Intelligent analysis method and system for geotechnical engineering data

Abstract

The invention relates to the technical field of data analysis, in particular to a geotechnical engineering data intelligent analysis method and system.The geotechnical engineering data intelligent analysis method comprises the following steps that soil type, density, water content and external load data in underground construction are collected, the soil bearing capacity is calculated and adjusted through a Lagrange multiplier method, a multiplier is set for each environment and engineering constraint, and the soil bearing capacity is adjusted; and generating optimized soil bearing capacity data. According to the method, the soil type, the density, the water content and the external load data in underground construction are collected, the soil bearing capacity is calculated and adjusted in cooperation with the Lagrange multiplier method, specific multipliers are set for each environment and engineering constraint, and the soil bearing capacity data are optimized. And the data precision is improved, so that more detailed soil bearing estimation is provided before construction. Then, key probability distribution parameters of diffusivity and degradation rate soil pollution behaviors are set, multiple pollution scenes are randomly constructed through a Monte Carlo method, and multiple dynamic change conditions can be simulated;

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a method and system for intelligent analysis of geotechnical engineering data. Background Art

[0002] The field of data analysis technology covers the entire process from data collection, processing, analysis to result interpretation and decision support. In this field, statistics, machine learning, artificial intelligence and other methods are used to extract useful information and patterns from data. The purpose is to support business decisions and optimize problem solutions through data insights. It is not only used in business and finance, but also widely used in engineering, medicine, social sciences and other fields. Through the analysis of large amounts of data, it helps people better understand complex phenomena and develop more effective strategies and solutions.

[0003] Among them, the intelligent analysis method of geotechnical data is to apply data analysis technology in the field of geotechnical engineering to intelligently process and analyze geological data, structural monitoring data and other related information. The method can be used for a variety of purposes such as predicting underground conditions, optimizing building design, and monitoring construction safety. By analyzing the data, the properties and reactions of soil and rock under different pressures and environmental conditions can be more accurately evaluated, so that more informed decisions can be made during the design and construction stages to improve the safety and economy of construction projects.

[0004] However, existing technologies are unable to fully predict and simulate the actual performance and response of soil in a changing environment. As a result, soil analysis results may deviate from actual conditions, affecting engineering safety and design optimization. For example, failure to fully consider the changing characteristics of soil types under different moisture and temperature conditions may lead to insufficient soil bearing capacity during the implementation phase, increasing construction risks and costs. In addition, existing technologies are difficult to dynamically simulate a variety of possible pollution behaviors in pollution risk assessment, which limits their extensiveness and flexibility in complex environments. This may lead to an underestimate of pollution risks, thereby affecting environmental protection and subsequent land use decision-making, Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a geotechnical engineering data intelligent analysis method and system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a geotechnical engineering data intelligent analysis method, comprising the following steps:

[0007] S1: Collect soil type, density, moisture content and external load data in underground construction, calculate and adjust soil bearing capacity using Lagrange multiplier method, set multipliers for each environmental and engineering constraint, and generate optimized soil bearing capacity data;

[0008] S2: According to the optimized soil bearing capacity data, key probability distribution parameters of soil pollution behavior of diffusion rate and degradation rate are set, and a variety of pollution scenarios are randomly constructed by Monte Carlo method, each scenario includes corresponding soil type, temperature and humidity conditions, and simulated pollution distribution data is generated;

[0009] S3: Analyze the simulated pollution distribution data, quantify the risk level of soil pollution in each scenario, calculate the probability distribution of pollutant diffusion and the maximum impact area, and generate scenario risk analysis results;

[0010] S4: Based on the scenario risk analysis results, refer to the diffusion probability and impact range under multiple scenarios, evaluate and summarize the pollution risk level of the entire target area, and generate geotechnical engineering data evaluation results.

[0011] As a further solution of the present invention, the steps for obtaining the optimized soil bearing capacity data are specifically as follows:

[0012] S111: Collect data on soil type T, density D, moisture content H and external load L in underground construction, using the formula:

[0013]

[0014] and

[0015]

[0016] and

[0017]

[0018] and

[0019]

[0020] Among them, d a represents the soil density of the ath sample, h a represents the water content of the ath sample, l a represents the external load of the ath sample, n is the total number of samples, I is the indicator function, when T a = k, the value is 1, otherwise it is 0, T a is the soil type of the ath sample, n is the total number of samples, and k is the classification index of the soil type;

[0021] The overall density D of the soil in the area is obtained by integration total , the overall soil moisture content in the area H total , the total amount of external pressure on the soil in the area is L total and the occurrence frequency T of the target soil in the entire sampling area freq (k);

[0022] S112: Based on the overall density D of the soil in the area total , the overall soil moisture content in the area H total , the total amount of external pressure on the soil in the area is L total and the occurrence frequency T of the target soil in the entire sampling area freq (k), using the formula:

[0023] L(T,D,H,L,λ)=f(T freq ,D total ,H total ,L total )-λ·(g(T freq ,D total ,H total ,L total )-b)

[0024] Integrate data into function L;

[0025] Among them, f(T freq ,D total ,H total ,L total ) represents the soil bearing capacity function considering the soil type frequency, g(T freq ,D total ,H total ,L total ) is the environmental constraint function of the adjusted reference soil overall characteristics, λ is the Lagrange multiplier used to balance the constraint condition, and b is the constraint condition constant;

[0026] S113: According to the function L, the formula is adopted:

[0027]

[0028] Calculate the soil bearing capacity C and obtain optimized soil bearing capacity data;

[0029] Among them, L(T j ,D j ,H j ,L j ,λ j ) is the function result under the jth constraint condition, T j , D j , H j , L j represent the soil type, density, water content and external load under the jth condition, λ j is the Lagrange multiplier for the jth condition, and m is the total number of environmental and engineering condition constraints.

[0030] As a further solution of the present invention, the step of obtaining the key probability distribution parameters is specifically as follows:

[0031] S211: According to the soil bearing capacity C, the formula is:

[0032]

[0033] and

[0034]

[0035] Estimate the diffusion rate β and degradation rate δ of pollutants;

[0036] Among them, k1, k2, k3, and k4 are adjustment parameters associated with soil properties and external environmental conditions;

[0037] S212: According to the diffusion rate β and degradation rate δ, the formula is used:

[0038]

[0039] and

[0040]

[0041] Get the adjusted diffusion rate β adjusted and degradation rate δ adjusted , and set the key probability distribution parameters accordingly.

[0042] As a further solution of the present invention, the step of obtaining the simulated pollution distribution data is specifically as follows:

[0043] S221: Based on the random sample of soil type T, temperature Θ, and humidity H of the target scene, the formula is used:

[0044]

[0045] Calculate the simulation score S of the i-th scenario i ;

[0046] Among them, Θ and H are the temperature and humidity parameters of the scene, Θ i and H i is the reference value of the temperature and humidity of the scene, σ Θ and σ H is the adjustment factor for temperature and humidity, e is the natural exponential function used to adjust for temperature effects;

[0047] S222: Based on the adjusted diffusion rate β adjusted and degradation rate δ adjusted , combined with the simulation score S of the i-th scenario i , using the formula:

[0048]

[0049] Calculate the simulated pollution distribution data P of the i-th scenario i , get the simulated pollution distribution data;

[0050] Among them, log is the natural logarithm function, which is used to simulate the effect of temperature on pollution diffusion.

[0051] As a further solution of the present invention, the steps for obtaining the quantified risk level of soil pollution in each scenario are specifically as follows:

[0052] S311: Based on the simulated pollution distribution data P of the i-th scene i , using the formula:

[0053] R i =α1·log(1+P i )

[0054] Calculate the risk assessment value R of the i-th scenario i ;

[0055] Among them, α1 is the adjustment coefficient used to quantify the relationship between risk and pollutant concentration, and log is the natural logarithm function used to convert pollutant concentration into a nonlinear risk score;

[0056] S312: Based on the risk assessment value R of the i-th scenario i , using the formula:

[0057] Q i =β1·R i

[0058] Calculate the quantitative risk value Q of the i-th scenario i ;

[0059] Among them, β1 is the coefficient used to convert the risk assessment value into a quantitative risk level. If Q i If Q exceeds the preset risk threshold θ, the scenario is classified as high risk. i If θ is lower than or equal to θ, the scenario is classified as low risk.

[0060] As a further solution of the present invention, the steps of obtaining the scenario risk analysis results are specifically as follows:

[0061] S321: Based on the quantified risk value Q of the i-th scenario i , using the formula:

[0062]

[0063] Calculate the probability distribution value P of pollutant diffusion spread ;

[0064] Among them, γ1 is the shape parameter used to control the slope of the function, μ1 is the location parameter that determines the center of the probability distribution, e is the base of the natural exponential, and ξ1 is used to adjust Q i The impact of |Q i | indicates Q i The absolute value of

[0065] S322: Based on the probability distribution value P of the pollutant diffusion spread , using the formula:

[0066]

[0067] Calculate the maximum impact area A of the pollutant max , get the scenario risk analysis results;

[0068] Among them, σ1 is the proportionality coefficient used to convert the probability into an area value, and η1 is used to increase the quadratic term of the diffusion probability.

[0069] As a further solution of the present invention, the steps for obtaining the geotechnical engineering data evaluation results are specifically as follows:

[0070] S411: According to the maximum impact area A of the pollutant max , using the formula:

[0071]

[0072] Calculate the total contamination probability P of the target area total ;

[0073] Among them, A max,i is the maximum impact area of ​​the i-th scenario, o is the total number of scenarios, λ1 is the adjustment coefficient, which is used to adjust the impact of the size of the impact area on the pollution probability, κ1 is the shape factor of the impact area, which adjusts the impact of the shape on the pollution probability, and ρ1 is the response coefficient of the environmental conditions, which is used to adjust the impact of environmental changes on the pollution probability;

[0074] S412: Based on the total contamination probability P of the target area total , using the formula:

[0075]

[0076] Calculate the pollution risk level R of the entire target area total , and obtain the geotechnical engineering data evaluation results;

[0077] Among them, ω1 is a proportional factor used to convert probability into risk level, and φ1 is a weight factor used to enhance the influence of probability value.

[0078] A geotechnical engineering data intelligent analysis system, the geotechnical engineering data intelligent analysis system is used to execute the above-mentioned geotechnical engineering data intelligent analysis method, the system comprises:

[0079] The data collection and optimization module uses the Lagrange multiplier method to adjust the multipliers of each environmental and engineering constraint based on the type, density, moisture content and external load data of the soil in underground construction to generate optimized soil bearing capacity data;

[0080] The pollution simulation module sets diffusion rate and degradation rate parameters based on the optimized soil bearing capacity data, randomly constructs soil pollution scenarios through the Monte Carlo method, and generates simulated pollution distribution data;

[0081] The risk assessment module quantifies the risk level of soil pollution in each scenario based on the simulated pollution distribution data, calculates the diffusion probability distribution of pollutants and the maximum impact area, and generates scenario risk analysis results;

[0082] The pollution impact analysis module evaluates the diffusion probability and impact range under multiple scenarios based on the scenario risk analysis results, analyzes the pollution situation in the target area, and generates pollution impact analysis data;

[0083] The risk level summary module summarizes the pollution risk level of the entire target area based on the pollution impact analysis data, evaluates the overall environmental risk, and generates geotechnical engineering data evaluation results.

[0084] Compared with the prior art, the advantages and positive effects of the present invention are:

[0085] In the present invention, by collecting soil type, density, water content and external load data in underground construction, the soil bearing capacity is calculated and adjusted in conjunction with the Lagrange multiplier method, and specific multipliers are set for each environment and engineering constraint to optimize the soil bearing capacity data. The data accuracy is improved, thereby providing a more detailed soil bearing estimate before construction. Next, the key probability distribution parameters of the soil pollution behavior of the diffusion rate and degradation rate are set, and a variety of pollution scenarios are randomly constructed through the Monte Carlo method, which can simulate a variety of dynamic changes, significantly improving the reliability of predicting pollution behavior and the adaptability of the response strategy. Finally, the risk level of the simulated pollution distribution data is quantified, and the pollution risk level of the entire target area is evaluated accordingly, providing a risk assessment result based on actual data for engineering decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] Figure 1 It is a schematic diagram of the workflow of the present invention;

[0087] Figure 2 A flow chart of the steps for obtaining soil bearing capacity data optimized for the present invention;

[0088] Figure 3 A flow chart of the steps for obtaining key probability distribution parameters for the present invention;

[0089] Figure 4 A flow chart of the steps for obtaining the simulated pollution distribution data of the present invention;

[0090] Figure 5 A flow chart of the steps for obtaining quantified risk levels of soil contamination in each scenario of the present invention;

[0091] Figure 6 A flowchart of the steps for obtaining the scenario risk analysis results of the present invention;

[0092] Figure 7 The present invention is a flowchart of the steps for obtaining the geotechnical engineering data evaluation results. DETAILED DESCRIPTION

[0093] 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.

[0094] 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.

[0095] See also Figure 1 The present invention provides a technical solution: a method for intelligent analysis of geotechnical engineering data, comprising the following steps:

[0096] S1: Collect soil type, density, moisture content and external load data in underground construction, calculate and adjust soil bearing capacity using Lagrange multiplier method, set multipliers for each environmental and engineering constraint, and generate optimized soil bearing capacity data;

[0097] S2: According to the optimized soil bearing capacity data, the key probability distribution parameters of the diffusion rate and degradation rate of soil pollution behavior are set, and a variety of pollution scenarios are randomly constructed through the Monte Carlo method. Each scenario includes the corresponding soil type, temperature and humidity conditions to generate simulated pollution distribution data;

[0098] S3: Analyze the simulated pollution distribution data, quantify the risk level of soil pollution in each scenario, calculate the probability distribution of pollutant diffusion and the maximum impact area, and generate scenario risk analysis results;

[0099] S4: Based on the results of scenario risk analysis, refer to the diffusion probability and impact range under multiple scenarios, evaluate and summarize the pollution risk level of the entire target area, and generate geotechnical engineering data assessment results;

[0100] The optimized soil bearing capacity data include adjusted soil stability parameters, groundwater level changes, and corresponding soil density. The simulated pollution distribution data include the soil diffusion rate, ambient temperature changes, and soil moisture content measurement data for each scenario. The scenario risk analysis results include the soil contamination probability under each scenario, the soil type distribution in the affected area, and the predicted pollutant concentration level. The geotechnical engineering data assessment results include the integrated regional pollution risk level and geological variability analysis.

[0101] See also Figure 2 , the steps for obtaining optimized soil bearing capacity data are as follows:

[0102] S111: Collect data on soil type T, density D, moisture content H and external load L in underground construction, using the formula:

[0103]

[0104] and

[0105]

[0106] and

[0107]

[0108] and

[0109]

[0110] Among them, d a represents the soil density of the ath sample, h a represents the water content of the ath sample, l a represents the external load of the ath sample, n is the total number of samples, I is the indicator function, when T a = k, the value is 1, otherwise it is 0, T ais the soil type of the ath sample, n is the total number of samples, and k is the classification index of the soil type;

[0111] The overall density D of the soil in the area is obtained by integration total , the overall soil moisture content in the area H total , the total amount of external pressure on the soil in the area is L total and the occurrence frequency T of the target soil in the entire sampling area freq (k);

[0112] S112: According to the overall density of soil in the area D total , the overall soil moisture content in the area H total , the total amount of external pressure on the soil in the area is L total and the occurrence frequency T of the target soil in the entire sampling area freq (k), using the formula:

[0113] L(T,D,H,L,λ)=f(T freq ,D total ,H total ,L total )-λ·(g(T freq ,D total ,H total ,L total )-b)

[0114] Integrate data into function L;

[0115] Among them, f(T freq ,D total ,H total ,L total ) represents the soil bearing capacity function considering the soil type frequency, g(T freq ,D total ,H total ,L total ) is the environmental constraint function of the adjusted reference soil overall characteristics, λ is the Lagrange multiplier used to balance the constraint condition, and b is the constraint condition constant;

[0116] S113: According to the function L, the formula is:

[0117]

[0118] Calculate the soil bearing capacity C and obtain optimized soil bearing capacity data;

[0119] Among them, L(T j ,D j ,H j ,L j ,λ j) is the function result under the jth constraint condition, T j , D j , H j , L j

[0120] represent the soil type, density, water content and external load under the jth condition, λ j

[0121] is the Lagrange multiplier for the jth condition, m is the total number of environmental and engineering condition constraints;

[0122] The calculation process is as follows:

[0123] For the formula:

[0124]

[0125] The collected soil density sample data are: d1 = 1.2, d2 = 1.4, d3 = 1.3 (unit: g / cm 3 );

[0126] Calculate the total density:

[0127] D total =1.2+1.4+1.3=3.9g / cm 3

[0128] For the formula:

[0129]

[0130] The collected moisture content sample data are: h1 = 20%, h2 = 22%, h3 = 25%;

[0131] Calculate the total moisture content:

[0132] H total =20+22+25=67%

[0133] For the formula:

[0134]

[0135] The collected external load sample data are: l1 = 100, l2 = 150, l3 = 120 (unit: kN / m 2 );

[0136] Calculate the total external load:

[0137] L total =100+150+120=370kN / m 2

[0138] For the formula:

[0139]

[0140] For the frequency of soil occurrence in the entire sampling area, T freq (k), set soil type k to (clay):

[0141]

[0142] First calculate f(T freq ,D total ,H total ,L total ):

[0143]

[0144] For the formula:

[0145] L(T,D,H,L,λ)=f(T freq ,D total ,H total ,L total )-λ·(g(T freq ,D total ,H total ,L total )-b)

[0146] It can be expressed as:

[0147] L=f-λ·(gb)

[0148] in:

[0149] g=f·0.9

[0150] Set parameter b = 100 (unit: kN / m 2 ), λ=0.05;

[0151] Calculate the function g:

[0152] g = 299.79 × 0.9 = 269.81 kN / m 2

[0153] Three different engineering conditions are set, and the corresponding Lagrange multipliers are: λ1=0.01, λ2=0.02, λ3=0.03;

[0154] Calculate L for each value of λ:

[0155] For λ1=0.01:

[0156] L=299.79-0.01×(269.81-100)=299.79-0.01×169.81=299.14kN / m 2

[0157] For λ2 = 0.02:

[0158] L=299.79-0.02×(269.81-100)=299.79-0.02×169.81=298.50kN / m 2

[0159] For λ3=0.03:

[0160] L=299.79-0.03×(269.81-100)=299.79-0.03×169.81=297.85kN / m 2

[0161] For the formula:

[0162]

[0163] Substitute into numerical calculations:

[0164]

[0165] If the average soil bearing capacity of the area is 250.28 kN / m 2 , optimized bearing capacity 298.28kN / m 2 There is an upward trend, indicating that by adjusting various engineering constraints and using appropriate Lagrangian multipliers, the bearing capacity of the soil is enhanced, enabling it to support heavier loads or more complex underground construction projects.

[0166] See also Figure 3 , the specific steps for obtaining the key probability distribution parameters are as follows:

[0167] S211: Based on the soil bearing capacity C, use the formula:

[0168]

[0169] and

[0170]

[0171] Estimate the diffusion rate β and degradation rate δ of pollutants;

[0172] Among them, k1, k2, k3, and k4 are adjustment parameters associated with soil properties and external environmental conditions;

[0173] S212: Based on the diffusion rate β and degradation rate δ, the formula is:

[0174]

[0175] and

[0176]

[0177] Get the adjusted diffusion rate β adjusted and degradation rate δ adjusted , and accordingly set the key probability distribution parameters;

[0178] The calculation process is as follows:

[0179] The parameters k1=150, k2=50, k3=120, and k4=40 are set; these are derived from the study of pollution behavior under similar soil conditions, ensuring its adaptability and response sensitivity in real-world scenarios.

[0180] For the formula:

[0181]

[0182] Setting parameter α β =0.2,θ β =0.5, α δ =0.15,θ δ =0.4, P env =0.3 based on the most recent environmental monitoring data;

[0183] For the formula:

[0184]

[0185] Results adjusted and δ adjusted Represents more accurate diffusion and degradation rates after adjusting for environmental parameters. These adjusted parameters provide more accurate simulation results that better reflect the pollution behavior in a specific environment.

[0186] See also Figure 4 , the specific steps for obtaining simulated pollution distribution data are:

[0187] S221: Based on the random sample of soil type T, temperature Θ, and humidity H of the target scene, the formula is used:

[0188]

[0189] Calculate the simulation score S of the i-th scenario i ;

[0190] Among them, Θ and H are the temperature and humidity parameters of the scene, Θ i and H iis the reference value of temperature and humidity in the scene, σ Θ and σ H is the adjustment factor for temperature and humidity, e is the natural exponential function used to adjust for temperature effects;

[0191] S222: According to the adjusted diffusion rate β adjusted and degradation rate δ adjusted , combined with the simulation score S of the i-th scenario i , using the formula:

[0192]

[0193] Calculate the simulated pollution distribution data P for the i-th scenario i , get the simulated pollution distribution data;

[0194] Among them, log is the natural logarithm function, which is used to simulate the effect of temperature on pollution diffusion;

[0195] The calculation process is as follows:

[0196] For the formula:

[0197]

[0198] Set the parameters T = 1.0, soil type influence factor to 1 (standardization), Θ = 25 °C, H = 30%, Θ i =20℃、H i =25%,σ Θ =5℃、σ H =5%;

[0199]

[0200] For the formula:

[0201]

[0202] Analysis results i =1.7521 represents the probability value of pollutant distribution under given simulation conditions. The pollutant distribution index under normal environment may be around 1.0. The results show that considering the adjusted environment and soil characteristics, the probability of pollution distribution is increased by about 75.21% compared with the baseline situation, which shows the impact of environmental adjustment on the potential for pollution transmission.

[0203] See also Figure 5 The specific steps to quantify the risk level of soil pollution in each scenario are as follows:

[0204] S311: Based on the simulated pollution distribution data P of the i-th scenario i , using the formula:

[0205] R i =α1·log(1+P i )

[0206] Calculate the risk assessment value R of the i-th scenario i ;

[0207] Among them, α1 is the adjustment coefficient used to quantify the relationship between risk and pollutant concentration, and log is the natural logarithm function used to convert pollutant concentration into a nonlinear risk score;

[0208] S312: Based on the risk assessment value R of the i-th scenario i , using the formula:

[0209] Q i =β1·R i

[0210] Calculate the quantitative risk value Q of the i-th scenario i ;

[0211] Among them, β1 is the coefficient used to convert the risk assessment value into a quantitative risk level. If Q i If Q exceeds the preset risk threshold θ, the scenario is classified as high risk. i is lower than or equal to θ, then the scenario is classified as low risk;

[0212] The calculation process is as follows:

[0213] Set parameter α1 to 2.0, which is usually determined based on previous environmental studies or risk assessment studies for similar scenarios.

[0214] For the formula:

[0215] R i =α1·log(1+P i )

[0216] R i =2.0·log(1+1.7521)=2.0·log(2.7521)

[0217] Using logarithmic calculations:

[0218] R i =2.0·1.013=2.026

[0219] β1 is 1.5, a value based on common practices in risk management and region-specific safety standards;

[0220] For the formula:

[0221] Q i =β1·R i

[0222] Q i =1.5·2.026=3.039

[0223] Results i =3.039 represents the quantitative risk value of the scenario under the given simulation conditions.

[0224] See also Figure 6 , the specific steps for obtaining the scenario risk analysis results are:

[0225] S321: Based on the quantitative risk value Q of the i-th scenario i , using the formula:

[0226]

[0227] Calculate the probability distribution value P of pollutant diffusion spread ;

[0228] Among them, γ1 is the shape parameter used to control the slope of the function, μ1 is the location parameter that determines the center of the probability distribution, e is the base of the natural exponential, and ξ1 is used to adjust Q i The absolute value function is introduced to simulate the enhancement or inhibition of diffusion by the environmental impact of mutations. i | indicates Q i The absolute value of increases the sensitivity of the model to extreme risk values;

[0229] S322: Based on the probability distribution value P of pollutant diffusion spread , using the formula:

[0230]

[0231] Calculate the maximum impact area A of the pollutant max , get the scenario risk analysis results;

[0232] Among them, σ1 is the proportionality coefficient, which is used to convert the probability into a specific area value, and η1 is used to increase the quadratic term of the diffusion probability to simulate the accelerating effect of the probability growth on the area;

[0233] The calculation process is as follows:

[0234] For the formula:

[0235]

[0236] The parameters are set as γ1 = 0.5, obtained from environmental science literature, μ1 = 3.0, based on average environmental risk assessment, ξ1 = 0.1, Q i =3.039;

[0237]

[0238] For the formula:

[0239]

[0240] Set parameter σ1 = 1000m 2 , based on standard data from geological and environmental engineering, η1 = 2, determined based on advanced environmental simulations;

[0241]

[0242] A max =1000·(0.6551+2·0.1842)

[0243] A max =1000·(0.6551+0.3684)

[0244] A max =1000·1.0235=1023.5m 2

[0245] Maximum impact area A max =1023.5m 2 A relatively large affected area is shown, indicating that additional mitigation measures may be required in this scenario.

[0246] See also Figure 7 , the specific steps for obtaining geotechnical engineering data evaluation results are:

[0247] S411: Based on the area with the greatest impact of pollutants A max , using the formula:

[0248]

[0249] Calculate the total contamination probability P of the target area total ;

[0250] Among them, A max,i is the maximum impact area of ​​the i-th scenario, o is the total number of scenarios, λ1 is the adjustment coefficient, which is used to adjust the impact of the size of the impact area on the pollution probability, κ1 is the shape factor of the impact area, which adjusts the impact of the shape on the pollution probability, and ρ1 is the response coefficient of the environmental conditions, which is used to adjust the impact of environmental changes on the pollution probability;

[0251] S412: Based on the total contamination probability P of the target area total , using the formula:

[0252]

[0253] Calculate the pollution risk level R of the entire target area total , and obtain the geotechnical engineering data evaluation results;

[0254] Among them, ω1 is a scaling factor used to convert probability into risk level, and φ1 is a weighting factor used to enhance the influence of high probability values;

[0255] The calculation process is as follows:

[0256] For the formula:

[0257]

[0258] Setting Parameter A max =1023.5m 2 , λ1 is 0.05, determined by analysis of soil and environmental data, κ1 is 0.1, set based on actual measurements of topographic effects, ρ1 is 0.2, set based on long-term climate data, and o is 1, only one scenario is analyzed;

[0259] First, calculate the function f:

[0260]

[0261] f(1023.5,0.05,0.1,0.2)=0.05·1023.5 0.1 ·e -0.2·1023.5

[0262] f(1023.5,0.05,0.1,0.2)=0.05·2.026·e -204.7 ≈0.05·2.026·0≈0

[0263] Because e -204.7 is close to 0, so f(A max,i ,λ1,κ1,ρ1) are also close to 0.

[0264]

[0265] For the formula:

[0266]

[0267] ω1 is 100, which is set through field monitoring and data analysis, and φ1 is 1.5, which is set based on environmental impact assessment;

[0268] R total =100·0 1.5 =0

[0269] Results total =0 means that the pollution risk level of the entire target area is very low.

[0270] A geotechnical engineering data intelligent analysis system, the geotechnical engineering data intelligent analysis system is used to execute the above geotechnical engineering data intelligent analysis method, the system comprises:

[0271] The data collection and optimization module uses the Lagrange multiplier method to adjust the multipliers of each environmental and engineering constraint based on the type, density, moisture content and external load data of the soil in underground construction to generate optimized soil bearing capacity data;

[0272] The pollution simulation module sets diffusion rate and degradation rate parameters based on optimized soil bearing capacity data, randomly constructs soil pollution scenarios through the Monte Carlo method, and generates simulated pollution distribution data;

[0273] The risk assessment module quantifies the risk level of soil pollution in each scenario based on simulated pollution distribution data, calculates the diffusion probability distribution of pollutants and the maximum impact area, and generates scenario risk analysis results;

[0274] The pollution impact analysis module evaluates the diffusion probability and impact range under multiple scenarios based on the scenario risk analysis results, analyzes the pollution situation in the target area, and generates pollution impact analysis data;

[0275] The risk level summary module summarizes the pollution risk level of the entire target area based on the pollution impact analysis data, evaluates the overall environmental risk, and generates geotechnical engineering data assessment results.

[0276] 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. A geotechnical engineering data intelligent analysis method, characterized in that: The following steps are involved: Collect data on soil type, density, moisture content and external loads in underground construction, calculate and adjust soil bearing capacity using the Lagrange multiplier method, set multipliers for each environmental and engineering constraint, and generate optimized soil bearing capacity data; According to the optimized soil bearing capacity data, key probability distribution parameters of soil pollution behavior of diffusion rate and degradation rate are set, and a variety of pollution scenarios are randomly constructed by Monte Carlo method, each scenario includes corresponding soil type, temperature and humidity conditions, to generate simulated pollution distribution data; Analyze the simulated pollution distribution data, quantify the risk level of soil pollution in each scenario, calculate the probability distribution of pollutant diffusion and the maximum impact area, and generate scenario risk analysis results; Based on the scenario risk analysis results, with reference to the diffusion probability and impact range under multiple scenarios, the pollution risk level of the entire target area is evaluated and summarized to generate geotechnical engineering data assessment results.

2. The geotechnical engineering data intelligent analysis method according to claim 1, characterized in that: The steps for obtaining the optimized soil bearing capacity data are specifically as follows: Collect data on soil type T, density D, water content H and external load L in underground construction, using the formula: and and and Among them, d a represents the soil density of the ath sample, h a represents the water content of the ath sample, I a represents the external load of the ath sample, n is the total number of samples, I is the indicator function, when T a = k, the value is 1, otherwise it is 0, T a is the soil type of the ath sample, n is the total number of samples, and k is the classification index of the soil type; The overall density D of the soil in the area is obtained by integration total , the overall soil moisture content in the area H total , the total amount of external pressure on the soil in the area is L total and the occurrence frequency T of the target soil in the entire sampling area freq (k); According to the overall density D of the soil in the area total , the overall soil moisture content in the area H total , the total amount of external pressure on the soil in the area is L total and the occurrence frequency T of the target soil in the entire sampling area freq (k), using the formula: L(T,D,H,L,λ)=f(T freq ,D total ,H total ,L total )-λ·(g(T freq ,D total ,H total ,L total )-b) Integrate data into function L; Among them, f(T freq , D total , H total , L total ) represents the soil bearing capacity function considering the soil type frequency, g(T freq , D total , H total , L total ) is the environmental constraint function of the adjusted reference soil overall characteristics, λ is the Lagrange multiplier used to balance the constraint condition, and b is the constraint condition constant; According to the function L, the formula is adopted: Calculate the soil bearing capacity C and obtain optimized soil bearing capacity data; Among them, L(T j , D j , H j , L j ,λ j ) is the function result under the jth constraint condition, T j , D j , H j , L j represent the soil type, density, water content and external load under the jth condition, λ j is the Lagrange multiplier for the jth condition, and m is the total number of environmental and engineering condition constraints.

3. The geotechnical engineering data intelligent analysis method according to claim 2, characterized in that: The steps for obtaining the key probability distribution parameters are as follows: According to the soil bearing capacity C, the formula is used: and Estimate the diffusion rate β and degradation rate 6 of pollutants; Among them, k1, k2, k3, and k4 are adjustment parameters associated with soil properties and external environmental conditions; According to the diffusion rate β and the degradation rate 6, the formula is used: and Get the adjusted diffusion rate β adjusted and degradation rate δ adjusted , and set the key probability distribution parameters accordingly.

4. The geotechnical engineering data intelligent analysis method according to claim 3, characterized in that: The steps for obtaining the simulated pollution distribution data are specifically as follows: Based on the random samples of soil type T, temperature Θ, and humidity H of the target scene, the formula is used: Calculate the simulation score S of the i-th scenario i ; Among them, Θ and H are the temperature and humidity parameters of the scene, Θ i and H i is the reference value of the temperature and humidity of the scene, σ Θ and σ H is the adjustment factor for temperature and humidity, e is the natural exponential function used to adjust for temperature effects; According to the adjusted diffusion rate β adjusted and degradation rate δ adjusted , combined with the simulation score S of the i-th scenario i , using the formula: Calculate the simulated pollution distribution data P for the i-th scenario i , get the simulated pollution distribution data; Among them, log is the natural logarithm function, which is used to simulate the effect of temperature on pollution diffusion.

5. The geotechnical engineering data intelligent analysis method according to claim 4, characterized in that: The specific steps for obtaining the quantified risk level of soil pollution in each scenario are as follows: According to the simulated pollution distribution data P of the i-th scenario i , using the formula: Ri=α1·1and(1+P i ) Calculate the risk assessment value R of the i-th scenario i ; Among them, α1 is the adjustment coefficient used to quantify the relationship between risk and pollutant concentration, and log is the natural logarithm function used to convert pollutant concentration into a nonlinear risk score; According to the risk assessment value R of the i-th scenario i , using the formula: Q i =β1·R i Calculate the quantitative risk value Q of the i-th scenario i ; Among them, β1 is the coefficient used to convert the risk assessment value into a quantitative risk level. If Q i If Q exceeds the preset risk threshold θ, the scenario is classified as high risk. i If θ is lower than or equal to θ, the scenario is classified as low risk.

6. The geotechnical engineering data intelligent analysis method according to claim 5, characterized in that: The steps for obtaining the scenario risk analysis results are specifically as follows: According to the quantitative risk value Q of the i-th scenario i , using the formula: Calculate the probability distribution value P of pollutant diffusion spread ; Among them, γ1 is the shape parameter used to control the slope of the function, μ1 is the location parameter that determines the center of the probability distribution, e is the base of the natural exponential, and ξ1 is used to adjust Q i The influence of |Qi| represents Q i The absolute value of According to the probability distribution value P of the pollutant diffusion spread , using the formula: Calculate the maximum impact area A of the pollutant max , get the scenario risk analysis results; Among them, σ1 is the proportionality coefficient used to convert the probability into an area value, and η1 is used to increase the quadratic term of the diffusion probability.

7. The geotechnical engineering data intelligent analysis method according to claim 6, characterized in that: The steps for obtaining the geotechnical engineering data evaluation results are specifically as follows: According to the maximum impact area A of the pollutant max , using the formula: Calculate the total contamination probability P of the target area total ; Among them, A max，i is the maximum impact area of ​​the i-th scenario, o is the total number of scenarios, λ1 is the adjustment coefficient, which is used to adjust the impact of the size of the impact area on the pollution probability, K1 is the shape factor of the impact area, which adjusts the impact of the shape on the pollution probability, ρ1 is the response coefficient of the environmental conditions, which is used to adjust the impact of environmental changes on the pollution probability; According to the total contamination probability P of the target area total , using the formula: Calculate the pollution risk level R of the entire target area total , and obtain the geotechnical engineering data evaluation results; Among them, ω1 is a proportional factor used to convert probability into risk level, and φ1 is a weight factor used to enhance the influence of probability value.

8. A geotechnical engineering data intelligent analysis system, characterized in that: According to any one of claims 1 to 7, the method for intelligent analysis of geotechnical engineering data comprises: The data collection and optimization module uses the Lagrange multiplier method to adjust the multipliers of each environmental and engineering constraint based on the type, density, moisture content and external load data of the soil in underground construction to generate optimized soil bearing capacity data; The pollution simulation module sets diffusion rate and degradation rate parameters based on the optimized soil bearing capacity data, randomly constructs soil pollution scenarios through the Monte Carlo method, and generates simulated pollution distribution data; The risk assessment module quantifies the risk level of soil pollution in each scenario based on the simulated pollution distribution data, calculates the diffusion probability distribution of pollutants and the maximum impact area, and generates scenario risk analysis results; The pollution impact analysis module evaluates the diffusion probability and impact range under multiple scenarios based on the scenario risk analysis results, analyzes the pollution situation in the target area, and generates pollution impact analysis data; The risk level summary module summarizes the pollution risk level of the entire target area based on the pollution impact analysis data, evaluates the overall environmental risk, and generates geotechnical engineering data evaluation results.

Images