Underground engineering unfavorable geology pre-control analysis method and system fused with multi-source data

Abstract

The invention provides a tunnel unfavorable geology pre-control analysis method and system fusing multi-source data, and relates to the technical field of tunnel geology analysis and data processing, and the method comprises the steps: obtaining multiple types of credible data exposed by geological exploration, advanced drilling, advanced geophysical prospecting and a working plane, and respectively generating space coordinate points; according to an assignment rule, assigning an initial value to each space coordinate point and the corresponding parameter, and generating a space coordinate matrix; different space coordinate points in the space coordinate matrix are endowed with confidence values, and a multi-class confidence space domain is generated; according to a confidence domain association mapping rule, obtaining data domain parameters and a relationship between the data domains, determining spatial distribution of the parameters in the confidence domain, obtaining parameter feedback of individual spatial coordinate points through a posterior updating method of the confidence domain rule, and by utilizing a high-dimensional traversal optimization method, taking a minimum residual error between a parameter calculation value and an actual value as a target, obtaining a confidence domain relation between the confidence domain and the actual value; and continuously adjusting parameters in the confidence domain distribution rule to obtain an optimal pre-control parameter so as to guide actual engineering application.

Description

Technical Field

[0001] The present disclosure relates to the technical field of underground engineering geological analysis and data processing, and particularly to a method and system for pre-control analysis of unfavorable geology in underground engineering that integrates multi-source data. Background Art

[0002] The statements in this part merely provide background technical information related to the present disclosure and do not necessarily constitute prior art.

[0003] During the actual excavation process of underground engineering, the interactive information obtained presents some characteristics when utilized: the data information sources are extensive and diverse in form. Commonly used geological exploration data, advanced drilling data, advanced geophysical exploration data, and data revealed at the working face can all reflect the geological information of underground engineering to a certain extent. However, for these multi-source data, there is still a lack of a feasible rule to process them efficiently and scientifically, and thus guide the design of pre-control parameters. Especially in the case of limited exploration data, integrating multi-source data and determining geotechnical parameters remains a huge challenge. Due to the existence of these problems, the excavation process of underground engineering still highly relies on subjective decision-making and empirical analysis, resulting in misjudgments of unfavorable geological conditions and further causing construction accidents. In the construction of urban underground space, the consequences caused by this risk may further lead to the failure of surface transportation facilities and the damage of adjacent buildings. Therefore, solving the problem of multi-source data fusion analysis during the tunneling process of underground engineering is of great significance for the safe and efficient construction of underground engineering.

[0004] Currently, there are two main problems: The first problem is how to map multi-source data into a spatial model. The current methods cannot well explain how to express the geological information at non-exploration points, and the rules for establishing a spatial model for different types of data are obviously different. This situation has not been well explained and studied. The second problem is how to perform an objective and reasonable fusion calculation on multi-source data, establish a multi-source data interaction processing rule, and obtain the geological risk data with the highest confidence.

[0005] Regarding the above problems, the prior art has introduced means such as Bayesian and machine learning into this research. For example, a Bayesian geostatistical method has been developed for coal seam surface modeling using multi-source geological data at different stages and scales, etc. However, these methods still have the following limitations:

[0006] Risk analysis relies too much on subjective experience. At the same time, a large number of studies set too rough targets for the final risk assessment. The target value setting in the research process of many Bayesian methods and machine learning methods also relies on experience, and lacks persuasiveness for small data. The results obtained by such methods are often qualitative results within the region, which cannot process detailed stratigraphic information, cannot show the full picture of geological risks faced during underground engineering excavation, and cannot further guide the fine pre-control of risks. There are still many areas that need to be improved and further explored. Summary of the invention

[0007] In order to solve the above problems, the present invention proposes an underground engineering adverse geological pre-control analysis method and system that integrates multi-source data, establishes association rules for multiple data of underground engineering, sets a posterior update process for the trust region distribution rule, and continuously adjusts the parameters in the trust region distribution rule by feedback of parameters of individual monitoring points and utilizing a high-dimensional traversal optimization method to calculate the range of the grouting reinforcement circle of each section of the underground engineering, so as to guide actual engineering applications.

[0008] According to some embodiments, the present disclosure adopts the following technical solutions:

[0009] The underground engineering adverse geological pre-control analysis method integrating multi-source data includes:

[0010] According to the surrounding rock environment of underground projects, multiple types of reliable data from geological exploration, advance drilling, advance geophysical exploration and working surface exposure are obtained, and spatial coordinate points and corresponding parameters are generated respectively;

[0011] According to the assignment rules, each spatial coordinate point and the corresponding parameter are assigned an initial value to generate multiple spatial coordinate matrices; different spatial coordinate points in each spatial coordinate matrix are assigned a confidence value to generate multiple types of confidence space domains;

[0012] According to the trust domain association mapping rule, the data domain parameters and the relationship between data domains are obtained, and the spatial distribution of the parameters in the trust domain is determined. The parameter feedback of individual spatial coordinate points is obtained through the posterior update method of the trust domain rule. The high-dimensional traversal optimization method is used to minimize the residual between the calculated value and the actual value of the parameter, and the parameters in the trust domain distribution rule are continuously adjusted to obtain the optimal pre-control parameters.

[0013] Based on the obtained optimal pre-control parameters, the scope of the grouting reinforcement circle of each section of the underground project is calculated to guide the actual engineering application.

[0014] According to some embodiments, the present disclosure adopts the following technical solutions:

[0015] The underground engineering adverse geological pre-control analysis system integrating multi-source data includes:

[0016] A data acquisition module, which is used to obtain various types of reliable data from geological exploration, advanced drilling, advanced geophysical prospecting, and the exposure of the working face for the surrounding rock environment of underground engineering, and respectively generate spatial coordinate points and corresponding parameters;

[0017] A confidence space domain generation module, which is used to assign initial values to each spatial coordinate point and corresponding parameter according to the assignment rule to generate multiple spatial coordinate matrices; assign confidence values to different spatial coordinate points in each spatial coordinate matrix to generate multiple types of confidence space domains;

[0018] A pre-control analysis module, which is used to obtain data domain parameters and the relationships between data domains according to the confidence domain association mapping rule, determine the spatial distribution of parameters in the confidence domain, obtain the parameter feedback of individual spatial coordinate points through the posterior update method of the confidence domain rule, and use the high-dimensional traversal optimization method to continuously adjust the parameters in the confidence domain distribution rule with the goal of minimizing the residual between the parameter calculated value and the actual value to obtain the optimal pre-control parameters; calculate the range of the grouting reinforcement circle for each section of the underground engineering according to the obtained optimal pre-control parameters to guide the actual engineering application.

[0019] According to some embodiments, the present disclosure adopts the following technical solutions:

[0020] A computer program product, including a computer program, which when executed by a processor implements the underground engineering bad geology pre-control analysis method for fusing multi-source data as described above.

[0021] According to some embodiments, the present disclosure adopts the following technical solutions:

[0022] A non-transitory computer-readable storage medium, which is used to store computer instructions, and when the computer instructions are executed by a processor, the underground engineering bad geology pre-control analysis method for fusing multi-source data as described above is implemented.

[0023] According to some embodiments, the present disclosure adopts the following technical solutions:

[0024] An electronic device, including: a processor, a memory, and a computer program; wherein, the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device runs, the processor executes the computer program stored in the memory so that the electronic device executes and implements the underground engineering bad geology pre-control analysis method for fusing multi-source data as described above.

[0025] Compared with the prior art, the beneficial effects of the present disclosure are:

[0026] A method for analyzing and pre-controlling adverse geology in underground engineering by integrating multi-source data uses mileage as the longitudinal scale of spatial data, which is conducive to the rapid input of engineering survey data. It establishes a rule for selecting surrounding rock parameters under the most credible risk conditions to guide the parameter adjustment and design of pre-control measures. At the same time, a traversal optimization method is designed for confidence rules, making the analysis results depend on objective conditions as much as possible and getting rid of the influence of subjective experience. This method provides an objective, rapid, and automated analysis means for risk pre-control during the excavation process of underground engineering, realizing the integrated utilization of multi-source data. The results of the present invention have been practically applied to ensure the safe and economic construction of underground engineering.

[0027] A method for analyzing and pre-controlling adverse geology in underground engineering by integrating multi-source data can continuously adjust pre-control parameters during the tunneling process of underground engineering to achieve refined processing. This can be seen from the adjustment of each calculation unit (10m) in the calculation results. By further calculating the volume of the spatial area of grouting reinforcement based on the results of the gradually reinforced range, it is obtained that the spatial volume of grouting reinforcement after optimized design is reduced by 20.64% compared with the original design. In addition, the design of the above method in the present invention significantly reduces the cost in actual engineering construction and helps to achieve a more refined pre-control parameter design. Brief Description of the Drawings

[0028] The specification drawings forming a part of the present disclosure are used to provide a further understanding of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation to the present disclosure.

[0029] Figure 1 It is the overall flowchart of the method for the embodiment of the present disclosure;

[0030] Figure 2 It is the flowchart of the posterior update rule of the confidence domain for the embodiment of the present disclosure. Detailed Description of the Embodiments

[0031] The present disclosure will be further described below in conjunction with the drawings and embodiments.

[0032] It should be noted that the following detailed descriptions are all illustrative and are intended to provide a further description of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present disclosure belongs.

[0033] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0034] Example 1

[0035] In an embodiment of the present disclosure, a method for pre - controlling unfavorable geology in underground engineering by fusing multi - source data is provided. Based on a confidence - based method for fusing multi - source data in the underground engineering tunneling process, the fusion analysis of multi - source data during the tunneling process is realized, and mathematical rules are established to guide the parameter adjustment of pre - control measures, and then safety prevention and control are carried out. The steps are as follows:

[0036] Step 1: For the surrounding rock environment of the underground engineering, obtain various types of reliable data from geological exploration, advanced drilling, advanced geophysical exploration, and the exposure at the working face, and respectively generate spatial coordinate points and corresponding parameters;

[0037] Step 2: According to the assignment rule, assign initial values to each spatial coordinate point and the corresponding parameters to generate multiple spatial coordinate matrices; assign confidence values to different spatial coordinate points in each spatial coordinate matrix to generate multiple types of confidence spatial domains;

[0038] Step 3: According to the confidence domain correlation mapping rule, obtain the data domain parameters and the relationships between data domains, determine the spatial distribution of the parameters in the confidence domain, through the posterior update method of the confidence domain rule, obtain the parameter feedback of individual spatial coordinate points, and use the high - dimensional traversal optimization method to continuously adjust the parameters in the confidence domain distribution rule with the goal of minimizing the residual between the parameter calculated value and the actual value, and obtain the optimal pre - control parameters;

[0039] Step 4: According to the obtained optimal pre - control parameters, calculate the range of the grouting reinforcement circle for each section of the underground engineering to guide the actual engineering application.

[0040] As an embodiment, the specific implementation process of the method for pre - controlling unfavorable geology in underground engineering by fusing multi - source data of the present disclosure is as follows:

[0041] Step 1: For the surrounding rock environment of the underground engineering, obtain various types of reliable data from geological exploration, advanced drilling, advanced geophysical exploration, and the exposure at the working face, and respectively generate spatial coordinate points and corresponding parameters;

[0042] Specifically, for the surrounding rock environment of underground engineering, underground space coordinate points are established at a certain interval (0.5m * 0.5m * 0.5m). This spatial range is roughly a cuboid space distributed along the mileage in the longitudinal scale, and the transverse section is a rectangular range reaching (20m, 25m) (the coordinate origin is the midpoint of the starting operation surface of underground engineering tunneling).

[0043] Step 2: According to the assignment rules, initial values are assigned to each spatial coordinate point and corresponding parameters to generate multiple spatial coordinate matrices; confidence values are assigned to different spatial coordinate points in each spatial coordinate matrix to generate multiple types of confidence space domains;

[0044] Specifically, an initial value (0) regarding a certain parameter is assigned to each spatial coordinate point. This parameter can be the permeability coefficient, cohesion, internal friction angle, lateral pressure coefficient, etc. After obtaining 4 types of credible data from geological exploration, advanced drilling, advanced geophysical prospecting, and exposure at the working face, table files of spatial coordinate points and corresponding parameters are respectively generated.

[0045] Among them, the process of generating the table file of spatial coordinate points and corresponding parameters is as follows: Based on geological exploration data, with the center of the construction opening of underground engineering as the zero coordinate point, using python (VTK) as the compilation basis to construct the geological space coordinate system in front of the underground engineering tunneling, and selecting coordinate points at a certain interval (0.5m * 0.5m * 0.5m) to form the spatial point cloud file in front of the tunneling. The file contains the three-dimensional information of each spatial coordinate point.

[0046] Meanwhile, according to certain assignment rules, values are also assigned to the coordinate points in the associated areas. In this way, for each underground environmental parameter, 4 spatial coordinate matrices based on 4 types of exploration data are formed.

[0047] Among them, the construction process of the spatial coordinate matrix is as follows: Based on the spatial point cloud file, combined with geological exploration, advanced drilling, advanced geophysical prospecting, and exposure information at the working face, attribute columns are added to the information of each spatial coordinate point in the file. The added attributes include physical parameters such as permeability coefficient, cohesion, internal friction angle, and lateral pressure coefficient, forming a new spatial coordinate matrix file, that is, a data set of spatial coordinates + physical parameters.

[0048] Furthermore, a confidence value η is assigned to different coordinate points in each coordinate matrix c . Its meaning is the credibility of the data corresponding to each coordinate point. According to the characteristics of 4 types of exploration methods, namely geological exploration, advanced drilling, advanced geophysical prospecting, and exposure at the working face, a confidence value is assigned to each coordinate point to establish 4 types of confidence space domains. The coordinate matrix and the corresponding confidence domain are multiplied, and after weighted averaging, the maximum confidence value of a certain coordinate point relative to a certain parameter can be obtained.

[0049] Among them, a confidence value is assigned to each coordinate point, and the process of establishing four types of confidence space domains is as follows: Based on the spatial coordinate matrix file, a new attribute column, that is, the confidence value, is added. The number of confidence value attributes corresponds to the number of added physical parameter attributes, so that each spatial coordinate point in the file corresponds to various physical information and its confidence value. Among them, the confidence value of the spatial coordinate + single physical information is the confidence domain of a certain physical parameter.

[0050] The assignment process is as follows: The physical parameter confidence value of the deterministic or revealing coordinate point is assigned 1. For the coordinate point with uncertainty or non-revealing but having a spatial association with the former, the physical parameter confidence value is assigned with attenuation according to the rules in step 3, and the physical parameter confidence value of the remaining coordinate points is assigned 0.

[0051] Step 3: According to the confidence domain association mapping rule, obtain the data domain parameters and the relationships between data domains, determine the spatial distribution of the parameters in the confidence domain, through the posterior update method of the confidence domain rule, obtain the parameter feedback of individual spatial coordinate points, and use the high-dimensional traversal optimization method. With the goal of minimizing the residual between the parameter calculated value and the actual value, continuously adjust the parameters in the confidence domain distribution rule to obtain the optimal pre-control parameters;

[0052] Specifically, the multi-source data association rules (spatial mapping rules and horizontal and vertical variation rules) of underground engineering are as follows. First, four data confidence domains are introduced.

[0053] 1. Geological exploration data:

[0054] Specifically, for the vertical spatial variation, there is geological exploration data of the coordinate point S1(l x ,l y ,l z ) which is ρ g,s1 , and there is geological exploration data of the adjacent survey coordinate point S2(l x ,l y ,l z +Δl) which is ρ g,s2 . Then the interpolation method is used to determine the geological data of the coordinate point S Δ (l x ,l y ,l z +Δz), that is:

[0055] ρ g,sΔ ρ’ g,sΔ =(ρ g,s1 -ρ g,s2 )·(Δz / Δl)+ρ g,s1

[0056] Among them, ρ' 1,sΔ is the geological data of the coordinate point S Δ (lx , l y , l z Geological data of (+Δz).

[0057] For horizontal spatial variability, at the same l z In the planar space, any point S' Δ (l x +Δx, l y , l z +Δz) of the parameter data ρ' g,sΔ is:

[0058] ρ’ g,sΔ = ρ g,sΔ

[0059] 2. Advanced drilling data:

[0060] Specifically, for the advanced drilling data, set an extension limit e in the horizontal and vertical scales d , and this spatial range presents an approximate cylindrical shape. If there is advanced drilling data of the coordinate point S1(l x , l y , l z ) is ρ p,s1 , then for S Δ (l x +Δx, l y +Δy, l z ) the advanced drilling data is ρ d,sΔ = ρ d,s1 . At the same time, for S Δ (l x +Δx, l y +Δy, l z +Δz), then the following situation occurs:

[0061]

[0062] 3. Advanced geophysical exploration data:

[0063] For the advanced geophysical exploration data, the Kriging interpolation method is used for the data - free area.

[0064] 4. Data revealed at the working face:

[0065] Specifically, for the data revealed at the working face, set an extension limit e in the horizontal and vertical scales s . If there is sampling test data (or data that can be directly observed) of the coordinate point S1(l x , l y , l z ) is ρ s,s1 , then for the S closest to this coordinate pointΔ (l x +Δx, l y +Δy, l z +Δz), there are the following situations:

[0066]

[0067] As an embodiment, the confidence domain mapping method and the horizontal and vertical variation rules are as follows:

[0068] 1. Geological exploration data:

[0069] Specifically, for geological exploration data, the distribution form of the confidence domain is that the confidence level is high in the linear area where the drilling is located, and the confidence level decreases as the distance from the drilling area increases. This form is characterized by a normal distribution. For the confidence level of the coordinate point, there is:

[0070]

[0071] where μg, is a parameter of the normal distribution.

[0072] 2. Advanced drilling data:

[0073] Specifically, for advanced drilling data, the distribution form of the confidence domain is that the confidence level is high in the linear area where the drilling is located, and the confidence level decreases as the distance from the drilling area increases. This form is characterized by a normal distribution. For the confidence level of the coordinate point S Δ (l x , l y , l z +Δz), there is:

[0074]

[0075] where μ d , is a parameter of the normal distribution.

[0076] Since the geological exposure distance of the advanced drilling is short, the value of the normal distribution parameter is small, so that the confidence level in space quickly reaches 0 after leaving the drilling coordinates.

[0077] 3. Advanced geophysical exploration data:

[0078] In the longitudinal scale, the closer to the working face, the higher the confidence level. In the horizontal scale, the confidence level of the area P directly in front of the working face is relatively high, and the confidence level of other areas decreases as the distance from the directly in front area increases.

[0079] For the coordinate point S Δ (l x , ly , l z Regarding the confidence level of +Δz), we have:

[0080]

[0081] 4. Data revealed at the working face:

[0082] Specifically, for the data revealed at the working face, only the data measured at the test points and the area within a certain range (both horizontally and vertically) around them are set as reliable. The setting rule is similar to the advanced prediction rule, and a decay area (Gaussian distribution) is set according to the rule of decreasing confidence level. Set the planar area of the working face as P s , the planar area affected by the working face within the l z condition is P Δs . Then the data points in the P s area have a high confidence level, and the data points extending longitudinally along this plane rapidly decay to zero confidence level. The same is true for the confidence level of the area spreading around the working plane, that is, the confidence level of the data points decreases accordingly when they are within the area P Δs - P s .

[0083] Furthermore, for the coordinate point S Δ (l x , l y , l z +Δz), the confidence level is:

[0084]

[0085] Furthermore, the present disclosure proposes a posterior update method for the confidence domain rule. As Figure 2 shown, from the above content, it can be obtained that the rules of the data domain and the confidence domain have a great impact on the final parameters. The extension rule of the data domain mainly depends on the relationship between data, but the distribution rule of the confidence domain has certain subjectivity and regionality. Therefore, the present disclosure sets a posterior update process for the confidence domain distribution rule. By feeding back the parameters of individual monitoring points and using the high-dimensional traversal optimization method, the parameters in the confidence domain distribution rule are continuously adjusted. For the coordinate point (l x , l y , l z ), the input parameters of the posterior process are the Gaussian parameters of each confidence domain, the optimization objective is the residual between the parameter calculation value and the actual value, and the traversal objective is to minimize the residual.

[0086] As an alternative implementation, based on the above analysis, the present disclosure obtains the parameter calculation formula at any coordinate point (l x , l y , l z ):

[0087]

[0088] Among them, S * is the parameter at the coordinate point, t is a correction coefficient. When t > 1.0, it can make the data of high-confidence coordinate points have a more significant impact on the final result. In this disclosure, t = 2.50.

[0089] Furthermore, when (l x , l y ) ∈ P, (Δx 2 + Δy 2 + Δz 2 ) 1 / 2 ≤ e d , and (Δx 2 + Δy 2 + Δz 2 ) 1 / 2 ≤ e s , there is the following formula:

[0090]

[0091] As an embodiment, according to the above pre-control parameter analysis process, an application study of a certain tunnel project is carried out to verify the application effect of this method.

[0092] Specifically, the input information is the spatial distribution of the surrounding rock permeability coefficient, and the output information is the grouting reinforcement circle range of different construction sections. The analysis process includes the following:

[0093] The first step: Model the geological section according to the multi-source data fusion analysis method;

[0094] The second step: Establish a calculation method for a reasonable grouting reinforcement circle range applicable to underground engineering;

[0095] The third step: Determine the input rules of multi-source data and calculate the grouting reinforcement circle range of each section of underground engineering to guide the actual engineering application.

[0096] This disclosure takes a simpler and more direct grouting reinforcement circle as the research object. The purpose of this disclosure is to introduce the multi-source data fusion analysis method. Therefore, whether it is the parameter of the grouting reinforcement circle range or the parameters of other measures, this approach can be used to solve the problem. In addition, when using this method for calculation in this disclosure, multiple coordinate point planes perpendicular to the tunneling direction are selected as the research objects, so that the associated calculation can be carried out using tabular files, thereby reducing the overall data calculation amount.

[0097] Specifically, according to relevant research results, it is assumed that the surrounding rock of underground engineering, the grouting reinforcement ring, and the shotcrete are all isotropic, homogeneous, and continuous media; the underwater underground engineering is circular, the water flow is a steady flow, and its motion law follows Darcy's theorem. At the same time, based on the derivation of groundwater dynamics theory, the tunnel drainage volume Q, the water pressure P on the surface of the primary support, and the external water pressure Pg of the grouting reinforcement ring conform to the following formulas:

[0098]

[0099] Among them, E is the thickness of the grouting reinforcement ring, E = r g - r1; Q is the tunnel drainage volume (m3 / s); P is the water pressure on the surface of the initial value (kPa); P g is the external water pressure of the grouting reinforcement ring (kPa); k r is the permeability coefficient of the surrounding rock (m / s); k1 is the permeability coefficient of the initial support (m / s); k g is the permeability coefficient of the initial support (m / s); H is the permeability coefficient of the grouting body (m / s); r0 is the radius of the inner surface of the primary support (m); r1 is the radius of the outer surface of the primary support (m); r2 is the far-field distance, equal to H; r g is the outer radius of the grouting reinforcement ring (m); γ is the specific weight of water (kN / m3); h1 is the water head on the outer surface of the lining (m); h g is the water head outside the grouting reinforcement ring (m).

[0100] Among them, the selection of some parameters: H = r2 water level height; k1 the permeability coefficient of the initial support is 6.5×10-10 m / s; γ the specific weight of water is 10 kN / m3.

[0101] Specifically, as an alternative implementation method, in the present disclosure, for the input of multi-source data, the principle of conservatism is followed. That is, in the same mileage, the 90th percentile value of the corresponding parameter values of all (l x , l y ) is taken as the input value at this mileage. And the pre-control parameters at this mileage are calculated under the input of the input value. In the application research of the present disclosure, the input parameter is the permeability coefficient, and the pre-control parameter is the range of the grouting reinforcement ring. In addition, it should be noted that in the application research of the present disclosure, the reason for choosing the 90th percentile value as the input value is to avoid the adverse effects caused by extreme data.

[0102] Specifically, according to the above calculation process, the pre-control parameters (grouting reinforcement range) of the application tunnel section are analyzed.

[0103] Further, in the applied research of the present disclosure, for the original construction plan, the grouting reinforcement range mainly relies on the calculations of geological exploration and subjective experience. Compared with the optimized design method, the range of the construction sections for parameters in the original construction plan is larger, and for sections with poor geology, a more conservative design is often adopted. The optimized design method of the present invention can continuously adjust the pre-control parameters during the tunneling process to achieve refined treatment. This can be seen from the adjustment of each calculation unit (10 m) in the calculation results. By calculating the volume of the spatial area of the grouting reinforcement based on the results of the gradually reinforced range, it is obtained that the spatial volume of the grouting reinforcement after the optimized design is reduced by 20.64% compared with the original design. In addition, the design of the above method in the present invention significantly reduces the cost in actual engineering construction and helps to achieve a more refined pre-control parameter design.

[0104] Specifically, the present disclosure selects to carry out applied research on the range of the grouting reinforcement circle with a relatively direct and simple calculation process. In addition, it only needs to provide a spatial distribution data situation to verify the fusion analysis method.

[0105] Example 2

[0106] In an embodiment of the present disclosure, a tunnel bad geology pre-control analysis system integrating multi-source data is provided, including:

[0107] A data acquisition module, configured to obtain various types of reliable data such as geological exploration, advanced drilling, advanced geophysical prospecting, and working face exposure for the tunnel surrounding rock environment, and respectively generate spatial coordinate points and corresponding parameters;

[0108] A confidence space domain generation module, configured to assign initial values to each spatial coordinate point and corresponding parameter according to the assignment rule to generate multiple spatial coordinate matrices; assign confidence values to different spatial coordinate points in each spatial coordinate matrix to generate multiple types of confidence space domains;

[0109] A pre-control analysis module, configured to obtain data domain parameters and the relationships between data domains according to the confidence domain association mapping rule, determine the spatial distribution of parameters in the confidence domain, obtain the parameter feedback of individual spatial coordinate points through the posterior update method of the confidence domain rule, and use the high-dimensional traversal optimization method to continuously adjust the parameters in the confidence domain distribution rule with the goal of minimizing the residual between the parameter calculated value and the actual value to obtain the optimal pre-control parameters; calculate the range of the grouting reinforcement circle for each section of the tunnel according to the obtained optimal pre-control parameters to guide the actual engineering application.

[0110] Example 3

[0111] In an embodiment of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, it implements the tunnel bad geology pre-control analysis method integrating multi-source data.

[0112] Example 4

[0113] In one embodiment of the present disclosure, a non-transitory computer-readable storage medium is provided. The non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the tunnel bad geological pre-control analysis method for fusing multi-source data as described above is implemented.

[0114] Example 5

[0115] In one embodiment of the present disclosure, an electronic device is provided, including: a processor, a memory, and a computer program; wherein, the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device runs, the processor executes the computer program stored in the memory so that the electronic device executes the tunnel bad geological pre-control analysis method for fusing multi-source data as described above.

[0116] The present disclosure is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present disclosure. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in one or more flows and / or one or more blocks. Figure 1 one or more flows and / or blocks Figure 1 or the functions specified in a plurality of blocks.

[0117] These computer program instructions can also be loaded onto a computer or other programmable data processing devices, so that a series of operation steps are executed on the computer or other programmable devices to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable devices provide steps for implementing the functions specified in one or more flows and / or one or more blocks. Figure 1 one or more flows and / or blocks Figure 1 or the functions specified in a plurality of blocks.

[0118] Although the specific implementation manners of the present disclosure have been described above in conjunction with the accompanying drawings, it is not a limitation on the scope of protection of the present disclosure. Those skilled in the art should understand that based on the technical solutions of the present disclosure, various modifications or deformations that can be made by those skilled in the art without creative efforts are still within the scope of protection of the present disclosure.

Claims

1. A method for pre-control analysis of tunnel adverse geology integrating multi-source data, characterized in that, Including: For the tunnel surrounding rock environment, obtain various types of reliable data from geological exploration, advanced drilling, advanced geophysical prospecting, and face exposure, and generate spatial coordinate points and corresponding parameters respectively; According to the assignment rules, assign initial values to each spatial coordinate point and corresponding parameter to generate multiple spatial coordinate matrices; Assign confidence values to different spatial coordinate points in each spatial coordinate matrix to generate multiple types of confidence space domains; According to the confidence domain association mapping rules, obtain the data domain parameters and the relationships between data domains, determine the spatial distribution of parameters in the confidence domain, through the posterior update method of the confidence domain rules, obtain the parameter feedback of individual spatial coordinate points, and use the high-dimensional traversal optimization method to minimize the residual between the parameter calculated value and the actual value as the goal, and continuously adjust the parameters in the confidence domain distribution rules to obtain the optimal pre-control parameters; According to the obtained optimal pre-control parameters, calculate the range of the grouting reinforcement circle for each section of the tunnel to guide the actual engineering application.

2. The tunnel bad geological pre-control analysis method for fusing multi-source data according to claim 1, characterized in that, For the tunnel surrounding rock environment, establish underground space coordinate points at set intervals for the underground space. The spatial range is a cuboid space distributed along the mileage in a longitudinal scale, and a rectangular range in the transverse cross-section. The coordinate origin is the midpoint of the tunnel invert. After obtaining various types of reliable data from geological exploration, advanced drilling, advanced geophysical prospecting, and face exposure, generate a table file of spatial coordinate points and corresponding parameters respectively. According to the assignment rules, assign initial values to each spatial coordinate point and corresponding parameter. For each underground environmental parameter, 4 spatial coordinate matrices based on 4 types of exploration data are formed, and the corresponding parameters are permeability coefficient, cohesion, internal friction angle, or lateral pressure coefficient.

3. The tunnel bad geological pre-control analysis method for fusing multi-source data according to claim 1, characterized in that Assign confidence values to different coordinate points in each spatial coordinate matrix. The confidence value is the credibility of the data corresponding to each coordinate point. According to the characteristics of the four types of exploration data, namely geological exploration, advanced drilling, advanced geophysical prospecting, and face exposure, assign a confidence value to each coordinate point to establish 4 types of confidence space domains, and perform a multiplication operation on the coordinate matrix and the corresponding confidence domain, and then obtain the maximum confidence value of a certain coordinate point relative to a certain parameter after weighted averaging.

4. The tunnel adverse geology pre-control analysis method for fusing multi-source data according to claim 1, wherein According to the confidence domain association mapping rules, obtain the data domain parameters and the relationships between data domains, and determine the spatial distribution of parameters in the confidence domain, including: for geological exploration data and advanced drilling data, the distribution form of the confidence domain is a high confidence level in the linear area where the drilling is located, and the confidence level decreases as the distance from the drilling area increases, and its form is characterized by a normal distribution.

5. The tunnel adverse geology pre-control analysis method for fusing multi-source data according to claim 4, characterized in that, For advanced geophysical prospecting data, in the longitudinal scale, the closer to the working face, the higher the confidence level; in the transverse scale, the confidence level is higher in the area directly in front of the working face, and the confidence level in other areas decreases as the distance from the directly in front area increases; for face exposure data, only the data measured at the test point and the area within a set range around it are set as reliable, and the attenuation area is set according to the rule of decreasing confidence level.

6. The tunnel adverse geology pre-control analysis method for fusing multi-source data according to claim 1, characterized in that A posterior update process is set for the confidence domain distribution rule. By feeding back the parameters of individual monitoring points and using the high-dimensional traversal optimization method, the parameters in the confidence domain distribution rule are continuously adjusted. For coordinate points, the input parameters of the posterior process are the Gaussian parameters of each confidence domain. The optimization objective is the residual between the parameter calculated value and the actual value, and the traversal objective is to minimize the residual. Finally, the pre-control parameters are obtained, and the grouting reinforcement circle range of each section of the tunnel is calculated using the pre-control parameters.

7. Tunnel adverse geology pre-control analysis system integrating multi-source data, characterized in that, Including: A data acquisition module, which is used to obtain various types of reliable data such as geological exploration, advanced drilling, advanced geophysical prospecting, and working face exposure for the tunnel surrounding rock environment, and generate spatial coordinate points and corresponding parameters respectively. A confidence space domain generation module, which is used to assign initial values to each spatial coordinate point and corresponding parameter according to the assignment rule to generate multiple spatial coordinate matrices; and assign confidence values to different spatial coordinate points in each spatial coordinate matrix to generate multiple types of confidence space domains. A pre-control analysis module, which is used to obtain the data domain parameters and the relationships between data domains according to the confidence domain association mapping rule, determine the spatial distribution of the parameters in the confidence domain, obtain the parameter feedback of individual spatial coordinate points through the posterior update method of the confidence domain rule, and use the high-dimensional traversal optimization method to continuously adjust the parameters in the confidence domain distribution rule with the goal of minimizing the residual between the parameter calculated value and the actual value to obtain the optimal pre-control parameters; calculate the grouting reinforcement circle range of each section of the tunnel according to the obtained optimal pre-control parameters to guide the actual engineering application.

8. A computer program product comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the tunnel adverse geology pre-control analysis method for fusing multi-source data according to any one of claims 1-6.

9. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, it implements the tunnel adverse geology pre-control analysis method for fusing multi-source data according to any one of claims 1-6.

10. An electronic device, characterized in that, Including: A processor, a memory, and a computer program; wherein, the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device runs, the processor executes the computer program stored in the memory so that the electronic device executes and implements the tunnel adverse geology pre-control analysis method for fusing multi-source data according to any one of claims 1-6.

Images