Tunnel stability risk assessment method and system based on data analysis

Abstract

The present invention discloses a tunnel stability risk assessment method and system based on data analysis, which relates to the technical field of tunnel risk analysis, and constructs a finite element simulation model for tunnel stability analysis; analyzes tunnel structure record data to form multiple data groups, and classifies these data groups by similarity to obtain reference tunnel characteristic factor data groups. Then, these reference characteristic factors are imported into the finite element simulation model as input parameters to obtain the performance results of the model, and the results are subjected to stability risk analysis to obtain risk assessment results; the scheme also extracts and simplifies the internal surface of the tunnel in the simulation model, constructs an initial tunnel internal structure model, and obtains a reference tunnel internal structure model; by constructing a tunnel internal structure model for comparison and comparing it with the reference model, the above technical scheme of the present invention realizes accurate and efficient assessment of tunnel stability, and provides a strong guarantee for the safe construction and operation of tunnel engineering.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel risk analysis, and in particular to a tunnel stability risk assessment method and system based on data analysis. Background Art

[0002] In today's society, with the acceleration of urbanization and the continuous improvement of transportation infrastructure, tunnel projects, as important channels connecting cities and regions, are increasing in scale and number. Tunnel projects not only carry huge traffic flows, but also often pass through complex and changeable geological environments. Therefore, their stability has become the focus of attention in the engineering and academic circles.

[0003] Traditional tunnel stability risk assessment methods mainly rely on expert experience and on-site investigations. Experts will conduct qualitative or quantitative assessments of tunnel stability based on factors such as the tunnel's geological conditions, construction methods, and support structures, combined with their own professional knowledge and experience. However, this method has many limitations. On the one hand, expert experience is highly subjective, and different experts may come up with completely different assessment results; on the other hand, on-site investigations require a lot of manpower, material resources, and time, and are limited by on-site conditions, making it difficult to fully and accurately obtain relevant information on tunnel stability. Summary of the invention

[0004] The purpose of the present invention is to provide a stability risk assessment method and system capable of performing in-depth data analysis on tunnel stability.

[0005] The present invention discloses a tunnel stability risk assessment method based on data analysis, comprising:

[0006] Construct a finite element simulation model for tunnel stability analysis;

[0007] Acquire a number of tunnel structure record data, analyze the tunnel structure record data, determine a tunnel characteristic factor data group, each tunnel characteristic factor data group includes a number of tunnel characteristic factor parameters, classify the several tunnel characteristic factor data groups by similarity, and perform averaging calculation on each group of classified tunnel characteristic factor data groups to obtain a reference tunnel characteristic factor data group;

[0008] Each reference tunnel characteristic factor parameter in the reference tunnel characteristic factor data group is used as an input parameter and input into a finite element simulation model for tunnel stability analysis to obtain a finite element simulation model performance, and stability risk analysis is performed on the finite element simulation model performance to obtain a risk assessment result;

[0009] The internal surface of the tunnel represented by the finite element simulation model is extracted and simplified to obtain the initial tunnel internal structure model, and the rock quality performance and joint network performance at different positions are determined, and the corresponding performance is configured on the initial tunnel internal structure model to obtain the reference tunnel internal structure model;

[0010] When conducting feature analysis on the current tunnel, a comparison tunnel internal structure model is constructed, and the comparison tunnel internal structure model is compared with different reference tunnel internal models to find a matching reference tunnel internal model, and the risk assessment result corresponding to the reference tunnel internal model is used as the stability risk assessment result of the current tunnel.

[0011] In some embodiments of the present invention, a method for constructing a finite element simulation model for tunnel stability analysis includes:

[0012] According to the actual size of the tunnel, determine the scope of the finite element simulation model for tunnel stability analysis, and set boundary conditions for the finite element simulation model for tunnel stability analysis;

[0013] According to the actual material of the tunnel, the material properties are set using the finite element simulation model for tunnel stability analysis, including density, elastic modulus and Poisson's ratio;

[0014] Draw the tunnel outline in the finite element simulation software according to the actual size and shape of the tunnel, and add geological structures, including rock layers, faults and cracks;

[0015] The finite element simulation model is meshed for tunnel stability analysis and loads are applied.

[0016] In some embodiments of the present invention, a method for similarity classification of a plurality of tunnel characteristic factor data sets includes:

[0017] Determine the parameter difference between the corresponding tunnel characteristic factor parameters, set a parameter difference interval for the tunnel characteristic factor parameters, each parameter difference interval is correspondingly set with a corresponding similarity parameter, and determine the similarity parameter corresponding to the tunnel characteristic factor parameter by analyzing the parameter difference interval to which the parameter difference belongs;

[0018] Analyze the tunnel characteristic factor parameters related to the tunnel direction in the tunnel characteristic factor data group, determine the tunnel direction characteristics, construct a tunnel direction polyline, and configure different tunnel characteristic factor parameters at corresponding positions on the tunnel direction polyline based on the position nodes to which other tunnel characteristic factor parameters belong;

[0019] Comparing the tunnel direction polylines, including comparing the shape similarity parameters between the tunnel direction polylines, and analyzing the parameter differences of other tunnel characteristic factor parameters corresponding to different position nodes, and determining the similarity parameters corresponding to each tunnel characteristic factor parameter;

[0020] Based on the shape similarity parameters and the continuous performance of similarity parameters of each tunnel characteristic factor parameter on the tunnel strike polyline, the similarity between the tunnel characteristic factor data groups is determined, and based on the similarity, it is determined whether the two are classified into the same category.

[0021] In some embodiments of the present invention, the method for determining the similarity between tunnel characteristic factor data sets includes:

[0022] Compare the similar parameter corresponding to the tunnel characteristic factor parameter with the preset value, and if it is greater than or equal to the preset value, mark the tunnel characteristic factor parameter as similar;

[0023] Based on the shape similarity parameters and the proportion of similar marks of characteristic factor parameters of the same type of tunnels on the tunnel strike line, the similarity between the tunnel characteristic factor data groups is determined;

[0024] Among them, the expression for calculating the similarity is: ;

[0025] in, For similarity, The length of the polyline between the tunnel direction polylines whose approach features meet the preset standards. is the sum of the total lengths of the tunnel's direction polyline, is the influence adjustment coefficient of the proportion of similar broken line lengths, Adjust the constant for the influence of the proportion of the length of the similar broken lines, is the shape similarity parameter weight adjustment coefficient, For the The similarity ratio of the characteristic factor parameters of each type of tunnel, For the The influence adjustment coefficient of the characteristic factor parameters of each type of tunnel, For the The influence adjustment constant of the characteristic factor parameters of each type of tunnel, For the The weight adjustment coefficient of each type of tunnel characteristic factor parameter, It is the total number of tunnel characteristic factor parameters other than the tunnel direction.

[0026] In some embodiments of the present invention, the method for extracting and simplifying the inner surface of a tunnel of a finite element simulation model includes:

[0027] A number of position acquisition points are randomly set on the inner surface of the tunnel of the finite element simulation model, and adjacent position acquisition points are connected by lines, and the surface formed by the adjacent connecting lines is determined to obtain an initial reference tunnel inner structure model;

[0028] A number of dynamic change circles are randomly constructed in the tunnel space of the initial reference tunnel internal structure model, and the diameter of each dynamic change circle dynamically increases until the dynamic change circle is completely restricted by the position acquisition point, and the center point of the dynamic change circle is determined, and the center points are connected to obtain the tunnel strike line of the initial reference tunnel internal structure model.

[0029] In some embodiments of the present invention, the method for constructing a tunnel internal structure model for comparison includes:

[0030] Laser scanning technology is used to scan the interior of the tunnel to obtain point cloud data inside the tunnel, and based on the point cloud data inside the tunnel, several position collection points are determined, and adjacent position collection points are connected, and the surface formed by adjacent connecting lines is determined to obtain an initial comparison tunnel internal structure model, and the tunnel strike line of the initial comparison tunnel internal structure model is determined to obtain a comparison tunnel internal structure model.

[0031] In some embodiments of the present invention, the method of comparing the comparison tunnel internal structure model with different reference tunnel internal structure models includes:

[0032] Align and overlap the tunnel strike lines of the comparison tunnel internal structure model and the reference tunnel internal structure model, and compare the overlap degree of the initial comparison tunnel internal structure model and the reference tunnel internal structure model at the same time. If the overlap degree is greater than or equal to a preset value, it is determined that the reference tunnel internal structure model at this time meets the initial adaptation requirements for the comparison tunnel internal structure model;

[0033] Call the reference tunnel characteristic factor parameters corresponding to the reference tunnel internal structure model that meets the initial adaptation requirements, and compare the parameter difference between each reference characteristic factor parameter and the characteristic reference factor parameter currently collected in the tunnel. If the parameter difference is less than or equal to the preset value, the corresponding reference characteristic factor parameter is identified as the adaptation parameter, and the adaptation parameter ratio of the adaptation parameter to the reference characteristic factor parameter is determined. If the adaptation parameter ratio is greater than or equal to the preset value, it is determined that the reference tunnel internal structure model at this time is adapted to the comparison tunnel internal structure model.

[0034] Among them, the method of determining the degree of overlap includes:

[0035] A number of distance analysis points are randomly set on the internal structure model of the comparison tunnel, and the shortest distance between each distance analysis point and the internal structure model of the reference tunnel is determined. If the shortest distance is less than or equal to a preset value, the distance analysis point is identified as a model overlap point, and the ratio of the number of model overlap points to the number of distance analysis points is calculated. The degree of overlap is determined based on the preset ratio interval to which the ratio belongs.

[0036] In some embodiments of the present invention, a method for performing stability risk analysis on a finite element simulation model performance includes:

[0037] The finite element simulation model is used to calculate the stress distribution and strain of the tunnel structure under given loads and boundary conditions, and to analyze stress concentration areas to determine whether these areas exceed the strength limit of the material, thereby assessing the risk of tunnel structure damage.

[0038] In some embodiments of the present invention, a tunnel stability risk assessment system based on data analysis is also disclosed, comprising:

[0039] The first module is used to build a finite element simulation model for tunnel stability analysis;

[0040] The second module is used to obtain a number of tunnel structure record data, analyze the tunnel structure record data, determine a tunnel characteristic factor data group, each tunnel characteristic factor data group includes a number of tunnel characteristic factor parameters, classify the several tunnel characteristic factor data groups by similarity, and perform an average calculation on each group of classified tunnel characteristic factor data groups to obtain a reference tunnel characteristic factor data group;

[0041] The third module is used to input each reference tunnel characteristic factor parameter in the reference tunnel characteristic factor data group as an input parameter into the finite element simulation model for tunnel stability analysis, obtain the finite element simulation model performance, perform stability risk analysis on the finite element simulation model performance, and obtain a risk assessment result;

[0042] The fourth module is used to extract and simplify the internal surface of the tunnel represented by the finite element simulation model to obtain the initial tunnel internal structure model, determine the rock quality performance and joint network performance at different positions, and configure the corresponding performance on the initial tunnel internal structure model to obtain the reference tunnel internal structure model;

[0043] The fifth module is used to construct a tunnel internal structure model for comparison when conducting feature analysis on the current tunnel, and compare the comparison tunnel internal structure model with different reference tunnel internal models to find a matching reference tunnel internal model, and use the risk assessment result corresponding to the reference tunnel internal model as the stability risk assessment result of the current tunnel.

[0044] The present invention discloses a tunnel stability risk assessment method and system based on data analysis, which relates to the technical field of tunnel risk analysis, and constructs a finite element simulation model for tunnel stability analysis; analyzes tunnel structure record data to form multiple data groups, and classifies these data groups by similarity to obtain reference tunnel characteristic factor data groups. Then, these reference characteristic factors are imported into the finite element simulation model as input parameters to obtain the performance results of the model, and the results are subjected to stability risk analysis to obtain risk assessment results; the scheme also extracts and simplifies the internal surface of the tunnel in the simulation model, constructs an initial tunnel internal structure model, and obtains a reference tunnel internal structure model; by constructing a tunnel internal structure model for comparison and comparing it with the reference model, the above technical scheme of the present invention realizes accurate and efficient assessment of tunnel stability, and provides a strong guarantee for the safe construction and operation of tunnel engineering.

[0045] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is a method step diagram of a tunnel stability risk assessment method based on data analysis disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0048] The following will be combined with the accompanying drawings and specific embodiments to clearly and completely describe the technical solution of the present invention. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention and cannot be understood as limiting the scope of protection of the present invention. Those skilled in the art in this field can make some non-essential improvements and adjustments based on the content of the present invention described below. In the present invention, unless otherwise clearly specified and limited, the technical terms used in the present invention should be the common meanings understood by the technical personnel described in the present invention.

[0049] Example:

[0050] The present invention discloses a tunnel stability risk assessment method based on data analysis, comprising:

[0051] Step S100, constructing a finite element simulation model for tunnel stability analysis.

[0052] The core of step S100 is to construct a mechanical analysis model of the tunnel through finite element simulation technology to simulate the stability behavior of the tunnel under complex geological and engineering conditions. First, according to the actual size and geological conditions of the tunnel, determine the calculation range of the model and set reasonable boundary conditions (such as bottom fixation and lateral constraints) to ensure that the model can truly reflect the stress distribution around the tunnel. Subsequently, define material parameters according to the actual material properties of the surrounding rock and support structure (such as elastic modulus, Poisson's ratio, cohesion, etc.) to provide a reliable physical basis for simulation. Draw the geometric outline of the tunnel in the finite element software, and add geological structures (such as rock formations, faults, and cracks) to simulate the complex geological environment. Finally, mesh the model, use fine meshes in the area around the tunnel to improve the calculation accuracy, use coarse meshes in the peripheral area to reduce the amount of calculation, and apply initial geostress and other loads (such as groundwater pressure) to complete the construction of the finite element simulation model. This step is the basis for subsequent risk analysis, and its accuracy directly affects the credibility of the assessment results.

[0053] In some embodiments of the present invention, a method for constructing a finite element simulation model for tunnel stability analysis includes:

[0054] Step S101, determining the range of the finite element simulation model for tunnel stability analysis according to the actual size of the tunnel, and setting boundary conditions for the finite element simulation model for tunnel stability analysis.

[0055] When constructing a finite element simulation model for tunnel stability analysis, it is first necessary to determine the calculation range of the model based on the actual size of the tunnel. Generally, in order to avoid the influence of boundary effects on the calculation results, the range of the model should be much larger than the actual size of the tunnel. For example, the height and width of the model can be taken as 5 times the diameter of the tunnel, while the length is extended according to the actual length of the tunnel. After determining the range, it is necessary to set boundary conditions to simulate the constraints in actual engineering. Common boundary conditions include: fixed vertical displacement at the bottom of the model to simulate the support of the bedrock, lateral constraint horizontal displacement to simulate the lateral constraint of the surrounding rock, and free or applied stress boundary at the top to simulate the stress state of the surface. By reasonably setting the model range and boundary conditions, it is ensured that the simulated mechanical behavior can truly reflect the actual stress conditions of the tunnel.

[0056] Step S102, according to the actual material of the tunnel, the material properties including density, elastic modulus and Poisson's ratio are set for the finite element simulation model for tunnel stability analysis.

[0057] According to the actual materials of the tunnel, setting the material properties of the finite element simulation model is a key step to ensure the accuracy of the simulation results. Material properties include parameters such as density, elastic modulus, Poisson's ratio, cohesion, and internal friction angle of the surrounding rock and support structure. These parameters are usually obtained through laboratory tests or field measurements, and can also be assigned with reference to relevant geological survey reports and engineering experience. The material properties of the surrounding rock need to take into account its layered characteristics (such as hard rock layers and weak interlayers) and heterogeneity.

[0058] Step S103, according to the actual size and shape of the tunnel, draw the outline of the tunnel in the finite element simulation software, and add the geological structure, including rock layers, faults and fissures.

[0059] In finite element simulation software, drawing the geometric outline of the tunnel according to its actual size and shape is the basis for building the model. The drawing of the tunnel outline needs to take into account its cross-sectional shape (such as circular, horseshoe-shaped) and longitudinal changes (such as slope, curvature). Subsequently, according to the geological survey data, geological structures are added to the model, including complex geological features such as stratification, faults, and fissures of the rock formations. The stratification of the rock formations can be simulated by regions with different material properties, and faults and fissures can be characterized by interface units or discrete fracture network models. By adding geological structures, the model can more realistically reflect the geological environment around the tunnel and provide more accurate input conditions for subsequent stability analysis.

[0060] Step S104, meshing the tunnel stability analysis using a finite element simulation model and applying loads.

[0061] Meshing is an important part of building a finite element simulation model, which directly affects the calculation accuracy and efficiency. Due to the significant stress concentration effect in the area around the tunnel, a fine mesh is required to improve the calculation accuracy; the stress change in the peripheral area is small, and a coarser mesh can be used to reduce the amount of calculation. After the meshing is completed, the load needs to be applied according to the actual engineering conditions. Common loads include initial geostress (such as self-weight stress, tectonic stress) and external loads (such as construction load, groundwater pressure). The initial geostress can be estimated by geostress measurement data or theoretical formulas, and the construction load is defined according to the specific construction process. Through reasonable meshing and load application, it is ensured that the model can accurately simulate the mechanical behavior of the tunnel under complex geological and engineering conditions.

[0062] Step S200, obtaining a number of tunnel structure record data, analyzing the tunnel structure record data, determining a tunnel characteristic factor data group, each tunnel characteristic factor data group including a number of tunnel characteristic factor parameters, classifying the several tunnel characteristic factor data groups by similarity, and averaging each group of classified tunnel characteristic factor data groups to obtain a reference tunnel characteristic factor data group.

[0063] The purpose of step S200 is to extract key characteristic factors and classify them by analyzing a large amount of tunnel structure record data to form a reference data group to support risk assessment. First, tunnel characteristic factor parameters (such as surrounding rock grade, support type, burial depth, etc.) are obtained from historical or measured data, and the difference between each parameter is calculated. According to the preset difference interval, the similarity parameter of each parameter is determined to provide a quantitative basis for similarity analysis. Subsequently, a tunnel strike polyline is constructed based on the tunnel strike characteristics, and other characteristic factor parameters are configured at the position nodes on the polyline to form a data visualization expression. By comparing the shape similarity parameters of different tunnel strike polylines and the parameter difference at the position nodes, the similarity parameters of each parameter are determined. Finally, the similarity between the tunnel characteristic factor data groups is calculated by combining the shape similarity parameters and the similarity parameters of each parameter, and the data groups with high similarity are classified, and the averaged results are calculated to obtain the reference tunnel characteristic factor data group. This step extracts representative reference data in a data-driven manner to provide standardized input for subsequent risk assessment.

[0064] In some embodiments of the present invention, a method for similarity classification of a plurality of tunnel characteristic factor data sets includes:

[0065] Step S201, determine the parameter difference between the corresponding tunnel characteristic factor parameters, set a parameter difference interval for the tunnel characteristic factor parameters, each parameter difference interval is set with a corresponding similarity parameter, and determine the similarity parameter corresponding to the tunnel characteristic factor parameter by analyzing the parameter difference interval to which the parameter difference belongs.

[0066] When classifying several tunnel characteristic factor data groups by similarity, it is first necessary to clarify the parameter difference between the characteristic factor parameters of each tunnel (such as surrounding rock grade, support type, burial depth, etc.). This difference reflects the specific differences between different tunnels in a certain characteristic factor. In order to quantify this difference, a parameter difference interval is set for each tunnel characteristic factor parameter, and each interval corresponds to a similarity parameter. By analyzing the parameter difference interval to which the specific difference of a tunnel characteristic factor parameter belongs, the similarity parameter corresponding to the parameter can be determined. This step lays the foundation for subsequent similarity analysis by converting the parameter difference into a quantitative indicator.

[0067] Step S202, analyzing the tunnel characteristic factor parameters about the tunnel direction in the tunnel characteristic factor data group, determining the tunnel direction characteristics, constructing a tunnel direction polyline, and configuring different tunnel characteristic factor parameters at corresponding positions on the tunnel direction polyline based on the position nodes to which other tunnel characteristic factor parameters belong.

[0068] The tunnel direction feature is an important parameter in the tunnel characteristic factor data set, which reflects the spatial distribution and morphology of the tunnel. First, the tunnel characteristic factor parameters about the tunnel direction in the tunnel characteristic factor data set are analyzed to extract its direction features (such as straight lines, curves, broken lines, etc.). Based on these features, a tunnel direction broken line is constructed to visualize the tunnel direction in two-dimensional or three-dimensional space. Subsequently, other tunnel characteristic factor parameters (such as surrounding rock grade, hydrogeological conditions, etc.) are configured according to their position nodes on the tunnel direction broken line, so that these parameters are associated with the specific spatial position of the tunnel. Through this step, the tunnel characteristic factor data set is converted into a broken line form containing spatial information, which is convenient for subsequent comparison and analysis.

[0069] Step S203, comparing the tunnel direction polylines, including comparing the shape similarity parameters between the tunnel direction polylines, analyzing the parameter differences of other tunnel characteristic factor parameters corresponding to different position nodes, and determining the similarity parameters corresponding to each tunnel characteristic factor parameter.

[0070] Step S204, based on the shape similarity parameters and the continuous performance of the similarity parameters of each tunnel characteristic factor parameter on the tunnel direction polyline, determine the similarity between the tunnel characteristic factor data groups, and based on the similarity, determine whether the two are classified into the same category.

[0071] In some embodiments of the present invention, the method for determining the similarity between tunnel characteristic factor data sets includes:

[0072] Step S2041, compare the similar parameter corresponding to the tunnel characteristic factor parameter with the preset value, and if it is greater than or equal to the preset value, mark the tunnel characteristic factor parameter as similar.

[0073] Step S2042, based on the shape similarity parameter and the similarity mark ratio of the characteristic factor parameters of the same type of tunnels on the tunnel direction polyline, determine the similarity between the tunnel characteristic factor data groups.

[0074] Among them, the expression for calculating the similarity is: 。

[0075] in, For similarity, The length of the polyline between the tunnel direction polylines whose approach features meet the preset standards. is the sum of the total lengths of the tunnel's direction polyline, is the influence adjustment coefficient of the proportion of similar broken line lengths, Adjust the constant for the influence of the proportion of the length of the similar broken lines, is the shape similarity parameter weight adjustment coefficient, For the The similarity ratio of the characteristic factor parameters of each type of tunnel, For the The influence adjustment coefficient of the characteristic factor parameters of each type of tunnel, For the The influence adjustment constant of the characteristic factor parameters of each type of tunnel, For the The weight adjustment coefficient of each type of tunnel characteristic factor parameter, It is the total number of tunnel characteristic factor parameters other than the tunnel direction.

[0076] Step S300, taking each reference tunnel characteristic factor parameter in the reference tunnel characteristic factor data group as an input parameter, inputting it into a finite element simulation model for tunnel stability analysis, obtaining a finite element simulation model performance, performing stability risk analysis on the finite element simulation model performance, and obtaining a risk assessment result.

[0077] The core of step S300 is to input the reference tunnel characteristic factor parameters into the finite element simulation model and evaluate the stability risk of the tunnel through numerical simulation. First, the parameters in the reference tunnel characteristic factor data group (such as surrounding rock mechanical properties, support strength, etc.) are loaded into the finite element model as input conditions. Using the model's solution function, the mechanical responses of the tunnel such as stress distribution, displacement field, and plastic zone range under given loads and boundary conditions are calculated. By analyzing these results, the stress concentration areas and potential damage locations in the tunnel structure are identified to determine whether they exceed the strength limit of the material. Based on the simulation results, combined with engineering experience or theoretical standards, reference risk values ​​(such as stability, medium risk, high risk, etc.) are configured to provide a benchmark for subsequent tunnel risk assessment. This step converts geological and engineering parameters into intuitive mechanical performance through numerical simulation, providing a scientific basis for risk analysis.

[0078] In some embodiments of the present invention, a method for performing stability risk analysis on a finite element simulation model performance includes:

[0079] Step S301, calculate the stress distribution and strain of the tunnel structure under given loads and boundary conditions through a finite element simulation model, analyze stress concentration areas, determine whether these areas exceed the strength limit of the material, and thus assess the risk of tunnel structure damage.

[0080] Step S400, extract and simplify the internal surface of the tunnel represented by the finite element simulation model to obtain an initial tunnel internal structure model, determine the rock quality performance and joint network performance at different positions, and configure the corresponding performance on the initial tunnel internal structure model to obtain a reference tunnel internal structure model.

[0081] The goal of step S400 is to construct a reference tunnel internal structure model by extracting and simplifying the tunnel internal surface of the finite element simulation model to support subsequent model comparison. First, randomly select several location acquisition points on the tunnel internal surface of the finite element model, and connect adjacent points to form a geometric surface to obtain an initial tunnel internal structure model. Subsequently, a dynamically changing circle is randomly generated in the model, and its diameter is dynamically expanded until the circle boundary contacts the acquisition point, and the center point of the circle is recorded and connected to form a tunnel strike line. Next, based on the simulation results or field data, the rock quality performance and joint network characteristics at different locations are determined, and they are configured on the initial model to form a reference tunnel internal structure model. This step simplifies the complex finite element simulation results into geometric and geological models that are easy to compare, providing visual support for subsequent risk matching.

[0082] In some embodiments of the present invention, the method for extracting and simplifying the inner surface of a tunnel of a finite element simulation model includes:

[0083] Step S401, randomly setting a number of position acquisition points on the inner surface of the tunnel of the finite element simulation model, connecting adjacent position acquisition points, determining the surface formed by adjacent connection lines, and obtaining an initial reference tunnel inner structure model.

[0084] When extracting and simplifying the internal surface of the tunnel for the finite element simulation model, it is first necessary to randomly set a number of position acquisition points on the internal surface of the tunnel. The selection of these points should be as evenly distributed as possible to cover the entire internal surface of the tunnel. Subsequently, the adjacent position acquisition points are connected to form a series of continuous line segments. By connecting these line segments, the geometric faces (such as triangular faces or quadrilateral faces) formed between adjacent line segments are further determined to generate the initial reference tunnel internal structure model. This step simplifies the complex internal surface of the tunnel into a geometric model composed of points and faces, which not only retains the basic structural characteristics of the tunnel, but also significantly reduces the complexity of the model.

[0085] Step S402, randomly construct a number of dynamic change circles for the tunnel space of the initial reference tunnel internal structure model, and the diameter of each dynamic change circle dynamically increases until the dynamic change circle is completely restricted by the position acquisition point, and determine the center point of the dynamic change circle, connect the center points, and obtain the tunnel strike line of the initial reference tunnel internal structure model.

[0086] Based on the initial reference tunnel internal structure model, the spatial orientation information of the tunnel is further extracted. First, a number of dynamically changing circles are randomly constructed in the tunnel space. The diameter of each dynamically changing circle dynamically increases from the initial value until the boundary of the circle is completely restricted by the position acquisition point (that is, the circle is in contact with the internal surface of the tunnel). The center points of these dynamically changing circles are recorded, and these center points are connected in spatial order to obtain the tunnel orientation line of the initial reference tunnel internal structure model. This orientation line reflects the spatial extension direction and morphological characteristics of the tunnel, and provides important geometric information for subsequent analysis and modeling.

[0087] Step S500, when performing feature analysis on the current tunnel, construct a comparison tunnel internal structure model, and compare the comparison tunnel internal structure model with different reference tunnel internal models to find a matching reference tunnel internal model, and use the risk assessment result corresponding to the reference tunnel internal model as the stability risk assessment result of the current tunnel.

[0088] The core of step S500 is to achieve stability risk assessment by constructing an internal structure model for comparison of the current tunnel and comparing it with the reference model. First, the internal point cloud data of the current tunnel is obtained by laser scanning technology. Based on the data, the location collection points are randomly selected and connected into a surface to generate the initial internal structure model of the tunnel for comparison, and its tunnel strike line is determined. Subsequently, the tunnel strike line of the comparison model is aligned with the reference model, and the degree of overlap between the two is calculated (such as the model overlap rate evaluated by random distance analysis points). If the overlap reaches the preset value, it is determined that the initial adaptation requirements are met. Next, the characteristic factor parameters of the reference model are compared with the parameters of the comparison model for the difference amount. If the proportion of the adaptation parameters reaches the preset value, it is confirmed that the reference model is adapted to the comparison model. Finally, the reference risk value corresponding to the adapted reference model is the stability risk assessment result of the current tunnel. This step realizes the quantitative risk assessment of the real-time tunnel through model comparison and parameter analysis.

[0089] In some embodiments of the present invention, the method for constructing a tunnel internal structure model for comparison includes:

[0090] Step S501, using laser scanning technology to scan the interior of the tunnel to obtain point cloud data of the interior of the tunnel, and based on the point cloud data of the interior of the tunnel, determine a number of position acquisition points, and connect adjacent position acquisition points, determine the surface formed by adjacent connecting lines, and obtain an initial comparison tunnel internal structure model, and determine the tunnel strike line of the initial comparison tunnel internal structure model to obtain a comparison tunnel internal structure model.

[0091] When constructing the internal structure model of the tunnel for comparison, laser scanning technology is first used to perform high-precision scanning of the interior of the tunnel to obtain point cloud data of the interior of the tunnel. Laser scanning can quickly and accurately capture the three-dimensional geometric information of the tunnel surface and provide basic data for subsequent modeling. Based on the acquired point cloud data, several position acquisition points are determined on the internal surface of the tunnel. These acquisition points should be distributed as evenly as possible to cover the entire internal surface of the tunnel. Subsequently, adjacent position acquisition points are connected to form a series of continuous line segments. By connecting these line segments, the geometric faces (such as triangular faces or quadrilateral faces) formed between adjacent line segments are further determined to generate the initial internal structure model of the tunnel for comparison. This step converts the laser scanning data into a geometric model composed of points and faces, which not only retains the actual characteristics of the tunnel but also simplifies the complexity of the data.

[0092] In some embodiments of the present invention, the method of comparing the comparison tunnel internal structure model with different reference tunnel internal structure models includes:

[0093] Step S502, align and overlap the tunnel strike lines of the comparison tunnel internal structure model and the reference tunnel internal structure model, and compare the degree of overlap between the initial comparison tunnel internal structure model and the reference tunnel internal structure model. If the degree of overlap is greater than or equal to a preset value, it is determined that the reference tunnel internal structure model at this time meets the initial adaptation requirements for the comparison tunnel internal structure model.

[0094] Step S503, calling the reference tunnel characteristic factor parameters corresponding to the reference tunnel internal structure model that meets the initial adaptation requirements, and comparing the parameter difference between each reference characteristic factor parameter and the characteristic reference factor parameter currently collected in the tunnel; if the parameter difference is less than or equal to the preset value, the corresponding reference characteristic factor parameter is identified as the adaptation parameter, and the adaptation parameter ratio of the adaptation parameter to the reference characteristic factor parameter is determined; if the adaptation parameter ratio is greater than or equal to the preset value, it is determined that the reference tunnel internal structure model at this time is adapted to the comparison tunnel internal structure model.

[0095] Among them, the method of determining the degree of overlap includes:

[0096] Step S5021, a number of distance analysis points are randomly set on the tunnel internal structure model for comparison, and the shortest distance between each distance analysis point and the reference tunnel internal structure model is determined. If the shortest distance is less than or equal to a preset value, the distance analysis point is identified as a model overlap point, and the ratio of the number of model overlap points to the number of distance analysis points is calculated, and the overlap degree is determined based on the preset ratio interval to which the ratio belongs.

[0097] In some embodiments of the present invention, a tunnel stability risk assessment system based on data analysis is also disclosed, comprising:

[0098] The first module is used to build a finite element simulation model for tunnel stability analysis;

[0099] The second module is used to obtain a number of tunnel structure record data, analyze the tunnel structure record data, determine a tunnel characteristic factor data group, each tunnel characteristic factor data group includes a number of tunnel characteristic factor parameters, classify the several tunnel characteristic factor data groups by similarity, and perform an average calculation on each group of classified tunnel characteristic factor data groups to obtain a reference tunnel characteristic factor data group;

[0100] The third module is used to input each reference tunnel characteristic factor parameter in the reference tunnel characteristic factor data group as an input parameter into the finite element simulation model for tunnel stability analysis, obtain the finite element simulation model performance, perform stability risk analysis on the finite element simulation model performance, and obtain a risk assessment result;

[0101] The fourth module is used to extract and simplify the internal surface of the tunnel represented by the finite element simulation model to obtain the initial tunnel internal structure model, determine the rock quality performance and joint network performance at different positions, and configure the corresponding performance on the initial tunnel internal structure model to obtain the reference tunnel internal structure model;

[0102] The fifth module is used to construct a tunnel internal structure model for comparison when conducting feature analysis on the current tunnel, and compare the comparison tunnel internal structure model with different reference tunnel internal models to find a matching reference tunnel internal model, and use the risk assessment result corresponding to the reference tunnel internal model as the stability risk assessment result of the current tunnel.

[0103] The present invention discloses a tunnel stability risk assessment method and system based on data analysis, which relates to the technical field of tunnel risk analysis, and constructs a finite element simulation model for tunnel stability analysis; analyzes tunnel structure record data to form multiple data groups, and classifies these data groups by similarity to obtain reference tunnel characteristic factor data groups. Then, these reference characteristic factors are imported into the finite element simulation model as input parameters to obtain the performance results of the model, and the results are subjected to stability risk analysis to obtain risk assessment results; the scheme also extracts and simplifies the internal surface of the tunnel in the simulation model, constructs an initial tunnel internal structure model, and obtains a reference tunnel internal structure model; by constructing a tunnel internal structure model for comparison and comparing it with the reference model, the above technical scheme of the present invention realizes accurate and efficient assessment of tunnel stability, and provides a strong guarantee for the safe construction and operation of tunnel engineering.

[0104] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present invention can be implemented by hardware, or by software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present invention.

[0105] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A tunnel stability risk assessment method based on data analysis, characterized in that: include: Construct a finite element simulation model for tunnel stability analysis; Acquire a number of tunnel structure record data, analyze the tunnel structure record data, determine a tunnel characteristic factor data group, each tunnel characteristic factor data group includes a number of tunnel characteristic factor parameters, classify the several tunnel characteristic factor data groups by similarity, and perform averaging calculation on each group of classified tunnel characteristic factor data groups to obtain a reference tunnel characteristic factor data group; Each reference tunnel characteristic factor parameter in the reference tunnel characteristic factor data group is used as an input parameter and input into a finite element simulation model for tunnel stability analysis to obtain a finite element simulation model performance, and stability risk analysis is performed on the finite element simulation model performance to obtain a risk assessment result; The internal surface of the tunnel represented by the finite element simulation model is extracted and simplified to obtain the initial reference tunnel internal structure model, and the rock quality performance and joint network performance at different positions are determined, and the corresponding performance is configured on the initial reference tunnel internal structure model to obtain the reference tunnel internal structure model; When conducting feature analysis on the current tunnel, a comparison tunnel internal structure model is constructed, and the comparison tunnel internal structure model is compared with different reference tunnel internal models to find a matching reference tunnel internal model, and the risk assessment result corresponding to the reference tunnel internal model is used as the stability risk assessment result of the current tunnel.

2. The tunnel stability risk assessment method based on data analysis according to claim 1 is characterized in that: Methods for constructing finite element simulation models for tunnel stability analysis include: According to the actual size of the tunnel, determine the scope of the finite element simulation model for tunnel stability analysis, and set boundary conditions for the finite element simulation model for tunnel stability analysis; According to the actual material of the tunnel, the material properties are set using the finite element simulation model for tunnel stability analysis, including density, elastic modulus and Poisson's ratio; Draw the tunnel outline in the finite element simulation software according to the actual size and shape of the tunnel, and add geological structures, including rock layers, faults and cracks; The finite element simulation model is meshed for tunnel stability analysis and loads are applied.

3. The tunnel stability risk assessment method based on data analysis according to claim 1 is characterized in that: The method for similarity classification of several tunnel characteristic factor data sets includes: Determine the parameter difference between the corresponding tunnel characteristic factor parameters, set a parameter difference interval for the tunnel characteristic factor parameters, each parameter difference interval is correspondingly set with a corresponding similarity parameter, and determine the similarity parameter corresponding to the tunnel characteristic factor parameter by analyzing the parameter difference interval to which the parameter difference belongs; Analyze the tunnel characteristic factor parameters related to the tunnel direction in the tunnel characteristic factor data group, determine the tunnel direction characteristics, construct a tunnel direction polyline, and configure different tunnel characteristic factor parameters at corresponding positions on the tunnel direction polyline based on the position nodes to which other tunnel characteristic factor parameters belong; Comparing the tunnel direction polylines, including comparing the shape similarity parameters between the tunnel direction polylines, and analyzing the parameter differences of other tunnel characteristic factor parameters corresponding to different position nodes, and determining the similarity parameters corresponding to each tunnel characteristic factor parameter; Based on the shape similarity parameters and the continuous performance of similarity parameters of each tunnel characteristic factor parameter on the tunnel strike polyline, the similarity between the tunnel characteristic factor data groups is determined, and based on the similarity, it is determined whether the two are classified into the same category.

4. The tunnel stability risk assessment method based on data analysis according to claim 3 is characterized in that: Methods for determining the degree of similarity between tunnel characteristic factor data sets include: Compare the similar parameter corresponding to the tunnel characteristic factor parameter with the preset value, and if it is greater than or equal to the preset value, mark the tunnel characteristic factor parameter as similar; Based on the shape similarity parameters and the proportion of similar marks of characteristic factor parameters of the same type of tunnels on the tunnel strike line, the similarity between the tunnel characteristic factor data groups is determined; Among them, the expression for calculating the similarity is: ； in, For similarity, The length of the polyline between the tunnel direction polylines whose approach features meet the preset standards. is the sum of the total lengths of the tunnel's direction polyline, is the influence adjustment coefficient of the proportion of similar broken line lengths, Adjust the constant for the influence of the proportion of the length of the similar broken lines, is the shape similarity parameter weight adjustment coefficient, For the The similarity ratio of the characteristic factor parameters of each type of tunnel, For the The influence adjustment coefficient of the characteristic factor parameters of each type of tunnel, For the The influence adjustment constant of the characteristic factor parameters of each type of tunnel, For the The weight adjustment coefficient of each type of tunnel characteristic factor parameter, It is the total number of tunnel characteristic factor parameters other than the tunnel direction.

5. The tunnel stability risk assessment method based on data analysis according to claim 1 is characterized in that: Methods for extracting and simplifying the internal surface of the tunnel in the finite element simulation model include: A number of position acquisition points are randomly set on the inner surface of the tunnel of the finite element simulation model, and adjacent position acquisition points are connected by lines, and the surface formed by the adjacent connecting lines is determined to obtain an initial reference tunnel inner structure model; A number of dynamic change circles are randomly constructed in the tunnel space of the initial reference tunnel internal structure model, and the diameter of each dynamic change circle dynamically increases until the dynamic change circle is completely restricted by the position acquisition point, and the center point of the dynamic change circle is determined, and the center points are connected to obtain the tunnel strike line of the initial reference tunnel internal structure model.

6. The tunnel stability risk assessment method based on data analysis according to claim 5 is characterized in that: The method of constructing the internal structure model of the tunnel for comparison includes: Laser scanning technology is used to scan the interior of the tunnel to obtain point cloud data inside the tunnel, and based on the point cloud data inside the tunnel, several position collection points are determined, and adjacent position collection points are connected, and the surface formed by adjacent connecting lines is determined to obtain an initial comparison tunnel internal structure model, and the tunnel strike line of the initial comparison tunnel internal structure model is determined to obtain a comparison tunnel internal structure model.

7. The tunnel stability risk assessment method based on data analysis according to claim 6 is characterized in that: The method of comparing the comparison tunnel internal structure model with different reference tunnel internal structure models includes: Align and overlap the tunnel strike lines of the comparison tunnel internal structure model and the reference tunnel internal structure model, and compare the overlap degree of the initial comparison tunnel internal structure model and the reference tunnel internal structure model at the same time. If the overlap degree is greater than or equal to a preset value, it is determined that the reference tunnel internal structure model at this time meets the initial adaptation requirements for the comparison tunnel internal structure model; Call the reference tunnel characteristic factor parameters corresponding to the reference tunnel internal structure model that meets the initial adaptation requirements, and compare the parameter difference between each reference characteristic factor parameter and the characteristic reference factor parameter currently collected in the tunnel. If the parameter difference is less than or equal to the preset value, the corresponding reference characteristic factor parameter is identified as the adaptation parameter, and the adaptation parameter ratio of the adaptation parameter to the reference characteristic factor parameter is determined. If the adaptation parameter ratio is greater than or equal to the preset value, it is determined that the reference tunnel internal structure model at this time is adapted to the comparison tunnel internal structure model. Among them, the method of determining the degree of overlap includes: A number of distance analysis points are randomly set on the internal structure model of the comparison tunnel, and the shortest distance between each distance analysis point and the internal structure model of the reference tunnel is determined. If the shortest distance is less than or equal to a preset value, the distance analysis point is identified as a model overlap point, and the ratio of the number of model overlap points to the number of distance analysis points is calculated. The degree of overlap is determined based on the preset ratio interval to which the ratio belongs.

8. The tunnel stability risk assessment method based on data analysis according to claim 1 is characterized in that: Methods for performing stability risk analysis on finite element simulation model performance include: The finite element simulation model is used to calculate the stress distribution and strain of the tunnel structure under given loads and boundary conditions, and to analyze stress concentration areas to determine whether these areas exceed the strength limit of the material, thereby assessing the risk of tunnel structure damage.

9. A tunnel stability risk assessment system based on data analysis, characterized in that: A method for tunnel stability risk assessment based on data analysis for executing any one of claims 1 to 8, comprising: The first module is used to build a finite element simulation model for tunnel stability analysis; The second module is used to obtain a number of tunnel structure record data, analyze the tunnel structure record data, determine a tunnel characteristic factor data group, each tunnel characteristic factor data group includes a number of tunnel characteristic factor parameters, classify the several tunnel characteristic factor data groups by similarity, and perform an average calculation on each group of classified tunnel characteristic factor data groups to obtain a reference tunnel characteristic factor data group; The third module is used to input each reference tunnel characteristic factor parameter in the reference tunnel characteristic factor data group as an input parameter into the finite element simulation model for tunnel stability analysis, obtain the finite element simulation model performance, perform stability risk analysis on the finite element simulation model performance, and obtain a risk assessment result; The fourth module is used to extract and simplify the internal surface of the tunnel represented by the finite element simulation model to obtain the initial tunnel internal structure model, determine the rock quality performance and joint network performance at different positions, and configure the corresponding performance on the initial tunnel internal structure model to obtain the reference tunnel internal structure model; The fifth module is used to construct a tunnel internal structure model for comparison when conducting feature analysis on the current tunnel, and compare the comparison tunnel internal structure model with different reference tunnel internal models to find a matching reference tunnel internal model, and use the risk assessment result corresponding to the reference tunnel internal model as the stability risk assessment result of the current tunnel.

Images