deformation monitoring system. The method calculates the tunnel crown settlement value, crown convergence value and waist convergence value through a sub-controller, and converts them into language evaluation values, thereby providing early warning information for construction, enabling workers to understand the tunnel safety status in real time and detect hidden dangers in advance.

[0005] However, whether it is the laser displacement monitoring method in the first technical solution or the quantitative evaluation of tunnel section deformation in the second technical solution, the monitoring of tunnel surrounding rock deformation is limited to the displacement changes at discrete positions, lacking in-depth analysis of the spatial propagation between monitoring points and the correlation of overall spatial deformation. Due to the characteristics of heterogeneity and complex stress field of tunnel surrounding rock, its deformation often has a certain propagation correlation between different positions. Ignoring this spatial correlation for deformation warning may delay the identification and response to potential risks, and even lead to misjudgment of deformation trends, thereby affecting the safety and accuracy of construction decisions. Summary of the invention

[0006] The purpose of the present invention is to improve the deficiencies in the prior art and provide an intelligent monitoring system for tunnel construction deformation, which can realize timely and accurate early warning of tunnel construction risks by adding deformation spatial propagation correlation analysis of different monitoring points in tunnel surrounding rock deformation monitoring.

[0007] The purpose of the present invention can be achieved through the following technical solutions: an intelligent monitoring system for tunnel construction deformation, comprising the following modules: a multi-point deformation monitoring module: the deformation monitoring equipment is deployed on the tunnel surrounding rock surface according to a determined regional layout density, and is used to synchronously collect deformation data of each monitoring point.

[0008] Spatiotemporal data fusion module: The deformation data of the monitoring points collected by the deformation monitoring equipment are spatially mapped to build a dynamic spatial deformation database containing time series.

[0009] Spatial correlation analysis module: Based on the dynamic spatial deformation database containing time series, the dominant-slave spatial deformation correlation modeling method is used to analyze the spatial deformation correlation between monitoring points, and the spatial deformation correlation network of the tunnel surrounding rock is constructed.

[0010] Intelligent early warning module: When the spatial deformation correlation network of the tunnel surrounding rock exceeds the set safety threshold, an early warning display will be given through the three-dimensional visualization interface.

[0011] As a preferred implementation of the above scheme, the analysis of spatial deformation association between monitoring points using the dominant-slave spatial deformation association modeling method includes the following steps: traversing all monitoring points in the tunnel surrounding rock and grouping them in pairs to form multiple control groups.

[0012] The time series deformation data of each monitoring point are extracted from the dynamic spatial deformation database containing time series. Correlation analysis is performed on the time series deformation data of two monitoring points in each control group, and the deformation correlation index is calculated.

[0013] The deformation correlation index calculated for each control group is compared with the preset correlation threshold, and the control groups that meet the conditions are screened out to form several associated monitoring point groups.

[0014] The causal relationship analysis of the associated monitoring point group is carried out to identify the dominant monitoring points that play a leading role in deformation and the subordinate monitoring points affected by them, thereby clarifying the dominant-slave relationship of deformation propagation.

[0015] As a preferred implementation of the above scheme, the causal relationship analysis of the associated monitoring point group refers to the following process: in a coordinate system with time as the horizontal axis and deformation as the vertical axis, the time series deformation data of two monitoring points in the associated monitoring point group are respectively plotted as two deformation change curves.

[0016] The inflection points on the two deformation change curves are identified and marked, and the inflection points on the two curves are mapped one by one to form a plurality of inflection point groups.

[0017] For each inflection point group, the collection time of the corresponding inflection points in the two deformation change curves is extracted, and the proportion of each monitoring point with an earlier collection time in the inflection point group is counted. The monitoring point with the largest proportion is selected and identified as the dominant monitoring point of the associated monitoring point group, while the other monitoring point is identified as a subordinate monitoring point.

[0018] The causal relationship results of all associated monitoring point groups are compared and analyzed. If it is found that the subordinate monitoring point of a certain associated monitoring point group serves as the dominant monitoring point in another associated monitoring point group, the two associated monitoring point groups are merged to form a new associated monitoring point group.

[0019] In the new group of associated monitoring points, only the first dominant monitoring point is retained as the dominant monitoring point, and all other monitoring points are identified as subordinate monitoring points.

[0020] As a preferred implementation of the above scheme, the process of constructing the spatial deformation association network of the tunnel surrounding rock is as follows: time lag relationship analysis is performed on the subordinate monitoring points in the associated monitoring point group, and based on this, deformation association lines are established from the dominant monitoring points to the subordinate associated monitoring points.

[0021] Assign attribute information to each deformation association line.

[0022] All deformation association lines are integrated to form a global spatial deformation association network.

[0023] Use visualization tools to display spatial deformation association networks.

[0024] As a preferred implementation of the above scheme, when the spatial deformation association network of the tunnel surrounding rock exceeds the set safety threshold, an early warning display is performed through a three-dimensional visualization interface. See the following process: a corresponding safety threshold range is set for each attribute of the attribute information of the deformation association line.

[0025] During the tunnel construction process, the attribute information of each deformation association line in the spatial deformation association network of the tunnel surrounding rock is monitored in real time.

[0026] If the attribute information of a deformation association line exceeds the preset safety threshold, a local warning is triggered.

[0027] If the attribute information of multiple deformation association lines exceeds the safety threshold at the same time, a global warning is triggered.

[0028] When a local or global warning is triggered, the warning information is displayed through a three-dimensional visualization interface.

[0029] Combining all the above-mentioned technical solutions, the positive effects of the present invention are as follows: 1. The present invention constructs a dynamic spatial deformation database containing a time series by performing multi-point deformation monitoring on the tunnel surrounding rock, and analyzes the spatial deformation correlation between the monitoring points based on the database, and constructs a spatial deformation correlation network of the tunnel surrounding rock. When the spatial deformation correlation network exceeds the preset safety threshold, an early warning display is performed, which can capture abnormal deformation trends in time, significantly shorten the early warning lag time, and improve construction safety.

[0030] 2. When triggering an early warning based on tunnel surrounding rock deformation monitoring, the present invention distinguishes between local and global early warnings and displays the early warning results in three-dimensional visualization, which helps with priority management and enables construction personnel to take targeted emergency measures according to the early warning level. At the same time, the three-dimensional visualization makes the early warning information more intuitive, reduces the time for understanding, and thus speeds up decision-making and response. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0032] Figure 1 It is a schematic diagram of system module connection of the present invention.

[0033] Figure 2 This is a diagram of the implementation steps of analyzing the spatial deformation association between monitoring points using the dominant-slave spatial deformation association modeling method in the present invention.

[0034] Figure 3 This is a flow chart of the cause-effect relationship analysis of the associated monitoring point group in the present invention. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] The present invention proposes an intelligent monitoring system for tunnel construction deformation, which comprises a multi-point deformation monitoring module, a spatiotemporal data fusion module, a spatial correlation analysis module and an intelligent early warning module.

[0037] See also Figure 1 As shown, the multi-point deformation monitoring module collects deformation data of each monitoring point through deformation monitoring equipment, and transmits these discrete real-time monitoring data to the spatiotemporal data fusion module.

[0038] The dynamic spatial deformation database generated by the spatiotemporal data fusion module is passed to the spatial correlation analysis module as input data.

[0039] The spatial deformation association network and related analysis results generated by the spatial association analysis module are transmitted to the intelligent warning module.

[0040] The several modules that constitute the above system flow in sequence from collection, fusion, analysis to early warning to form a complete processing chain. There is a strong dependency between the modules. The output of the previous module is the input of the next module. Through the close connection between the modules, the system realizes the intelligent management of the whole process from data collection to analysis and then to early warning, providing efficient and accurate safety guarantee for tunnel construction.

[0041] In a specific implementation, the multi-point deformation monitoring module is deployed on the tunnel surrounding rock surface by the deformation monitoring equipment according to a determined regional layout density, and is used to synchronously collect deformation data of each monitoring point.

[0042] It should be pointed out that deformation monitoring equipment refers to a type of professional instrument or device specifically used to sense and record the deformation information of the tunnel surrounding rock surface in real time. These devices can accurately capture the deformation characteristics of the surrounding rock such as displacement, strain and settlement during the construction process, and provide key data support for the evaluation and analysis of the stability of the surrounding rock. Specifically, deformation monitoring equipment may include but is not limited to the following types: displacement monitoring equipment (such as laser scanners), strain monitoring equipment (such as fiber grating sensors) and settlement monitoring equipment (such as levels), and one or more of these functions can be integrated into one according to actual needs to achieve multi-dimensional deformation monitoring.

[0043] In the manner in which the above scheme can be implemented, the determined regional layout density is obtained as follows: a three-dimensional geometric model of the tunnel surrounding rock is constructed according to the design drawings of the tunnel and the geological exploration data.

[0044] It is important to understand that geological exploration data is an important basis for building a three-dimensional geometric model of the tunnel surrounding rock. These data can reflect key information such as the geological structure, rock and soil properties, and hydrological conditions of the tunnel area. Specifically, the geological exploration data are shown in Table 1.

[0045] Table 1: Some geological exploration data

[0046]

[0047] The above geological exploration data can be obtained through a variety of technical means, exemplified by coring and geophysical exploration. Coring refers to extracting rock and soil samples through drilling and conducting detailed analysis of their physical and mechanical properties in the laboratory; while geophysical exploration is based on the changes in the physical field, using technical means such as seismic wave method, resistivity method or radar detection to conduct non-contact detection and inversion analysis of underground geological structure and lithology distribution.

[0048] The three-dimensional geometric model is divided into finite element grids, and each grid cell corresponds to a specific rock area.

[0049] The historical load data of similar tunnel construction are input into the 3D geometric model, and the numerical simulation of the tunnel construction process is carried out according to the set time step.

[0050] It should be added that the similar tunnels mentioned above refer to tunnel projects that are similar or identical to the current tunnels in the following aspects: geological conditions: similar surrounding rock type, stratum structure, groundwater conditions, etc.

[0051] Design parameters: tunnel section shape, size, burial depth, support structure, etc. are similar.

[0052] Construction method: Use similar construction techniques (such as drilling and blasting, shield tunneling, TBM, etc.).

[0053] By selecting “similar tunnels” with similar characteristics to the current tunnel, the reference value and applicability of historical data can be improved.

[0054] It should also be added that historical load data refers to a data set of various external and internal forces and related parameters recorded during the construction of similar tunnels. These data can reflect the actual load conditions borne by the tunnel surrounding rock and support structure during construction. The specific load data are shown in Table 2.

[0055] Table 2: Some historical load data

[0056]

[0057] It should be further added that the time step refers to the time interval divided when the entire construction process is discretized according to the time dimension. It is an important parameter in numerical simulation and is used to control the time resolution of the calculation, thereby capturing the dynamic response of the surrounding rock during the construction process.

[0058] The deformation gradient distribution of each finite element grid of the tunnel surrounding rock is extracted through numerical simulation results.

[0059] The deformation gradient of the finite element mesh is matched according to the preset mapping relationship between the deformation gradient and the layout density, so as to determine the layout density of the deformation monitoring equipment in different areas of the tunnel surrounding rock.

[0060] In the specific example implementation of the above operation, it is assumed that three types of deformation gradients are pre-set, namely high deformation gradient, medium deformation gradient and low deformation gradient, and the corresponding deformation monitoring equipment layout density is assigned to each type of deformation gradient according to the predefined mapping relationship between deformation gradient and layout density. Specifically: High deformation gradient areas correspond to higher layout densities, and the layout spacing of deformation monitoring equipment is set to 0.5 meters to ensure high-precision monitoring of areas with severe deformation. Medium deformation gradient areas correspond to medium layout densities, and the layout spacing of deformation monitoring equipment is set to 1 meter to balance monitoring accuracy and cost. Low deformation gradient areas correspond to lower layout densities, and the layout spacing of deformation monitoring equipment is set to 2 meters to meet basic monitoring needs for areas with slower deformation.

[0061] Through the above mapping relationship, the finite element mesh deformation gradient extracted from the numerical simulation results is matched with the corresponding deformation monitoring equipment layout density, so as to determine the sensor layout scheme in different areas of the tunnel surrounding rock. This method can achieve the optimal configuration of sensor layout according to the actual deformation characteristics of the tunnel surrounding rock, ensuring that key areas are fully monitored while reducing the cost and complexity of the overall monitoring system.

[0062] It should be explained that the layout density of the above-mentioned tunnel surrounding rock monitoring points is based on the actual geometric structure, physical and mechanical properties of the surrounding rock and the load change law during the historical construction process. Finite element analysis is used to simulate the actual construction environment and surrounding rock response, thereby realizing the targeted optimization layout of deformation monitoring equipment in different areas.

[0063] Specifically, this method emphasizes the use of high-density deployment strategies in key areas with large deformation gradients (such as vaults, side walls, fault zones, etc.) to fully capture the subtle deformation characteristics of these parts. Compared with the traditional uniform deployment method, this method effectively avoids the problems of insufficient monitoring in key areas and data redundancy in non-key areas. While ensuring the monitoring effect, it significantly reduces the number of unnecessary sensors, thereby reducing hardware investment and installation and maintenance costs, and improving the economy and efficiency of the monitoring system.

[0064] It should be understood that the core idea of ​​the finite element analysis mentioned above is to discretize a complex continuum (such as tunnel surrounding rock) into multiple simple units (i.e., finite element meshes) and analyze the mechanical response of each unit by solving the control equations. In this process, the deformation gradient is used as a tensor that describes the rate of change of deformation in space and is used to quantify the deformation difference between different positions inside the object. With the help of the finite element method, the local deformation gradient of each mesh can be calculated. The calculation of the deformation gradient is based on a series of control equations, including equilibrium equations, geometric equations, and constitutive equations, which together describe the mechanical behavior of the surrounding rock under external loads. The specific calculation method belongs to the scope of the prior art and will not be elaborated in detail here.

[0065] As a specific implementation of the above solution, the deformation data of the monitoring point may include information such as displacement, strain and settlement of the monitoring point. Specifically, a single type or multiple types of data may be selected for collection according to monitoring requirements.

[0066] In further implementation, the spatiotemporal data fusion module spatially maps the deformation data of the monitoring points collected by the deformation monitoring equipment and constructs a dynamic spatial deformation database containing time series.

[0067] In the preferred operation of the above implementation, the deformation data of the monitoring points collected by the deformation monitoring equipment are spatially mapped according to the following process: a three-dimensional coordinate system is defined on the three-dimensional geometric model of the tunnel surrounding rock.

[0068] It should be noted that the definition of the three-dimensional coordinate system for the tunnel surrounding rock model usually adopts the rectangular coordinate system or cylindrical coordinate system, because it is convenient to describe the spatial position and deformation characteristics of the tunnel. The selection of the origin of the coordinate system should be combined with the geometric characteristics of the tunnel and the construction reference point to ensure the intuitiveness of subsequent calculations and analysis. Common ways to define the origin include: a fixed point on the center line of the tunnel: for example, the center point directly below the tunnel vault is used as the origin.

[0069] Ground point of tunnel entrance or exit: A clear ground point at the tunnel entrance or exit is taken as the origin.

[0070] Geological exploration benchmark point: Use the fixed reference point set during the geological exploration process as the origin.

[0071] Exemplarily, when the three-dimensional coordinate system adopts rectangular coordinates, the directions of the coordinate axes are as follows: X-axis: usually defined along the longitudinal direction of the tunnel (ie, the direction of the centerline of the tunnel), indicating the extension direction of the tunnel.

[0072] Y-axis: perpendicular to the longitudinal direction of the tunnel, indicating the transverse direction of the tunnel (usually pointing to one side wall of the tunnel).

[0073] Z axis: perpendicular to the tunnel plane, indicating the vertical direction (usually upward is positive, in line with the convention of gravity direction).

[0074] The three-dimensional spatial coordinates of each monitoring point are located based on the defined three-dimensional coordinate system to ensure that the coordinates of the monitoring point are consistent with the coordinate system of the three-dimensional geological model.

[0075] A unique identifier is assigned to each grid unit divided into the three-dimensional geometric model of the tunnel surrounding rock.

[0076] The interpolation algorithm is used to perform spatial interpolation operations on the deformation data of the monitoring points, and then the calculated interpolation results are allocated to the corresponding grid units in the three-dimensional geometric model.

[0077] It should be added that before performing spatial interpolation operation on the deformation data of the monitoring points using the interpolation algorithm, the collected deformation data needs to be denoised, filtered, corrected, and time-synchronized.

[0078] It should be explained that since the data collected by deformation monitoring equipment is usually discrete point data, and the three-dimensional geological model is continuous, it is necessary to use an interpolation algorithm to expand the discrete point data to the entire model. Specifically, one of the interpolation algorithms can be selected according to the needs: Inverse distance weighted method: The deformation of any point in the model is calculated based on the distance weight of the monitoring point, which is suitable for situations where local changes are relatively gentle.

[0079] Kriging interpolation method: takes spatial autocorrelation into account, provides more accurate interpolation results, and is suitable for complex geological conditions.

[0080] Radial basis function method: interpolation is achieved by fitting functions, which is suitable for scenarios with high precision requirements.

[0081] In a further preferred operation of the above implementation, the construction of a dynamic spatial deformation database including a time series is implemented as follows: during tunnel construction, deformation data of each monitoring point is collected in real time and stored in a time series.

[0082] The spatial framework based on the three-dimensional geometric model superimposes the time series deformation data of each monitoring point into the corresponding grid unit one by one, thus forming a dynamic spatial deformation database integrating spatial and temporal dimensions.

[0083] The present invention expands the discrete monitoring point data to the entire model by utilizing finite element meshing and interpolation algorithms, thereby ensuring the continuity and integrity of the data in space. At the same time, the time series deformation data of the monitoring points are combined with the spatial information of the monitoring points to achieve synchronous superposition of the deformation data in time and space dimensions. The final dynamic spatial deformation database integrates information in both time and space dimensions, and can fully reflect the spatiotemporal evolution characteristics of the tunnel surrounding rock during the construction process.

[0084] Further implemented, the spatial correlation analysis module is used to analyze the spatial deformation correlation between monitoring points based on the dynamic spatial deformation database containing time series by adopting the dominant-slave spatial deformation correlation modeling method, and to construct the spatial deformation correlation network of the tunnel surrounding rock.

[0085] As an improved implementation of the above solution, see Figure 2 As shown, the dominant-slave spatial deformation association modeling method is used to analyze the spatial deformation association between monitoring points, including the following steps: traversing all monitoring points of the tunnel surrounding rock and grouping them in pairs to form multiple control groups.

[0086] In the above implementation example, it is assumed that 6 monitoring points (A, B, C, D, E, F) are arranged on the surrounding rock surface during the construction of a tunnel. The 6 monitoring points (A, B, C, D, E, F) are grouped in pairs to form multiple control groups. Possible control groups include: (A, B), (A, C), (A, D), (A, E), (A, F), (B, C), (B, D), (B, E), (B, F), (C, D), (C, E), (C, F), (D, E), (D, F), (E, F).

[0087] The time series deformation data of each monitoring point are extracted from the dynamic spatial deformation database containing time series. Correlation analysis is performed on the time series deformation data of two monitoring points in each control group, and the deformation correlation index is calculated.

[0088] The deformation correlation index calculated for each control group is compared with the preset correlation threshold, and the control groups that meet the conditions are screened out to form several associated monitoring point groups.

[0089] For example, the correlation analysis mentioned above can use the Pearson correlation coefficient, and the deformation correlation index obtained is the correlation coefficient. The value range of the Pearson correlation coefficient is [−1, 1], where the closer the absolute value of the correlation coefficient is to 1, the stronger the linear correlation between the time series deformation data of the two monitoring points. The correlation coefficient mainly reflects the deformation synchronization between the monitoring points: when the correlation coefficient of the two monitoring points is high, it means that when one of the monitoring points is deformed, the other monitoring point also shows significant correlated deformation. This phenomenon usually suggests that the two may be affected by similar external loads or geological conditions, or there is some physical connection in space, such as the effect of stress transfer. This provides an important basis for revealing the deformation propagation law and spatial correlation characteristics inside the tunnel surrounding rock.

[0090] Continuing to apply the above examples, the deformation correlation indicators of some control groups are obtained as shown in Table 3.

[0091] Table 3: Deformation correlation indicators of some control groups

[0092]

[0093] When the correlation threshold is set to 0.8, the correlation index of each control group is compared with the threshold, and the associated monitoring point groups that meet the conditions are screened out as (A, B), (B, C), (C, D), and (E, F).

[0094] See also Figure 3 As shown in the figure, a causal relationship analysis is performed on the associated monitoring point group to identify the dominant monitoring points that play a dominant role in deformation and the subordinate monitoring points affected by them, thereby clarifying the dominant-slave relationship of deformation propagation.

[0095] In the above correlation analysis, since the formation of the associated monitoring point group may be affected by physical mechanisms such as stress transfer, it is necessary to further conduct causal relationship analysis on the associated monitoring point group to clarify whether there is a causal effect between the monitoring points and its specific direction of action.

[0096] For specific cause-effect relationship analysis, refer to the following process: in a coordinate system with time as the horizontal axis and deformation as the vertical axis, the time series deformation data of two monitoring points in the associated monitoring point group are respectively plotted as two deformation change curves.

[0097] The inflection points on the two deformation change curves are identified and marked, and the inflection points on the two curves are mapped one by one to form a plurality of inflection point groups.

[0098] It is important to note that the inflection points mentioned above can be considered as points where deformation behavior changes significantly.

[0099] For each inflection point group, the collection time of the corresponding inflection points in the two deformation change curves is extracted, and the proportion of each monitoring point with an earlier collection time in the inflection point group is counted. The monitoring point with the largest proportion is selected and identified as the dominant monitoring point of the associated monitoring point group, while the other monitoring point is identified as a subordinate monitoring point.

[0100] It should be understood that the above principle for identifying the master and slave monitoring points in the associated monitoring point group is: among the several inflection point groups formed by the deformation change curve of the associated monitoring point group, if the deformation change sequence of a certain monitoring point is always ahead of another monitoring point, then the monitoring point can be determined to be the dominant monitoring point, and the other monitoring point is the subordinate monitoring point. This means that the deformation behavior of the subordinate monitoring point is driven or affected by the deformation of the dominant monitoring point to a certain extent, reflecting the causal relationship between the two and the spatiotemporal dependence of deformation propagation.

[0101] Continuing to apply the above example, the causal relationship corresponding to the screened associated monitoring point groups (A, B), (B, C), (C, D), and (E, F) is: in the associated monitoring point group (A, B), A is the dominant monitoring point and B is the subordinate monitoring point.

[0102] In the associated monitoring point group (B, C), B is the dominant monitoring point and C is the subordinate monitoring point.

[0103] In the associated monitoring point group (C, D), C is the dominant monitoring point and D is the subordinate monitoring point.

[0104] In the associated monitoring point group (E, F), E is the dominant monitoring point and F is the subordinate monitoring point.

[0105] The causal relationship results of all associated monitoring point groups are compared and analyzed. If it is found that the subordinate monitoring point of a certain associated monitoring point group serves as the dominant monitoring point in another associated monitoring point group, the two associated monitoring point groups are merged to form a new associated monitoring point group.

[0106] Further application of the above example shows that in the above-mentioned associated monitoring point groups (A, B), (B, C), (C, D), there is an associated intersection in which the subordinate monitoring point serves as the dominant monitoring point in another associated monitoring point group. At this time, (A, B), (B, C), (C, D) are combined to form a new associated monitoring point group (A, B, C, D), while the associated monitoring point group (E, F) does not have such an associated intersection and can be used as an independent associated monitoring point group.

[0107] In the new group of associated monitoring points, only the first dominant monitoring point is retained as the dominant monitoring point, and all other monitoring points are identified as subordinate monitoring points.

[0108] The above method is based on time series deformation data. Through steps such as inflection point identification and collection time proportion statistics, it objectively identifies the dominant monitoring points and subordinate monitoring points, avoiding the deviation that may be caused by subjective judgment. At the same time, by comparing the collection time proportion of the inflection points, it can clearly determine which monitoring point’s change affects another monitoring point, thereby revealing the directionality of deformation propagation.

[0109] As a further improvement of the above scheme, the spatial deformation association network of the tunnel surrounding rock is constructed as follows: the time lag relationship of the subordinate monitoring points in the associated monitoring point group is analyzed, and based on this, a deformation association line pointing from the dominant monitoring point to the subordinate associated monitoring point is established.

[0110] Attribute information is assigned to each deformation association line, wherein the attribute information includes deformation propagation direction, deformation association degree and deformation propagation speed.

[0111] All deformation association lines are integrated to form a global spatial deformation association network.

[0112] Use visualization tools to display spatial deformation association networks.

[0113] The above-mentioned process of analyzing the time lag relationship of the subordinate monitoring points in the associated monitoring point group is as follows: for each associated monitoring point group, the number of subordinate monitoring points contained therein is counted.

[0114] If there are multiple subordinate monitoring points in a certain associated monitoring point group, the correlation coefficient between each subordinate monitoring point and the time series deformation data of the dominant monitoring point at different lag orders is calculated.

[0115] It should be added that the lag order represents the number of time delay steps of the time series of the slave monitoring point relative to the dominant monitoring point. Specifically, it quantifies the time difference between the deformation response of the slave monitoring point and the deformation of the dominant monitoring point, reflecting the time delay characteristics of deformation propagation between the two.

[0116] Assume that the time series of the dominant monitoring point is , the time series of the subordinate monitoring points is .

[0117] For the lag order k, define , that is, the time series of the subordinate monitoring points is delayed backward by k steps.

[0118] calculate and Correlation coefficient , where k is the lag order.

[0119] Under different lag orders, the lag order that makes the correlation coefficient reach the maximum value is found, and this lag order is used as the time lag value of the subordinate monitoring point relative to the dominant monitoring point.

[0120] The specific calculation method of the time lag value involved above has been described in detail in the prior art and will not be repeated here.

[0121] The time lag values ​​between each subordinate monitoring point and the dominant monitoring point are arranged in ascending order, thereby forming a time lag relationship sequence of the subordinate monitoring points. This sequence reflects the time response order of the subordinate monitoring points relative to the dominant monitoring point.

[0122] The above method calculates the correlation coefficient of two time series (deformation data of the dominant monitoring point and the subordinate monitoring point) at different lag orders, and finds the lag order that makes the correlation strongest, so as to quantify the time lag relationship between the subordinate monitoring point and the dominant monitoring point, clarify the time delay characteristics of the deformation of the subordinate monitoring point driven by the dominant monitoring point, and reflect the deformation propagation path from the dominant monitoring point to the subordinate monitoring point in the associated monitoring point group composed of multiple subordinate monitoring points.

[0123] In the example of the associated monitoring point group (A, B, C, D) containing multiple subordinate monitoring points above, the time lag relationship of B, C, and D is B < C < D, so the deformed association line from the dominant monitoring point to the subordinate associated monitoring points is A → B → C → D.

[0124] Furthermore, in the deformed association line attribute information, the deformation propagation direction is the direction from the dominant monitoring point to the subordinate monitoring point; the deformation association degree is the deformation correlation index between the dominant monitoring point and the subordinate monitoring point; the deformation propagation speed can be symbolically represented by the time lag value between the dominant monitoring point and the subordinate monitoring point, where the larger the time lag value, the smaller the deformation propagation speed.

[0125] It should be noted that when there are multiple subordinate monitoring points in the deformed association line, its deformation association degree includes multiple deformation correlation indexes.

[0126] Finally, specifically in implementation, the intelligent early warning module is used to perform early warning display through a three-dimensional visualization interface when the spatial deformation association network of the tunnel surrounding rock exceeds the set safety threshold.

[0127] The specific operation of the above implementation is: for the attribute information of the deformed association line, a corresponding safety threshold range is set for each attribute, and the safety threshold range can set the safety threshold according to the tunnel construction conditions.

[0128] It should be noted that since the deformation propagation direction in the attribute information does not have numerical characteristics, it is difficult to identify anomalies by setting safety thresholds. Therefore, anomaly detection can be carried out by monitoring the change of the deformation propagation direction. Specifically, if the dominant monitoring point no longer points to the subordinate monitoring point, this may reflect two situations: one is that the association strength between the dominant monitoring point and the subordinate monitoring point is significantly weakened or even tends to zero, resulting in the loss of the original association relationship between the two; the other is that the causal relationship between the two has changed, indicating that the deformation propagation mechanism may have changed due to external factors.

[0129] During the tunnel construction process, the attribute information of each deformed association line in the spatial deformation association network of the tunnel surrounding rock is monitored in real time.

[0130] If the attribute information of a certain deformed association line exceeds the preset safety threshold range, a local early warning is triggered.

[0131] If the attribute information of multiple deformed association lines exceeds the safety threshold at the same time, a global early warning is triggered.

[0132] When a local or global early warning is triggered, the early warning information is displayed through a three-dimensional visualization interface.

[0133] In a preferred example, when a local or global warning is triggered, the warning information is intuitively displayed through a three-dimensional visualization interface. Specifically, it includes: highlighting: highlighting abnormal deformation correlation lines and related monitoring points with color coding (such as red indicates exceeding the threshold).

[0134] Dynamic Annotation: Add text or icon annotations to the 3D model to clearly display the specific value and degree of the super-threshold attribute.

[0135] Animation demonstration: Display the deformation propagation path and trend through animation to help users quickly understand the problem.

[0136] When triggering an early warning based on tunnel surrounding rock deformation monitoring, the present invention distinguishes between local and global early warnings and presents the early warning results in three-dimensional visualization, which helps with priority management and enables construction personnel to take targeted emergency measures according to the early warning level. At the same time, the three-dimensional visualization makes the early warning information more intuitive, reduces the time for understanding, and thus speeds up decision-making and response.

[0137] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.

Claims

1. An intelligent monitoring system for tunnel construction deformation, characterized in that: Includes the following modules: Multi-point deformation monitoring module: The deformation monitoring equipment is deployed on the tunnel surrounding rock surface according to the determined regional layout density to synchronously collect deformation data of each monitoring point; Spatiotemporal data fusion module: spatially map the deformation data of the monitoring points collected by the deformation monitoring equipment and build a dynamic spatial deformation database containing time series; Spatial correlation analysis module: Based on the dynamic spatial deformation database containing time series, the dominant-slave spatial deformation correlation modeling method is used to analyze the spatial deformation correlation between monitoring points and construct the spatial deformation correlation network of the tunnel surrounding rock; Intelligent early warning module: When the spatial deformation correlation network of the tunnel surrounding rock exceeds the set safety threshold, an early warning display will be given through the three-dimensional visualization interface.

2. The intelligent monitoring system for tunnel construction deformation according to claim 1, characterized in that: The determined regional layout density is obtained as follows: Build a 3D geometric model of the tunnel surrounding rock based on the tunnel design drawings and geological exploration data; The three-dimensional geometric model is divided into finite element grids, and each grid cell corresponds to a specific rock area; Input historical load data of similar tunnel construction into the 3D geometric model and carry out numerical simulation of the tunnel construction process according to the set time step; The deformation gradient distribution of each finite element grid of the tunnel surrounding rock is extracted through numerical simulation results; The deformation gradient of the finite element mesh is matched according to the preset mapping relationship between the deformation gradient and the layout density, so as to determine the layout density of the deformation monitoring equipment in different areas of the tunnel surrounding rock.

3. The intelligent monitoring system for tunnel construction deformation according to claim 2, characterized in that: The spatial mapping of the deformation data of the monitoring points collected by the deformation monitoring equipment refers to the following process: Define a three-dimensional coordinate system on the three-dimensional geometric model of the tunnel surrounding rock; Locate the three-dimensional spatial coordinates of each monitoring point based on the defined three-dimensional coordinate system; Assign a unique identifier to each grid unit divided into the three-dimensional geometric model of the tunnel surrounding rock; The interpolation algorithm is used to perform spatial interpolation operations on the deformation data of the monitoring points, and then the calculated interpolation results are allocated to the corresponding grid units in the three-dimensional geometric model.

4. The intelligent monitoring system for tunnel construction deformation according to claim 3, characterized in that: The construction of a dynamic spatial deformation database containing time series is implemented as follows: During tunnel construction, deformation data of each monitoring point is collected in real time and stored in time series; The spatial framework based on the three-dimensional geometric model superimposes the time series deformation data of each monitoring point into the corresponding grid unit one by one, thus forming a dynamic spatial deformation database integrating spatial and temporal dimensions.

5. The intelligent monitoring system for tunnel construction deformation according to claim 1, characterized in that: The method of analyzing the spatial deformation association between monitoring points by using the dominant-slave spatial deformation association modeling method comprises the following steps: Traverse all monitoring points in the tunnel surrounding rock and group them into two groups to form multiple control groups; Extract the time series deformation data of each monitoring point from the dynamic spatial deformation database containing time series, perform correlation analysis on the time series deformation data of two monitoring points in each control group, and calculate the deformation correlation index; Compare the deformation correlation index calculated for each control group with the preset correlation threshold, screen out the control groups that meet the conditions, and form several associated monitoring point groups; The causal relationship analysis of the associated monitoring point group is carried out to identify the dominant monitoring points that play a leading role in deformation and the subordinate monitoring points affected by them, thereby clarifying the dominant-slave relationship of deformation propagation.

6. The intelligent monitoring system for tunnel construction deformation according to claim 5, characterized in that: The causal relationship analysis of the associated monitoring point group refers to the following process: In a coordinate system with time as the horizontal axis and deformation as the vertical axis, the time series deformation data of two monitoring points in the associated monitoring point group are respectively plotted as two deformation change curves; Identify and mark the inflection points on the two deformation change curves, and map the inflection points on the two curves one by one to form a number of inflection point groups; For each inflection point group, the collection time of the corresponding inflection points in the two deformation change curves is extracted, and the proportion of each monitoring point with an earlier collection time in the inflection point group is counted. The monitoring point with the largest proportion is selected and identified as the dominant monitoring point of the associated monitoring point group, while the other monitoring point is identified as a subordinate monitoring point. Compare and analyze the causal relationship results of all associated monitoring point groups. If it is found that the subordinate monitoring point of a certain associated monitoring point group is the dominant monitoring point in another associated monitoring point group, then merge the two associated monitoring point groups to form a new associated monitoring point group. In the new group of associated monitoring points, only the first dominant monitoring point is retained as the dominant monitoring point, and all other monitoring points are identified as subordinate monitoring points.

7. The intelligent monitoring system for tunnel construction deformation according to claim 6, characterized in that: The process of constructing the spatial deformation association network of the tunnel surrounding rock is as follows: Conduct time lag relationship analysis on the subordinate monitoring points in the associated monitoring point group, and based on this, establish a deformation association line from the dominant monitoring point to the subordinate associated monitoring point; Assign attribute information to each deformation association line; Integrate all deformation association lines to form a global spatial deformation association network; Use visualization tools to display spatial deformation association networks.

8. The intelligent monitoring system for tunnel construction deformation according to claim 7, characterized in that: The time lag relationship analysis of the subordinate monitoring points in the associated monitoring point group is performed as follows: For each associated monitoring point group, count the number of subordinate monitoring points it contains; If there are multiple subordinate monitoring points in a certain associated monitoring point group, the correlation coefficient between each subordinate monitoring point and the deformation data of the time series of the dominant monitoring point at different lag orders is calculated respectively; Find the lag order that makes the correlation coefficient reach the maximum value under different lag orders, and use the lag order as the time lag value of the subordinate monitoring point relative to the dominant monitoring point; The time lag values ​​between each subordinate monitoring point and the dominant monitoring point are arranged in order from small to large, thereby forming a time lag relationship sequence of the subordinate monitoring points.

9. The intelligent monitoring system for tunnel construction deformation according to claim 7, characterized in that: The attribute information includes deformation propagation direction, deformation correlation degree and deformation propagation speed.

10. The intelligent monitoring system for tunnel construction deformation according to claim 9, characterized in that: When the spatial deformation correlation network of the tunnel surrounding rock exceeds the set safety threshold, the warning display is performed through the three-dimensional visualization interface. See the following process: According to the attribute information of the deformation association line, a corresponding safety threshold range is set for each attribute; During the tunnel construction process, the attribute information of each deformation association line in the spatial deformation association network of the tunnel surrounding rock is monitored in real time; If the attribute information of a certain deformation association line exceeds the preset safety threshold range, a local warning is triggered; If the attribute information of multiple deformation association lines exceeds the safety threshold at the same time, a global warning is triggered; When a local or global warning is triggered, the warning information is displayed through a three-dimensional visualization interface.

Images