A method and system for intelligent assessment of landslide risk in tunnel surrounding areas

Abstract

The present invention relates to the technical field of geological material analysis, and specifically to an intelligent landslide risk assessment method and system for the surrounding area of ​​a tunnel, comprising the following steps: extracting wave velocity, attenuation coefficient, and density parameters from geological elastic wave data, performing digital coding, and forming an initial data set. In the present invention, an initial data set with high information density is constructed through geological elastic wave data analysis, the quality and efficiency of data screening are improved, the careful observation of stress distribution and surface displacement during data selection is optimized, and the ability to capture dynamic changes in geological conditions is enhanced. By simulating elastic wave propagation, cracks and cavities in geological media are accurately analyzed, providing more detailed insights into geological heterogeneity. This method not only calibrates landslide triggering factors more accurately, but also effectively identifies and evaluates high-risk areas, greatly improving the risk management and early warning accuracy of tunnels and key infrastructure, and reducing the potential impact of geological disasters.

Description

Technical Field

[0001] The present invention relates to the technical field of geological material analysis, and in particular to a method and system for intelligently assessing landslide risks in a tunnel peripheral area. Background Art

[0002] The field of geological material analysis technology covers a variety of methods and techniques used to study and evaluate materials below the Earth's surface, such as soils, rocks, sediments, etc. These techniques are often used to understand the composition, structure, physical and chemical properties of geological materials, and their behavior in natural and artificial environments. Analytical methods include physical testing, chemical analysis, mineralogical identification, and non-destructive detection techniques using modern sensors and data processing technology. These analyses are essential for predicting the behavior of geological materials under specific environmental conditions, such as in construction, civil engineering, mining, environmental science, and geohazard assessment.

[0003] Among them, an intelligent landslide risk assessment method for the area around the tunnel refers to the use of advanced monitoring technology and data analysis tools to predict and evaluate the stability of soil and rock around the tunnel, thereby identifying risk factors that may cause landslides. This method usually includes geological exploration, real-time monitoring equipment (such as ground radar and sensors), and data analysis software, which work together to collect and analyze geological data in real time to provide early warning of potential landslides and collapses. The main purpose of this technology is to enhance tunnel safety, reduce losses caused by geological disasters, and ensure the safe operation of transportation and engineering projects.

[0004] Existing technologies predict the behavior of geological materials based on static analysis of physical and chemical properties, and lack the ability to respond immediately to dynamic changes in geological conditions. In critical geological engineering projects, insufficient monitoring of tiny cracks and cavities may lead to potential risks being ignored and increase the incidence of safety accidents. In addition, traditional methods are inefficient in processing and updating large amounts of geological data and are difficult to meet the needs of rapid decision-making, which leads to delays in risk identification and implementation of response measures, which may cause significant losses without timely warning. Therefore, existing technologies have obvious deficiencies in improving geological engineering safety and disaster emergency response capabilities. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent landslide risk assessment method and system for the area surrounding a tunnel.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a method for intelligently assessing landslide risk in the surrounding area of ​​a tunnel, comprising the following steps:

[0007] S1: Extract wave velocity, attenuation coefficient, and density parameters from geological elastic wave data, perform digital coding, and form an initial data set. By comparing the differences between differentiated data points, screen data samples, and generate an initial representative data set based on the rock structure and hydrogeological conditions in the data;

[0008] S2: Based on the initial representative data set, perform multi-point crossover and adaptive mutation on the data, pay attention to the changes in stress distribution and surface displacement in the parameters, optimize the data selection process, and generate an optimized parameter set;

[0009] S3: using the optimized parameter set, performing elastic wave propagation simulation, monitoring the wave propagation path and energy distribution, analyzing the cracks and cavities of the geological medium from the wave response, and obtaining geological heterogeneity analysis results;

[0010] S4: Based on the geological heterogeneity analysis results, subdivide the multi-level geological data, compare and analyze the stability indicators between the multi-level geological data, conduct multi-scale analysis, calibrate key landslide triggering factors, identify landslide risk areas, and generate a landslide risk assessment model.

[0011] As a further solution of the present invention, the steps of obtaining the wave velocity, attenuation coefficient and density parameters are specifically as follows:

[0012] S111: Using the wave propagation time and propagation distance recorded in the geological elastic wave data, the formula is:

[0013]

[0014] Calculate the generated wave speed;

[0015] Among them, t represents the propagation time of the wave, d represents the propagation distance, v represents the wave speed, ∈ is the time error compensation coefficient, and k is the nonlinear exponential adjustment of the time error;

[0016] S112: Based on the wave amplitude attenuation and propagation distance, the attenuation coefficient formula is used:

[0017]

[0018] Calculate and generate the attenuation coefficient;

[0019] Among them, ln is the natural logarithm, A0 is the initial amplitude, α is the attenuation coefficient, β is the nonlinear adjustment coefficient of amplitude attenuation, k is the nonlinear influence index of amplitude, and δ is the distance adjustment coefficient;

[0020] S113: Combining the attenuation coefficient and the wave speed, using a density parameter estimation formula:

[0021]

[0022] Estimate the density of geological media and obtain density parameters;

[0023] Among them, ρ represents the density parameter, γ is the coefficient adjusted according to the characteristics of the geological medium, and ξ is the correction term for density calculation.

[0024] As a further solution of the present invention, the step of obtaining the initial representative data set is specifically:

[0025] S121: Perform digital encoding based on the wave speed, the attenuation coefficient and the density parameter, using the formula:

[0026]

[0027] and

[0028]

[0029] Calculate the mean and variance of the data to obtain statistical description results μ and σ 2 ;

[0030] Among them, x i represents multiple data points, N represents the total number of data points, μ represents the average value of the data, σ 2 represents the variance of the data;

[0031] S122: Use the statistical description results μ and σ 2 As a screening criterion, the data set was filtered to exclude any The outliers of the range are calculated using the formula:

[0032]

[0033] Filter data points to generate filtered data sets;

[0034] Among them, x filtered represents the filtered data set, μ, Used to define screening criteria;

[0035] S123: The filtered data set x filtered Perform cluster analysis to identify key trends and groups, using the clustering formula:

[0036]

[0037] An initial representative data set was generated through cluster analysis;

[0038] Among them, S represents the sum of variance within the cluster, K represents the number of clusters, and N k , μ k represent the number of data points and the mean value in each cluster, respectively.

[0039] As a further solution of the present invention, the step of obtaining the optimized parameter set is specifically:

[0040] S211: Select the key variables stress distribution and surface displacement from the initial representative data set and perform multi-point cross analysis using the formula:

[0041]

[0042] Generate multi-point cross analysis results S cross ;

[0043] Among them, S d represents stress distribution data points, D represents surface displacement data points, and w i,j Represents the cross weight of data points i and j;

[0044] S212: Perform adaptive mutation analysis on the multi-point crossover analysis results to adaptively adjust the impact of each data point using the formula:

[0045]

[0046] Generate adaptive mutation analysis results S adaptive ;

[0047] Among them, μ cross is the average of the results, λ k It is the adaptive coefficient adjusted according to the degree of data deviation;

[0048] S213: Combining the adaptive mutation analysis results with the original data set to optimize data selection, using the formula:

[0049]

[0050] Generate optimized parameter set P opt ;

[0051] Among them, α n is the coefficient of weighted selection.

[0052] As a further solution of the present invention, the steps for obtaining the geological heterogeneity analysis results are specifically as follows:

[0053] S311: Initialize the parameters of elastic wave propagation simulation using the optimized parameter set, set the energy and initial waveform for the simulation, and use the formula:

[0054]

[0055] Generate the initial settings for the simulation E init ;

[0056] Among them, β n represents the energy distribution coefficient, is a single parameter in the optimized parameter set;

[0057] S312: Using the initial settings of the simulation, perform elastic wave propagation simulation, monitor the path and energy distribution of the wave, and use the formula:

[0058]

[0059] Get the wave propagation monitoring result Φ;

[0060] Where T represents the simulation time, γt,E init To set E based on the initial energy init The wave propagation function of

[0061] S313: Based on the wave propagation monitoring results, cracks and cavities in the geological medium are analyzed using the formula:

[0062]

[0063] Generate geological heterogeneity analysis results H;

[0064] Among them, α i is the sensitivity adjustment coefficient, Φ i is the wave propagation data of the target monitoring point, κ is the adjustment factor of the balance sensitivity, Φ avg is the average value of the wave propagation data.

[0065] As a further solution of the present invention, the steps for obtaining the landslide risk assessment model are specifically as follows:

[0066] S411: Based on the geological heterogeneity analysis results, the geological data is subdivided to characterize the multi-layer geological structure using the formula:

[0067]

[0068] Generate subdivided multi-layer geological data G layered ;

[0069] Among them, δ i The quantitative coefficient representing the difference between levels, H i Obtained from geological heterogeneity analysis;

[0070] S412: Using the subdivided multi-layer geological data, comparing and analyzing the stability indicators between the multi-layer geological data, and performing multi-scale analysis, using the formula:

[0071]

[0072] Generate stability index Smulti ;

[0073] Among them, ω j is the weight, σ is the stability adjustment parameter, μ j , μ avg They are the single layer and average stability indexes, respectively;

[0074] S413: According to the stability index, key landslide triggering factors are calibrated and landslide risk areas are identified using the formula:

[0075]

[0076] Generate landslide risk assessment model R risk ;

[0077] Among them, ξ k Indicates risk sensitivity. is a single level of data extracted from the multi-layer stability index, Θ k is the set risk threshold.

[0078] A landslide risk intelligent assessment system for a tunnel surrounding area, the landslide risk intelligent assessment system for a tunnel surrounding area is used to execute the above-mentioned landslide risk intelligent assessment method for a tunnel surrounding area, the system comprising:

[0079] The data acquisition module collects geological elastic wave data, extracts wave velocity, attenuation coefficient, and density parameters to form an initial data set, and screens data samples by differentiating the differences between data points to generate an initial representative data set;

[0080] The data analysis module performs multi-point crossover and adaptive adjustment on the data points based on the initial representative data set, pays attention to the changes in stress distribution and surface displacement, optimizes the data selection process, and generates an optimized parameter set;

[0081] The simulation verification module uses the optimized parameter set to simulate elastic wave propagation, monitor the wave propagation path and energy distribution, analyze the cracks and cavities of the geological medium, and obtain geological heterogeneity analysis results;

[0082] The risk assessment module is based on the geological heterogeneity analysis results, subdivides multi-level geological data, compares and analyzes the stability indicators between the multi-level geological data, performs multi-scale analysis, calibrates key landslide triggering factors, identifies landslide risk areas, and generates a landslide risk assessment model.

[0083] Compared with the prior art, the advantages and positive effects of the present invention are:

[0084] In the present invention, an initial data set with high information density is constructed through geological elastic wave data analysis, which improves the quality and efficiency of data screening. In addition, the careful observation of stress distribution and surface displacement during data selection is optimized, which enhances the ability to capture dynamic changes in geological conditions. By simulating elastic wave propagation, cracks and voids in geological media are accurately analyzed, providing more detailed insights into geological heterogeneity. This method not only calibrates landslide triggering factors more accurately, but also effectively identifies and evaluates high-risk areas, greatly improving the risk management and early warning accuracy of tunnels and critical infrastructure, and reducing the potential impact of geological disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0085] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0086] Figure 2 This is a flow chart of the steps for obtaining the wave velocity, attenuation coefficient and density parameters of the present invention;

[0087] Figure 3 A flowchart of the steps for obtaining the initial representative data set of the present invention;

[0088] Figure 4 A flow chart of the steps for obtaining the optimized parameter set of the present invention;

[0089] Figure 5 A flow chart of the steps for obtaining the geological heterogeneity analysis results of the present invention;

[0090] Figure 6 The figure is a flow chart of the steps for obtaining the landslide risk assessment model of the present invention. DETAILED DESCRIPTION

[0091] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0092] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying 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 limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0093] Embodiment 1

[0094] See also Figure 1 The present invention provides a technical solution: a method for intelligently assessing landslide risk in a tunnel surrounding area, comprising the following steps:

[0095] S1: Extract wave velocity, attenuation coefficient, and density parameters from geological elastic wave data, perform digital coding, and form an initial data set. By comparing the differences between differentiated data points, screen data samples, and generate an initial representative data set based on the rock structure and hydrogeological conditions in the data;

[0096] S2: Based on the initial representative data set, multi-point crossover and adaptive mutation are performed on the data, focusing on the changes in stress distribution and surface displacement in the parameters, optimizing the data selection process, and generating the optimized parameter set;

[0097] S3: Use the optimized parameter set to simulate elastic wave propagation, monitor the wave propagation path and energy distribution, analyze the cracks and cavities in the geological medium from the wave response, and obtain the results of geological heterogeneity analysis;

[0098] S4: Based on the results of geological heterogeneity analysis, subdivide multi-level geological data, compare and analyze the stability indicators between multi-layer geological data, conduct multi-scale analysis, calibrate key landslide triggering factors, identify landslide risk areas, and generate a landslide risk assessment model.

[0099] The initial representative data set includes rock physical properties and hydrogeological properties. The optimized parameter set includes stress field parameters and displacement measurement parameters. The geological heterogeneity analysis results are specifically fracture characteristics and cavity characteristics. The landslide risk assessment model specifically includes formation stability indicators, landslide triggering factors, and risk area positioning.

[0100] See also Figure 2 , the specific steps for obtaining wave velocity, attenuation coefficient and density parameters are as follows:

[0101] S111: Using the wave propagation time and propagation distance recorded in the geological elastic wave data, the formula is:

[0102]

[0103] Calculate the generated wave speed;

[0104] Among them, t represents the propagation time of the wave, d represents the propagation distance, v represents the wave speed, ∈ is the time error compensation coefficient, and k is the nonlinear exponential adjustment of the time error;

[0105] S112: Based on the wave amplitude attenuation and propagation distance, the attenuation coefficient formula is used:

[0106]

[0107] Calculate and generate the attenuation coefficient;

[0108] Among them, ln is the natural logarithm, A0 is the initial amplitude, α is the attenuation coefficient, β is the nonlinear adjustment coefficient of amplitude attenuation, k is the nonlinear influence index of amplitude, and δ is the distance adjustment coefficient;

[0109] S113: Combine the attenuation coefficient and wave velocity, and use the density parameter estimation formula:

[0110]

[0111] Estimate the density of geological media and obtain density parameters;

[0112] Among them, ρ represents the density parameter, γ is the coefficient adjusted according to the characteristics of the geological medium, and ξ is the correction term for density calculation.

[0113] Formula analysis and derivation of step 1:

[0114] formula:

[0115] Parameter explanation:

[0116] v: wave speed

[0117] d: propagation distance, assumed to be 500 meters

[0118] t: wave propagation time, assumed to be 2 seconds

[0119] ∈: time error compensation coefficient, assumed to be 0.05

[0120] k: nonlinear exponential adjustment of time error, assumed to be 2

[0121] Calculation process:

[0122] First, determine the value of,t,d,∈,k,.

[0123] Calculate the wave speed v using the formula:

[0124] Calculation time error adjustment: t adj =t+∈t k =2+0.05×2 2 = 2.2 seconds

[0125] Calculate the wave speed:

[0126] result:

[0127] The wave velocity v≈227.27 m / s represents the speed at which elastic waves pass through geological media under given conditions.

[0128] Formula analysis and derivation of step 2:

[0129] formula:

[0130]

[0131] Parameter explanation:

[0132] α: Attenuation coefficient

[0133] lnA / A0: Logarithmic attenuation ratio of the amplitude, assuming A0 is the initial amplitude of 1.0 and A is the received amplitude of 0.5

[0134] β: nonlinear adjustment coefficient of amplitude attenuation, assumed to be 0.1

[0135] k: nonlinear influence index of amplitude, continue to use 2

[0136] d: Transmission distance, continue to use 500 meters

[0137] δ: distance adjustment factor, assumed to be 10 meters

[0138] Calculation process:

[0139] Calculate the logarithmic attenuation ratio of the amplitude: lnA / A0=ln(0.5 / 1.0)=-0.693

[0140] Calculate the nonlinear compensation of the amplitude: βA k =0.1×0.5 2 =0.0125

[0141] Calculate the adjusted distance: d adj =d+δ=500+10=510

[0142] Calculate the attenuation coefficient:

[0143] result:

[0144] The attenuation coefficient α=0.00133 represents the energy attenuation rate per unit distance.

[0145] Formula analysis and derivation of step 3:

[0146] formula:

[0147]

[0148] Parameter explanation:

[0149] ρ: density parameter

[0150] γ: adjustment factor for geological medium characteristics, assumed to be 0.8

[0151] v: wave speed calculated above, 227.27 m / s

[0152] α: attenuation coefficient calculated above, 0.00133

[0153] ξ: correction term for density calculation, assumed to be 0.0001

[0154] Calculation process:

[0155] Calculate the product of wave velocity and attenuation coefficient: v 2 α=227.27 2 ×0.00133=68.887

[0156] Add density correction: denom = 68.887 + 0.0001 = 68.8871

[0157] Calculate the density parameters:

[0158] result:

[0159] The density parameter ρ≈0.0116 can be used to describe the density characteristics of geological media.

[0160] See also Figure 3 , the steps to obtain the initial representative data set are as follows:

[0161] S121: Digital encoding based on wave velocity, attenuation coefficient and density parameters, using the formula:

[0162]

[0163] and

[0164]

[0165] Calculate the mean and variance of the data to obtain statistical description results μ and σ 2 ;

[0166] Among them, x i represents multiple data points, N represents the total number of data points, μ represents the average value of the data, σ 2 represents the variance of the data;

[0167] S122: Using statistics to describe the results μ and σ 2 As a screening criterion, the data set was filtered to exclude any The outliers of the range are calculated using the formula:

[0168]

[0169] Filter data points to generate filtered data sets;

[0170] Among them, x filteredrepresents the filtered data set, μ, Used to define screening criteria;

[0171] S123: For the filtered data set x filtered Perform cluster analysis to identify key trends and groups, using the clustering formula:

[0172]

[0173] An initial representative data set was generated through cluster analysis;

[0174] Among them, S represents the sum of variance within the cluster, K represents the number of clusters, and N k , μ k represent the number of data points and the mean value in each cluster, respectively.

[0175] Step 1: Calculate the mean and variance of the data

[0176] Detailed explanation and derivation of the formula:

[0177] The average value calculation formula is:

[0178]

[0179] Variance calculation formula:

[0180]

[0181] Calculation process and examples:

[0182] Suppose there is a set of data x i =[10,20,30,40,50], calculate the mean and variance of this set of data.

[0183] Calculate the mean μ:

[0184]

[0185] Calculate the variance σ 2 :

[0186]

[0187] Result interpretation:

[0188] The mean μ=30 represents the center point in the data set.

[0189] Variance σ 2 =250 indicates the degree of deviation of the data points from the mean value. The larger the variance, the more scattered the data distribution.

[0190] Step 2: Filter the dataset

[0191] Detailed explanation and derivation of the formula:

[0192]

[0193] Calculation process and examples:

[0194] Using the results from step 1, μ = 30 and σ 2 =250, filter data.

[0195] Calculate the filter range:

[0196]

[0197] Apply filters:

[0198] x filtered =[10,20,30,40,50](all original data are within the screening range)

[0199] Result interpretation:

[0200] This means that all data points are retained in the filtered dataset because they are within the calculated bounds.

[0201] Step 3: Cluster analysis

[0202] Detailed explanation and derivation of the formula:

[0203]

[0204] Calculation process and examples:

[0205] Suppose that the data is clustered into two groups according to some method: C1 = [10, 20, 30], C2 = [40, 50].

[0206] Calculate the mean μ for each group k :

[0207] μ1=20,μ2=45

[0208] Compute the sum of the variances for each group:

[0209]

[0210] Calculate the total S:

[0211] S = 3 × 100 + 2 × 50 = 400

[0212] Result interpretation:

[0213] S=400 represents the weighted sum of the differences within the cluster, which can be used to evaluate the quality of the clustering.

[0214] See also Figure 4 , the specific steps for obtaining the optimized parameter set are:

[0215] S211: Select the key variables stress distribution and surface displacement from the initial representative data set and perform multi-point cross analysis using the formula:

[0216]

[0217] Generate multi-point cross analysis results S cross ;

[0218] Among them, S d represents stress distribution data points, D represents surface displacement data points, and w i,j Represents the cross weight of data points i and j;

[0219] S212: Perform adaptive mutation analysis on the results of multi-point crossover analysis to adaptively adjust the impact of each data point using the formula:

[0220]

[0221] Generate adaptive mutation analysis results S adaptive ;

[0222] Among them, μ cross is the average of the results, λ k It is the adaptive coefficient adjusted according to the degree of data deviation;

[0223] S213: Combine the adaptive mutation analysis results with the original data set to optimize data selection using the formula:

[0224]

[0225] Generate optimized parameter set P opt ;

[0226] Among them, α n is the coefficient of weighted selection.

[0227] Step 1: Multi-point cross-analysis

[0228] Formula Detail

[0229]

[0230] Parameter explanation and derivation:

[0231] and D j Represent the i-th stress distribution data point and the j-th surface displacement data point respectively. Assume that in a certain measurement, the stress distribution is S d =[100,150,200] in kPa, and the surface displacement is D=[0.5,0.8,1.2] in cm.

[0232] w i,j are weight coefficients adjusted according to correlation, and are assumed to be 1.

[0233] Assume that only the first pair of data points are calculated And D1 = 0.5cm.

[0234] Calculation process:

[0235] calculate

[0236] calculate

[0237] Calculate S cross for

[0238] This value represents the product of normalized stress and displacement and is used to quantify the combined effect of the two.

[0239] Step 2: Adaptive mutation analysis

[0240] Formula Detail

[0241] Parameter explanation and derivation:

[0242] μ cross Assume the average value is 0.5 (this is S cross assumed mean value of ).

[0243] λ k Assume a value of 2 (a simple adjustment factor, increasing sensitivity to mutations).

[0244] k is assumed to be 1 (this is the coefficient of standard exponential growth).

[0245] Calculation process:

[0246] S cross -μ cross =0.4999-0.5=-0.0001.

[0247] 1+e -1×(-0.0001) =1+e 0.0001 ≈1.0001(using e x ≈1+x when x is very small).

[0248]

[0249] This value indicates that the degree of adaptive mutation is very small, reflecting that the differences between data points are very close to the average level.

[0250] Step 3: Optimized parameter set

[0251] Formula Detail

[0252]

[0253] Parameter explanation and derivation:

[0254] α n Assume 1 (to simplify the calculation, all data points are considered equally important).

[0255] Use the result of the previous step, 0.00000001.

[0256] Calculation process:

[0257]

[0258] This value represents an element in the optimized parameter set, which is very small, indicating that the changes in the original data have been effectively controlled and reduced during the optimization process.

[0259] See also Figure 5 , the specific steps for obtaining geological heterogeneity analysis results are:

[0260] S311: Initialize the parameters of the elastic wave propagation simulation using the optimized parameter set, set the energy and initial waveform for the simulation, using the formula:

[0261]

[0262] Generate the initial settings for the simulation E init ;

[0263] Among them, β n represents the energy distribution coefficient, is a single parameter in the optimized parameter set;

[0264] S312: Using the initial settings of the simulation, perform an elastic wave propagation simulation and monitor the path and energy distribution of the wave using the formula:

[0265]

[0266] Get the wave propagation monitoring result Φ;

[0267] Where T represents the simulation time, γt,E init To set E based on the initial energy init The wave propagation function of

[0268] S313: Based on the wave propagation monitoring results, analyze the cracks and cavities in the geological medium using the formula:

[0269]

[0270] Generate geological heterogeneity analysis results H;

[0271] Among them, α i is the sensitivity adjustment coefficient, Φ i is the wave propagation data of the target monitoring point, κ is the adjustment factor of the balance sensitivity, Φ avg is the average value of the wave propagation data.

[0272] Step 1: Calculation of initial setup

[0273] formula:

[0274]

[0275] Parameter details:

[0276] β n : Energy distribution coefficient, which is a preset parameter, set according to the specific needs of the simulation to adjust the influence of different parameters on the simulation results.

[0277] The nth parameter in the optimized parameter set represents a specific physical or chemical property, such as the elastic modulus or density of the rock.

[0278] Calculation example:

[0279] Assumptions:

[0280] β1=0.5,β2=0.3

[0281] (Rock elastic modulus, assumed unit: GPa)

[0282] (Rock density, assumed unit: g / cm ∧ 3)

[0283] Calculation process:

[0284] E init =0.5×2 2 +0.3×3 2

[0285] E init =0.5×4+0.3×9

[0286] E init =2+2.7

[0287] E init =4.7

[0288] This result represents the total value of the initial energy settings calculated based on the optimized parameter set, and the units are some form of energy, depending on the actual environment and unit system of the simulation.

[0289] Step 2: Wave Propagation Monitoring Results

[0290] formula:

[0291]

[0292] Parameter details:

[0293] T: The total time of the simulation, for example 10 seconds.

[0294] γt,E init : The wave propagation function at time t, which depends on the initial energy setting E init。 .

[0295] Calculation example:

[0296] Assume T = 10 seconds, γt, E init =E init ·e -0.1t , where e is the base of natural logarithms.

[0297] Calculation process:

[0298]

[0299] Using integral calculation, we get:

[0300]

[0301] Φ=4.7×(10-0.904)

[0302] Φ=42.752

[0303] This result represents the total energy propagation of the wave over a 10-second period, taking into account the decay of energy over time.

[0304] Step 3: Geological heterogeneity analysis

[0305] formula:

[0306]

[0307] Parameter details:

[0308] α i : Sensitivity adjustment coefficient, set according to actual needs.

[0309] Φ i : Wave propagation data of the target monitoring point.

[0310] κ: Adjustment factor of equilibrium sensitivity, generally less than 1.

[0311] Φ avg: Average value of wave propagation data.

[0312] Calculation example:

[0313] Assumptions:

[0314] α1=1,α2=1.5

[0315] Φ1=40,Φ2=45

[0316] Φ avg =42.5,κ=0.5

[0317] Calculation process:

[0318]

[0319] This result represents an overall score of geological heterogeneity derived from the analysis of wave propagation data in the simulated environment, with high values ​​indicating greater geological complexity or heterogeneity.

[0320] See also Figure 6 , the specific steps for obtaining the landslide risk assessment model are:

[0321] S411: Based on the results of geological heterogeneity analysis, the geological data are subdivided to characterize the multi-layer geological structure using the formula:

[0322]

[0323] Generate subdivided multi-layer geological data G layered ;

[0324] Among them, δ i The quantitative coefficient representing the difference between levels, H i Obtained from geological heterogeneity analysis;

[0325] S412: Using the subdivided multi-layer geological data, compare and analyze the stability indicators between the multi-layer geological data, and conduct multi-scale analysis using the formula:

[0326]

[0327] Generate stability index S multi ;

[0328] Among them, ω j is the weight, σ is the stability adjustment parameter, μ j , μ avg They are the single layer and average stability indexes, respectively;

[0329] S413: Based on the stability index, key landslide triggering factors are calibrated and landslide risk areas are identified using the formula:

[0330]

[0331] Generate landslide risk assessment model R risk ;

[0332] Among them, ξ k Represents risk sensitivity, is a single level of data extracted from the multi-layer stability index, Θ k is the set risk threshold.

[0333] Detailed explanation of the formula and calculation process of step 1

[0334] formula:

[0335]

[0336] Parameter Description:

[0337] δ i : The coefficient of variability of each layer of geological data. It is assumed that this coefficient reflects the differences in physical properties between geological layers.

[0338] H i : Geological heterogeneity data of corresponding layers, obtained from geological analysis results.

[0339] Calculation example:

[0340] Assume there are three layers of geological data, the coefficient of variation δ i They are 0.5, 0.3, and 0.2 respectively. Geological heterogeneity data H i They are 10, 15, and 5 respectively.

[0341] Calculation process:

[0342] G layered =0.5×10 2 +0.3×15 2 +0.2×5 2

[0343] G layered =0.5×100+0.3×225+0.2×25

[0344] G layered =50+67.5+5

[0345] G layered =122.5

[0346] Detailed explanation of the formula and calculation process of step 2

[0347] formula:

[0348]

[0349] Parameter Description:

[0350] ω j : Layer weight, adjust the influence of each layer of data.

[0351] The geological layer data obtained from step 1.

[0352] σ: Stability adjustment parameter to balance the influence of different levels.

[0353] μ j and μ avg : Average stability index of a single layer and all layers.

[0354] Calculation example:

[0355] Assume weight ω j is 1.2, 1.0, 0.8, and the average stability index μ avg is 10, the stability index μ of the multilayer j ) is 12, 9, 11, and the stability adjustment parameter (σ) is 1.

[0356] Calculation process:

[0357]

[0358] S multi ≈2.39+2.404+1.923

[0359] S multi ≈6.717

[0360] Detailed explanation of the formula and calculation process of step 3

[0361] formula:

[0362]

[0363] Parameter Description:

[0364] ξ k : Regional risk sensitivity coefficient.

[0365] S multik : The stability index obtained from step 2.

[0366] Θ k : Threshold of landslide triggering factor.

[0367] Calculation example:

[0368] Assuming the risk sensitivity coefficient ξ k is 0.9, the threshold of landslide trigger factor Θ k is 3.

[0369] Calculation process:

[0370]

[0371] R risk =0.9·(1-205.575)

[0372] R risk =0.9·(-204.575)

[0373] R risk =-184.1175

[0374] This result R risk Represents a comprehensive landslide risk assessment based on current stability indicators and risk sensitivity. Negative values ​​indicate that some assumptions in the calculation need to be adjusted or the suitability of the model needs to be reassessed.

[0375] A landslide risk intelligent assessment system for a tunnel surrounding area, the landslide risk intelligent assessment system for a tunnel surrounding area is used to execute the above-mentioned landslide risk intelligent assessment method for a tunnel surrounding area, and the system comprises:

[0376] The data acquisition module collects geological elastic wave data, extracts wave velocity, attenuation coefficient, and density parameters to form an initial data set, and screens data samples by differentiating the differences between data points to generate an initial representative data set;

[0377] The data analysis module performs multi-point cross-talk and adaptive adjustment of data points based on the initial representative data set, focusing on the changes in stress distribution and surface displacement, optimizing the data selection process, and generating an optimized parameter set;

[0378] The simulation verification module uses the optimized parameter set to simulate elastic wave propagation, monitor the wave propagation path and energy distribution, analyze the cracks and cavities in the geological medium, and obtain the results of geological heterogeneity analysis;

[0379] The risk assessment module is based on the results of geological heterogeneity analysis, subdivides multi-level geological data, compares and analyzes the stability indicators between multi-layer geological data, conducts multi-scale analysis, calibrates key landslide triggering factors, identifies landslide risk areas, and generates a landslide risk assessment model.

[0380] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. An intelligent landslide risk assessment method for tunnel surrounding areas, characterized in that: The following steps are involved: Extract the wave velocity, attenuation coefficient, and density parameters from the geological elastic wave data, perform digital coding, and form an initial data set. By comparing the differences between differentiated data points, screen the data samples, and generate an initial representative data set based on the rock structure and hydrogeological conditions in the data. Based on the initial representative data set, multi-point crossover and adaptive mutation are performed on the data, focusing on the changes in stress distribution and surface displacement in the parameters, optimizing the data selection process, and generating an optimized parameter set; Using the optimized parameter set, elastic wave propagation simulation is performed to monitor the wave propagation path and energy distribution, and cracks and cavities in the geological medium are analyzed from the wave response to obtain geological heterogeneity analysis results; Based on the geological heterogeneity analysis results, multiple layers of geological data are subdivided, stability indicators between multiple layers of geological data are compared and analyzed, multi-scale analysis is performed, key landslide triggering factors are calibrated, landslide risk areas are identified, and a landslide risk assessment model is generated; The specific steps of generating the optimized parameter set are: The key variables stress distribution and surface displacement were selected from the initial representative data set and multi-point cross analysis was performed using the formula: Generate multi-point cross analysis results ; in, represents stress distribution data points, represents the surface displacement data points, Representative data points and The cross weight of An adaptive mutation analysis is performed on the multi-point crossover analysis results to adaptively adjust the impact of each data point using the formula: Generating Adaptive Mutation Analysis Results ; in, is the average value of the multi-point cross-analysis results, is the adaptive coefficient adjusted according to the degree of data deviation, is the coefficient of standard exponential growth; The adaptive mutation analysis results were combined with the original data set to optimize data selection using the formula: Generate optimized parameter set ; in, is the coefficient of weighted selection, Represents an index; The steps for obtaining the geological heterogeneity analysis results are specifically as follows: Initialize the parameters of the elastic wave propagation simulation using the optimized parameter set, set the energy and initial waveform for the simulation, using the formula: Generate initial settings for simulation ; in, represents the energy distribution coefficient, is the first parameter in the optimized parameter set parameters; Using the initial settings of the simulation described above, perform an elastic wave propagation simulation and monitor the wave path and energy distribution using the formula: Get wave propagation data ; in, represents the simulation time, Based on the initial energy setting The wave propagation function, represents the propagation time of the wave; Based on the wave propagation monitoring results, the cracks and cavities of the geological medium are analyzed using the formula: Generate geological heterogeneity analysis results ; in, is the sensitivity adjustment factor, is the wave propagation data of the target monitoring point, is the target monitoring point, is the adjustment factor for balance sensitivity, is the average value of wave propagation data; The specific steps of generating the landslide risk assessment model are: Based on the geological heterogeneity analysis results, the geological data are subdivided to characterize the multi-layer geological structure using the formula: Generate subdivided multi-layer geological data ; in, The quantitative coefficient representing the difference between levels, From the analysis of geological heterogeneity, For different layers in a multi-layered geological structure; By using the subdivided multi-layer geological data, the stability indicators between the multi-layer geological data are compared and analyzed, and a multi-scale analysis is performed, using the formula: Generate stability index ; in, is the weight, is the stability adjustment parameter, , They are the single layer and average stability indexes, respectively; According to the stability index, the key landslide triggering factors are calibrated and the landslide risk areas are identified using the formula: Generate a landslide risk assessment model ; in, Represents risk sensitivity, Represents the index, is the set risk threshold.

2. The intelligent landslide risk assessment method for the tunnel surrounding area according to claim 1 is characterized in that: The steps for obtaining the wave velocity, attenuation coefficient and density parameters are specifically as follows: Using the wave propagation time and propagation distance recorded in the geological elastic wave data, the formula is adopted: Calculate the generated wave speed; in represents the propagation distance, represents the wave speed, is the time error compensation coefficient, is the nonlinear exponential adjustment of the time error; The attenuation coefficient formula is adopted by the wave amplitude attenuation and propagation distance: Calculate and generate the attenuation coefficient; in, is the natural logarithm with a natural constant as base, is the initial amplitude, is the received amplitude, is the attenuation coefficient, is the nonlinear adjustment coefficient of amplitude attenuation, is the nonlinear influence index of the amplitude, is the distance adjustment factor; Combining the attenuation coefficient and the wave speed, the density parameter estimation formula is adopted: Estimate the density of geological media and obtain density parameters; in, represents the density parameter, is a coefficient adjusted according to the characteristics of geological media. is a correction term for density calculation.

3. The intelligent landslide risk assessment method for the tunnel surrounding area according to claim 2 is characterized in that: The steps for obtaining the initial representative data set are specifically as follows: Based on the wave velocity, the attenuation coefficient and the density parameter, digital encoding is performed using the formula: and Calculate the mean and variance of the data to obtain statistical description results and ; in, Represents multiple data points, Represents data points The total number of represents the average value of the data, represents the variance of the data; Describe the results using the statistics and As a screening criterion, the data set was filtered to exclude any The outliers of the range are calculated using the formula: Filter data points to generate filtered data sets; in, represents the filtered data set, , Used to define screening criteria; After filtering the data set Perform cluster analysis to identify key trends and groups, using the clustering formula: An initial representative data set was generated through cluster analysis; in, represents the sum of variance within the cluster, represents the number of clusters, , Represent the number of data points and the mean value in each cluster, yes The index in the collection, is the category, Indicates kind.

4. An intelligent landslide risk assessment system for tunnel surrounding areas, characterized in that: According to the intelligent landslide risk assessment method for the tunnel surrounding area according to any one of claims 1-2, the system comprises: The data acquisition module collects geological elastic wave data, extracts wave velocity, attenuation coefficient, and density parameters to form an initial data set, and screens data samples by differentiating the differences between data points to generate an initial representative data set; The data analysis module performs multi-point crossover and adaptive adjustment on the data points based on the initial representative data set, pays attention to the changes in stress distribution and surface displacement, optimizes the data selection process, and generates an optimized parameter set; The simulation verification module uses the optimized parameter set to simulate elastic wave propagation, monitor the wave propagation path and energy distribution, analyze the cracks and cavities of the geological medium, and obtain geological heterogeneity analysis results; The risk assessment module subdivides multiple layers of geological data based on the geological heterogeneity analysis results, compares and analyzes the stability indicators between multiple layers of geological data, performs multi-scale analysis, calibrates key landslide triggering factors, identifies landslide risk areas, and generates a landslide risk assessment model.

Images