A method, device and medium for determining the safe distance of a karst cave based on risk prediction

Abstract

The present invention discloses a method, device, equipment and storage medium for determining the safe distance of a karst cave based on risk prediction, including obtaining geological survey data of a target karst area, constructing a geological simulation model of the target karst area according to the geological survey data; constructing a spatial simulation distribution model of the target cave according to the characteristic information of the target cave; integrating the geological simulation model and the spatial simulation distribution model based on tunnel design parameters to obtain a tunnel construction model of the target cave; embedding pre-selected vehicle information into the tunnel construction model to obtain a corresponding tunnel operation model; creating various disaster simulation events and performing risk prediction on the tunnel operation model, and determining the safe distance of the target cave according to the risk prediction results. The present invention optimizes tunnel design and construction, ensures the safety of tunnel construction and operation, and provides accurate data model support for actual tunnel engineering.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel construction, and in particular to a method, device, equipment and storage medium for determining a safe distance of a karst cave based on risk prediction. Background Art

[0002] With the continuous development of tunnel engineering, the construction safety of tunnel engineering in karst areas has also become an issue that cannot be ignored. In karst geological engineering, caves have an important impact on the stability and safety of tunnel structures.

[0003] The construction of tunnel projects may lead to failure, deformation, or even collapse of tunnel structures and water and mud inrush due to inaccurate judgment of the safe distance of karst caves, which will bring serious safety hazards to the construction and operation of tunnels. Accurately evaluating the interaction between karst caves and tunnels and reasonably determining the safe distance are of great significance to the design and construction of tunnel projects in karst areas.

[0004] The existing methods for determining the safe distance of karst caves mainly rely on empirical formulas or empirical judgments, lack systematic analysis and quantitative methods, and ignore a large number of main control factors, which brings safety hazards to the construction, design, operation and maintenance of karst tunnels. In addition, traditional assessment methods often fail to fully consider the comprehensive influence of geological conditions, cave characteristics, tunnel construction, vehicle operation and other factors, resulting in inaccurate assessment results or lack of scientific basis.

[0005] It can be seen that how to use quantitative methods to improve the safety, reliability and economy of tunnel engineering design, construction and operation and maintenance in karst areas has become a technical problem that technical personnel in this field need to solve urgently. Summary of the invention

[0006] The present invention provides a method, device, equipment and storage medium for determining the safe distance of a karst cave based on risk prediction. By designing specific steps of the method for determining the safe distance of a karst cave, the tunnel design and construction are optimized, the safety of tunnel construction and operation is ensured, and accurate data model support is provided for actual tunnel engineering.

[0007] In order to solve the above technical problems, an embodiment of the present invention provides a method for determining a safe distance of a cave based on risk prediction, the method comprising:

[0008] The geological survey data of the target karst area are obtained, and a geological simulation model of the target karst area is constructed according to the geological survey data.

[0009] According to the characteristic information of the target cave, a spatial simulation distribution model of the target cave is constructed.

[0010] Based on tunnel design parameters, the geological simulation model and the spatial simulation distribution model are integrated to obtain a tunnel construction model of the target cave.

[0011] The pre-selected vehicle information is embedded into the tunnel construction model to obtain a corresponding tunnel operation model.

[0012] Create various disaster simulation events and perform risk prediction on the tunnel operation model, and determine the safe distance of the target cave based on the risk prediction results.

[0013] Furthermore, the geological survey data at least includes engineering geological data and hydrogeological data.

[0014] The step of acquiring geological survey data of the target karst region and constructing a geological simulation model of the target karst region according to the geological survey data includes:

[0015] According to the engineering geological data and the hydrogeological data, a fracture-surrounding rock geological model and a fault-surrounding rock geological model of the target karst area are constructed respectively.

[0016] Furthermore, the construction of the fracture-surrounding rock geological model of the target karst area includes:

[0017] Based on the fracture attribute data in the engineering geological data and the fracture attribute data in the hydrogeological data, corresponding fracture rose diagrams are generated.

[0018] The occurrence, direction and quantity distribution law of the cracks in the crack rose diagram are used as independent variables, the spatial coordinates of the cracks and the total number of crack surfaces are used as dependent variables, and random crack surfaces are generated through a random crack generation program.

[0019] A fracture body is generated according to the random fracture surface and imported into a 3D model to form the fracture-surrounding rock geological model.

[0020] Furthermore, the construction of the fault-surrounding rock geological model of the target karst area includes:

[0021] Based on the fault information data in the engineering geological data, an initial geometric model of the fault is established.

[0022] The initial geometric model is processed according to preset simulation software, and an upper fault wedge, a fracture zone, and a lower fault wedge are sequentially generated on the initial geometric model to obtain the fault-surrounding rock geological model.

[0023] Furthermore, the characteristic information at least includes diameter distribution information, cave height distribution information, point karst rate information, line karst rate information, surface karst rate information, body karst rate information, and cave burial depth distribution information.

[0024] The method further comprises:

[0025] Statistical analysis is performed on each of the characteristic information to construct a spatial simulation distribution model of the target cave.

[0026] Furthermore, the performing statistical analysis on each of the characteristic information includes:

[0027] The distribution histogram corresponding to each of the feature information is drawn in turn.

[0028] A preset fitting method is selected to fit each of the distribution histograms to obtain a priori probability density function corresponding to each of the feature information, wherein the preset fitting method at least includes exponential distribution fitting, normal distribution fitting, Poisson distribution fitting, lognormal distribution fitting or F distribution function fitting.

[0029] According to the Bayesian update algorithm, the prior probability density function corresponding to each feature information is screened and updated in turn to obtain the posterior probability density function of each feature information.

[0030] The posterior probability density function is used to construct a spatial simulation distribution model of the target cave.

[0031] Furthermore, constructing a spatial simulation distribution model of the target cave according to the characteristic information of the target cave includes:

[0032] Inputting each of the characteristic information after statistical analysis into a cellular automaton algorithm to construct a spatial simulation distribution model of the target cave; or,

[0033] The characteristic information after statistical analysis is input into a three-dimensional surface reconstruction algorithm based on the Poisson equation to construct a spatial simulation model of the target cave.

[0034] Furthermore, based on the tunnel design parameters, the geological simulation model and the spatial simulation distribution model are integrated to obtain a tunnel construction model of the target cave, including:

[0035] The tunnel design information data selected by the user is converted into the tunnel design parameters.

[0036] Based on the tunnel design parameters, integration target data and evaluation standard data are determined.

[0037] A corresponding integration method is selected to integrate the geological simulation model and the spatial simulation distribution model to obtain a tunnel construction model of the target cave, wherein the integration method includes at least one of the following methods: average fusion, weighted average fusion, voting fusion or stacking fusion.

[0038] Furthermore, embedding the pre-selected vehicle information into the tunnel construction model to obtain a corresponding tunnel operation model includes:

[0039] A vehicle dynamic load function is established based on the vehicle type, vehicle operating speed and vehicle load distribution of the pre-selected vehicle.

[0040] The vehicle dynamic load function is embedded in the tunnel construction model to obtain the tunnel operation model.

[0041] Furthermore, the creating of various disaster simulation events and performing risk prediction on the tunnel operation model, and determining the safe distance of the target cave according to the risk prediction results, include:

[0042] Sensitivity factor analysis is performed on the tunnel construction model and the tunnel operation model respectively.

[0043] Several simulation conditions are generated based on the sensitivity factor analysis results.

[0044] A corresponding disaster simulation event is created for each of the simulation conditions, and the probability of occurrence of each of the disaster simulation events is calculated.

[0045] Based on a preset quantitative disaster formula, the disaster risk corresponding to each of the disaster simulation events is quantified.

[0046] Draw a mapping diagram between each quantified disaster risk and different cave distances.

[0047] According to the mapping relationship diagram, the maximum value of the cave treatment distance corresponding to each of the disaster simulation events is determined, and the maximum value of the cave treatment distance is used as the safety distance of the target cave.

[0048] Furthermore, the sensitivity factor analysis of the tunnel construction model and the tunnel operation model includes:

[0049] The orthogonal analysis method is used to select the uncertain factors in the tunnel construction model and the tunnel operation model respectively; the uncertain factors at least include surrounding rock grade, lateral pressure coefficient, groundwater level, water pressure in the cavity, cave burial depth, cave shape, excavation footage, vehicle load, and the relative distance and position between the cave and the tunnel.

[0050] A sensitivity factor analysis is performed on each of the uncertain factors, and each of the uncertain factors is ranked according to the obtained sensitivity.

[0051] Furthermore, the method generates several simulation conditions according to the sensitivity factor analysis results; creates corresponding disaster simulation events for each simulation condition, and calculates the probability of occurrence of each disaster simulation event, including:

[0052] A number of the uncertain factors that meet the conditions are selected and the attribute value range corresponding to each of the uncertain factors is determined.

[0053] Based on the qualified uncertain factors and the corresponding attribute value ranges, a Monte Carlo method is used to generate several different simulation conditions.

[0054] A disaster simulation event is created for each of the simulation conditions, and the probability of occurrence of each of the disaster simulation events is calculated; the disaster simulation events at least include: sudden water and mud bursts, collapse, shield head falling, large deformation during tunnel construction, and collapse, large deformation, and collapse of adjacent structures during tunnel operation.

[0055] Furthermore, the preset quantitative catastrophe formula is:

[0056] R=P×(C1+C2)

[0057] Among them, R is the disaster risk; P is the disaster probability; C1 and C2 are the direct losses and indirect losses corresponding to the disaster simulation events respectively.

[0058] Another embodiment of the present invention provides a device for determining a safe distance of a cave based on risk prediction, comprising:

[0059] The data acquisition module is used to acquire geological survey data of the target karst area and construct a geological simulation model of the target karst area according to the geological survey data.

[0060] The cave space module is used to construct a spatial simulation distribution model of the target cave according to the characteristic information of the target cave.

[0061] The tunnel construction module is used to integrate the geological simulation model and the spatial simulation distribution model based on tunnel design parameters to obtain a tunnel construction model of the target cave.

[0062] The tunnel operation module is used to embed the pre-selected vehicle information into the tunnel construction model to obtain a corresponding tunnel operation model.

[0063] The safety distance determination module is used to create various disaster simulation events and perform risk prediction on the tunnel operation model, and determine the safety distance of the target cave according to the risk prediction results.

[0064] Another embodiment of the present invention provides a computer device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, the method for determining the safe distance of a cave based on risk prediction as described above is implemented.

[0065] Yet another embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the method for determining the safe distance of a cave based on risk prediction as described above is implemented.

[0066] Compared with the prior art, the embodiments of the present invention have the following advantages:

[0067] (1) By comprehensively considering the combined effects of geological, karst cave, tunnel and operational factors, quantitative analysis and evaluation of tunnel construction can ensure the safety and reliability of tunnel construction in karst areas;

[0068] (2) By accurately determining the safe distance of the cave, the safety of the tunnel after it is built and put into operation can be ensured, effectively avoiding safety accidents during driving;

[0069] (3) Reasonable setting of safety distance based on the model calculation results can minimize the amount of tunnel construction while ensuring safety, thereby reducing the construction cost;

[0070] (4) Based on the organic combination of different data models, data processing simulation services and advanced information network technology are used to effectively analyze a variety of safety data of tunnel caves. An intelligent analysis platform for cave safety distances composed of various models is built to accurately obtain safety distances, thereby optimizing tunnel design and construction, ensuring the safety of tunnel construction and operation, eliminating tunnel disaster risks, and providing accurate data model support for actual tunnel projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 A flowchart of the steps of a method for determining a safe distance of a karst cave based on risk prediction provided by an embodiment of the present invention;

[0072] Figure 2 A diagram of the construction process of a fracture-surrounding rock geological model for a method for determining a safe distance of a karst cave based on risk prediction provided in an embodiment of the present invention;

[0073] Figure 3 A diagram of the fault-surrounding rock geological model construction process of the risk prediction-based karst cave safety distance determination method provided in an embodiment of the present invention;

[0074] Figure 4 A schematic diagram of the process of establishing a spatial simulation distribution model of a karst cave provided in an embodiment of the present invention;

[0075] Figure 5 A schematic diagram of determining the cave treatment distance provided by an embodiment of the present invention;

[0076] Figure 6A structural block diagram of a device for determining a safe distance of a cave based on risk prediction and based on adversarial learning provided by an embodiment of the present invention;

[0077] Figure 7 A structural diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0078] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0079] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0080] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used herein are only for illustrative purposes, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0081] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0082] An embodiment of the present invention provides a method for determining a cave safety distance based on risk prediction. For details, see Figure 1 , Figure 1 A flow chart showing the steps of a method for determining a safe distance of a karst cave based on risk prediction provided by an embodiment of the present invention includes steps S11 to S15:

[0083] Step S11, obtaining geological survey data of a target karst area, and constructing a geological simulation model of the target karst area according to the geological survey data.

[0084] Preferably, the embodiment of the present invention first uniformly collects all relevant information data. For ease of display, please refer to Table 1. Table 1 shows a summary table of all data in one embodiment of the present invention. The engineering geological conditions and hydrogeological conditions in the table refer to the geological survey data in step S11, the cave information in the table refers to the target cave characteristic information in step S12, the tunnel construction in the table refers to the tunnel design parameters in step S13, and the tunnel operation in the table refers to the vehicle information in step S14.

[0085]

[0086]

[0087] Table 1

[0088] Preferably, geological survey data of the target karst area can be collected by using geological exploration, drilling measurement and other methods, and the geological survey data at least includes engineering geological data and hydrogeological data; then the engineering geological information and hydrogeological information are quantified to obtain engineering geological data and hydrogeological data, and a fracture-fault-surrounding rock geological model is constructed.

[0089] Specifically, the construction of the fracture-fault-surrounding rock geological model includes two parts:

[0090] 1) Construct fracture-rock geological model: Figure 2 As shown, Figure 2 A diagram showing the construction process of the fracture-surrounding rock geological model of the risk prediction-based cave safety distance determination method provided in an embodiment of the present invention is shown, and the specific steps are:

[0091] Based on the fracture attribute data in the engineering geological data and the fracture attribute data in the hydrogeological data, the corresponding fracture rose diagram is generated; specifically, the fracture attribute data includes fracture direction, dip, occurrence and quantity.

[0092] With the occurrence, direction and quantity distribution law of cracks in the crack rose diagram as independent variables, and the spatial coordinates of the cracks and the total number of crack surfaces as dependent variables, random crack surfaces were generated in AutoCAD through a random crack generation program.

[0093] Finally, the fracture body is generated according to the random fracture surface in 3DEC and imported into the 3D model in the finite difference software Flac to form the fracture-surrounding rock geological model.

[0094] 2) Construct fault-rock geological model: Figure 3 As shown, Figure 3 A diagram showing a fault-surrounding rock geological model construction process of a cave safety distance determination method based on risk prediction provided by an embodiment of the present invention is shown, and the specific steps are:

[0095] Based on the fault information data in the engineering geological data, the initial geometric model of the fault is established in Gocad.

[0096] The upper fault wedge was generated by importing it into Flac 3D software; the fracture zone was defined according to the fault geometry model; and finally, the lower fault wedge was generated on the other side of the fracture zone to complete the fault-surrounding rock geological model.

[0097] By investigating and quantifying geological information in advance and establishing a three-dimensional geological model of the karst area based on the geological data, it is possible to fully and accurately express the geological conditions and various geological structures of the complex karst landforms, intuitively reflect the spatial distribution of the karst area and the information such as faults and fissures and their mutual relationships, and improve the accuracy and intuitiveness of geological engineering surveys, so as to facilitate subsequent evaluation and analysis in combination with tunnel design data.

[0098] Step S12: constructing a spatial simulation distribution model of the target cave according to the characteristic information of the target cave.

[0099] Preferably, the characteristic information at least includes diameter distribution information, cave height distribution information, point karst rate information, line karst rate information, surface karst rate information, body karst rate information, and cave depth distribution information. Of course, the characteristic information may also include other types of information data, which are not specifically limited in the embodiments of the present invention.

[0100] In the above embodiment, statistical analysis is performed on each of the characteristic information. Specifically, this embodiment takes the hole height distribution as an example. Other types of characteristic information can be referred to accordingly. The statistical analysis steps are described in detail as follows:

[0101] 1) Collect borehole height data of the same rock system as the project, and determine the range, number of groups and group interval of the borehole height data.

[0102] 2) Draw a histogram of the hole height distribution, and use exponential distribution, normal distribution, Poisson distribution, lognormal distribution, F distribution and other functions for fitting to obtain the hole height prior probability density function PDFf(l,λ) of the macro site, where the parameter to be updated is λ. According to the empirical conjugate distribution table shown in Table 2, the prior distribution PDF of parameter λ is f′(λ).

[0103]

[0104]

[0105] Table 2

[0106] 3) Using the Bayesian update algorithm, according to the hole height data of the actual project, the posterior distribution PDF of the updated parameter λ is obtained as f″(λ)=KL(λ)f′(λ), where K is the normalization constant and L(λ) is the likelihood function.

[0107] 4) The posterior probability distribution function f'(l,λ) of the hole height of a specific site is obtained through the Bayesian update algorithm.

[0108] like Figure 4 As shown, Figure 4 A schematic diagram of the process of establishing a spatial simulation distribution model of a karst cave provided in an embodiment of the present invention is shown. After completing the statistical analysis of karst geological characteristic information, a spatial simulation distribution model of a karst cave group is established based on the above characteristic information.

[0109] Specifically, a spatial simulation distribution model of the target cave is constructed. In this embodiment, it is assumed that the cave is spherical, and two methods for establishing the spatial simulation distribution model are provided, which are as follows:

[0110] 1) Inputting each of the characteristic information after statistical analysis into a cellular automaton algorithm, and using the cellular automaton algorithm to establish a cave model, including:

[0111] Select the target rock mass and determine its size and geometry.

[0112] A three-dimensional space model is established and divided into cellular grids based on the cellular automaton algorithm.

[0113] The cave generation rules are input into the three-dimensional space model. These rules will guide the behavior of the cellular automaton. The cave generation rules specifically include cave diameter distribution, cave height distribution, point karst rate, line karst rate, surface karst rate, body karst rate, cave burial depth distribution, and rock soluble coefficient parameters.

[0114] An iterative time step is set for the three-dimensional space model and an iterative simulation is performed. In each iterative time step, the cell decides whether to generate a cave according to surrounding conditions and rules.

[0115] Finally, the generated cave group is used as a spatial simulation distribution model of the cave and exported into a grid file format. Optionally, the file suffix is ​​.f3grid or .flac3d.

[0116] 2) Inputting each of the characteristic information after statistical analysis into a three-dimensional surface reconstruction algorithm based on the Poisson equation, and establishing a cave model using a three-dimensional Poisson process method, including:

[0117] Select the target rock mass and determine its size and geometry.

[0118] According to the point dissolution rate of karst and the horizontal area of ​​rock mass, the number of caves in the rock mass space is calculated.

[0119] The three-dimensional coordinates of the sphere center of the cave are generated according to the karst burial depth distribution and the cave location distribution.

[0120] Assuming that the cave is spherical and the cave height is used as the radius, a cave model is generated according to the cave height distribution, and the filling material parameters and water pressure parameters in the cave are assigned.

[0121] Through the above process, a karst cave spatial simulation distribution model that can reflect the spatial distribution of the cave is established. This can accurately grasp the karst cave structure and characteristics before tunnel construction, predict and evaluate the impact of the cave on tunnel construction, formulate targeted construction plans, improve construction efficiency and reduce costs.

[0122] Step S13, based on the tunnel design parameters, the geological simulation model and the spatial simulation distribution model are integrated to obtain a tunnel construction model of the target cave.

[0123] Tunnel design parameters are collected and quantified, and integrated target data and evaluation standard data are determined based on the tunnel design parameters.

[0124] Based on the tunnel design parameters, the geological simulation model and the spatial simulation distribution model of the cave are integrated using any integration method including average fusion, weighted average fusion, voting fusion or stacking fusion to obtain the tunnel construction model.

[0125] According to the tunnel construction model, the influence of mechanical vibration and surrounding rock stress unloading on tunnels and caves during tunnel excavation and their response laws are analyzed, and targeted measures are specified.

[0126] The geological simulation model reflecting karst geology and the spatial simulation distribution model reflecting the spatial distribution in the cave are reasonably integrated by combining the tunnel design parameters. This can comprehensively evaluate the actual tunnel construction by integrating the various attributes of geology and caves, improve the prediction accuracy, and combine the advantages of the two closely with tunnel design, thereby improving the generalization ability and overall performance of the model.

[0127] Step S14, embedding the pre-selected vehicle information into the tunnel construction model to obtain a corresponding tunnel operation model.

[0128] The vehicle dynamic load function is established and embedded in the model according to the vehicle type, average vehicle speed, maximum speed, acceleration and vehicle load distribution, which is used to analyze the stress and vibration level applied to different parts of the tunnel to form a tunnel operation model.

[0129] In addition, the vehicle dynamic load model can also be established by monitoring the dynamic loads of trains of similar levels during operation, fitting the dynamic load function, and embedding the vehicle dynamic load finite element simulation software to form a vehicle dynamic load model.

[0130] Taking future vehicle operation conditions into consideration during tunnel design can improve the tunnel's capacity and safety, and allow tunnel design to take operation conditions into consideration during the construction phase. This can reduce safety hazards after the tunnel is built and put into use, optimize design solutions, reduce operating costs, and meet future transportation development needs.

[0131] Step S15, creating various disaster simulation events and performing risk prediction on the tunnel operation model, and determining the safe distance of the target cave according to the risk prediction results.

[0132] The orthogonal analysis method was used to conduct sensitivity analysis on the tunnel construction model and the tunnel operation model. Specifically, the uncertain factors include surrounding rock grade, lateral pressure coefficient, groundwater level, water pressure in the cavity, cave depth, cave shape, excavation footage, vehicle load, relative distance and position between the cave and the tunnel, etc.

[0133] According to the results of sensitivity analysis, various uncertain factors are ranked.

[0134] According to actual needs, select uncertain factors with higher sensitivity and determine the value range of each selected uncertain factor.

[0135] According to the selected uncertain factors, the Monte Carlo method is used to generate several different simulation conditions, and the simulation conditions that do not conform to the actual project are deleted, leaving the simulation conditions that conform to the actual situation.

[0136] A disaster simulation event is created for each simulation condition, and whether a disaster occurs in the karst tunnel is determined based on local strain, local stress, plastic strain criteria, etc.

[0137] Specifically, the disaster simulation events include: disasters such as sudden water and mud, collapse, shield machine head falling, large deformation during tunnel construction, and disasters such as collapse, large deformation, and collapse of adjacent structures during tunnel operation.

[0138] In this embodiment, the criteria for determining a disaster are:

[0139] Strength failure criterion: Based on the Griffth and Hoek-Brown criteria, when the surrounding rock stress level exceeds the strength range of the surrounding rock, the karst tunnel is judged to be a disaster.

[0140] Plastic zone breakthrough criterion: When the plastic zone area exceeds the cross-sectional area of ​​the tunnel, or the plastic zone between the tunnel and the karst cave is connected, a karst tunnel disaster is judged.

[0141] Strain failure criterion: When the rock mass forms a continuous plastic zone or sliding surface, resulting in strain concentration, or the strain exceeds the limiting strain of the surrounding rock, a karst tunnel disaster is judged.

[0142] According to the types of disaster simulation events and disaster judgment criteria mentioned above, the occurrence probability of each disaster simulation event is calculated. Assuming that there are n simulation conditions and the number of disaster simulation events is f, the disaster probability is p=f / n.

[0143] The disaster risk is quantified by combining the disaster probability and the corresponding disaster consequences. This embodiment quantifies the disaster process based on a preset disaster quantification formula, specifically:

[0144] R=P×(C1+C2)

[0145] Among them, R is the disaster risk; P is the disaster probability; C1 and C2 are the direct losses and indirect losses corresponding to the disaster simulation events respectively.

[0146] like Figure 5 As shown, Figure 5 A schematic diagram of cave treatment distance determination provided in an embodiment of the present invention is shown. According to the relationship between cave distance and risk, a mapping relationship diagram between each quantified disaster risk and different cave distances is drawn.

[0147] According to the mapping relationship diagram, the cave treatment distance corresponding to each disaster simulation event is determined, and the maximum value of the cave treatment distance corresponding to each disaster simulation event is taken as the safe distance of the cave.

[0148] The method for determining the safe distance of a karst cave based on risk prediction of the present invention can ensure the safety and reliability of tunnel construction in karst areas by comprehensively considering the comprehensive influence of geological, karst cave, tunnel and operation factors; by accurately determining the safe distance of the karst cave and taking corresponding measures, the safety of the tunnel after it is built and put into operation can be ensured, thereby effectively avoiding safety accidents during driving; by reasonably setting the safe distance according to the calculation results of the model, the engineering volume of the tunnel can be minimized while ensuring safety, thereby reducing the engineering cost.

[0149] The embodiment of the present invention further provides a device for determining a safe distance of a cave based on risk prediction, which is used to execute the method for determining a safe distance of a cave based on risk prediction as described above. Figure 6 The structure block diagram of the device for determining the safe distance of a karst cave based on risk prediction according to an embodiment of the present invention includes:

[0150] The data acquisition module 21 is used to acquire geological survey data of the target karst area and construct a geological simulation model of the target karst area according to the geological survey data.

[0151] The cave space module 22 is used to construct a spatial simulation distribution model of the target cave according to the characteristic information of the target cave.

[0152] The tunnel construction module 23 is used to integrate the geological simulation model and the spatial simulation distribution model based on tunnel design parameters to obtain a tunnel construction model of the target cave.

[0153] The tunnel operation module 24 is used to embed the pre-selected vehicle information into the tunnel construction model to obtain a corresponding tunnel operation model.

[0154] The safety distance determination module 25 is used to create various disaster simulation events and perform risk prediction on the tunnel operation model, and determine the safety distance of the target cave according to the risk prediction results.

[0155] The technical features and technical effects of the system proposed in the embodiment of the present invention are the same as those of the method proposed in the embodiment of the present invention, and are not described in detail here. Each module in the above system can be implemented in whole or in part by software, hardware, and a combination thereof. Each of the above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0156] An embodiment of the present invention also provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute the method for determining the cave safety distance based on risk prediction as described above.

[0157] The embodiment of the present invention further provides a computer device, Figure 7 The present invention provides a structural block diagram of a preferred embodiment of a computer device, wherein the computer device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the method for determining the safe distance of a cave based on risk prediction as described above when executing the computer program.

[0158] Preferably, the computer program can be divided into one or more modules / units (such as computer program 1, computer program 2, ...), and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the computer device.

[0159] The processor may be a central processing unit (CPU), or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor. The processor is the control center of the computer device, and various parts of the computer device are connected using various interfaces and lines.

[0160] The memory mainly includes a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function, etc., and the data storage area can store related data, etc. In addition, the memory can be a high-speed random access memory, or a non-volatile memory, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, and a flash card (Flash Card), etc., or the memory can also be other volatile solid-state storage devices.

[0161] It should be noted that the above-mentioned computer device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that Figure 7 The structural block diagram is merely an example of a computer device and does not constitute a limitation of the computer device, and may include more or less components than shown in the figure, or combine certain components, or different components.

[0162] In summary, the method, device, equipment and storage medium for determining the safe distance of a cave based on risk prediction provided by the embodiments of the present invention have the following beneficial effects:

[0163] (1) By comprehensively considering the combined effects of geological, karst cave, tunnel and operational factors, quantitative analysis and evaluation of tunnel construction can ensure the safety and reliability of tunnel construction in karst areas;

[0164] (2) By accurately determining the safe distance of the cave, the safety of the tunnel after it is built and put into operation can be ensured, effectively avoiding safety accidents during driving;

[0165] (3) Reasonable setting of safety distance based on the model calculation results can minimize the amount of tunnel construction while ensuring safety, thereby reducing the construction cost;

[0166] (4) Based on the organic combination of different data models, data processing simulation services and advanced information network technology are used to effectively analyze a variety of safety data of tunnel caves, build a unified intelligent analysis platform for cave safety distances, and achieve accurate acquisition of safety distances, thereby optimizing tunnel design and construction, ensuring the safety of tunnel construction and operation, eliminating tunnel disaster risks, and providing accurate data model support for actual tunnel projects.

[0167] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for determining the safe distance of a cave based on risk prediction, characterized in that: include: Acquiring geological survey data of a target karst area, and constructing a geological simulation model of the target karst area according to the geological survey data; Constructing a spatial simulation distribution model of the target cave according to the characteristic information of the target cave; Based on tunnel design parameters, the geological simulation model and the spatial simulation distribution model are integrated to obtain a tunnel construction model of the target cave; embedding the pre-selected vehicle information into the tunnel construction model to obtain a corresponding tunnel operation model; Creating various disaster simulation events and performing risk prediction on the tunnel operation model, and determining the safe distance of the target cave according to the risk prediction results; Specifically include: The tunnel construction model and the tunnel operation model are respectively subjected to sensitivity factor analysis; the sensitivity factor analysis process comprises: using the orthogonal analysis method to select the uncertain factors in the tunnel construction model and the tunnel operation model respectively; the uncertain factors at least include the surrounding rock grade, lateral pressure coefficient, groundwater level, water pressure in the karst cavity, karst cave burial depth, karst cave shape, excavation footage, vehicle load, and the relative distance and position between the karst cave and the tunnel; performing sensitivity factor analysis on each of the uncertain factors, and ranking each of the uncertain factors according to the obtained sensitivity; Generate several simulation conditions based on the sensitivity factor analysis results; Creating corresponding disaster simulation events for each of the simulation conditions, and calculating the probability of occurrence of each of the disaster simulation events; Based on a preset quantitative disaster formula, quantify the disaster risk corresponding to each of the disaster simulation events; Draw a mapping diagram between each quantified disaster risk and different cave distances; According to the mapping relationship diagram, the maximum value of the cave treatment distance corresponding to each of the disaster simulation events is determined, and the maximum value of the cave treatment distance is used as the safety distance of the target cave.

2. The method for determining the safe distance of a cave based on risk prediction according to claim 1, characterized in that: The geological survey data at least includes engineering geological data and hydrogeological data; then, The step of acquiring geological survey data of the target karst region and constructing a geological simulation model of the target karst region according to the geological survey data includes: According to the engineering geological data and the hydrogeological data, a fracture-surrounding rock geological model and a fault-surrounding rock geological model of the target karst area are constructed respectively.

3. The method for determining the safe distance of a karst cave based on risk prediction according to claim 2, characterized in that: The constructing of the fracture-surrounding rock geological model of the target karst area includes: Generate corresponding fracture rose diagrams based on fracture attribute data in the engineering geological data and fracture attribute data in the hydrogeological data respectively; Taking the occurrence, direction and quantity distribution law of the cracks in the crack rose diagram as independent variables, taking the spatial coordinates of the cracks and the total number of crack surfaces as dependent variables, a random crack surface is generated through a random crack generation program; A fracture body is generated according to the random fracture surface and imported into a 3D model to form the fracture-surrounding rock geological model.

4. The method for determining the safe distance of a cave based on risk prediction according to claim 2, characterized in that: The constructing of the fault-surrounding rock geological model of the target karst area includes: Based on the fault information data in the engineering geological data, an initial geometric model of the fault is established; The initial geometric model is processed according to preset simulation software, and an upper fault wedge, a fracture zone, and a lower fault wedge are sequentially generated on the initial geometric model to obtain the fault-surrounding rock geological model.

5. The method for determining the safe distance of a karst cave based on risk prediction according to claim 1, characterized in that: The characteristic information at least includes diameter distribution information, cave height distribution information, point karst rate information, line karst rate information, surface karst rate information, body karst rate information, and cave burial depth distribution information; The method further comprises: Statistical analysis is performed on each of the characteristic information to construct a spatial simulation distribution model of the target cave.

6. The method for determining the safe distance of a karst cave based on risk prediction according to claim 5, characterized in that: The statistical analysis of each feature information includes: Draw a distribution histogram corresponding to each of the feature information in sequence; Selecting a preset fitting method to fit each of the distribution histograms to obtain a priori probability density function corresponding to each of the feature information, wherein the preset fitting method at least includes exponential distribution fitting, normal distribution fitting, Poisson distribution fitting, lognormal distribution fitting or F distribution function fitting; According to the Bayesian update algorithm, the prior probability density function corresponding to each feature information is sequentially screened and updated to obtain the posterior probability density function of each feature information; The posterior probability density function is used to construct a spatial simulation distribution model of the target cave.

7. The method for determining the safe distance of a karst cave based on risk prediction according to claim 6, characterized in that: The step of constructing a spatial simulation distribution model of the target cave according to the characteristic information of the target cave comprises: Inputting each of the characteristic information after statistical analysis into a cellular automaton algorithm to construct a spatial simulation distribution model of the target cave; or, The characteristic information after statistical analysis is input into a three-dimensional surface reconstruction algorithm based on the Poisson equation to construct a spatial simulation model of the target cave.

8. The method for determining the safe distance of a karst cave based on risk prediction according to claim 1, characterized in that: The step of integrating the geological simulation model and the spatial simulation distribution model based on the tunnel design parameters to obtain a tunnel construction model of the target cave comprises: Converting the tunnel design information data selected by the user into the tunnel design parameters; Based on the tunnel design parameters, determining integrated target data and evaluation standard data; A corresponding integration method is selected to integrate the geological simulation model and the spatial simulation distribution model to obtain a tunnel construction model of the target cave, wherein the integration method includes at least one of the following methods: average fusion, weighted average fusion, voting fusion or stacking fusion.

9. The method for determining the safe distance of a karst cave based on risk prediction according to claim 1, characterized in that: The embedding of the pre-selected vehicle information into the tunnel construction model to obtain a corresponding tunnel operation model includes: Establishing a vehicle dynamic load function based on the vehicle type, vehicle operating speed and vehicle load distribution of the pre-selected vehicle; The vehicle dynamic load function is embedded in the tunnel construction model to obtain the tunnel operation model.

10. The method for determining the safe distance of a karst cave based on risk prediction according to claim 1, characterized in that: The method generates several simulation conditions according to the sensitivity factor analysis results; Creating a corresponding disaster simulation event for each of the simulation conditions and calculating the probability of occurrence of each of the disaster simulation events include: Selecting a number of the uncertain factors that meet the conditions and determining the attribute value range corresponding to each of the uncertain factors; Based on the qualified uncertain factors and the corresponding attribute value ranges, a Monte Carlo method is used to generate several different simulation conditions; A disaster simulation event is created for each of the simulation conditions, and the probability of occurrence of each of the disaster simulation events is calculated; the disaster simulation events at least include: sudden water and mud bursts, collapse, shield head falling, large deformation during tunnel construction, and collapse, large deformation, and collapse of adjacent structures during tunnel operation.

11. The method for determining the safe distance of a karst cave based on risk prediction according to claim 10, characterized in that: The preset quantitative catastrophe formula is: R=P×(C1+C2) Among them, R is the disaster risk; P is the disaster probability; C1 and C2 are the direct losses and indirect losses corresponding to the disaster simulation events respectively.

12. A device for determining the safe distance of a cave based on risk prediction, characterized in that: include: A data acquisition module, used to acquire geological survey data of a target karst area, and to construct a geological simulation model of the target karst area according to the geological survey data; The karst cave space module is used to construct a spatial simulation distribution model of the target karst cave according to the characteristic information of the target karst cave; A tunnel construction module, used to integrate the geological simulation model and the spatial simulation distribution model based on tunnel design parameters to obtain a tunnel construction model of the target cave; A tunnel operation module, used for embedding pre-selected vehicle information into the tunnel construction model to obtain a corresponding tunnel operation model; A safety distance determination module is used to create various disaster simulation events and perform risk prediction on the tunnel operation model, and determine the safety distance of the target cave according to the risk prediction results; Specifically include: The tunnel construction model and the tunnel operation model are respectively subjected to sensitivity factor analysis; the sensitivity factor analysis process comprises: using the orthogonal analysis method to select the uncertain factors in the tunnel construction model and the tunnel operation model respectively; the uncertain factors at least include the surrounding rock grade, lateral pressure coefficient, groundwater level, water pressure in the karst cavity, karst cave burial depth, karst cave shape, excavation footage, vehicle load, and the relative distance and position between the karst cave and the tunnel; performing sensitivity factor analysis on each of the uncertain factors, and ranking each of the uncertain factors according to the obtained sensitivity; Generate several simulation conditions based on the sensitivity factor analysis results; Creating corresponding disaster simulation events for each of the simulation conditions, and calculating the probability of occurrence of each of the disaster simulation events; Based on a preset quantitative disaster formula, quantify the disaster risk corresponding to each of the disaster simulation events; Draw a mapping diagram between each quantified disaster risk and different cave distances; According to the mapping relationship diagram, the maximum value of the cave treatment distance corresponding to each of the disaster simulation events is determined, and the maximum value of the cave treatment distance is used as the safety distance of the target cave.

13. A computer device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the method for determining the safe distance of a cave based on risk prediction as described in any one of claims 1 to 11 is implemented.

14. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the method for determining the safe distance of a cave based on risk prediction as described in any one of claims 1 to 11 is implemented.

Images